per backend I/O statistics

From edc6da2601350edf8647b309ada4ecec4a86dd64 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 22 Aug 2024 15:16:50 +0000
Subject: [PATCH v2 1/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds a new
pg_my_stat_io view to display "my" backend I/O statistics. The KIND_IO stats
are still "fixed amount" ones as the maximum number of backend is fixed.

The statistics snapshot is made for the global stats (the aggregated ones) and
for my backend stats. The snapshot is not build in each backend to copy all
the others backends stats, as 1/ there is no use case (there is no need to get
others backends I/O statistics while taking care of the stats_fetch_consistency)
and 2/ that could be memory expensive depending of the number of max connections.

A subsequent commit will add a new pg_stat_get_backend_io() function to be
able to retrieve the I/O statistics for a given backend pid (each execution
re-fetches counters from shared memory because as stated above there is no
snapshots being created in each backend to copy the other backends stats).

Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                  |   4 +-
 doc/src/sgml/monitoring.sgml              |  28 ++++++
 src/backend/catalog/system_views.sql      |  22 +++++
 src/backend/utils/activity/pgstat.c       |  11 ++-
 src/backend/utils/activity/pgstat_io.c    |  91 ++++++++++++++---
 src/backend/utils/activity/pgstat_shmem.c |   4 +-
 src/backend/utils/adt/pgstatfuncs.c       | 114 +++++++++++++++++++++-
 src/include/catalog/pg_proc.dat           |   9 ++
 src/include/pgstat.h                      |  14 ++-
 src/include/utils/pgstat_internal.h       |  14 ++-
 src/test/regress/expected/rules.out       |  19 ++++
 src/test/regress/expected/stats.out       |  44 ++++++++-
 src/test/regress/sql/stats.sql            |  25 ++++-
 13 files changed, 366 insertions(+), 33 deletions(-)
   8.5% doc/src/sgml/
  29.4% src/backend/utils/activity/
  23.9% src/backend/utils/adt/
   4.4% src/include/catalog/
   3.1% src/include/utils/
   3.1% src/include/
  14.4% src/test/regress/expected/
  10.0% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 0aec11f443..2a59b97093 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8331,7 +8331,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
+        <structname>pg_stat_io</structname></link>,
+        <link linkend="monitoring-pg-my-stat-io-view">
+        <structname>pg_my_stat_io</structname></link>, in the output of
         <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
         is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 933de6fe07..b28ca4e0ca 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -488,6 +488,16 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_my_stat_io</structname><indexterm><primary>pg_my_stat_io</primary></indexterm></entry>
+      <entry>
+       One row for each combination of context and target object containing
+       my backend I/O statistics.
+       See <link linkend="monitoring-pg-my-stat-io-view">
+       <structname>pg_my_stat_io</structname></link> for details.
+     </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
       <entry>One row per replication slot, showing statistics about the
@@ -2948,6 +2958,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
 
 
 
+ </sect2>
+
+ <sect2 id="monitoring-pg-my-stat-io-view">
+  <title><structname>pg_my_stat_io</structname></title>
+
+  <indexterm>
+   <primary>pg_my_stat_io</primary>
+  </indexterm>
+
+  <para>
+   The <structname>pg_my_stat_io</structname> view will contain one row for each
+   combination of target I/O object and I/O context, showing
+   my backend I/O statistics. Combinations which do not make sense are
+   omitted. The fields are exactly the same as the ones in the <link
+   linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+   view.
+  </para>
+
  </sect2>
 
  <sect2 id="monitoring-pg-stat-bgwriter-view">
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 7fd5d256a1..b4939b7bc6 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1168,6 +1168,28 @@ SELECT
        b.stats_reset
 FROM pg_stat_get_io() b;
 
+CREATE VIEW pg_my_stat_io AS
+SELECT
+       b.backend_type,
+       b.object,
+       b.context,
+       b.reads,
+       b.read_time,
+       b.writes,
+       b.write_time,
+       b.writebacks,
+       b.writeback_time,
+       b.extends,
+       b.extend_time,
+       b.op_bytes,
+       b.hits,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.fsync_time,
+       b.stats_reset
+FROM pg_stat_get_my_io() b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 178b5ef65a..53b6e0bcd5 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -406,10 +406,12 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 
-		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
+		.init_backend_cb = pgstat_io_init_backend_cb,
+		.snapshot_ctl_off = offsetof(PgStat_Snapshot, global_io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
-		.shared_data_off = offsetof(PgStatShared_IO, stats),
-		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
+		/* [de-]serialize global_stats only */
+		.shared_data_off = offsetof(PgStatShared_IO, global_stats),
+		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->global_stats),
 
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
@@ -581,6 +583,9 @@ pgstat_shutdown_hook(int code, Datum arg)
 
 	pgstat_report_stat(true);
 
+	/* reset the pgstat_io counter related to this proc number */
+	pgstat_reset_io_counter_internal(MyProcNumber, GetCurrentTimestamp());
+
 	/* there shouldn't be any pending changes left */
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 8af55989ee..f2b36d8efa 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -31,6 +31,7 @@ typedef struct PgStat_PendingIO
 static PgStat_PendingIO PendingIOStats;
 bool		have_iostats = false;
 
+void		pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Check that stats have not been counted for any combination of IOObject,
@@ -154,11 +155,19 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 }
 
 PgStat_IO *
-pgstat_fetch_stat_io(void)
+pgstat_fetch_global_stat_io(void)
 {
 	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
 
-	return &pgStatLocal.snapshot.io;
+	return &pgStatLocal.snapshot.global_io;
+}
+
+PgStat_Backend_IO *
+pgstat_fetch_my_stat_io(void)
+{
+	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
+
+	return &pgStatLocal.snapshot.my_io;
 }
 
 /*
@@ -174,13 +183,16 @@ pgstat_flush_io(bool nowait)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
+	PgStat_BktypeIO *global_bktype_shstats;
 
 	if (!have_iostats)
 		return false;
 
 	bktype_lock = &pgStatLocal.shmem->io.locks[MyBackendType];
 	bktype_shstats =
-		&pgStatLocal.shmem->io.stats.stats[MyBackendType];
+		&pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	global_bktype_shstats =
+		&pgStatLocal.shmem->io.global_stats.stats[MyBackendType];
 
 	if (!nowait)
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
@@ -194,19 +206,28 @@ pgstat_flush_io(bool nowait)
 			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
 			{
 				instr_time	time;
+				PgStat_Counter counter;
+
+				counter = PendingIOStats.counts[io_object][io_context][io_op];
 
-				bktype_shstats->counts[io_object][io_context][io_op] +=
-					PendingIOStats.counts[io_object][io_context][io_op];
+				bktype_shstats->counts[io_object][io_context][io_op] += counter;
+
+				global_bktype_shstats->counts[io_object][io_context][io_op] +=
+					counter;
 
 				time = PendingIOStats.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
+
+				global_bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
 
 	Assert(pgstat_bktype_io_stats_valid(bktype_shstats, MyBackendType));
+	Assert(pgstat_bktype_io_stats_valid(global_bktype_shstats, MyBackendType));
 
 	LWLockRelease(bktype_lock);
 
@@ -260,13 +281,35 @@ pgstat_io_init_shmem_cb(void *stats)
 		LWLockInitialize(&stat_shmem->locks[i], LWTRANCHE_PGSTATS_DATA);
 }
 
+void
+pgstat_reset_io_counter_internal(int index, TimestampTz ts)
+{
+	LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[0];
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[index].stats;
+
+
+	/*
+	 * Use the lock in the first BackendType's PgStat_BktypeIO to protect the
+	 * reset timestamp as well.
+	 */
+	LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
+
+	pgStatLocal.shmem->io.stat[index].stat_reset_timestamp = ts;
+
+	memset(bktype_shstats, 0, sizeof(*bktype_shstats));
+	LWLockRelease(bktype_lock);
+}
+
 void
 pgstat_io_reset_all_cb(TimestampTz ts)
 {
+	for (int i = 0; i < NumProcStatSlots; i++)
+		pgstat_reset_io_counter_internal(i, ts);
+
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
+		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
 
@@ -275,7 +318,7 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.shmem->io.stats.stat_reset_timestamp = ts;
+			pgStatLocal.shmem->io.global_stats.stat_reset_timestamp = ts;
 
 		memset(bktype_shstats, 0, sizeof(*bktype_shstats));
 		LWLockRelease(bktype_lock);
@@ -285,11 +328,28 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 void
 pgstat_io_snapshot_cb(void)
 {
+	/* First, our own stats */
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.my_io.stats;
+	LWLock	   *mybktype_lock = &pgStatLocal.shmem->io.locks[0];
+
+	LWLockAcquire(mybktype_lock, LW_SHARED);
+
+	pgStatLocal.snapshot.my_io.stat_reset_timestamp =
+		pgStatLocal.shmem->io.stat[MyProcNumber].stat_reset_timestamp;
+
+	pgStatLocal.snapshot.my_io.bktype =
+		pgStatLocal.shmem->io.stat[MyProcNumber].bktype;
+
+	*bktype_snap = *bktype_shstats;
+	LWLockRelease(mybktype_lock);
+
+	/* Now, the global stats */
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
-		PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.io.stats[i];
+		PgStat_BktypeIO *bktype_global_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
+		PgStat_BktypeIO *bktype_global_snap = &pgStatLocal.snapshot.global_io.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_SHARED);
 
@@ -298,11 +358,11 @@ pgstat_io_snapshot_cb(void)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.snapshot.io.stat_reset_timestamp =
-				pgStatLocal.shmem->io.stats.stat_reset_timestamp;
+			pgStatLocal.snapshot.global_io.stat_reset_timestamp =
+				pgStatLocal.shmem->io.global_stats.stat_reset_timestamp;
 
 		/* using struct assignment due to better type safety */
-		*bktype_snap = *bktype_shstats;
+		*bktype_global_snap = *bktype_global_shstats;
 		LWLockRelease(bktype_lock);
 	}
 }
@@ -485,3 +545,10 @@ pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 
 	return true;
 }
+
+void
+pgstat_io_init_backend_cb(void)
+{
+	/* Initialize our backend type in the IO statistics */
+	pgStatLocal.shmem->io.stat[MyProcNumber].bktype = MyBackendType;
+}
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index ec93bf6902..3cfcba9609 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -128,7 +128,7 @@ StatsShmemSize(void)
 {
 	Size		sz;
 
-	sz = MAXALIGN(sizeof(PgStat_ShmemControl));
+	sz = MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 	sz = add_size(sz, pgstat_dsa_init_size());
 
 	/* Add shared memory for all the custom fixed-numbered statistics */
@@ -172,7 +172,7 @@ StatsShmemInit(void)
 		Assert(!found);
 
 		/* the allocation of pgStatLocal.shmem itself */
-		p += MAXALIGN(sizeof(PgStat_ShmemControl));
+		p += MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 
 		/*
 		 * Create a small dsa allocation in plain shared memory. This is
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 97dc09ac0d..e72dc5daa7 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1363,14 +1363,17 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
 
-	backends_io_stats = pgstat_fetch_stat_io();
+	backends_io_stats = pgstat_fetch_global_stat_io();
 
 	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
 
 	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
 	{
-		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
-		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
+		Datum		bktype_desc;
+		PgStat_BktypeIO *bktype_stats;
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backends_io_stats->stats[bktype];
 
 		/*
 		 * In Assert builds, we can afford an extra loop through all of the
@@ -1462,6 +1465,111 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_my_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backend_io_stats = pgstat_fetch_my_stat_io();
+
+	bktype = backend_io_stats->bktype;
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_io_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_io_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index ff5436acac..62658e9a00 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5831,6 +5831,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: My backend IO statistics',
+  proname => 'pg_stat_get_my_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => '',
+  proallargtypes => '{text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_my_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index be2c91168a..9d63b1a5b7 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/proc.h"
 #include "utils/backend_progress.h" /* for backward compatibility */
 #include "utils/backend_status.h"	/* for backward compatibility */
 #include "utils/relcache.h"
@@ -76,6 +77,8 @@
  */
 #define PGSTAT_KIND_EXPERIMENTAL	128
 
+#define  NumProcStatSlots (MaxBackends + NUM_AUXILIARY_PROCS)
+
 static inline bool
 pgstat_is_kind_builtin(PgStat_Kind kind)
 {
@@ -351,6 +354,12 @@ typedef struct PgStat_IO
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend_IO
+{
+	TimestampTz stat_reset_timestamp;
+	BackendType bktype;
+	PgStat_BktypeIO stats;
+} PgStat_Backend_IO;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -559,7 +568,8 @@ extern instr_time pgstat_prepare_io_time(bool track_io_guc);
 extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 									IOOp io_op, instr_time start_time, uint32 cnt);
 
-extern PgStat_IO *pgstat_fetch_stat_io(void);
+extern PgStat_IO *pgstat_fetch_global_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
@@ -568,7 +578,7 @@ extern bool pgstat_tracks_io_object(BackendType bktype,
 									IOObject io_object, IOContext io_context);
 extern bool pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 								IOContext io_context, IOOp io_op);
-
+extern void pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Functions in pgstat_database.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 25820cbf0a..3b2f2b28dd 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -353,11 +353,12 @@ typedef struct PgStatShared_Checkpointer
 typedef struct PgStatShared_IO
 {
 	/*
-	 * locks[i] protects stats.stats[i]. locks[0] also protects
-	 * stats.stat_reset_timestamp.
+	 * locks[i] protects global_stats.stats[i]. locks[0] also protects
+	 * global_stats.stat_reset_timestamp.
 	 */
 	LWLock		locks[BACKEND_NUM_TYPES];
-	PgStat_IO	stats;
+	PgStat_IO	global_stats;
+	PgStat_Backend_IO	stat[FLEXIBLE_ARRAY_MEMBER];
 } PgStatShared_IO;
 
 typedef struct PgStatShared_SLRU
@@ -450,7 +451,6 @@ typedef struct PgStat_ShmemControl
 	PgStatShared_Archiver archiver;
 	PgStatShared_BgWriter bgwriter;
 	PgStatShared_Checkpointer checkpointer;
-	PgStatShared_IO io;
 	PgStatShared_SLRU slru;
 	PgStatShared_Wal wal;
 
@@ -460,6 +460,8 @@ typedef struct PgStat_ShmemControl
 	 */
 	void	   *custom_data[PGSTAT_KIND_CUSTOM_SIZE];
 
+	/* has to be at the end due to FLEXIBLE_ARRAY_MEMBER */
+	PgStatShared_IO io;
 } PgStat_ShmemControl;
 
 
@@ -481,7 +483,8 @@ typedef struct PgStat_Snapshot
 
 	PgStat_CheckpointerStats checkpointer;
 
-	PgStat_IO	io;
+	PgStat_Backend_IO	my_io;
+	PgStat_IO	global_io;
 
 	PgStat_SLRUStats slru[SLRU_NUM_ELEMENTS];
 
@@ -682,6 +685,7 @@ extern bool pgstat_flush_wal(bool nowait);
 extern bool pgstat_have_pending_wal(void);
 
 extern void pgstat_wal_init_backend_cb(void);
+extern void pgstat_io_init_backend_cb(void);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index a1626f3fae..785298d7b0 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1398,6 +1398,25 @@ pg_matviews| SELECT n.nspname AS schemaname,
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN pg_tablespace t ON ((t.oid = c.reltablespace)))
   WHERE (c.relkind = 'm'::"char");
+pg_my_stat_io| SELECT backend_type,
+    object,
+    context,
+    reads,
+    read_time,
+    writes,
+    write_time,
+    writebacks,
+    writeback_time,
+    extends,
+    extend_time,
+    op_bytes,
+    hits,
+    evictions,
+    reuses,
+    fsyncs,
+    fsync_time,
+    stats_reset
+   FROM pg_stat_get_my_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 6e08898b18..c489e528e0 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1261,9 +1261,14 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1285,16 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1314,23 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1551,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1567,14 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index d8ac0d06f4..c95cb71652 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -609,18 +609,26 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,7 +638,13 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
-
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -762,10 +776,15 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
 
 
 -- test BRIN index doesn't block HOT update
-- 
2.34.1

From 4e9e50f43a83cbba7caa6824c74df1e0f536cc3e Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 28 Aug 2024 12:59:02 +0000
Subject: [PATCH v2 2/2] Add pg_stat_get_backend_io()

Adding the pg_stat_get_backend_io() function to retrieve I/O statistics for
a particular backend pid. Note this function behaves as if stats_fetch_consistency
is set to none.
---
 doc/src/sgml/monitoring.sgml           |  18 ++++
 src/backend/utils/activity/pgstat_io.c |   6 ++
 src/backend/utils/adt/pgstatfuncs.c    | 120 +++++++++++++++++++++++++
 src/include/catalog/pg_proc.dat        |   9 ++
 src/include/pgstat.h                   |   1 +
 src/test/regress/expected/stats.out    |  25 ++++++
 src/test/regress/sql/stats.sql         |  16 +++-
 7 files changed, 194 insertions(+), 1 deletion(-)
  10.9% doc/src/sgml/
  47.1% src/backend/utils/adt/
   9.2% src/include/catalog/
  15.4% src/test/regress/expected/
  14.4% src/test/regress/sql/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index b28ca4e0ca..fb908172f8 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4770,6 +4770,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. This function behaves as if <varname>stats_fetch_consistency</varname>
+        is set to <literal>none</literal> (means each execution re-fetches
+        counters from shared memory).
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f2b36d8efa..780ba48d1a 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -170,6 +170,12 @@ pgstat_fetch_my_stat_io(void)
 	return &pgStatLocal.snapshot.my_io;
 }
 
+PgStat_Backend_IO *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	return &pgStatLocal.shmem->io.stat[procNumber];
+}
+
 /*
  * Flush out locally pending IO statistics
  *
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index e72dc5daa7..ca22251acd 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1570,6 +1570,126 @@ pg_stat_get_my_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		reset_time;
+	ProcNumber	procNumber;
+	PGPROC	   *proc;
+	BackendType bktype;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+	InitMaterializedSRF(fcinfo, 0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/* Maybe an auxiliary process? */
+	if (proc == NULL)
+		proc = AuxiliaryPidGetProc(backend_pid);
+
+	/* This backend_pid does not exist */
+	if (proc != NULL)
+	{
+		procNumber = GetNumberFromPGProc(proc);
+		backend_io_stats = pgstat_fetch_proc_stat_io(procNumber);
+		bktype = backend_io_stats->bktype;
+		reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backend_io_stats->stats;
+
+		/*
+		 * In Assert builds, we can afford an extra loop through all of the
+		 * counters checking that only expected stats are non-zero, since it
+		 * keeps the non-Assert code cleaner.
+		 */
+		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+		for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+		{
+			const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+			for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+			{
+				const char *context_name = pgstat_get_io_context_name(io_context);
+
+				Datum		values[IO_NUM_COLUMNS] = {0};
+				bool		nulls[IO_NUM_COLUMNS] = {0};
+
+				/*
+				 * Some combinations of BackendType, IOObject, and IOContext
+				 * are not valid for any type of IOOp. In such cases, omit the
+				 * entire row from the view.
+				 */
+				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+					continue;
+
+				values[IO_COL_BACKEND_TYPE] = bktype_desc;
+				values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+				values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+				if (backend_io_stats->stat_reset_timestamp != 0)
+					values[IO_COL_RESET_TIME] = reset_time;
+				else
+					nulls[IO_COL_RESET_TIME] = true;
+
+				/*
+				 * Hard-code this to the value of BLCKSZ for now. Future
+				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
+				 * and constant multipliers, once non-block-oriented IO (e.g.
+				 * temporary file IO) is tracked.
+				 */
+				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+				for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+				{
+					int			op_idx = pgstat_get_io_op_index(io_op);
+					int			time_idx = pgstat_get_io_time_index(io_op);
+
+					/*
+					 * Some combinations of BackendType and IOOp, of IOContext
+					 * and IOOp, and of IOObject and IOOp are not tracked. Set
+					 * these cells in the view NULL.
+					 */
+					if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+					{
+						PgStat_Counter count =
+							bktype_stats->counts[io_obj][io_context][io_op];
+
+						values[op_idx] = Int64GetDatum(count);
+					}
+					else
+						nulls[op_idx] = true;
+
+					/* not every operation is timed */
+					if (time_idx == IO_COL_INVALID)
+						continue;
+
+					if (!nulls[op_idx])
+					{
+						PgStat_Counter time =
+							bktype_stats->times[io_obj][io_context][io_op];
+
+						values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+					}
+					else
+						nulls[time_idx] = true;
+				}
+
+				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+									 values, nulls);
+			}
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 62658e9a00..0a540a590f 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5840,6 +5840,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_my_io' },
 
+{ oid => '8896', descr => 'statistics: per backend type IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '30', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9d63b1a5b7..2a2b4a2947 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -570,6 +570,7 @@ extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 
 extern PgStat_IO *pgstat_fetch_global_stat_io(void);
 extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index c489e528e0..aced015c2f 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1263,12 +1263,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1293,6 +1299,15 @@ SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
@@ -1553,6 +1568,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1575,6 +1592,14 @@ SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index c95cb71652..d05009e1f5 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -611,12 +611,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -626,6 +632,10 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
 SELECT sum(extends) AS my_io_sum_shared_after_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
@@ -778,6 +788,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
@@ -785,7 +797,9 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
   FROM pg_my_stat_io \gset
 SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
-
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
-- 
2.34.1

From 335949f1c408a99aed74c0231d5e436b5f319746 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 22 Aug 2024 15:16:50 +0000
Subject: [PATCH v3 1/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds a new
pg_my_stat_io view to display "my" backend I/O statistics. The KIND_IO stats
are still "fixed amount" ones as the maximum number of backend is fixed.

The statistics snapshot is made for the global stats (the aggregated ones) and
for my backend stats. The snapshot is not build in each backend to copy all
the others backends stats, as 1/ there is no use case (there is no need to get
others backends I/O statistics while taking care of the stats_fetch_consistency)
and 2/ that could be memory expensive depending of the number of max connections.

A subsequent commit will add a new pg_stat_get_backend_io() function to be
able to retrieve the I/O statistics for a given backend pid (each execution
re-fetches counters from shared memory because as stated above there is no
snapshots being created in each backend to copy the other backends stats).

Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                  |   4 +-
 doc/src/sgml/monitoring.sgml              |  28 ++++++
 src/backend/catalog/system_views.sql      |  22 +++++
 src/backend/utils/activity/pgstat.c       |  11 ++-
 src/backend/utils/activity/pgstat_io.c    |  91 ++++++++++++++---
 src/backend/utils/activity/pgstat_shmem.c |   4 +-
 src/backend/utils/adt/pgstatfuncs.c       | 114 +++++++++++++++++++++-
 src/include/catalog/pg_proc.dat           |   9 ++
 src/include/pgstat.h                      |  14 ++-
 src/include/utils/pgstat_internal.h       |  14 ++-
 src/test/regress/expected/rules.out       |  19 ++++
 src/test/regress/expected/stats.out       |  44 ++++++++-
 src/test/regress/sql/stats.sql            |  25 ++++-
 13 files changed, 366 insertions(+), 33 deletions(-)
   8.5% doc/src/sgml/
  29.4% src/backend/utils/activity/
  23.9% src/backend/utils/adt/
   4.4% src/include/catalog/
   3.1% src/include/utils/
   3.1% src/include/
  14.4% src/test/regress/expected/
  10.0% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 0aec11f443..2a59b97093 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8331,7 +8331,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
+        <structname>pg_stat_io</structname></link>,
+        <link linkend="monitoring-pg-my-stat-io-view">
+        <structname>pg_my_stat_io</structname></link>, in the output of
         <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
         is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 933de6fe07..b28ca4e0ca 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -488,6 +488,16 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_my_stat_io</structname><indexterm><primary>pg_my_stat_io</primary></indexterm></entry>
+      <entry>
+       One row for each combination of context and target object containing
+       my backend I/O statistics.
+       See <link linkend="monitoring-pg-my-stat-io-view">
+       <structname>pg_my_stat_io</structname></link> for details.
+     </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
       <entry>One row per replication slot, showing statistics about the
@@ -2948,6 +2958,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
 
 
 
+ </sect2>
+
+ <sect2 id="monitoring-pg-my-stat-io-view">
+  <title><structname>pg_my_stat_io</structname></title>
+
+  <indexterm>
+   <primary>pg_my_stat_io</primary>
+  </indexterm>
+
+  <para>
+   The <structname>pg_my_stat_io</structname> view will contain one row for each
+   combination of target I/O object and I/O context, showing
+   my backend I/O statistics. Combinations which do not make sense are
+   omitted. The fields are exactly the same as the ones in the <link
+   linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+   view.
+  </para>
+
  </sect2>
 
  <sect2 id="monitoring-pg-stat-bgwriter-view">
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 7fd5d256a1..b4939b7bc6 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1168,6 +1168,28 @@ SELECT
        b.stats_reset
 FROM pg_stat_get_io() b;
 
+CREATE VIEW pg_my_stat_io AS
+SELECT
+       b.backend_type,
+       b.object,
+       b.context,
+       b.reads,
+       b.read_time,
+       b.writes,
+       b.write_time,
+       b.writebacks,
+       b.writeback_time,
+       b.extends,
+       b.extend_time,
+       b.op_bytes,
+       b.hits,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.fsync_time,
+       b.stats_reset
+FROM pg_stat_get_my_io() b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index a7f2dfc744..deb30cd2fc 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -406,10 +406,12 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 
-		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
+		.init_backend_cb = pgstat_io_init_backend_cb,
+		.snapshot_ctl_off = offsetof(PgStat_Snapshot, global_io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
-		.shared_data_off = offsetof(PgStatShared_IO, stats),
-		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
+		/* [de-]serialize global_stats only */
+		.shared_data_off = offsetof(PgStatShared_IO, global_stats),
+		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->global_stats),
 
 		.flush_fixed_cb = pgstat_io_flush_cb,
 		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
@@ -587,6 +589,9 @@ pgstat_shutdown_hook(int code, Datum arg)
 
 	pgstat_report_stat(true);
 
+	/* reset the pgstat_io counter related to this proc number */
+	pgstat_reset_io_counter_internal(MyProcNumber, GetCurrentTimestamp());
+
 	/* there shouldn't be any pending changes left */
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index cc2ffc78aa..611ca21720 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -31,6 +31,7 @@ typedef struct PgStat_PendingIO
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
+void		pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Check that stats have not been counted for any combination of IOObject,
@@ -154,11 +155,19 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 }
 
 PgStat_IO *
-pgstat_fetch_stat_io(void)
+pgstat_fetch_global_stat_io(void)
 {
 	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
 
-	return &pgStatLocal.snapshot.io;
+	return &pgStatLocal.snapshot.global_io;
+}
+
+PgStat_Backend_IO *
+pgstat_fetch_my_stat_io(void)
+{
+	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
+
+	return &pgStatLocal.snapshot.my_io;
 }
 
 /*
@@ -192,13 +201,16 @@ pgstat_io_flush_cb(bool nowait)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
+	PgStat_BktypeIO *global_bktype_shstats;
 
 	if (!have_iostats)
 		return false;
 
 	bktype_lock = &pgStatLocal.shmem->io.locks[MyBackendType];
 	bktype_shstats =
-		&pgStatLocal.shmem->io.stats.stats[MyBackendType];
+		&pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	global_bktype_shstats =
+		&pgStatLocal.shmem->io.global_stats.stats[MyBackendType];
 
 	if (!nowait)
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
@@ -212,19 +224,28 @@ pgstat_io_flush_cb(bool nowait)
 			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
 			{
 				instr_time	time;
+				PgStat_Counter counter;
+
+				counter = PendingIOStats.counts[io_object][io_context][io_op];
 
-				bktype_shstats->counts[io_object][io_context][io_op] +=
-					PendingIOStats.counts[io_object][io_context][io_op];
+				bktype_shstats->counts[io_object][io_context][io_op] += counter;
+
+				global_bktype_shstats->counts[io_object][io_context][io_op] +=
+					counter;
 
 				time = PendingIOStats.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
+
+				global_bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
 
 	Assert(pgstat_bktype_io_stats_valid(bktype_shstats, MyBackendType));
+	Assert(pgstat_bktype_io_stats_valid(global_bktype_shstats, MyBackendType));
 
 	LWLockRelease(bktype_lock);
 
@@ -278,13 +299,35 @@ pgstat_io_init_shmem_cb(void *stats)
 		LWLockInitialize(&stat_shmem->locks[i], LWTRANCHE_PGSTATS_DATA);
 }
 
+void
+pgstat_reset_io_counter_internal(int index, TimestampTz ts)
+{
+	LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[0];
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[index].stats;
+
+
+	/*
+	 * Use the lock in the first BackendType's PgStat_BktypeIO to protect the
+	 * reset timestamp as well.
+	 */
+	LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
+
+	pgStatLocal.shmem->io.stat[index].stat_reset_timestamp = ts;
+
+	memset(bktype_shstats, 0, sizeof(*bktype_shstats));
+	LWLockRelease(bktype_lock);
+}
+
 void
 pgstat_io_reset_all_cb(TimestampTz ts)
 {
+	for (int i = 0; i < NumProcStatSlots; i++)
+		pgstat_reset_io_counter_internal(i, ts);
+
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
+		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
 
@@ -293,7 +336,7 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.shmem->io.stats.stat_reset_timestamp = ts;
+			pgStatLocal.shmem->io.global_stats.stat_reset_timestamp = ts;
 
 		memset(bktype_shstats, 0, sizeof(*bktype_shstats));
 		LWLockRelease(bktype_lock);
@@ -303,11 +346,28 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 void
 pgstat_io_snapshot_cb(void)
 {
+	/* First, our own stats */
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.my_io.stats;
+	LWLock	   *mybktype_lock = &pgStatLocal.shmem->io.locks[0];
+
+	LWLockAcquire(mybktype_lock, LW_SHARED);
+
+	pgStatLocal.snapshot.my_io.stat_reset_timestamp =
+		pgStatLocal.shmem->io.stat[MyProcNumber].stat_reset_timestamp;
+
+	pgStatLocal.snapshot.my_io.bktype =
+		pgStatLocal.shmem->io.stat[MyProcNumber].bktype;
+
+	*bktype_snap = *bktype_shstats;
+	LWLockRelease(mybktype_lock);
+
+	/* Now, the global stats */
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
-		PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.io.stats[i];
+		PgStat_BktypeIO *bktype_global_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
+		PgStat_BktypeIO *bktype_global_snap = &pgStatLocal.snapshot.global_io.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_SHARED);
 
@@ -316,11 +376,11 @@ pgstat_io_snapshot_cb(void)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.snapshot.io.stat_reset_timestamp =
-				pgStatLocal.shmem->io.stats.stat_reset_timestamp;
+			pgStatLocal.snapshot.global_io.stat_reset_timestamp =
+				pgStatLocal.shmem->io.global_stats.stat_reset_timestamp;
 
 		/* using struct assignment due to better type safety */
-		*bktype_snap = *bktype_shstats;
+		*bktype_global_snap = *bktype_global_shstats;
 		LWLockRelease(bktype_lock);
 	}
 }
@@ -503,3 +563,10 @@ pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 
 	return true;
 }
+
+void
+pgstat_io_init_backend_cb(void)
+{
+	/* Initialize our backend type in the IO statistics */
+	pgStatLocal.shmem->io.stat[MyProcNumber].bktype = MyBackendType;
+}
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index ec93bf6902..3cfcba9609 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -128,7 +128,7 @@ StatsShmemSize(void)
 {
 	Size		sz;
 
-	sz = MAXALIGN(sizeof(PgStat_ShmemControl));
+	sz = MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 	sz = add_size(sz, pgstat_dsa_init_size());
 
 	/* Add shared memory for all the custom fixed-numbered statistics */
@@ -172,7 +172,7 @@ StatsShmemInit(void)
 		Assert(!found);
 
 		/* the allocation of pgStatLocal.shmem itself */
-		p += MAXALIGN(sizeof(PgStat_ShmemControl));
+		p += MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 
 		/*
 		 * Create a small dsa allocation in plain shared memory. This is
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 33c7b25560..4c00570396 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1363,14 +1363,17 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
 
-	backends_io_stats = pgstat_fetch_stat_io();
+	backends_io_stats = pgstat_fetch_global_stat_io();
 
 	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
 
 	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
 	{
-		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
-		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
+		Datum		bktype_desc;
+		PgStat_BktypeIO *bktype_stats;
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backends_io_stats->stats[bktype];
 
 		/*
 		 * In Assert builds, we can afford an extra loop through all of the
@@ -1462,6 +1465,111 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_my_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backend_io_stats = pgstat_fetch_my_stat_io();
+
+	bktype = backend_io_stats->bktype;
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_io_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_io_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index ff5436acac..62658e9a00 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5831,6 +5831,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: My backend IO statistics',
+  proname => 'pg_stat_get_my_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => '',
+  proallargtypes => '{text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_my_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index be2c91168a..9d63b1a5b7 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/proc.h"
 #include "utils/backend_progress.h" /* for backward compatibility */
 #include "utils/backend_status.h"	/* for backward compatibility */
 #include "utils/relcache.h"
@@ -76,6 +77,8 @@
  */
 #define PGSTAT_KIND_EXPERIMENTAL	128
 
+#define  NumProcStatSlots (MaxBackends + NUM_AUXILIARY_PROCS)
+
 static inline bool
 pgstat_is_kind_builtin(PgStat_Kind kind)
 {
@@ -351,6 +354,12 @@ typedef struct PgStat_IO
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend_IO
+{
+	TimestampTz stat_reset_timestamp;
+	BackendType bktype;
+	PgStat_BktypeIO stats;
+} PgStat_Backend_IO;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -559,7 +568,8 @@ extern instr_time pgstat_prepare_io_time(bool track_io_guc);
 extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 									IOOp io_op, instr_time start_time, uint32 cnt);
 
-extern PgStat_IO *pgstat_fetch_stat_io(void);
+extern PgStat_IO *pgstat_fetch_global_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
@@ -568,7 +578,7 @@ extern bool pgstat_tracks_io_object(BackendType bktype,
 									IOObject io_object, IOContext io_context);
 extern bool pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 								IOContext io_context, IOOp io_op);
-
+extern void pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Functions in pgstat_database.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index bba90e898d..ea4cc6a2c6 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -366,11 +366,12 @@ typedef struct PgStatShared_Checkpointer
 typedef struct PgStatShared_IO
 {
 	/*
-	 * locks[i] protects stats.stats[i]. locks[0] also protects
-	 * stats.stat_reset_timestamp.
+	 * locks[i] protects global_stats.stats[i]. locks[0] also protects
+	 * global_stats.stat_reset_timestamp.
 	 */
 	LWLock		locks[BACKEND_NUM_TYPES];
-	PgStat_IO	stats;
+	PgStat_IO	global_stats;
+	PgStat_Backend_IO	stat[FLEXIBLE_ARRAY_MEMBER];
 } PgStatShared_IO;
 
 typedef struct PgStatShared_SLRU
@@ -463,7 +464,6 @@ typedef struct PgStat_ShmemControl
 	PgStatShared_Archiver archiver;
 	PgStatShared_BgWriter bgwriter;
 	PgStatShared_Checkpointer checkpointer;
-	PgStatShared_IO io;
 	PgStatShared_SLRU slru;
 	PgStatShared_Wal wal;
 
@@ -473,6 +473,8 @@ typedef struct PgStat_ShmemControl
 	 */
 	void	   *custom_data[PGSTAT_KIND_CUSTOM_SIZE];
 
+	/* has to be at the end due to FLEXIBLE_ARRAY_MEMBER */
+	PgStatShared_IO io;
 } PgStat_ShmemControl;
 
 
@@ -494,7 +496,8 @@ typedef struct PgStat_Snapshot
 
 	PgStat_CheckpointerStats checkpointer;
 
-	PgStat_IO	io;
+	PgStat_Backend_IO	my_io;
+	PgStat_IO	global_io;
 
 	PgStat_SLRUStats slru[SLRU_NUM_ELEMENTS];
 
@@ -629,6 +632,7 @@ extern bool pgstat_io_flush_cb(bool nowait);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
+extern void pgstat_io_init_backend_cb(void);
 
 
 /*
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index a1626f3fae..785298d7b0 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1398,6 +1398,25 @@ pg_matviews| SELECT n.nspname AS schemaname,
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN pg_tablespace t ON ((t.oid = c.reltablespace)))
   WHERE (c.relkind = 'm'::"char");
+pg_my_stat_io| SELECT backend_type,
+    object,
+    context,
+    reads,
+    read_time,
+    writes,
+    write_time,
+    writebacks,
+    writeback_time,
+    extends,
+    extend_time,
+    op_bytes,
+    hits,
+    evictions,
+    reuses,
+    fsyncs,
+    fsync_time,
+    stats_reset
+   FROM pg_stat_get_my_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 6e08898b18..c489e528e0 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1261,9 +1261,14 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1285,16 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1314,23 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1551,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1567,14 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index d8ac0d06f4..c95cb71652 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -609,18 +609,26 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,7 +638,13 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
-
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -762,10 +776,15 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
 
 
 -- test BRIN index doesn't block HOT update
-- 
2.34.1

From b5719ca7a1c6257929b71c45ba8cb9da3bd53665 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 28 Aug 2024 12:59:02 +0000
Subject: [PATCH v3 2/2] Add pg_stat_get_backend_io()

Adding the pg_stat_get_backend_io() function to retrieve I/O statistics for
a particular backend pid. Note this function behaves as if stats_fetch_consistency
is set to none.
---
 doc/src/sgml/monitoring.sgml           |  18 ++++
 src/backend/utils/activity/pgstat_io.c |   6 ++
 src/backend/utils/adt/pgstatfuncs.c    | 120 +++++++++++++++++++++++++
 src/include/catalog/pg_proc.dat        |   9 ++
 src/include/pgstat.h                   |   1 +
 src/test/regress/expected/stats.out    |  25 ++++++
 src/test/regress/sql/stats.sql         |  16 +++-
 7 files changed, 194 insertions(+), 1 deletion(-)
  10.9% doc/src/sgml/
  47.1% src/backend/utils/adt/
   9.2% src/include/catalog/
  15.4% src/test/regress/expected/
  14.4% src/test/regress/sql/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index b28ca4e0ca..fb908172f8 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4770,6 +4770,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. This function behaves as if <varname>stats_fetch_consistency</varname>
+        is set to <literal>none</literal> (means each execution re-fetches
+        counters from shared memory).
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 611ca21720..cf6a49cf48 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -170,6 +170,12 @@ pgstat_fetch_my_stat_io(void)
 	return &pgStatLocal.snapshot.my_io;
 }
 
+PgStat_Backend_IO *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	return &pgStatLocal.shmem->io.stat[procNumber];
+}
+
 /*
  * Check if there any IO stats waiting for flush.
  */
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 4c00570396..795ff4e2f6 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1570,6 +1570,126 @@ pg_stat_get_my_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		reset_time;
+	ProcNumber	procNumber;
+	PGPROC	   *proc;
+	BackendType bktype;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+	InitMaterializedSRF(fcinfo, 0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/* Maybe an auxiliary process? */
+	if (proc == NULL)
+		proc = AuxiliaryPidGetProc(backend_pid);
+
+	/* This backend_pid does not exist */
+	if (proc != NULL)
+	{
+		procNumber = GetNumberFromPGProc(proc);
+		backend_io_stats = pgstat_fetch_proc_stat_io(procNumber);
+		bktype = backend_io_stats->bktype;
+		reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backend_io_stats->stats;
+
+		/*
+		 * In Assert builds, we can afford an extra loop through all of the
+		 * counters checking that only expected stats are non-zero, since it
+		 * keeps the non-Assert code cleaner.
+		 */
+		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+		for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+		{
+			const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+			for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+			{
+				const char *context_name = pgstat_get_io_context_name(io_context);
+
+				Datum		values[IO_NUM_COLUMNS] = {0};
+				bool		nulls[IO_NUM_COLUMNS] = {0};
+
+				/*
+				 * Some combinations of BackendType, IOObject, and IOContext
+				 * are not valid for any type of IOOp. In such cases, omit the
+				 * entire row from the view.
+				 */
+				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+					continue;
+
+				values[IO_COL_BACKEND_TYPE] = bktype_desc;
+				values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+				values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+				if (backend_io_stats->stat_reset_timestamp != 0)
+					values[IO_COL_RESET_TIME] = reset_time;
+				else
+					nulls[IO_COL_RESET_TIME] = true;
+
+				/*
+				 * Hard-code this to the value of BLCKSZ for now. Future
+				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
+				 * and constant multipliers, once non-block-oriented IO (e.g.
+				 * temporary file IO) is tracked.
+				 */
+				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+				for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+				{
+					int			op_idx = pgstat_get_io_op_index(io_op);
+					int			time_idx = pgstat_get_io_time_index(io_op);
+
+					/*
+					 * Some combinations of BackendType and IOOp, of IOContext
+					 * and IOOp, and of IOObject and IOOp are not tracked. Set
+					 * these cells in the view NULL.
+					 */
+					if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+					{
+						PgStat_Counter count =
+							bktype_stats->counts[io_obj][io_context][io_op];
+
+						values[op_idx] = Int64GetDatum(count);
+					}
+					else
+						nulls[op_idx] = true;
+
+					/* not every operation is timed */
+					if (time_idx == IO_COL_INVALID)
+						continue;
+
+					if (!nulls[op_idx])
+					{
+						PgStat_Counter time =
+							bktype_stats->times[io_obj][io_context][io_op];
+
+						values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+					}
+					else
+						nulls[time_idx] = true;
+				}
+
+				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+									 values, nulls);
+			}
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 62658e9a00..0a540a590f 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5840,6 +5840,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_my_io' },
 
+{ oid => '8896', descr => 'statistics: per backend type IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '30', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9d63b1a5b7..2a2b4a2947 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -570,6 +570,7 @@ extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 
 extern PgStat_IO *pgstat_fetch_global_stat_io(void);
 extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index c489e528e0..aced015c2f 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1263,12 +1263,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1293,6 +1299,15 @@ SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
@@ -1553,6 +1568,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1575,6 +1592,14 @@ SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index c95cb71652..d05009e1f5 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -611,12 +611,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -626,6 +632,10 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
 SELECT sum(extends) AS my_io_sum_shared_after_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
@@ -778,6 +788,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
@@ -785,7 +797,9 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
   FROM pg_my_stat_io \gset
 SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
-
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
-- 
2.34.1

From 2bc490060ce8ed6557ca5a586f36cd43e7480d8e Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 22 Aug 2024 15:16:50 +0000
Subject: [PATCH v4 1/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds a new
pg_my_stat_io view to display "my" backend I/O statistics. The KIND_IO stats
are still "fixed amount" ones as the maximum number of backend is fixed.

The statistics snapshot is made for the global stats (the aggregated ones) and
for my backend stats. The snapshot is not build in each backend to copy all
the others backends stats, as 1/ there is no use case (there is no need to get
others backends I/O statistics while taking care of the stats_fetch_consistency)
and 2/ that could be memory expensive depending of the number of max connections.

A subsequent commit will add a new pg_stat_get_backend_io() function to be
able to retrieve the I/O statistics for a given backend pid (each execution
re-fetches counters from shared memory because as stated above there is no
snapshots being created in each backend to copy the other backends stats).

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                  |   4 +-
 doc/src/sgml/monitoring.sgml              |  28 ++++++
 src/backend/catalog/system_views.sql      |  22 +++++
 src/backend/utils/activity/pgstat.c       |  11 ++-
 src/backend/utils/activity/pgstat_io.c    |  93 +++++++++++++++---
 src/backend/utils/activity/pgstat_shmem.c |   4 +-
 src/backend/utils/adt/pgstatfuncs.c       | 114 +++++++++++++++++++++-
 src/include/catalog/pg_proc.dat           |   9 ++
 src/include/pgstat.h                      |  14 ++-
 src/include/utils/pgstat_internal.h       |  14 ++-
 src/test/regress/expected/rules.out       |  19 ++++
 src/test/regress/expected/stats.out       |  44 ++++++++-
 src/test/regress/sql/stats.sql            |  25 ++++-
 13 files changed, 368 insertions(+), 33 deletions(-)
   8.4% doc/src/sgml/
  29.9% src/backend/utils/activity/
  23.7% src/backend/utils/adt/
   4.4% src/include/catalog/
   3.1% src/include/utils/
   3.1% src/include/
  14.3% src/test/regress/expected/
   9.9% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 0aec11f443..2a59b97093 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8331,7 +8331,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
+        <structname>pg_stat_io</structname></link>,
+        <link linkend="monitoring-pg-my-stat-io-view">
+        <structname>pg_my_stat_io</structname></link>, in the output of
         <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
         is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 933de6fe07..b28ca4e0ca 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -488,6 +488,16 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_my_stat_io</structname><indexterm><primary>pg_my_stat_io</primary></indexterm></entry>
+      <entry>
+       One row for each combination of context and target object containing
+       my backend I/O statistics.
+       See <link linkend="monitoring-pg-my-stat-io-view">
+       <structname>pg_my_stat_io</structname></link> for details.
+     </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
       <entry>One row per replication slot, showing statistics about the
@@ -2948,6 +2958,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
 
 
 
+ </sect2>
+
+ <sect2 id="monitoring-pg-my-stat-io-view">
+  <title><structname>pg_my_stat_io</structname></title>
+
+  <indexterm>
+   <primary>pg_my_stat_io</primary>
+  </indexterm>
+
+  <para>
+   The <structname>pg_my_stat_io</structname> view will contain one row for each
+   combination of target I/O object and I/O context, showing
+   my backend I/O statistics. Combinations which do not make sense are
+   omitted. The fields are exactly the same as the ones in the <link
+   linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+   view.
+  </para>
+
  </sect2>
 
  <sect2 id="monitoring-pg-stat-bgwriter-view">
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 7fd5d256a1..b4939b7bc6 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1168,6 +1168,28 @@ SELECT
        b.stats_reset
 FROM pg_stat_get_io() b;
 
+CREATE VIEW pg_my_stat_io AS
+SELECT
+       b.backend_type,
+       b.object,
+       b.context,
+       b.reads,
+       b.read_time,
+       b.writes,
+       b.write_time,
+       b.writebacks,
+       b.writeback_time,
+       b.extends,
+       b.extend_time,
+       b.op_bytes,
+       b.hits,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.fsync_time,
+       b.stats_reset
+FROM pg_stat_get_my_io() b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index a7f2dfc744..fda4ca9a4a 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -406,10 +406,12 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 
-		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
+		.init_backend_cb = pgstat_io_init_backend_cb,
+		.snapshot_ctl_off = offsetof(PgStat_Snapshot, global_io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
-		.shared_data_off = offsetof(PgStatShared_IO, stats),
-		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
+		/* [de-]serialize global_stats only */
+		.shared_data_off = offsetof(PgStatShared_IO, global_stats),
+		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->global_stats),
 
 		.flush_fixed_cb = pgstat_io_flush_cb,
 		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
@@ -587,6 +589,9 @@ pgstat_shutdown_hook(int code, Datum arg)
 
 	pgstat_report_stat(true);
 
+	/* reset the pgstat_io counter related to this proc number */
+	pgstat_reset_io_counter_internal(MyProcNumber, 0);
+
 	/* there shouldn't be any pending changes left */
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index cc2ffc78aa..d32121fc1f 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -31,6 +31,7 @@ typedef struct PgStat_PendingIO
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
+void		pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Check that stats have not been counted for any combination of IOObject,
@@ -154,11 +155,19 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 }
 
 PgStat_IO *
-pgstat_fetch_stat_io(void)
+pgstat_fetch_global_stat_io(void)
 {
 	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
 
-	return &pgStatLocal.snapshot.io;
+	return &pgStatLocal.snapshot.global_io;
+}
+
+PgStat_Backend_IO *
+pgstat_fetch_my_stat_io(void)
+{
+	pgstat_snapshot_fixed(PGSTAT_KIND_IO);
+
+	return &pgStatLocal.snapshot.my_io;
 }
 
 /*
@@ -192,13 +201,16 @@ pgstat_io_flush_cb(bool nowait)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
+	PgStat_BktypeIO *global_bktype_shstats;
 
 	if (!have_iostats)
 		return false;
 
 	bktype_lock = &pgStatLocal.shmem->io.locks[MyBackendType];
 	bktype_shstats =
-		&pgStatLocal.shmem->io.stats.stats[MyBackendType];
+		&pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	global_bktype_shstats =
+		&pgStatLocal.shmem->io.global_stats.stats[MyBackendType];
 
 	if (!nowait)
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
@@ -212,19 +224,28 @@ pgstat_io_flush_cb(bool nowait)
 			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
 			{
 				instr_time	time;
+				PgStat_Counter counter;
+
+				counter = PendingIOStats.counts[io_object][io_context][io_op];
 
-				bktype_shstats->counts[io_object][io_context][io_op] +=
-					PendingIOStats.counts[io_object][io_context][io_op];
+				bktype_shstats->counts[io_object][io_context][io_op] += counter;
+
+				global_bktype_shstats->counts[io_object][io_context][io_op] +=
+					counter;
 
 				time = PendingIOStats.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
+
+				global_bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
 
 	Assert(pgstat_bktype_io_stats_valid(bktype_shstats, MyBackendType));
+	Assert(pgstat_bktype_io_stats_valid(global_bktype_shstats, MyBackendType));
 
 	LWLockRelease(bktype_lock);
 
@@ -278,13 +299,35 @@ pgstat_io_init_shmem_cb(void *stats)
 		LWLockInitialize(&stat_shmem->locks[i], LWTRANCHE_PGSTATS_DATA);
 }
 
+void
+pgstat_reset_io_counter_internal(int index, TimestampTz ts)
+{
+	LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[0];
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[index].stats;
+
+
+	/*
+	 * Use the lock in the first BackendType's PgStat_BktypeIO to protect the
+	 * reset timestamp as well.
+	 */
+	LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
+
+	pgStatLocal.shmem->io.stat[index].stat_reset_timestamp = ts;
+
+	memset(bktype_shstats, 0, sizeof(*bktype_shstats));
+	LWLockRelease(bktype_lock);
+}
+
 void
 pgstat_io_reset_all_cb(TimestampTz ts)
 {
+	for (int i = 0; i < NumProcStatSlots; i++)
+		pgstat_reset_io_counter_internal(i, ts);
+
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
+		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
 
@@ -293,7 +336,7 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.shmem->io.stats.stat_reset_timestamp = ts;
+			pgStatLocal.shmem->io.global_stats.stat_reset_timestamp = ts;
 
 		memset(bktype_shstats, 0, sizeof(*bktype_shstats));
 		LWLockRelease(bktype_lock);
@@ -303,11 +346,28 @@ pgstat_io_reset_all_cb(TimestampTz ts)
 void
 pgstat_io_snapshot_cb(void)
 {
+	/* First, our own stats */
+	PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stat[MyProcNumber].stats;
+	PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.my_io.stats;
+	LWLock	   *mybktype_lock = &pgStatLocal.shmem->io.locks[0];
+
+	LWLockAcquire(mybktype_lock, LW_SHARED);
+
+	pgStatLocal.snapshot.my_io.stat_reset_timestamp =
+		pgStatLocal.shmem->io.stat[MyProcNumber].stat_reset_timestamp;
+
+	pgStatLocal.snapshot.my_io.bktype =
+		pgStatLocal.shmem->io.stat[MyProcNumber].bktype;
+
+	*bktype_snap = *bktype_shstats;
+	LWLockRelease(mybktype_lock);
+
+	/* Now, the global stats */
 	for (int i = 0; i < BACKEND_NUM_TYPES; i++)
 	{
 		LWLock	   *bktype_lock = &pgStatLocal.shmem->io.locks[i];
-		PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i];
-		PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.io.stats[i];
+		PgStat_BktypeIO *bktype_global_shstats = &pgStatLocal.shmem->io.global_stats.stats[i];
+		PgStat_BktypeIO *bktype_global_snap = &pgStatLocal.snapshot.global_io.stats[i];
 
 		LWLockAcquire(bktype_lock, LW_SHARED);
 
@@ -316,11 +376,11 @@ pgstat_io_snapshot_cb(void)
 		 * the reset timestamp as well.
 		 */
 		if (i == 0)
-			pgStatLocal.snapshot.io.stat_reset_timestamp =
-				pgStatLocal.shmem->io.stats.stat_reset_timestamp;
+			pgStatLocal.snapshot.global_io.stat_reset_timestamp =
+				pgStatLocal.shmem->io.global_stats.stat_reset_timestamp;
 
 		/* using struct assignment due to better type safety */
-		*bktype_snap = *bktype_shstats;
+		*bktype_global_snap = *bktype_global_shstats;
 		LWLockRelease(bktype_lock);
 	}
 }
@@ -503,3 +563,12 @@ pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 
 	return true;
 }
+
+void
+pgstat_io_init_backend_cb(void)
+{
+	/* Initialize our backend type in the IO statistics */
+	pgStatLocal.shmem->io.stat[MyProcNumber].bktype = MyBackendType;
+	/* Set the stat_reset_timestamp to zero */
+	pgStatLocal.shmem->io.stat[MyProcNumber].stat_reset_timestamp = 0;
+}
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index ec93bf6902..3cfcba9609 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -128,7 +128,7 @@ StatsShmemSize(void)
 {
 	Size		sz;
 
-	sz = MAXALIGN(sizeof(PgStat_ShmemControl));
+	sz = MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 	sz = add_size(sz, pgstat_dsa_init_size());
 
 	/* Add shared memory for all the custom fixed-numbered statistics */
@@ -172,7 +172,7 @@ StatsShmemInit(void)
 		Assert(!found);
 
 		/* the allocation of pgStatLocal.shmem itself */
-		p += MAXALIGN(sizeof(PgStat_ShmemControl));
+		p += MAXALIGN(sizeof(PgStat_ShmemControl) + mul_size(sizeof(PgStat_Backend_IO), NumProcStatSlots));
 
 		/*
 		 * Create a small dsa allocation in plain shared memory. This is
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 33c7b25560..4c00570396 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1363,14 +1363,17 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
 
-	backends_io_stats = pgstat_fetch_stat_io();
+	backends_io_stats = pgstat_fetch_global_stat_io();
 
 	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
 
 	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
 	{
-		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
-		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
+		Datum		bktype_desc;
+		PgStat_BktypeIO *bktype_stats;
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backends_io_stats->stats[bktype];
 
 		/*
 		 * In Assert builds, we can afford an extra loop through all of the
@@ -1462,6 +1465,111 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_my_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backend_io_stats = pgstat_fetch_my_stat_io();
+
+	bktype = backend_io_stats->bktype;
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_io_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_io_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 53a081ed88..4d5af3d7cf 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5880,6 +5880,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: My backend IO statistics',
+  proname => 'pg_stat_get_my_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => '',
+  proallargtypes => '{text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_my_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index be2c91168a..9d63b1a5b7 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -16,6 +16,7 @@
 #include "portability/instr_time.h"
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
+#include "storage/proc.h"
 #include "utils/backend_progress.h" /* for backward compatibility */
 #include "utils/backend_status.h"	/* for backward compatibility */
 #include "utils/relcache.h"
@@ -76,6 +77,8 @@
  */
 #define PGSTAT_KIND_EXPERIMENTAL	128
 
+#define  NumProcStatSlots (MaxBackends + NUM_AUXILIARY_PROCS)
+
 static inline bool
 pgstat_is_kind_builtin(PgStat_Kind kind)
 {
@@ -351,6 +354,12 @@ typedef struct PgStat_IO
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend_IO
+{
+	TimestampTz stat_reset_timestamp;
+	BackendType bktype;
+	PgStat_BktypeIO stats;
+} PgStat_Backend_IO;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -559,7 +568,8 @@ extern instr_time pgstat_prepare_io_time(bool track_io_guc);
 extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 									IOOp io_op, instr_time start_time, uint32 cnt);
 
-extern PgStat_IO *pgstat_fetch_stat_io(void);
+extern PgStat_IO *pgstat_fetch_global_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
@@ -568,7 +578,7 @@ extern bool pgstat_tracks_io_object(BackendType bktype,
 									IOObject io_object, IOContext io_context);
 extern bool pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 								IOContext io_context, IOOp io_op);
-
+extern void pgstat_reset_io_counter_internal(int index, TimestampTz ts);
 
 /*
  * Functions in pgstat_database.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index bba90e898d..ea4cc6a2c6 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -366,11 +366,12 @@ typedef struct PgStatShared_Checkpointer
 typedef struct PgStatShared_IO
 {
 	/*
-	 * locks[i] protects stats.stats[i]. locks[0] also protects
-	 * stats.stat_reset_timestamp.
+	 * locks[i] protects global_stats.stats[i]. locks[0] also protects
+	 * global_stats.stat_reset_timestamp.
 	 */
 	LWLock		locks[BACKEND_NUM_TYPES];
-	PgStat_IO	stats;
+	PgStat_IO	global_stats;
+	PgStat_Backend_IO	stat[FLEXIBLE_ARRAY_MEMBER];
 } PgStatShared_IO;
 
 typedef struct PgStatShared_SLRU
@@ -463,7 +464,6 @@ typedef struct PgStat_ShmemControl
 	PgStatShared_Archiver archiver;
 	PgStatShared_BgWriter bgwriter;
 	PgStatShared_Checkpointer checkpointer;
-	PgStatShared_IO io;
 	PgStatShared_SLRU slru;
 	PgStatShared_Wal wal;
 
@@ -473,6 +473,8 @@ typedef struct PgStat_ShmemControl
 	 */
 	void	   *custom_data[PGSTAT_KIND_CUSTOM_SIZE];
 
+	/* has to be at the end due to FLEXIBLE_ARRAY_MEMBER */
+	PgStatShared_IO io;
 } PgStat_ShmemControl;
 
 
@@ -494,7 +496,8 @@ typedef struct PgStat_Snapshot
 
 	PgStat_CheckpointerStats checkpointer;
 
-	PgStat_IO	io;
+	PgStat_Backend_IO	my_io;
+	PgStat_IO	global_io;
 
 	PgStat_SLRUStats slru[SLRU_NUM_ELEMENTS];
 
@@ -629,6 +632,7 @@ extern bool pgstat_io_flush_cb(bool nowait);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
+extern void pgstat_io_init_backend_cb(void);
 
 
 /*
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index a1626f3fae..785298d7b0 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1398,6 +1398,25 @@ pg_matviews| SELECT n.nspname AS schemaname,
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN pg_tablespace t ON ((t.oid = c.reltablespace)))
   WHERE (c.relkind = 'm'::"char");
+pg_my_stat_io| SELECT backend_type,
+    object,
+    context,
+    reads,
+    read_time,
+    writes,
+    write_time,
+    writebacks,
+    writeback_time,
+    extends,
+    extend_time,
+    op_bytes,
+    hits,
+    evictions,
+    reuses,
+    fsyncs,
+    fsync_time,
+    stats_reset
+   FROM pg_stat_get_my_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 6e08898b18..c489e528e0 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1261,9 +1261,14 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1285,16 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1314,23 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1551,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1567,14 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index d8ac0d06f4..c95cb71652 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my]_stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -609,18 +609,26 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,7 +638,13 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
-
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -762,10 +776,15 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
 
 
 -- test BRIN index doesn't block HOT update
-- 
2.34.1

From 1988e754cec0771c8fc207c266ddea9dda5e70aa Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 28 Aug 2024 12:59:02 +0000
Subject: [PATCH v4 2/2] Add pg_stat_get_backend_io()

Adding the pg_stat_get_backend_io() function to retrieve I/O statistics for
a particular backend pid. Note this function behaves as if stats_fetch_consistency
is set to none.
---
 doc/src/sgml/monitoring.sgml           |  18 ++++
 src/backend/utils/activity/pgstat_io.c |   6 ++
 src/backend/utils/adt/pgstatfuncs.c    | 120 +++++++++++++++++++++++++
 src/include/catalog/pg_proc.dat        |   9 ++
 src/include/pgstat.h                   |   1 +
 src/test/regress/expected/stats.out    |  25 ++++++
 src/test/regress/sql/stats.sql         |  16 +++-
 7 files changed, 194 insertions(+), 1 deletion(-)
  10.9% doc/src/sgml/
  47.1% src/backend/utils/adt/
   9.2% src/include/catalog/
  15.4% src/test/regress/expected/
  14.4% src/test/regress/sql/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index b28ca4e0ca..fb908172f8 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4770,6 +4770,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. This function behaves as if <varname>stats_fetch_consistency</varname>
+        is set to <literal>none</literal> (means each execution re-fetches
+        counters from shared memory).
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index d32121fc1f..9764fd399b 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -170,6 +170,12 @@ pgstat_fetch_my_stat_io(void)
 	return &pgStatLocal.snapshot.my_io;
 }
 
+PgStat_Backend_IO *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	return &pgStatLocal.shmem->io.stat[procNumber];
+}
+
 /*
  * Check if there any IO stats waiting for flush.
  */
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 4c00570396..795ff4e2f6 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1570,6 +1570,126 @@ pg_stat_get_my_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend_IO *backend_io_stats;
+	Datum		reset_time;
+	ProcNumber	procNumber;
+	PGPROC	   *proc;
+	BackendType bktype;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+	InitMaterializedSRF(fcinfo, 0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/* Maybe an auxiliary process? */
+	if (proc == NULL)
+		proc = AuxiliaryPidGetProc(backend_pid);
+
+	/* This backend_pid does not exist */
+	if (proc != NULL)
+	{
+		procNumber = GetNumberFromPGProc(proc);
+		backend_io_stats = pgstat_fetch_proc_stat_io(procNumber);
+		bktype = backend_io_stats->bktype;
+		reset_time = TimestampTzGetDatum(backend_io_stats->stat_reset_timestamp);
+
+		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+		bktype_stats = &backend_io_stats->stats;
+
+		/*
+		 * In Assert builds, we can afford an extra loop through all of the
+		 * counters checking that only expected stats are non-zero, since it
+		 * keeps the non-Assert code cleaner.
+		 */
+		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+		for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+		{
+			const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+			for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+			{
+				const char *context_name = pgstat_get_io_context_name(io_context);
+
+				Datum		values[IO_NUM_COLUMNS] = {0};
+				bool		nulls[IO_NUM_COLUMNS] = {0};
+
+				/*
+				 * Some combinations of BackendType, IOObject, and IOContext
+				 * are not valid for any type of IOOp. In such cases, omit the
+				 * entire row from the view.
+				 */
+				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+					continue;
+
+				values[IO_COL_BACKEND_TYPE] = bktype_desc;
+				values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+				values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+				if (backend_io_stats->stat_reset_timestamp != 0)
+					values[IO_COL_RESET_TIME] = reset_time;
+				else
+					nulls[IO_COL_RESET_TIME] = true;
+
+				/*
+				 * Hard-code this to the value of BLCKSZ for now. Future
+				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
+				 * and constant multipliers, once non-block-oriented IO (e.g.
+				 * temporary file IO) is tracked.
+				 */
+				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+				for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+				{
+					int			op_idx = pgstat_get_io_op_index(io_op);
+					int			time_idx = pgstat_get_io_time_index(io_op);
+
+					/*
+					 * Some combinations of BackendType and IOOp, of IOContext
+					 * and IOOp, and of IOObject and IOOp are not tracked. Set
+					 * these cells in the view NULL.
+					 */
+					if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+					{
+						PgStat_Counter count =
+							bktype_stats->counts[io_obj][io_context][io_op];
+
+						values[op_idx] = Int64GetDatum(count);
+					}
+					else
+						nulls[op_idx] = true;
+
+					/* not every operation is timed */
+					if (time_idx == IO_COL_INVALID)
+						continue;
+
+					if (!nulls[op_idx])
+					{
+						PgStat_Counter time =
+							bktype_stats->times[io_obj][io_context][io_op];
+
+						values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+					}
+					else
+						nulls[time_idx] = true;
+				}
+
+				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+									 values, nulls);
+			}
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 4d5af3d7cf..c4295f7c4d 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5889,6 +5889,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_my_io' },
 
+{ oid => '8896', descr => 'statistics: per backend type IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '30', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9d63b1a5b7..2a2b4a2947 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -570,6 +570,7 @@ extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 
 extern PgStat_IO *pgstat_fetch_global_stat_io(void);
 extern PgStat_Backend_IO *pgstat_fetch_my_stat_io(void);
+extern PgStat_Backend_IO *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index c489e528e0..aced015c2f 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1263,12 +1263,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1293,6 +1299,15 @@ SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
@@ -1553,6 +1568,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1575,6 +1592,14 @@ SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index c95cb71652..d05009e1f5 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -611,12 +611,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -626,6 +632,10 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
 SELECT sum(extends) AS my_io_sum_shared_after_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
@@ -778,6 +788,8 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_io \gset
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
   FROM pg_my_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
@@ -785,7 +797,9 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
   FROM pg_my_stat_io \gset
 SELECT :my_io_stats_post_reset < :my_io_stats_pre_reset;
-
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS backend_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :backend_io_stats_post_reset < :backend_io_stats_pre_reset;
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
-- 
2.34.1

From 89de6e71540912ca294be38fea0ed5636b718521 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v5 1/4] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds a new
statistics kind and a new pg_my_stat_io view to display "my" backend I/O statistics.

The new KIND is named PGSTAT_KIND_PER_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to serialize the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so a
new "to_serialize" field is added in the PgStat_KindInfo struct.

Also adding a new function pg_stat_reset_single_backend_io_counters() to be
able to reset the I/O stats for a given backend pid.

A subsequent commit will add a new pg_stat_get_backend_io() function to be
able to retrieve the I/O statistics for a given backend pid.

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                      |   4 +-
 doc/src/sgml/monitoring.sgml                  |  43 ++++++
 src/backend/catalog/system_functions.sql      |   2 +
 src/backend/catalog/system_views.sql          |  22 ++++
 src/backend/utils/activity/backend_status.c   |   3 +
 src/backend/utils/activity/pgstat.c           |  34 ++++-
 src/backend/utils/activity/pgstat_io.c        | 114 ++++++++++++++--
 src/backend/utils/activity/pgstat_shmem.c     |  30 ++++-
 src/backend/utils/adt/pgstatfuncs.c           | 124 ++++++++++++++++++
 src/include/catalog/pg_proc.dat               |  14 ++
 src/include/pgstat.h                          |  27 +++-
 src/include/utils/pgstat_internal.h           |  13 ++
 .../injection_points/injection_stats.c        |   1 +
 src/test/regress/expected/rules.out           |  19 +++
 src/test/regress/expected/stats.out           |  60 ++++++++-
 src/test/regress/sql/stats.sql                |  31 ++++-
 src/tools/pgindent/typedefs.list              |   2 +
 17 files changed, 517 insertions(+), 26 deletions(-)
  10.2% doc/src/sgml/
  29.7% src/backend/utils/activity/
  19.2% src/backend/utils/adt/
   5.1% src/include/catalog/
   7.2% src/include/
  14.7% src/test/regress/expected/
  10.4% src/test/regress/sql/
   3.1% src/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index d54f904956..fbabf371a6 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8361,7 +8361,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
+        <structname>pg_stat_io</structname></link>,
+        <link linkend="monitoring-pg-my-stat-io-view">
+        <structname>pg_my_stat_io</structname></link>, in the output of
         <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
         is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 331315f8d3..fc6aded3da 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -488,6 +488,16 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_my_stat_io</structname><indexterm><primary>pg_my_stat_io</primary></indexterm></entry>
+      <entry>
+       One row for each combination of context and target object containing
+       my backend I/O statistics.
+       See <link linkend="monitoring-pg-my-stat-io-view">
+       <structname>pg_my_stat_io</structname></link> for details.
+     </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
       <entry>One row per replication slot, showing statistics about the
@@ -2946,7 +2956,23 @@ description | Waiting for a newly initialized WAL file to reach durable storage
    </para>
   </note>
 
+ </sect2>
 
+ <sect2 id="monitoring-pg-my-stat-io-view">
+  <title><structname>pg_my_stat_io</structname></title>
+
+  <indexterm>
+   <primary>pg_my_stat_io</primary>
+  </indexterm>
+
+  <para>
+   The <structname>pg_my_stat_io</structname> view will contain one row for each
+   combination of target I/O object and I/O context, showing
+   my backend I/O statistics. Combinations which do not make sense are
+   omitted. The fields are exactly the same as the ones in the <link
+   linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+   view.
+  </para>
 
  </sect2>
 
@@ -4971,6 +4997,23 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_single_backend_io_counters</primary>
+        </indexterm>
+        <function>pg_stat_reset_single_backend_io_counters</function> ( <type>int4</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets I/O statistics for a single backend to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..8a1ae44fca 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_backend_io_counters(int4) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 3456b821bc..09af4a40a8 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1170,6 +1170,28 @@ SELECT
        b.stats_reset
 FROM pg_stat_get_io() b;
 
+CREATE VIEW pg_my_stat_io AS
+SELECT
+       b.backend_type,
+       b.object,
+       b.context,
+       b.reads,
+       b.read_time,
+       b.writes,
+       b.write_time,
+       b.writebacks,
+       b.writeback_time,
+       b.extends,
+       b.extend_time,
+       b.op_bytes,
+       b.hits,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.fsync_time,
+       b.stats_reset
+FROM pg_stat_get_my_io() b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index bdb3a296ca..aa683e150c 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -249,6 +249,9 @@ pgstat_beinit(void)
 	Assert(MyProcNumber >= 0 && MyProcNumber < NumBackendStatSlots);
 	MyBEEntry = &BackendStatusArray[MyProcNumber];
 
+	/* Create the per backend stat entry */
+	pgstat_create_backend_stat(MyProcNumber);
+
 	/* Set up a process-exit hook to clean up */
 	on_shmem_exit(pgstat_beshutdown_hook, 0);
 }
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index ea8c5691e8..aacf61c9a4 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -281,6 +281,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "database",
 
 		.fixed_amount = false,
+		.to_serialize = true,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -297,6 +298,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "relation",
 
 		.fixed_amount = false,
+		.to_serialize = true,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -311,6 +313,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "function",
 
 		.fixed_amount = false,
+		.to_serialize = true,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -324,6 +327,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "replslot",
 
 		.fixed_amount = false,
+		.to_serialize = true,
 
 		.accessed_across_databases = true,
 
@@ -340,6 +344,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "subscription",
 
 		.fixed_amount = false,
+		.to_serialize = true,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -352,6 +357,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_PER_BACKEND] = {
+		.name = "perbackend",
+
+		.fixed_amount = false,
+		.to_serialize = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_PendingIO),
+
+		.flush_pending_cb = pgstat_per_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -359,6 +380,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "archiver",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -374,6 +396,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "bgwriter",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -389,6 +412,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "checkpointer",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -404,6 +428,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "io",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -421,6 +446,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "slru",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -438,6 +464,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.name = "wal",
 
 		.fixed_amount = true,
+		.to_serialize = true,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -515,7 +542,7 @@ pgstat_discard_stats(void)
 
 	/*
 	 * Reset stats contents. This will set reset timestamps of fixed-numbered
-	 * stats to the current time (no variable stats exist).
+	 * stats to the current time (the per-backend variable stat exists too).
 	 */
 	pgstat_reset_after_failure();
 }
@@ -756,7 +783,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / backend / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of fixed-numbered stats */
@@ -1660,6 +1687,9 @@ pgstat_write_statsfile(XLogRecPtr redo)
 
 		kind_info = pgstat_get_kind_info(ps->key.kind);
 
+		if (!kind_info->to_serialize)
+			continue;
+
 		/* if not dropped the valid-entry refcount should exist */
 		Assert(pg_atomic_read_u32(&ps->refcount) > 0);
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index cc2ffc78aa..a2bb11adc9 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -21,13 +21,6 @@
 #include "utils/pgstat_internal.h"
 
 
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
-
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
@@ -82,12 +75,17 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op)
 void
 pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint32 cnt)
 {
+	PgStat_PendingIO *entry_ref;
+
 	Assert((unsigned int) io_object < IOOBJECT_NUM_TYPES);
 	Assert((unsigned int) io_context < IOCONTEXT_NUM_TYPES);
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
+	entry_ref->counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
 }
@@ -122,6 +120,10 @@ void
 pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 						instr_time start_time, uint32 cnt)
 {
+	PgStat_PendingIO *entry_ref;
+
+	entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+
 	if (track_io_timing)
 	{
 		instr_time	io_time;
@@ -148,6 +150,8 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+		INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+					   io_time);
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
@@ -161,6 +165,13 @@ pgstat_fetch_stat_io(void)
 	return &pgStatLocal.snapshot.io;
 }
 
+PgStat_Backend *
+pgstat_fetch_my_stat_io(void)
+{
+	return (PgStat_Backend *)
+		pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid, MyProcNumber);
+}
+
 /*
  * Check if there any IO stats waiting for flush.
  */
@@ -171,12 +182,18 @@ pgstat_io_have_pending_cb(void)
 }
 
 /*
- * Simpler wrapper of pgstat_io_flush_cb()
+ * Simpler wrapper of pgstat_io_flush_cb() and pgstat_per_backend_flush_cb().
  */
 void
 pgstat_flush_io(bool nowait)
 {
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+									 MyProcNumber, false, NULL);
+
 	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_per_backend_flush_cb(entry_ref, nowait);
 }
 
 /*
@@ -235,6 +252,49 @@ pgstat_io_flush_cb(bool nowait)
 	return false;
 }
 
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_PendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_PendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
 const char *
 pgstat_get_io_context_name(IOContext io_context)
 {
@@ -325,6 +385,38 @@ pgstat_io_snapshot_cb(void)
 	}
 }
 
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+
+	/* set the backend type */
+	shstatent->stats.bktype = MyBackendType;
+}
+
+PgStat_PendingIO *
+pgstat_prep_per_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
 /*
 * IO statistics are not collected for all BackendTypes.
 *
@@ -503,3 +595,9 @@ pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 
 	return true;
 }
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c
index c1b7ff76b1..b871c1d7d0 100644
--- a/src/backend/utils/activity/pgstat_shmem.c
+++ b/src/backend/utils/activity/pgstat_shmem.c
@@ -813,13 +813,24 @@ pgstat_free_entry(PgStatShared_HashEntry *shent, dshash_seq_status *hstat)
  */
 static bool
 pgstat_drop_entry_internal(PgStatShared_HashEntry *shent,
-						   dshash_seq_status *hstat)
+						   dshash_seq_status *hstat, bool ignore_aux_proc)
 {
 	Assert(shent->body != InvalidDsaPointer);
 
 	/* should already have released local reference */
 	if (pgStatEntryRefHash)
-		Assert(!pgstat_entry_ref_hash_lookup(pgStatEntryRefHash, shent->key));
+	{
+		/*
+		 * The following assertion is not correct when coming from
+		 * pgstat_discard_stats() and for per backend stats linked to an
+		 * auxiliary process.
+		 */
+		if (ignore_aux_proc && shent->key.kind == PGSTAT_KIND_PER_BACKEND &&
+			MyProcNumber >= MaxBackends)
+			return false;
+		else
+			Assert(!pgstat_entry_ref_hash_lookup(pgStatEntryRefHash, shent->key));
+	}
 
 	/*
 	 * Signal that the entry is dropped - this will eventually cause other
@@ -882,7 +893,7 @@ pgstat_drop_database_and_contents(Oid dboid)
 		if (p->key.dboid != dboid)
 			continue;
 
-		if (!pgstat_drop_entry_internal(p, &hstat))
+		if (!pgstat_drop_entry_internal(p, &hstat, false))
 		{
 			/*
 			 * Even statistics for a dropped database might currently be
@@ -941,7 +952,7 @@ pgstat_drop_entry(PgStat_Kind kind, Oid dboid, uint64 objid)
 	shent = dshash_find(pgStatLocal.shared_hash, &key, true);
 	if (shent)
 	{
-		freed = pgstat_drop_entry_internal(shent, NULL);
+		freed = pgstat_drop_entry_internal(shent, NULL, false);
 
 		/*
 		 * Database stats contain other stats. Drop those as well when
@@ -969,7 +980,7 @@ pgstat_drop_all_entries(void)
 		if (ps->dropped)
 			continue;
 
-		if (!pgstat_drop_entry_internal(ps, &hstat))
+		if (!pgstat_drop_entry_internal(ps, &hstat, true))
 			not_freed_count++;
 	}
 	dshash_seq_term(&hstat);
@@ -982,11 +993,20 @@ static void
 shared_stat_reset_contents(PgStat_Kind kind, PgStatShared_Common *header,
 						   TimestampTz ts)
 {
+	BackendType bktype;
 	const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
+	/* save the bktype */
+	if (kind == PGSTAT_KIND_PER_BACKEND)
+		bktype = ((PgStatShared_Backend *) header)->stats.bktype;
+
 	memset(pgstat_get_entry_data(kind, header), 0,
 		   pgstat_get_entry_len(kind));
 
+	/* restore the bktype */
+	if (kind == PGSTAT_KIND_PER_BACKEND)
+		((PgStatShared_Backend *) header)->stats.bktype = bktype;
+
 	if (kind_info->reset_timestamp_cb)
 		kind_info->reset_timestamp_cb(header, ts);
 }
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index f7b50e0b5a..fd16986156 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,111 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_my_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backend_stats = pgstat_fetch_my_stat_io();
+
+	bktype = backend_stats->bktype;
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1722,6 +1827,7 @@ pg_stat_reset_shared(PG_FUNCTION_ARGS)
 		pgstat_reset_of_kind(PGSTAT_KIND_BGWRITER);
 		pgstat_reset_of_kind(PGSTAT_KIND_CHECKPOINTER);
 		pgstat_reset_of_kind(PGSTAT_KIND_IO);
+		pgstat_reset_of_kind(PGSTAT_KIND_PER_BACKEND);
 		XLogPrefetchResetStats();
 		pgstat_reset_of_kind(PGSTAT_KIND_SLRU);
 		pgstat_reset_of_kind(PGSTAT_KIND_WAL);
@@ -1779,6 +1885,24 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_single_backend_io_counters(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/* Maybe an auxiliary process? */
+	if (proc == NULL)
+		proc = AuxiliaryPidGetProc(backend_pid);
+
+	if (proc)
+		pgstat_reset(PGSTAT_KIND_PER_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index f23321a41f..89eb89efe4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5903,6 +5903,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: my backend IO statistics',
+  proname => 'pg_stat_get_my_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => '',
+  proallargtypes => '{text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_my_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6042,6 +6051,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset collected IO statistics for a single backend',
+  proname => 'pg_stat_reset_single_backend_io_counters', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_single_backend_io_counters' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index df53fa2d4f..13b9c71759 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_PER_BACKEND	6
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -347,12 +348,24 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_PendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_PendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	BackendType bktype;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -562,6 +575,7 @@ extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 									IOOp io_op, instr_time start_time, uint32 cnt);
 
 extern PgStat_IO *pgstat_fetch_stat_io(void);
+extern PgStat_Backend *pgstat_fetch_my_stat_io(void);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
@@ -570,6 +584,7 @@ extern bool pgstat_tracks_io_object(BackendType bktype,
 									IOObject io_object, IOContext io_context);
 extern bool pgstat_tracks_io_op(BackendType bktype, IOObject io_object,
 								IOContext io_context, IOOp io_op);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 
 /*
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 61b2e1f96b..44a00d4779 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -194,6 +194,11 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		accessed_across_databases:1;
 
+	/*
+	 * Do serialize or not this kind of stats.
+	 */
+	bool		to_serialize:1;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -428,6 +433,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -630,9 +640,12 @@ extern void pgstat_flush_io(bool nowait);
 
 extern bool pgstat_io_have_pending_cb(void);
 extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
+extern PgStat_PendingIO *pgstat_prep_per_backend_pending(ProcNumber procnum);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
 /*
diff --git a/src/test/modules/injection_points/injection_stats.c b/src/test/modules/injection_points/injection_stats.c
index d89d055913..ca4b6b6e9f 100644
--- a/src/test/modules/injection_points/injection_stats.c
+++ b/src/test/modules/injection_points/injection_stats.c
@@ -39,6 +39,7 @@ static bool injection_stats_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 static const PgStat_KindInfo injection_stats = {
 	.name = "injection_points",
 	.fixed_amount = false,		/* Bounded by the number of points */
+	.to_serialize = true,
 
 	/* Injection points are system-wide */
 	.accessed_across_databases = true,
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 2b47013f11..f92516b047 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1398,6 +1398,25 @@ pg_matviews| SELECT n.nspname AS schemaname,
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN pg_tablespace t ON ((t.oid = c.reltablespace)))
   WHERE (c.relkind = 'm'::"char");
+pg_my_stat_io| SELECT backend_type,
+    object,
+    context,
+    reads,
+    read_time,
+    writes,
+    write_time,
+    writebacks,
+    writeback_time,
+    extends,
+    extend_time,
+    op_bytes,
+    hits,
+    evictions,
+    reuses,
+    fsyncs,
+    fsync_time,
+    stats_reset
+   FROM pg_stat_get_my_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..846e693483 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my_]stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1261,9 +1261,14 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1285,16 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1314,23 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1551,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1567,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+ pg_stat_reset_single_backend_io_counters 
+------------------------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..9cb14b7182 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my_]stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -609,18 +609,26 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- extends.
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -631,6 +639,14 @@ SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -762,10 +778,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 1847bbfa95..4188d056ca 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2117,6 +2117,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2132,6 +2133,7 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From edd45c3aa0731a9645dbcfe0475e40c642e92269 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 6 Nov 2024 16:19:44 +0000
Subject: [PATCH v5 2/4] Merge both IO stats flush callbacks

There is no need to keep both callbacks.

Merging both allows to save O(N^3) while looping on IOOBJECT_NUM_TYPES,
IOCONTEXT_NUM_TYPES and IOCONTEXT_NUM_TYPES.
---
 src/backend/utils/activity/pgstat.c    |  2 -
 src/backend/utils/activity/pgstat_io.c | 97 ++++++--------------------
 2 files changed, 23 insertions(+), 76 deletions(-)
 100.0% src/backend/utils/activity/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index aacf61c9a4..d051db5c10 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -435,8 +435,6 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_IO, stats),
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_io_flush_cb,
-		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
 		.snapshot_cb = pgstat_io_snapshot_cb,
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index a2bb11adc9..1384f8103e 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -21,10 +21,6 @@
 #include "utils/pgstat_internal.h"
 
 
-static PgStat_PendingIO PendingIOStats;
-static bool have_iostats = false;
-
-
 /*
  * Check that stats have not been counted for any combination of IOObject,
  * IOContext, and IOOp which are not tracked for the passed-in BackendType. If
@@ -83,11 +79,7 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
 	entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
-
-	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 	entry_ref->counts[io_object][io_context][io_op] += cnt;
-
-	have_iostats = true;
 }
 
 /*
@@ -148,8 +140,6 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 				INSTR_TIME_ADD(pgBufferUsage.local_blk_read_time, io_time);
 		}
 
-		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
-					   io_time);
 		INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
 					   io_time);
 	}
@@ -173,16 +163,7 @@ pgstat_fetch_my_stat_io(void)
 }
 
 /*
- * Check if there any IO stats waiting for flush.
- */
-bool
-pgstat_io_have_pending_cb(void)
-{
-	return have_iostats;
-}
-
-/*
- * Simpler wrapper of pgstat_io_flush_cb() and pgstat_per_backend_flush_cb().
+ * Simpler wrapper of pgstat_per_backend_flush_cb().
  */
 void
 pgstat_flush_io(bool nowait)
@@ -192,81 +173,39 @@ pgstat_flush_io(bool nowait)
 	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_PER_BACKEND, InvalidOid,
 									 MyProcNumber, false, NULL);
 
-	(void) pgstat_io_flush_cb(nowait);
 	(void) pgstat_per_backend_flush_cb(entry_ref, nowait);
 }
 
 /*
- * Flush out locally pending IO statistics
+ * Flush out locally pending backend statistics
  *
  * If no stats have been recorded, this function returns false.
- *
- * If nowait is true, this function returns true if the lock could not be
- * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 {
-	LWLock	   *bktype_lock;
+	PgStatShared_Backend *shbackendioent;
+	PgStat_PendingIO *pendingent;
 	PgStat_BktypeIO *bktype_shstats;
+	LWLock	   *bktype_lock;
+	PgStat_BktypeIO *bktype_global_shstats;
 
-	if (!have_iostats)
+	if (!pgstat_lock_entry(entry_ref, nowait))
 		return false;
 
+	/* global IO stats */
 	bktype_lock = &pgStatLocal.shmem->io.locks[MyBackendType];
-	bktype_shstats =
-		&pgStatLocal.shmem->io.stats.stats[MyBackendType];
+	bktype_global_shstats = &pgStatLocal.shmem->io.stats.stats[MyBackendType];
 
 	if (!nowait)
 		LWLockAcquire(bktype_lock, LW_EXCLUSIVE);
 	else if (!LWLockConditionalAcquire(bktype_lock, LW_EXCLUSIVE))
-		return true;
-
-	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
 	{
-		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
-		{
-			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
-			{
-				instr_time	time;
-
-				bktype_shstats->counts[io_object][io_context][io_op] +=
-					PendingIOStats.counts[io_object][io_context][io_op];
-
-				time = PendingIOStats.pending_times[io_object][io_context][io_op];
-
-				bktype_shstats->times[io_object][io_context][io_op] +=
-					INSTR_TIME_GET_MICROSEC(time);
-			}
-		}
-	}
-
-	Assert(pgstat_bktype_io_stats_valid(bktype_shstats, MyBackendType));
-
-	LWLockRelease(bktype_lock);
-
-	memset(&PendingIOStats, 0, sizeof(PendingIOStats));
-
-	have_iostats = false;
-
-	return false;
-}
-
-/*
- * Flush out locally pending backend statistics
- *
- * If no stats have been recorded, this function returns false.
- */
-bool
-pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
-{
-	PgStatShared_Backend *shbackendioent;
-	PgStat_PendingIO *pendingent;
-	PgStat_BktypeIO *bktype_shstats;
-
-	if (!pgstat_lock_entry(entry_ref, nowait))
+		pgstat_unlock_entry(entry_ref);
 		return false;
+	}
 
+	/* per backend IO stats */
 	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
 	bktype_shstats = &shbackendioent->stats.stats;
 	pendingent = (PgStat_PendingIO *) entry_ref->pending;
@@ -279,6 +218,7 @@ pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 			{
 				instr_time	time;
 
+				/* per backend IO stats */
 				bktype_shstats->counts[io_object][io_context][io_op] +=
 					pendingent->counts[io_object][io_context][io_op];
 
@@ -286,10 +226,19 @@ pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
+
+				/* global IO stats */
+				bktype_global_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				bktype_global_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
 
+	LWLockRelease(bktype_lock);
+
 	pgstat_unlock_entry(entry_ref);
 
 	return true;
-- 
2.34.1

From 2d710a44af4d2758a0f33703893712693dfaf0af Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 7 Nov 2024 12:10:37 +0000
Subject: [PATCH v5 3/4] Don't include other backend's stats in the snapshot

When stats_fetch_consistency is set to 'snapshot', don't include other backend's
stats in the snapshot. There is no use case, so save memory usage.
---
 src/backend/utils/activity/pgstat.c | 4 ++++
 1 file changed, 4 insertions(+)
 100.0% src/backend/utils/activity/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index d051db5c10..4982dec8a9 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -1181,6 +1181,10 @@ pgstat_build_snapshot(void)
 			!kind_info->accessed_across_databases)
 			continue;
 
+		/* there is no need to include other backend's stats */
+		if (kind == PGSTAT_KIND_PER_BACKEND && p->key.objid != MyProcNumber)
+			continue;
+
 		if (p->dropped)
 			continue;
 
-- 
2.34.1

From 2bf372f079e9cbecd82ce431622f7e683f659596 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 7 Nov 2024 14:27:05 +0000
Subject: [PATCH v5 4/4] Add pg_stat_get_backend_io()

Adding the pg_stat_get_backend_io() function to retrieve I/O statistics for
a particular backend pid.

Note that this function does not return any rows if stats_fetch_consistency
is set to 'snapshot' and the pid of interest is not our own pid (there is no use
case of retrieving other backend's stats with stats_fetch_consistency set to
'snapshot').
---
 doc/src/sgml/monitoring.sgml           | 17 ++++++++
 src/backend/catalog/system_views.sql   |  2 +-
 src/backend/utils/activity/pgstat_io.c | 18 ++++++++
 src/backend/utils/adt/pgstatfuncs.c    | 27 +++++++++++-
 src/include/catalog/pg_proc.dat        | 14 +++----
 src/include/pgstat.h                   |  1 +
 src/test/regress/expected/rules.out    |  2 +-
 src/test/regress/expected/stats.out    | 57 ++++++++++++++++++++++++++
 src/test/regress/sql/stats.sql         | 33 +++++++++++++++
 9 files changed, 160 insertions(+), 11 deletions(-)
  10.4% doc/src/sgml/
   5.8% src/backend/utils/activity/
   8.6% src/backend/utils/adt/
  16.0% src/include/catalog/
  32.9% src/test/regress/expected/
  24.1% src/test/regress/sql/

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index fc6aded3da..a6672548b8 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4814,6 +4814,23 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. This function does not return any rows if <varname>stats_fetch_consistency</varname>
+        is set to <literal>snapshot</literal> and the process ID is not our own.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 09af4a40a8..6f17f505f1 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1190,7 +1190,7 @@ SELECT
        b.fsyncs,
        b.fsync_time,
        b.stats_reset
-FROM pg_stat_get_my_io() b;
+FROM pg_stat_get_backend_io(NULL) b;
 
 CREATE VIEW pg_stat_wal AS
     SELECT
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 1384f8103e..1063c6bec3 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -162,6 +162,24 @@ pgstat_fetch_my_stat_io(void)
 		pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid, MyProcNumber);
 }
 
+/*
+ * Returns other backend's IO stats or NULL if pgstat_fetch_consistency is set
+ * to 'snapshot'.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	if (pgstat_fetch_consistency == PGSTAT_FETCH_CONSISTENCY_SNAPSHOT)
+		return NULL;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
 /*
  * Simpler wrapper of pgstat_per_backend_flush_cb().
  */
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index fd16986156..e2041be237 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1475,7 +1475,7 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 }
 
 Datum
-pg_stat_get_my_io(PG_FUNCTION_ARGS)
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
 {
 	ReturnSetInfo *rsinfo;
 	PgStat_Backend *backend_stats;
@@ -1487,7 +1487,30 @@ pg_stat_get_my_io(PG_FUNCTION_ARGS)
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
 
-	backend_stats = pgstat_fetch_my_stat_io();
+	if (PG_ARGISNULL(0) || PG_GETARG_INT32(0) == MyProcPid)
+		backend_stats = pgstat_fetch_my_stat_io();
+	else
+	{
+		PGPROC	   *proc;
+		ProcNumber	procNumber;
+		int			pid = PG_GETARG_INT32(0);
+
+		proc = BackendPidGetProc(pid);
+
+		/* maybe an auxiliary process? */
+		if (proc == NULL)
+			proc = AuxiliaryPidGetProc(pid);
+
+		if (proc != NULL)
+		{
+			procNumber = GetNumberFromPGProc(proc);
+			backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+			if (!backend_stats)
+				return (Datum) 0;
+		}
+		else
+			return (Datum) 0;
+	}
 
 	bktype = backend_stats->bktype;
 	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 89eb89efe4..fafee5a947 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5903,14 +5903,14 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
-{ oid => '8806', descr => 'statistics: my backend IO statistics',
-  proname => 'pg_stat_get_my_io', prorows => '5', proretset => 't',
+{ oid => '8806', descr => 'statistics: per backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
   provolatile => 'v', proparallel => 'r', prorettype => 'record',
-  proargtypes => '',
-  proallargtypes => '{text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
-  proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
-  proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
-  prosrc => 'pg_stat_get_my_io' },
+  proargtypes => 'int4', proisstrict => 'f',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
 
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 13b9c71759..54c9f8b45c 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -576,6 +576,7 @@ extern void pgstat_count_io_op_time(IOObject io_object, IOContext io_context,
 
 extern PgStat_IO *pgstat_fetch_stat_io(void);
 extern PgStat_Backend *pgstat_fetch_my_stat_io(void);
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
 extern const char *pgstat_get_io_context_name(IOContext io_context);
 extern const char *pgstat_get_io_object_name(IOObject io_object);
 
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index f92516b047..3cc0cfbcb5 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1416,7 +1416,7 @@ pg_my_stat_io| SELECT backend_type,
     fsyncs,
     fsync_time,
     stats_reset
-   FROM pg_stat_get_my_io() b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
+   FROM pg_stat_get_backend_io(NULL::integer) b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 846e693483..846ffb59f2 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1263,12 +1263,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1293,6 +1299,15 @@ SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
@@ -1331,6 +1346,48 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+-- Check the stats_fetch_consistency behavior on per backend I/O stats
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
+BEGIN;
+SET LOCAL stats_fetch_consistency = snapshot;
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
+SELECT pg_stat_force_next_flush();
+ pg_stat_force_next_flush 
+--------------------------
+ 
+(1 row)
+
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends = :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends = :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats with snapshot set
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
+ROLLBACK;
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 9cb14b7182..e597c4d597 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -611,12 +611,18 @@ SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(extends) AS my_io_sum_shared_before_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_my_stat_io
   WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -626,6 +632,10 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
 SELECT sum(extends) AS my_io_sum_shared_after_extends
   FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
 -- and fsyncs in the global stats (not for the backend).
@@ -647,6 +657,29 @@ SELECT current_setting('fsync') = 'off'
   OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
       AND :my_io_sum_shared_after_fsyncs= 0);
 
+-- Check the stats_fetch_consistency behavior on per backend I/O stats
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
+BEGIN;
+SET LOCAL stats_fetch_consistency = snapshot;
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
+SELECT pg_stat_force_next_flush();
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends = :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends = :backend_io_sum_shared_before_extends;
+-- Don't return any rows if querying other backend's stats with snapshot set
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ROLLBACK;
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
-- 
2.34.1

From 21d773ae2b64571b09a77d6de4c955338cf979ae Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v6] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind, a new pg_my_stat_io view to display "my" backend
I/O statistics, and 2 new functions:

- pg_stat_reset_single_backend_io_counters() to be able to reset the I/O stats
for a given backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_PER_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                    |   4 +-
 doc/src/sgml/monitoring.sgml                |  63 ++++++
 src/backend/catalog/system_functions.sql    |   2 +
 src/backend/catalog/system_views.sql        |  22 +++
 src/backend/utils/activity/Makefile         |   1 +
 src/backend/utils/activity/backend_status.c |   4 +
 src/backend/utils/activity/meson.build      |   1 +
 src/backend/utils/activity/pgstat.c         |  19 +-
 src/backend/utils/activity/pgstat_backend.c | 176 +++++++++++++++++
 src/backend/utils/activity/pgstat_io.c      |  37 +++-
 src/backend/utils/adt/pgstatfuncs.c         | 208 ++++++++++++++++++++
 src/include/catalog/pg_proc.dat             |  14 ++
 src/include/pgstat.h                        |  32 ++-
 src/include/utils/pgstat_internal.h         |  12 ++
 src/test/regress/expected/rules.out         |  19 ++
 src/test/regress/expected/stats.out         |  85 +++++++-
 src/test/regress/sql/stats.sql              |  47 ++++-
 src/tools/pgindent/typedefs.list            |   3 +
 18 files changed, 729 insertions(+), 20 deletions(-)
  11.6% doc/src/sgml/
  27.0% src/backend/utils/activity/
  22.4% src/backend/utils/adt/
   4.0% src/include/catalog/
   5.9% src/include/
  14.9% src/test/regress/expected/
  11.4% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index a84e60c09b..20a0862661 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8365,7 +8365,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
+        <structname>pg_stat_io</structname></link>,
+        <link linkend="monitoring-pg-my-stat-io-view">
+        <structname>pg_my_stat_io</structname></link>, in the output of
         <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
         is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..8e7a7a0f36 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -488,6 +488,16 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
      </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_my_stat_io</structname><indexterm><primary>pg_my_stat_io</primary></indexterm></entry>
+      <entry>
+       One row for each combination of context and target object containing
+       my backend I/O statistics.
+       See <link linkend="monitoring-pg-my-stat-io-view">
+       <structname>pg_my_stat_io</structname></link> for details.
+     </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_replication_slots</structname><indexterm><primary>pg_stat_replication_slots</primary></indexterm></entry>
       <entry>One row per replication slot, showing statistics about the
@@ -2946,7 +2956,23 @@ description | Waiting for a newly initialized WAL file to reach durable storage
    </para>
   </note>
 
+ </sect2>
+
+ <sect2 id="monitoring-pg-my-stat-io-view">
+  <title><structname>pg_my_stat_io</structname></title>
+
+  <indexterm>
+   <primary>pg_my_stat_io</primary>
+  </indexterm>
 
+  <para>
+   The <structname>pg_my_stat_io</structname> view will contain one row for each
+   combination of target I/O object and I/O context, showing
+   my backend I/O statistics. Combinations which do not make sense are
+   omitted. The fields are exactly the same as the ones in the <link
+   linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+   view.
+  </para>
 
  </sect2>
 
@@ -4790,6 +4816,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +5016,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_single_backend_io_counters</primary>
+        </indexterm>
+        <function>pg_stat_reset_single_backend_io_counters</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets I/O statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..1b21b242cd 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_backend_io_counters(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index da9a8fe99f..fce3b791bb 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1172,6 +1172,28 @@ SELECT
        b.stats_reset
 FROM pg_stat_get_io() b;
 
+CREATE VIEW pg_my_stat_io AS
+SELECT
+       b.backend_type,
+       b.object,
+       b.context,
+       b.reads,
+       b.read_time,
+       b.writes,
+       b.write_time,
+       b.writebacks,
+       b.writeback_time,
+       b.extends,
+       b.extend_time,
+       b.op_bytes,
+       b.hits,
+       b.evictions,
+       b.reuses,
+       b.fsyncs,
+       b.fsync_time,
+       b.stats_reset
+FROM pg_stat_get_backend_io(NULL) b;
+
 CREATE VIEW pg_stat_wal AS
     SELECT
         w.wal_records,
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index bdb3a296ca..249439b990 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -249,6 +249,10 @@ pgstat_beinit(void)
 	Assert(MyProcNumber >= 0 && MyProcNumber < NumBackendStatSlots);
 	MyBEEntry = &BackendStatusArray[MyProcNumber];
 
+	/* Create the per-backend statistics entry */
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Set up a process-exit hook to clean up */
 	on_shmem_exit(pgstat_beshutdown_hook, 0);
 }
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 6f8d237826..1449d6a3f4 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_PER_BACKEND] = {
+		.name = "per-backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_per_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -768,7 +785,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / backend / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of fixed-numbered stats */
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..f079f15ff2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,176 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of per-backend statistics.
+ *
+ * This file contains the implementation of per-backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns my backend IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_my_stat_io(void)
+{
+	return (PgStat_Backend *)
+		pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid, MyProcNumber);
+}
+
+/*
+ * Returns other backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Create the per-backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_per_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * per-backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the per-backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the per-backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_per_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..1af5b75df6 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -122,6 +124,7 @@ void
 pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 						instr_time start_time, uint32 cnt)
 {
+
 	if (track_io_timing)
 	{
 		instr_time	io_time;
@@ -148,6 +151,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_per_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
@@ -171,12 +183,21 @@ pgstat_io_have_pending_cb(void)
 }
 
 /*
- * Simpler wrapper of pgstat_io_flush_cb()
+ * Simpler wrapper of pgstat_io_flush_cb() and pgstat_per_backend_flush_cb().
  */
 void
 pgstat_flush_io(bool nowait)
 {
+	PgStat_EntryRef *entry_ref;
+
 	(void) pgstat_io_flush_cb(nowait);
+
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+	{
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_per_backend_flush_cb(entry_ref, nowait);
+	}
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 60a397dc56..0302970246 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1480,6 +1480,165 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+
+	/* just to keep compiler quiet */
+	bktype = B_INVALID;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	if (PG_ARGISNULL(0) || PG_GETARG_INT32(0) == MyProcPid)
+	{
+		backend_stats = pgstat_fetch_my_stat_io();
+		pid = MyProcPid;
+		bktype = MyBackendType;
+	}
+	else
+	{
+		PGPROC	   *proc;
+		ProcNumber	procNumber;
+
+		pid = PG_GETARG_INT32(0);
+		proc = BackendPidGetProc(pid);
+
+		/*
+		 * Maybe an auxiliary process? That should not be possible, due to
+		 * pgstat_tracks_per_backend_bktype() though.
+		 */
+		if (proc == NULL)
+			proc = AuxiliaryPidGetProc(pid);
+
+		if (proc != NULL)
+		{
+			procNumber = GetNumberFromPGProc(proc);
+			backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+			if (!backend_stats)
+				return (Datum) 0;
+		}
+		else
+			return (Datum) 0;
+	}
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1785,6 +1944,55 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_single_backend_io_counters(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	BackendType bktype;
+	int			backend_pid = PG_GETARG_INT32(0);
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Maybe an auxiliary process? That should not be possible, due to
+	 * pgstat_tracks_per_backend_bktype() though.
+	 */
+	if (proc == NULL)
+		proc = AuxiliaryPidGetProc(backend_pid);
+
+	/* Check that IO stats are collected for this backend type */
+	if (proc)
+	{
+		for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+		{
+			LocalPgBackendStatus *local_beentry;
+			PgBackendStatus *beentry;
+
+			/* Get the next one in the list */
+			local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+			beentry = &local_beentry->backendStatus;
+
+			/* looking for specific PID, ignore all the others */
+			if (beentry->st_procpid != backend_pid)
+				continue;
+
+			bktype = beentry->st_backendType;
+
+			if (!pgstat_tracks_per_backend_bktype(bktype))
+				PG_RETURN_VOID();
+			else
+			{
+				pgstat_reset(PGSTAT_KIND_PER_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+				break;
+			}
+		}
+	}
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index cbbe8acd38..6e5c2082a7 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: per backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4', proisstrict => 'f',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset collected IO statistics for a single backend',
+  proname => 'pg_stat_reset_single_backend_io_counters', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_single_backend_io_counters' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 59c28b4aca..c5151c8e6f 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_PER_BACKEND	6
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -347,12 +348,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -534,6 +546,14 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_my_stat_io(void);
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_per_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..625bb55864 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,13 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_BackendPendingIO *pgstat_prep_per_backend_pending(ProcNumber procnum);
+extern bool pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 3014d047fe..3922675bbf 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1398,6 +1398,25 @@ pg_matviews| SELECT n.nspname AS schemaname,
      LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
      LEFT JOIN pg_tablespace t ON ((t.oid = c.reltablespace)))
   WHERE (c.relkind = 'm'::"char");
+pg_my_stat_io| SELECT backend_type,
+    object,
+    context,
+    reads,
+    read_time,
+    writes,
+    write_time,
+    writebacks,
+    writeback_time,
+    extends,
+    extend_time,
+    op_bytes,
+    hits,
+    evictions,
+    reuses,
+    fsyncs,
+    fsync_time,
+    stats_reset
+   FROM pg_stat_get_backend_io(NULL::integer) b(backend_type, object, context, reads, read_time, writes, write_time, writebacks, writeback_time, extends, extend_time, op_bytes, hits, evictions, reuses, fsyncs, fsync_time, stats_reset);
 pg_policies| SELECT n.nspname AS schemaname,
     c.relname AS tablename,
     pol.polname AS policyname,
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..7f2fd873b9 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my_]stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,24 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1293,25 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1331,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the per-backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1576,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1592,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+ pg_stat_reset_single_backend_io_counters 
+------------------------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..497b2b438a 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_[my_]stat_io:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,40 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS backend_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset backend_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_my_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+SELECT sum(extends) AS backend_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :backend_io_sum_shared_after_extends > :backend_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -631,6 +651,18 @@ SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_my_stat_io
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the per-backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -762,10 +794,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_my_stat_io \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_my_stat_io \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_my_stat_io \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index b54428b38c..ea676361a5 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2120,6 +2120,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2135,6 +2136,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From 6662a78036e92035bd4899e4a92af42f3aaae944 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v7] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_single_backend_io_counters() to be able to reset the I/O stats
for a given backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_PER_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  37 ++++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  19 +-
 src/backend/utils/activity/pgstat_backend.c  | 182 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          | 166 +++++++++++++++++
 src/include/catalog/pg_proc.dat              |  14 ++
 src/include/pgstat.h                         |  31 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/test/regress/expected/stats.out          |  72 +++++++-
 src/test/regress/sql/stats.sql               |  38 +++-
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 598 insertions(+), 21 deletions(-)
  10.0% doc/src/sgml/
  30.9% src/backend/utils/activity/
  21.8% src/backend/utils/adt/
   4.6% src/include/catalog/
   7.1% src/include/
  13.0% src/test/regress/expected/
  11.6% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index e0c8325a39..8afca9b110 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..fb13c462d1 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4990,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_single_backend_io_counters</primary>
+        </indexterm>
+        <function>pg_stat_reset_single_backend_io_counters</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets I/O statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..1b21b242cd 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_backend_io_counters(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..29779ff99a 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -249,6 +249,10 @@ pgstat_beinit(void)
 	Assert(MyProcNumber >= 0 && MyProcNumber < NumBackendStatSlots);
 	MyBEEntry = &BackendStatusArray[MyProcNumber];
 
+	/* Create the per-backend statistics entry */
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Set up a process-exit hook to clean up */
 	on_shmem_exit(pgstat_beshutdown_hook, 0);
 }
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 18b7d9b47d..738ee778bb 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_PER_BACKEND] = {
+		.name = "per-backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_per_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -768,7 +785,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / backend / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of fixed-numbered stats */
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..dc7bf385c2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,182 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of per-backend statistics.
+ *
+ * This file contains the implementation of per-backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_PER_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_per_backend_flush_cb()
+ */
+void
+pgstat_flush_per_backend(bool nowait)
+{
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_per_backend_flush_cb(entry_ref, nowait);
+	}
+}
+
+/*
+ * Create the per-backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_per_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_PER_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * per-backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the per-backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the per-backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_per_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..93d34696b9 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_per_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +150,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_per_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_per_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..c083c5bf01 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_per_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_per_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..ce4d22e16c 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,151 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_per_backend_bktype() anyway. So don't need an extra call
+	 * to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	/* just to keep compiler quiet */
+	bktype = B_INVALID;
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1779,6 +1924,27 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_single_backend_io_counters(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_per_backend_bktype() anyway. So don't need an extra call
+	 * to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_PER_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..55dec76795 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: per backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset collected IO statistics for a single backend',
+  proname => 'pg_stat_reset_single_backend_io_counters', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_single_backend_io_counters' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 59c28b4aca..b7e8dcb1fd 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_PER_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -347,12 +348,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -534,6 +546,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_per_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..141e16d1d3 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_per_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_per_backend_pending(ProcNumber procnum);
+extern bool pgstat_per_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..ba8c3cfc88 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in per-backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1288,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1318,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the per-backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1563,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1579,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+ pg_stat_reset_single_backend_io_counters 
+------------------------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..f17799402f 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in per-backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +642,17 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the per-backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,10 +785,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_single_backend_io_counters() does
+SELECT pg_stat_reset_single_backend_io_counters(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From 1b03df28ceea635a2687baee4f8d1b3a3c1ae728 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v8] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_backend_stats() to be able to reset the stats for a given
backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  37 ++++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  22 ++-
 src/backend/utils/activity/pgstat_backend.c  | 182 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          | 169 +++++++++++++++++
 src/include/catalog/pg_proc.dat              |  14 ++
 src/include/pgstat.h                         |  31 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/test/regress/expected/stats.out          |  72 +++++++-
 src/test/regress/sql/stats.sql               |  38 +++-
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 604 insertions(+), 21 deletions(-)
   9.9% doc/src/sgml/
  31.2% src/backend/utils/activity/
  22.1% src/backend/utils/adt/
   4.4% src/include/catalog/
   7.1% src/include/
  12.9% src/test/regress/expected/
  11.5% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index e0c8325a39..8afca9b110 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..4a9464da61 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4990,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_backend_stats</primary>
+        </indexterm>
+        <function>pg_stat_reset_backend_stats</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..14eb99cd47 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_backend_stats(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..7f74011a00 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -249,6 +249,10 @@ pgstat_beinit(void)
 	Assert(MyProcNumber >= 0 && MyProcNumber < NumBackendStatSlots);
 	MyBEEntry = &BackendStatusArray[MyProcNumber];
 
+	/* Create the backend statistics entry */
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Set up a process-exit hook to clean up */
 	on_shmem_exit(pgstat_beshutdown_hook, 0);
 }
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 18b7d9b47d..563f2443f8 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_BACKEND] = {
+		.name = "backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -602,6 +619,9 @@ pgstat_shutdown_hook(int code, Datum arg)
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
 
+	/* drop the backend stats entry */
+	pgstat_drop_entry(PGSTAT_KIND_BACKEND, InvalidOid, MyProcNumber);
+
 	pgstat_detach_shmem();
 
 #ifdef USE_ASSERT_CHECKING
@@ -768,7 +788,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / backend / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of fixed-numbered stats */
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..e2d83024c2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,182 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of backend statistics.
+ *
+ * This file contains the implementation of backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_backend_flush_cb()
+ */
+void
+pgstat_flush_backend(bool nowait)
+{
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_backend_flush_cb(entry_ref, nowait);
+	}
+}
+
+/*
+ * Create the backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * Backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..e0c206a453 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +150,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..85e65557bb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..b939551d36 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,154 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	bktype = B_INVALID;
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* Looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	/* Backend is gone */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1779,6 +1927,27 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..437157ffa3 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset statistics for a single backend',
+  proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_backend_stats' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index ebfeef2f46..479773cfd2 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -362,12 +363,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -549,6 +561,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..811ed9b005 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_backend_pending(ProcNumber procnum);
+extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..3447e7b75d 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1288,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1318,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1563,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1579,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+ pg_stat_reset_backend_stats 
+-----------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..9c925005be 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +642,17 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,10 +785,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From 5bd09f37d6fdb3db38eff8ce30677d3989fcf64c Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v9] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_backend_stats() to be able to reset the stats for a given
backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  37 ++++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  23 ++-
 src/backend/utils/activity/pgstat_backend.c  | 182 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          | 169 +++++++++++++++++
 src/include/catalog/pg_proc.dat              |  14 ++
 src/include/pgstat.h                         |  31 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/test/regress/expected/stats.out          |  72 +++++++-
 src/test/regress/sql/stats.sql               |  38 +++-
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 605 insertions(+), 21 deletions(-)
   9.9% doc/src/sgml/
  31.3% src/backend/utils/activity/
  22.0% src/backend/utils/adt/
   4.4% src/include/catalog/
   7.0% src/include/
  12.8% src/test/regress/expected/
  11.5% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index e0c8325a39..8afca9b110 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..4a9464da61 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4990,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_backend_stats</primary>
+        </indexterm>
+        <function>pg_stat_reset_backend_stats</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..14eb99cd47 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_backend_stats(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..e9c3b87ac2 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -426,6 +426,10 @@ pgstat_bestart(void)
 
 	PGSTAT_END_WRITE_ACTIVITY(vbeentry);
 
+	/* Create the backend statistics entry */
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Update app name to current GUC setting */
 	if (application_name)
 		pgstat_report_appname(application_name);
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 18b7d9b47d..9dd9d60b00 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_BACKEND] = {
+		.name = "backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -602,6 +619,10 @@ pgstat_shutdown_hook(int code, Datum arg)
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
 
+	/* drop the backend stats entry */
+	if (!pgstat_drop_entry(PGSTAT_KIND_BACKEND, InvalidOid, MyProcNumber))
+		pgstat_request_entry_refs_gc();
+
 	pgstat_detach_shmem();
 
 #ifdef USE_ASSERT_CHECKING
@@ -768,7 +789,7 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush database / relation / function / ... stats */
+	/* flush database / relation / function / backend / ... stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of fixed-numbered stats */
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..e2d83024c2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,182 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of backend statistics.
+ *
+ * This file contains the implementation of backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_backend_flush_cb()
+ */
+void
+pgstat_flush_backend(bool nowait)
+{
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_backend_flush_cb(entry_ref, nowait);
+	}
+}
+
+/*
+ * Create the backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * Backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..e0c206a453 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +150,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..85e65557bb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..b939551d36 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,154 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	bktype = B_INVALID;
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* Looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	/* Backend is gone */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1779,6 +1927,27 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..437157ffa3 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset statistics for a single backend',
+  proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_backend_stats' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index ebfeef2f46..479773cfd2 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -362,12 +363,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -549,6 +561,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..811ed9b005 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_backend_pending(ProcNumber procnum);
+extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..3447e7b75d 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1288,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1318,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1563,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1579,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+ pg_stat_reset_backend_stats 
+-----------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..9c925005be 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +642,17 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,10 +785,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From d0df4be6cd052fc91970ec99933268f9b55940b7 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v9 1/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_backend_stats() to be able to reset the stats for a given
backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 src/include/catalog/pg_proc.dat              |  14 ++
 src/include/pgstat.h                         |  31 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  21 +++
 src/backend/utils/activity/pgstat_backend.c  | 182 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          | 169 +++++++++++++++++
 src/test/regress/expected/stats.out          |  72 +++++++-
 src/test/regress/sql/stats.sql               |  38 +++-
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  37 ++++
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 604 insertions(+), 20 deletions(-)
 create mode 100644 src/backend/utils/activity/pgstat_backend.c

diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..437157ffa3 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset statistics for a single backend',
+  proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_backend_stats' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index ebfeef2f46..479773cfd2 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -362,12 +363,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -549,6 +561,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..811ed9b005 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_backend_pending(ProcNumber procnum);
+extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..14eb99cd47 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_backend_stats(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..e9c3b87ac2 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -426,6 +426,10 @@ pgstat_bestart(void)
 
 	PGSTAT_END_WRITE_ACTIVITY(vbeentry);
 
+	/* Create the backend statistics entry */
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Update app name to current GUC setting */
 	if (application_name)
 		pgstat_report_appname(application_name);
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index b4e357c8a4..b72c779b2c 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_BACKEND] = {
+		.name = "backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -602,6 +619,10 @@ pgstat_shutdown_hook(int code, Datum arg)
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
 
+	/* drop the backend stats entry */
+	if (!pgstat_drop_entry(PGSTAT_KIND_BACKEND, InvalidOid, MyProcNumber))
+		pgstat_request_entry_refs_gc();
+
 	pgstat_detach_shmem();
 
 #ifdef USE_ASSERT_CHECKING
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..e2d83024c2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,182 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of backend statistics.
+ *
+ * This file contains the implementation of backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_backend_flush_cb()
+ */
+void
+pgstat_flush_backend(bool nowait)
+{
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_backend_flush_cb(entry_ref, nowait);
+	}
+}
+
+/*
+ * Create the backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * Backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..e0c206a453 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +150,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..85e65557bb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..b939551d36 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,154 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	bktype = B_INVALID;
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* Looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	/* Backend is gone */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1779,6 +1927,27 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..3447e7b75d 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1288,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1318,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1563,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1579,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+ pg_stat_reset_backend_stats 
+-----------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..9c925005be 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +642,17 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,10 +785,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 24bd504c21..fbdd6ce574 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..4a9464da61 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4990,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_backend_stats</primary>
+        </indexterm>
+        <function>pg_stat_reset_backend_stats</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.45.2

From 8c7fd33e98ec958308979dba9cb7897787ddc48e Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Tue, 17 Dec 2024 15:15:23 +0900
Subject: [PATCH v9 2/2] Tweaks on top of v9

Other notes for commit:
Requires a bump of CATALOG_VERSION_NO.
Requires a bump of PGSTAT_FILE_FORMAT_ID.
---
 src/include/catalog/pg_proc.dat             |  3 +-
 src/include/pgstat.h                        | 11 +++--
 src/backend/utils/activity/backend_status.c |  2 +-
 src/backend/utils/activity/pgstat_backend.c | 38 ++++++++-------
 src/backend/utils/activity/pgstat_io.c      |  2 -
 src/backend/utils/adt/pgstatfuncs.c         | 53 +++++++++------------
 src/test/regress/expected/stats.out         | 28 +++++++----
 src/test/regress/sql/stats.sql              | 12 +++--
 doc/src/sgml/monitoring.sgml                | 10 ++--
 9 files changed, 86 insertions(+), 73 deletions(-)

diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 437157ffa3..2dcc2d42da 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6061,8 +6061,7 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
-{ oid => '9987',
-  descr => 'statistics: reset statistics for a single backend',
+{ oid => '8807', descr => 'statistics: reset statistics for a single backend',
   proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
   prorettype => 'void', proargtypes => 'int4',
   prosrc => 'pg_stat_reset_backend_stats' },
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 479773cfd2..56ed1b8bb3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -363,11 +363,11 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
-typedef struct PgStat_BackendPendingIO
+typedef struct PgStat_PendingIO
 {
 	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_BackendPendingIO;
+} PgStat_PendingIO;
 
 typedef struct PgStat_IO
 {
@@ -375,6 +375,9 @@ typedef struct PgStat_IO
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+/* Backend statistics store the same amount of IO data as PGSTAT_KIND_IO */
+typedef PgStat_PendingIO PgStat_BackendPendingIO;
+
 typedef struct PgStat_Backend
 {
 	TimestampTz stat_reset_timestamp;
@@ -565,9 +568,9 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
  * Functions in pgstat_backend.c
  */
 
-extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern bool pgstat_tracks_backend_bktype(BackendType bktype);
-extern void pgstat_create_backend_stat(ProcNumber procnum);
+extern void pgstat_create_backend(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index e9c3b87ac2..bf33e33a4e 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -428,7 +428,7 @@ pgstat_bestart(void)
 
 	/* Create the backend statistics entry */
 	if (pgstat_tracks_backend_bktype(MyBackendType))
-		pgstat_create_backend_stat(MyProcNumber);
+		pgstat_create_backend(MyProcNumber);
 
 	/* Update app name to current GUC setting */
 	if (application_name)
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index e2d83024c2..6b2c9baa8c 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -3,11 +3,17 @@
  * pgstat_backend.c
  *	  Implementation of backend statistics.
  *
- * This file contains the implementation of backend statistics. It is kept
+ * This file contains the implementation of backend statistics.  It is kept
  * separate from pgstat.c to enforce the line between the statistics access /
- * storage implementation and the details about individual types of statistics.
+ * storage implementation and the details about individual types of
+ * statistics.
  *
- * Copyright (c) 2024, PostgreSQL Global Development Group
+ * This statistics kind uses a proc number as object ID for the hash table
+ * of pgstats.  Entries are created each time a process is spawned, and are
+ * dropped when the process exits.  These are not written to the pgstats file
+ * on disk.
+ *
+ * Copyright (c) 2001-2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/backend/utils/activity/pgstat_backend.c
@@ -19,10 +25,10 @@
 #include "utils/pgstat_internal.h"
 
 /*
- * Returns backend's IO stats.
+ * Returns statistics of a backend by proc number.
  */
 PgStat_Backend *
-pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+pgstat_fetch_stat_backend(ProcNumber procNumber)
 {
 	PgStat_Backend *backend_entry;
 
@@ -81,21 +87,21 @@ pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 void
 pgstat_flush_backend(bool nowait)
 {
-	if (pgstat_tracks_backend_bktype(MyBackendType))
-	{
-		PgStat_EntryRef *entry_ref;
+	PgStat_EntryRef *entry_ref;
 
-		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-										 MyProcNumber, false, NULL);
-		(void) pgstat_backend_flush_cb(entry_ref, nowait);
-	}
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+									 MyProcNumber, false, NULL);
+	(void) pgstat_backend_flush_cb(entry_ref, nowait);
 }
 
 /*
- * Create the backend statistics entry for procnum.
+ * Create backend statistics entry for proc number.
  */
 void
-pgstat_create_backend_stat(ProcNumber procnum)
+pgstat_create_backend(ProcNumber procnum)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Backend *shstatent;
@@ -113,7 +119,7 @@ pgstat_create_backend_stat(ProcNumber procnum)
 }
 
 /*
- * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ * Find or create a local PgStat_BackendPendingIO entry for proc number.
  */
 PgStat_BackendPendingIO *
 pgstat_prep_backend_pending(ProcNumber procnum)
@@ -136,7 +142,7 @@ pgstat_prep_backend_pending(ProcNumber procnum)
  * I/O stats are already visible in pg_stat_io and there is only one of those.
  *
  * Function returns true if BackendType participates in the backend stats
- * subsystem for IO and false if it does not.
+ * subsystem and false if it does not.
  *
  * When adding a new BackendType, also consider adding relevant restrictions to
  * pgstat_tracks_io_object() and pgstat_tracks_io_op().
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index e0c206a453..011a3326da 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,8 +20,6 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-typedef PgStat_BackendPendingIO PgStat_PendingIO;
-
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index b939551d36..640e687604 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,20 +1474,22 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+/*
+ * Returns I/O statistics for a backend with given PID.
+ */
 Datum
 pg_stat_get_backend_io(PG_FUNCTION_ARGS)
 {
 	ReturnSetInfo *rsinfo;
-	PgStat_Backend *backend_stats;
 	Datum		bktype_desc;
-	PgStat_BktypeIO *bktype_stats;
 	BackendType bktype;
 	Datum		reset_time;
-	int			num_backends = pgstat_fetch_stat_numbackends();
-	int			curr_backend;
 	int			pid;
 	PGPROC	   *proc;
 	ProcNumber	procNumber;
+	PgStat_Backend *backend_stats;
+	PgStat_BktypeIO *bktype_stats;
+	PgBackendStatus *beentry;
 
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
@@ -1496,40 +1498,28 @@ pg_stat_get_backend_io(PG_FUNCTION_ARGS)
 	proc = BackendPidGetProc(pid);
 
 	/*
-	 * Could be an auxiliary process but would not report any stats due to
-	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
-	 * AuxiliaryPidGetProc().
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
 	 */
 	if (!proc)
 		return (Datum) 0;
 
 	procNumber = GetNumberFromPGProc(proc);
-	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	backend_stats = pgstat_fetch_stat_backend(procNumber);
 
 	if (!backend_stats)
 		return (Datum) 0;
 
-	bktype = B_INVALID;
+	beentry = pgstat_get_beentry_by_proc_number(procNumber);
+	bktype = beentry->st_backendType;
 
-	/* Look for the backend type */
-	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
-	{
-		LocalPgBackendStatus *local_beentry;
-		PgBackendStatus *beentry;
+	/* If PID does not match, leave */
+	if (beentry->st_procpid != pid)
+		return (Datum) 0;
 
-		/* Get the next one in the list */
-		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
-		beentry = &local_beentry->backendStatus;
-
-		/* Looking for specific PID, ignore all the others */
-		if (beentry->st_procpid != pid)
-			continue;
-
-		bktype = beentry->st_backendType;
-		break;
-	}
-
-	/* Backend is gone */
+	/* Backend may be gone, so recheck in case */
 	if (bktype == B_INVALID)
 		return (Datum) 0;
 
@@ -1927,6 +1917,9 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * Reset statistics of backend with given PID.
+ */
 Datum
 pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
 {
@@ -1936,9 +1929,9 @@ pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
 	proc = BackendPidGetProc(backend_pid);
 
 	/*
-	 * Could be an auxiliary process but would not report any stats due to
-	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
-	 * AuxiliaryPidGetProc().
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
 	 */
 	if (!proc)
 		PG_RETURN_VOID();
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 3447e7b75d..150b6dcf74 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,8 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io and in backend stats:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1335,14 +1336,6 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
--- Don't return any rows if querying other backend's stats that are excluded
--- from the backend stats collection (like the checkpointer).
-SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
- ?column? 
-----------
- t
-(1 row)
-
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1603,6 +1596,23 @@ SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
  t
 (1 row)
 
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+SELECT pg_stat_get_backend_io(0);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 9c925005be..1e7d0ff665 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,8 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io and in backend stats:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -650,10 +651,6 @@ SELECT current_setting('fsync') = 'off'
   OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
       AND :my_io_sum_shared_after_fsyncs= 0);
 
--- Don't return any rows if querying other backend's stats that are excluded
--- from the backend stats collection (like the checkpointer).
-SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
-
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -801,6 +798,11 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+SELECT pg_stat_get_backend_io(0);
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 4a9464da61..d0d176cc54 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4801,11 +4801,13 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        <para>
         Returns I/O statistics about the backend with the specified
         process ID. The output fields are exactly the same as the ones in the
-        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
-        view. The function does not return I/O statistics for the checkpointer,
+        <structname>pg_stat_io</structname> view.
+       </para>
+       <para>
+        The function does not return I/O statistics for the checkpointer,
         the background writer, the startup process and the autovacuum launcher
-        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
-        view and there is only one of those.
+        as they are already visible in the <structname>pg_stat_io</structname>
+        view and there is only one of each.
        </para></entry>
       </row>
 
-- 
2.45.2

From 75a2549543edf418b6e282acab3f8ce272c5c42a Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 28 Oct 2024 12:50:32 +0000
Subject: [PATCH v10 1/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_backend_stats() to be able to reset the stats for a given
backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Bump catalog version needs to be done.
---
 src/include/catalog/pg_proc.dat              |  14 ++
 src/include/pgstat.h                         |  31 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  21 +++
 src/backend/utils/activity/pgstat_backend.c  | 182 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          | 169 +++++++++++++++++
 src/test/regress/expected/stats.out          |  72 +++++++-
 src/test/regress/sql/stats.sql               |  38 +++-
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  37 ++++
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 604 insertions(+), 20 deletions(-)
 create mode 100644 src/backend/utils/activity/pgstat_backend.c

diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..437157ffa3 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,11 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '9987',
+  descr => 'statistics: reset statistics for a single backend',
+  proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_backend_stats' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index ebfeef2f46..479773cfd2 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -362,12 +363,23 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_BackendPendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_BackendPendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -549,6 +561,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern bool pgstat_tracks_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend_stat(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..811ed9b005 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_backend_pending(ProcNumber procnum);
+extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..14eb99cd47 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_backend_stats(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..e9c3b87ac2 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -426,6 +426,10 @@ pgstat_bestart(void)
 
 	PGSTAT_END_WRITE_ACTIVITY(vbeentry);
 
+	/* Create the backend statistics entry */
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+		pgstat_create_backend_stat(MyProcNumber);
+
 	/* Update app name to current GUC setting */
 	if (application_name)
 		pgstat_report_appname(application_name);
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index b4e357c8a4..b72c779b2c 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_BACKEND] = {
+		.name = "backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -602,6 +619,10 @@ pgstat_shutdown_hook(int code, Datum arg)
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
 
+	/* drop the backend stats entry */
+	if (!pgstat_drop_entry(PGSTAT_KIND_BACKEND, InvalidOid, MyProcNumber))
+		pgstat_request_entry_refs_gc();
+
 	pgstat_detach_shmem();
 
 #ifdef USE_ASSERT_CHECKING
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..e2d83024c2
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,182 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of backend statistics.
+ *
+ * This file contains the implementation of backend statistics. It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of statistics.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns backend's IO stats.
+ */
+PgStat_Backend *
+pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_backend_flush_cb()
+ */
+void
+pgstat_flush_backend(bool nowait)
+{
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+		(void) pgstat_backend_flush_cb(entry_ref, nowait);
+	}
+}
+
+/*
+ * Create the backend statistics entry for procnum.
+ */
+void
+pgstat_create_backend_stat(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * Backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the backend stats
+ * subsystem for IO and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..e0c206a453 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,13 +20,7 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
+typedef PgStat_BackendPendingIO PgStat_PendingIO;
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -87,6 +81,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +150,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..85e65557bb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..b939551d36 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1474,6 +1474,154 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_Backend *backend_stats;
+	Datum		bktype_desc;
+	PgStat_BktypeIO *bktype_stats;
+	BackendType bktype;
+	Datum		reset_time;
+	int			num_backends = pgstat_fetch_stat_numbackends();
+	int			curr_backend;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	bktype = B_INVALID;
+
+	/* Look for the backend type */
+	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
+	{
+		LocalPgBackendStatus *local_beentry;
+		PgBackendStatus *beentry;
+
+		/* Get the next one in the list */
+		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
+		beentry = &local_beentry->backendStatus;
+
+		/* Looking for specific PID, ignore all the others */
+		if (beentry->st_procpid != pid)
+			continue;
+
+		bktype = beentry->st_backendType;
+		break;
+	}
+
+	/* Backend is gone */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+	bktype_stats = &backend_stats->stats;
+	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (backend_stats->stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = reset_time;
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1779,6 +1927,27 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * Could be an auxiliary process but would not report any stats due to
+	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
+	 * AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..3447e7b75d 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,7 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1259,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1288,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1318,31 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1563,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1579,30 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+ pg_stat_reset_backend_stats 
+-----------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..9c925005be 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,7 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +607,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +642,17 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+
+-- Don't return any rows if querying other backend's stats that are excluded
+-- from the backend stats collection (like the checkpointer).
+SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,10 +785,21 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
 
 -- test BRIN index doesn't block HOT update
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 24bd504c21..fbdd6ce574 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..4a9464da61 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,25 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view. The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
+        view and there is only one of those.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4990,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_backend_stats</primary>
+        </indexterm>
+        <function>pg_stat_reset_backend_stats</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.45.2

From 0e3c2c066698acaaad69824a619e78f2cc16a358 Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 18 Dec 2024 13:48:34 +0900
Subject: [PATCH v10 2/2] Tweaks on top of v9

Other notes for commit:
Requires a bump of CATALOG_VERSION_NO.
Requires a bump of PGSTAT_FILE_FORMAT_ID.
---
 src/include/catalog/pg_proc.dat             |   3 +-
 src/include/pgstat.h                        |  11 +-
 src/backend/utils/activity/backend_status.c |   2 +-
 src/backend/utils/activity/pgstat_backend.c |  38 ++-
 src/backend/utils/activity/pgstat_io.c      |   2 -
 src/backend/utils/adt/pgstatfuncs.c         | 305 ++++++++------------
 src/test/regress/expected/stats.out         |  28 +-
 src/test/regress/sql/stats.sql              |  12 +-
 doc/src/sgml/monitoring.sgml                |  10 +-
 9 files changed, 184 insertions(+), 227 deletions(-)

diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 437157ffa3..2dcc2d42da 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -6061,8 +6061,7 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
-{ oid => '9987',
-  descr => 'statistics: reset statistics for a single backend',
+{ oid => '8807', descr => 'statistics: reset statistics for a single backend',
   proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
   prorettype => 'void', proargtypes => 'int4',
   prosrc => 'pg_stat_reset_backend_stats' },
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 479773cfd2..56ed1b8bb3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -363,11 +363,11 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
-typedef struct PgStat_BackendPendingIO
+typedef struct PgStat_PendingIO
 {
 	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_BackendPendingIO;
+} PgStat_PendingIO;
 
 typedef struct PgStat_IO
 {
@@ -375,6 +375,9 @@ typedef struct PgStat_IO
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+/* Backend statistics store the same amount of IO data as PGSTAT_KIND_IO */
+typedef PgStat_PendingIO PgStat_BackendPendingIO;
+
 typedef struct PgStat_Backend
 {
 	TimestampTz stat_reset_timestamp;
@@ -565,9 +568,9 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
  * Functions in pgstat_backend.c
  */
 
-extern PgStat_Backend *pgstat_fetch_proc_stat_io(ProcNumber procNumber);
+extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern bool pgstat_tracks_backend_bktype(BackendType bktype);
-extern void pgstat_create_backend_stat(ProcNumber procnum);
+extern void pgstat_create_backend(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index e9c3b87ac2..bf33e33a4e 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -428,7 +428,7 @@ pgstat_bestart(void)
 
 	/* Create the backend statistics entry */
 	if (pgstat_tracks_backend_bktype(MyBackendType))
-		pgstat_create_backend_stat(MyProcNumber);
+		pgstat_create_backend(MyProcNumber);
 
 	/* Update app name to current GUC setting */
 	if (application_name)
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index e2d83024c2..6b2c9baa8c 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -3,11 +3,17 @@
  * pgstat_backend.c
  *	  Implementation of backend statistics.
  *
- * This file contains the implementation of backend statistics. It is kept
+ * This file contains the implementation of backend statistics.  It is kept
  * separate from pgstat.c to enforce the line between the statistics access /
- * storage implementation and the details about individual types of statistics.
+ * storage implementation and the details about individual types of
+ * statistics.
  *
- * Copyright (c) 2024, PostgreSQL Global Development Group
+ * This statistics kind uses a proc number as object ID for the hash table
+ * of pgstats.  Entries are created each time a process is spawned, and are
+ * dropped when the process exits.  These are not written to the pgstats file
+ * on disk.
+ *
+ * Copyright (c) 2001-2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/backend/utils/activity/pgstat_backend.c
@@ -19,10 +25,10 @@
 #include "utils/pgstat_internal.h"
 
 /*
- * Returns backend's IO stats.
+ * Returns statistics of a backend by proc number.
  */
 PgStat_Backend *
-pgstat_fetch_proc_stat_io(ProcNumber procNumber)
+pgstat_fetch_stat_backend(ProcNumber procNumber)
 {
 	PgStat_Backend *backend_entry;
 
@@ -81,21 +87,21 @@ pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 void
 pgstat_flush_backend(bool nowait)
 {
-	if (pgstat_tracks_backend_bktype(MyBackendType))
-	{
-		PgStat_EntryRef *entry_ref;
+	PgStat_EntryRef *entry_ref;
 
-		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-										 MyProcNumber, false, NULL);
-		(void) pgstat_backend_flush_cb(entry_ref, nowait);
-	}
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+									 MyProcNumber, false, NULL);
+	(void) pgstat_backend_flush_cb(entry_ref, nowait);
 }
 
 /*
- * Create the backend statistics entry for procnum.
+ * Create backend statistics entry for proc number.
  */
 void
-pgstat_create_backend_stat(ProcNumber procnum)
+pgstat_create_backend(ProcNumber procnum)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Backend *shstatent;
@@ -113,7 +119,7 @@ pgstat_create_backend_stat(ProcNumber procnum)
 }
 
 /*
- * Find or create a local PgStat_BackendPendingIO entry for procnum.
+ * Find or create a local PgStat_BackendPendingIO entry for proc number.
  */
 PgStat_BackendPendingIO *
 pgstat_prep_backend_pending(ProcNumber procnum)
@@ -136,7 +142,7 @@ pgstat_prep_backend_pending(ProcNumber procnum)
  * I/O stats are already visible in pg_stat_io and there is only one of those.
  *
  * Function returns true if BackendType participates in the backend stats
- * subsystem for IO and false if it does not.
+ * subsystem and false if it does not.
  *
  * When adding a new BackendType, also consider adding relevant restrictions to
  * pgstat_tracks_io_object() and pgstat_tracks_io_op().
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index e0c206a453..011a3326da 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,8 +20,6 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-typedef PgStat_BackendPendingIO PgStat_PendingIO;
-
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index b939551d36..18c74807a4 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1274,8 +1274,9 @@ pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
 }
 
 /*
-* When adding a new column to the pg_stat_io view, add a new enum value
-* here above IO_NUM_COLUMNS.
+* When adding a new column to the pg_stat_io view and the
+* pg_stat_get_backend_io() function, add a new enum value here above
+* IO_NUM_COLUMNS.
 */
 typedef enum io_stat_col
 {
@@ -1365,184 +1366,20 @@ pg_stat_us_to_ms(PgStat_Counter val_ms)
 	return val_ms * (double) 0.001;
 }
 
-Datum
-pg_stat_get_io(PG_FUNCTION_ARGS)
+/*
+ * pg_stat_fill_io_data
+ *
+ * Helper routine for pg_stat_get_io() and pg_stat_get_backend_io(),
+ * filling in a result tuplestore with one tuple for each object and each
+ * context supported by the caller, based on the contents of bktype_stats.
+ */
+static void
+pg_stat_fill_io_data(ReturnSetInfo *rsinfo,
+					 PgStat_BktypeIO *bktype_stats,
+					 BackendType bktype,
+					 TimestampTz stat_reset_timestamp)
 {
-	ReturnSetInfo *rsinfo;
-	PgStat_IO  *backends_io_stats;
-	Datum		reset_time;
-
-	InitMaterializedSRF(fcinfo, 0);
-	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
-
-	backends_io_stats = pgstat_fetch_stat_io();
-
-	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
-
-	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
-	{
-		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
-		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
-
-		/*
-		 * In Assert builds, we can afford an extra loop through all of the
-		 * counters checking that only expected stats are non-zero, since it
-		 * keeps the non-Assert code cleaner.
-		 */
-		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
-
-		/*
-		 * For those BackendTypes without IO Operation stats, skip
-		 * representing them in the view altogether.
-		 */
-		if (!pgstat_tracks_io_bktype(bktype))
-			continue;
-
-		for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
-		{
-			const char *obj_name = pgstat_get_io_object_name(io_obj);
-
-			for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
-			{
-				const char *context_name = pgstat_get_io_context_name(io_context);
-
-				Datum		values[IO_NUM_COLUMNS] = {0};
-				bool		nulls[IO_NUM_COLUMNS] = {0};
-
-				/*
-				 * Some combinations of BackendType, IOObject, and IOContext
-				 * are not valid for any type of IOOp. In such cases, omit the
-				 * entire row from the view.
-				 */
-				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
-					continue;
-
-				values[IO_COL_BACKEND_TYPE] = bktype_desc;
-				values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
-				values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
-				values[IO_COL_RESET_TIME] = reset_time;
-
-				/*
-				 * Hard-code this to the value of BLCKSZ for now. Future
-				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
-				 * and constant multipliers, once non-block-oriented IO (e.g.
-				 * temporary file IO) is tracked.
-				 */
-				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
-
-				for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
-				{
-					int			op_idx = pgstat_get_io_op_index(io_op);
-					int			time_idx = pgstat_get_io_time_index(io_op);
-
-					/*
-					 * Some combinations of BackendType and IOOp, of IOContext
-					 * and IOOp, and of IOObject and IOOp are not tracked. Set
-					 * these cells in the view NULL.
-					 */
-					if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
-					{
-						PgStat_Counter count =
-							bktype_stats->counts[io_obj][io_context][io_op];
-
-						values[op_idx] = Int64GetDatum(count);
-					}
-					else
-						nulls[op_idx] = true;
-
-					/* not every operation is timed */
-					if (time_idx == IO_COL_INVALID)
-						continue;
-
-					if (!nulls[op_idx])
-					{
-						PgStat_Counter time =
-							bktype_stats->times[io_obj][io_context][io_op];
-
-						values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
-					}
-					else
-						nulls[time_idx] = true;
-				}
-
-				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
-									 values, nulls);
-			}
-		}
-	}
-
-	return (Datum) 0;
-}
-
-Datum
-pg_stat_get_backend_io(PG_FUNCTION_ARGS)
-{
-	ReturnSetInfo *rsinfo;
-	PgStat_Backend *backend_stats;
-	Datum		bktype_desc;
-	PgStat_BktypeIO *bktype_stats;
-	BackendType bktype;
-	Datum		reset_time;
-	int			num_backends = pgstat_fetch_stat_numbackends();
-	int			curr_backend;
-	int			pid;
-	PGPROC	   *proc;
-	ProcNumber	procNumber;
-
-	InitMaterializedSRF(fcinfo, 0);
-	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
-
-	pid = PG_GETARG_INT32(0);
-	proc = BackendPidGetProc(pid);
-
-	/*
-	 * Could be an auxiliary process but would not report any stats due to
-	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
-	 * AuxiliaryPidGetProc().
-	 */
-	if (!proc)
-		return (Datum) 0;
-
-	procNumber = GetNumberFromPGProc(proc);
-	backend_stats = pgstat_fetch_proc_stat_io(procNumber);
-
-	if (!backend_stats)
-		return (Datum) 0;
-
-	bktype = B_INVALID;
-
-	/* Look for the backend type */
-	for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
-	{
-		LocalPgBackendStatus *local_beentry;
-		PgBackendStatus *beentry;
-
-		/* Get the next one in the list */
-		local_beentry = pgstat_get_local_beentry_by_index(curr_backend);
-		beentry = &local_beentry->backendStatus;
-
-		/* Looking for specific PID, ignore all the others */
-		if (beentry->st_procpid != pid)
-			continue;
-
-		bktype = beentry->st_backendType;
-		break;
-	}
-
-	/* Backend is gone */
-	if (bktype == B_INVALID)
-		return (Datum) 0;
-
-	bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
-	bktype_stats = &backend_stats->stats;
-	reset_time = TimestampTzGetDatum(backend_stats->stat_reset_timestamp);
-
-	/*
-	 * In Assert builds, we can afford an extra loop through all of the
-	 * counters checking that only expected stats are non-zero, since it keeps
-	 * the non-Assert code cleaner.
-	 */
-	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+	Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
 
 	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
 	{
@@ -1566,8 +1403,8 @@ pg_stat_get_backend_io(PG_FUNCTION_ARGS)
 			values[IO_COL_BACKEND_TYPE] = bktype_desc;
 			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
 			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
-			if (backend_stats->stat_reset_timestamp != 0)
-				values[IO_COL_RESET_TIME] = reset_time;
+			if (stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = TimestampTzGetDatum(stat_reset_timestamp);
 			else
 				nulls[IO_COL_RESET_TIME] = true;
 
@@ -1618,7 +1455,104 @@ pg_stat_get_backend_io(PG_FUNCTION_ARGS)
 								 values, nulls);
 		}
 	}
+}
 
+Datum
+pg_stat_get_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	PgStat_IO  *backends_io_stats;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	backends_io_stats = pgstat_fetch_stat_io();
+
+	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
+	{
+		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
+
+		/*
+		 * In Assert builds, we can afford an extra loop through all of the
+		 * counters checking that only expected stats are non-zero, since it
+		 * keeps the non-Assert code cleaner.
+		 */
+		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+		/*
+		 * For those BackendTypes without IO Operation stats, skip
+		 * representing them in the view altogether.
+		 */
+		if (!pgstat_tracks_io_bktype(bktype))
+			continue;
+
+		/* Save tuples with data from this PgStat_BktypeIO. */
+		pg_stat_fill_io_data(rsinfo, bktype_stats, bktype,
+							 backends_io_stats->stat_reset_timestamp);
+	}
+
+	return (Datum) 0;
+}
+
+/*
+ * Returns I/O statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	BackendType bktype;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+	PgStat_Backend *backend_stats;
+	PgStat_BktypeIO *bktype_stats;
+	PgBackendStatus *beentry;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+
+	backend_stats = pgstat_fetch_stat_backend(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	beentry = pgstat_get_beentry_by_proc_number(procNumber);
+	bktype = beentry->st_backendType;
+
+	/* If PID does not match, leave */
+	if (beentry->st_procpid != pid)
+		return (Datum) 0;
+
+	/* Backend may be gone, so recheck in case */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_stats = &backend_stats->stats;
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters checking that only expected stats are non-zero, since it keeps
+	 * the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	/* Save tuples with data from this PgStat_BktypeIO */
+	pg_stat_fill_io_data(rsinfo, bktype_stats, bktype,
+						 backend_stats->stat_reset_timestamp);
 	return (Datum) 0;
 }
 
@@ -1927,6 +1861,9 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * Reset statistics of backend with given PID.
+ */
 Datum
 pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
 {
@@ -1936,9 +1873,9 @@ pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
 	proc = BackendPidGetProc(backend_pid);
 
 	/*
-	 * Could be an auxiliary process but would not report any stats due to
-	 * pgstat_tracks_backend_bktype() anyway. So don't need an extra call to
-	 * AuxiliaryPidGetProc().
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
 	 */
 	if (!proc)
 		PG_RETURN_VOID();
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 3447e7b75d..150b6dcf74 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,8 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io and in backend stats:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1335,14 +1336,6 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
--- Don't return any rows if querying other backend's stats that are excluded
--- from the backend stats collection (like the checkpointer).
-SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
- ?column? 
-----------
- t
-(1 row)
-
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1603,6 +1596,23 @@ SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
  t
 (1 row)
 
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+SELECT pg_stat_get_backend_io(0);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 9c925005be..1e7d0ff665 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,8 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io and in backend stats:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -650,10 +651,6 @@ SELECT current_setting('fsync') = 'off'
   OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
       AND :my_io_sum_shared_after_fsyncs= 0);
 
--- Don't return any rows if querying other backend's stats that are excluded
--- from the backend stats collection (like the checkpointer).
-SELECT count(1) = 0 FROM pg_stat_get_backend_io(:checkpointer_pid);
-
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -801,6 +798,11 @@ SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) +
   FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
 
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+SELECT pg_stat_get_backend_io(0);
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 4a9464da61..d0d176cc54 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4801,11 +4801,13 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        <para>
         Returns I/O statistics about the backend with the specified
         process ID. The output fields are exactly the same as the ones in the
-        <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
-        view. The function does not return I/O statistics for the checkpointer,
+        <structname>pg_stat_io</structname> view.
+       </para>
+       <para>
+        The function does not return I/O statistics for the checkpointer,
         the background writer, the startup process and the autovacuum launcher
-        as they are already visible in the <link linkend="monitoring-pg-stat-io-view"> <structname>pg_stat_io</structname></link>
-        view and there is only one of those.
+        as they are already visible in the <structname>pg_stat_io</structname>
+        view and there is only one of each.
        </para></entry>
       </row>
 
-- 
2.45.2

From 636d82991ec029c9d792d54cfdb2c665063424cf Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 18 Dec 2024 05:45:49 +0000
Subject: [PATCH v11 1/2] Refactor pg_stat_get_io() to extract tuple building
 logic

Adding pg_stat_io_build_tuples(), a helper for pg_stat_get_io() filling in a
result tuplestore. The tuple building logic is now isolated in its own function,
so that it could be reused elsewhere (like in the following backend I/O stats
commit).
---
 src/backend/utils/adt/pgstatfuncs.c | 174 ++++++++++++++++------------
 1 file changed, 97 insertions(+), 77 deletions(-)
 100.0% src/backend/utils/adt/

diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index cdf37403e9..efd35f700a 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1365,29 +1365,117 @@ pg_stat_us_to_ms(PgStat_Counter val_ms)
 	return val_ms * (double) 0.001;
 }
 
+/*
+ * pg_stat_io_build_tuples
+ *
+ * Helper routine for pg_stat_get_io() filling in a result tuplestore with one
+ * tuple for each object and each context supported by the caller, based on the
+ * contents of bktype_stats.
+ */
+static void
+pg_stat_io_build_tuples(ReturnSetInfo *rsinfo,
+						PgStat_BktypeIO *bktype_stats,
+						BackendType bktype,
+						TimestampTz stat_reset_timestamp)
+{
+	Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
+
+	for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
+	{
+		const char *obj_name = pgstat_get_io_object_name(io_obj);
+
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			const char *context_name = pgstat_get_io_context_name(io_context);
+
+			Datum		values[IO_NUM_COLUMNS] = {0};
+			bool		nulls[IO_NUM_COLUMNS] = {0};
+
+			/*
+			 * Some combinations of BackendType, IOObject, and IOContext are
+			 * not valid for any type of IOOp. In such cases, omit the entire
+			 * row from the view.
+			 */
+			if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
+				continue;
+
+			values[IO_COL_BACKEND_TYPE] = bktype_desc;
+			values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
+			values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
+			if (stat_reset_timestamp != 0)
+				values[IO_COL_RESET_TIME] = TimestampTzGetDatum(stat_reset_timestamp);
+			else
+				nulls[IO_COL_RESET_TIME] = true;
+
+			/*
+			 * Hard-code this to the value of BLCKSZ for now. Future values
+			 * could include XLOG_BLCKSZ, once WAL IO is tracked, and constant
+			 * multipliers, once non-block-oriented IO (e.g. temporary file
+			 * IO) is tracked.
+			 */
+			values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
+
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				int			op_idx = pgstat_get_io_op_index(io_op);
+				int			time_idx = pgstat_get_io_time_index(io_op);
+
+				/*
+				 * Some combinations of BackendType and IOOp, of IOContext and
+				 * IOOp, and of IOObject and IOOp are not tracked. Set these
+				 * cells in the view NULL.
+				 */
+				if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
+				{
+					PgStat_Counter count =
+						bktype_stats->counts[io_obj][io_context][io_op];
+
+					values[op_idx] = Int64GetDatum(count);
+				}
+				else
+					nulls[op_idx] = true;
+
+				/* not every operation is timed */
+				if (time_idx == IO_COL_INVALID)
+					continue;
+
+				if (!nulls[op_idx])
+				{
+					PgStat_Counter time =
+						bktype_stats->times[io_obj][io_context][io_op];
+
+					values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
+				}
+				else
+					nulls[time_idx] = true;
+			}
+
+			tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
+								 values, nulls);
+		}
+	}
+}
+
 Datum
 pg_stat_get_io(PG_FUNCTION_ARGS)
 {
 	ReturnSetInfo *rsinfo;
 	PgStat_IO  *backends_io_stats;
-	Datum		reset_time;
 
 	InitMaterializedSRF(fcinfo, 0);
 	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
 
 	backends_io_stats = pgstat_fetch_stat_io();
 
-	reset_time = TimestampTzGetDatum(backends_io_stats->stat_reset_timestamp);
-
 	for (int bktype = 0; bktype < BACKEND_NUM_TYPES; bktype++)
 	{
-		Datum		bktype_desc = CStringGetTextDatum(GetBackendTypeDesc(bktype));
 		PgStat_BktypeIO *bktype_stats = &backends_io_stats->stats[bktype];
 
 		/*
 		 * In Assert builds, we can afford an extra loop through all of the
-		 * counters checking that only expected stats are non-zero, since it
-		 * keeps the non-Assert code cleaner.
+		 * counters (in pg_stat_io_build_tuples()), checking that only
+		 * expected stats are non-zero, since it keeps the non-Assert code
+		 * cleaner.
 		 */
 		Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
 
@@ -1398,77 +1486,9 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 		if (!pgstat_tracks_io_bktype(bktype))
 			continue;
 
-		for (int io_obj = 0; io_obj < IOOBJECT_NUM_TYPES; io_obj++)
-		{
-			const char *obj_name = pgstat_get_io_object_name(io_obj);
-
-			for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
-			{
-				const char *context_name = pgstat_get_io_context_name(io_context);
-
-				Datum		values[IO_NUM_COLUMNS] = {0};
-				bool		nulls[IO_NUM_COLUMNS] = {0};
-
-				/*
-				 * Some combinations of BackendType, IOObject, and IOContext
-				 * are not valid for any type of IOOp. In such cases, omit the
-				 * entire row from the view.
-				 */
-				if (!pgstat_tracks_io_object(bktype, io_obj, io_context))
-					continue;
-
-				values[IO_COL_BACKEND_TYPE] = bktype_desc;
-				values[IO_COL_CONTEXT] = CStringGetTextDatum(context_name);
-				values[IO_COL_OBJECT] = CStringGetTextDatum(obj_name);
-				values[IO_COL_RESET_TIME] = reset_time;
-
-				/*
-				 * Hard-code this to the value of BLCKSZ for now. Future
-				 * values could include XLOG_BLCKSZ, once WAL IO is tracked,
-				 * and constant multipliers, once non-block-oriented IO (e.g.
-				 * temporary file IO) is tracked.
-				 */
-				values[IO_COL_CONVERSION] = Int64GetDatum(BLCKSZ);
-
-				for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
-				{
-					int			op_idx = pgstat_get_io_op_index(io_op);
-					int			time_idx = pgstat_get_io_time_index(io_op);
-
-					/*
-					 * Some combinations of BackendType and IOOp, of IOContext
-					 * and IOOp, and of IOObject and IOOp are not tracked. Set
-					 * these cells in the view NULL.
-					 */
-					if (pgstat_tracks_io_op(bktype, io_obj, io_context, io_op))
-					{
-						PgStat_Counter count =
-							bktype_stats->counts[io_obj][io_context][io_op];
-
-						values[op_idx] = Int64GetDatum(count);
-					}
-					else
-						nulls[op_idx] = true;
-
-					/* not every operation is timed */
-					if (time_idx == IO_COL_INVALID)
-						continue;
-
-					if (!nulls[op_idx])
-					{
-						PgStat_Counter time =
-							bktype_stats->times[io_obj][io_context][io_op];
-
-						values[time_idx] = Float8GetDatum(pg_stat_us_to_ms(time));
-					}
-					else
-						nulls[time_idx] = true;
-				}
-
-				tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
-									 values, nulls);
-			}
-		}
+		/* save tuples with data from this PgStat_BktypeIO */
+		pg_stat_io_build_tuples(rsinfo, bktype_stats, bktype,
+								backends_io_stats->stat_reset_timestamp);
 	}
 
 	return (Datum) 0;
-- 
2.34.1

From 6447dbe922e1db379dfd65f8041bc55cf3a3c573 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 18 Dec 2024 06:39:02 +0000
Subject: [PATCH v11 2/2] per backend I/O statistics

While pg_stat_io provides cluster-wide I/O statistics, this commit adds the
ability to track and display per backend I/O statistics.

It adds a new statistics kind and 2 new functions:

- pg_stat_reset_backend_stats() to be able to reset the stats for a given
backend pid.
- pg_stat_get_backend_io() to retrieve I/O statistics for a given backend pid.

The new KIND is named PGSTAT_KIND_BACKEND as it could be used in the future
to store other statistics (than the I/O ones) per backend. The new KIND is
a variable-numbered one and has an automatic cap on the maximum number of
entries (as its hash key contains the proc number).

There is no need to write the per backend I/O stats to disk (no point to
see stats for backends that do not exist anymore after a re-start), so using
"write_to_file = false".

Note that per backend I/O statistics are not collected for the checkpointer,
the background writer, the startup process and the autovacuum launcher as those
are already visible in pg_stat_io and there is only one of those.

XXX: Requires a bump of CATALOG_VERSION_NO.
XXX: Requires a bump of PGSTAT_FILE_FORMAT_ID.
---
 doc/src/sgml/config.sgml                     |   8 +-
 doc/src/sgml/monitoring.sgml                 |  39 ++++
 src/backend/catalog/system_functions.sql     |   2 +
 src/backend/utils/activity/Makefile          |   1 +
 src/backend/utils/activity/backend_status.c  |   4 +
 src/backend/utils/activity/meson.build       |   1 +
 src/backend/utils/activity/pgstat.c          |  21 +++
 src/backend/utils/activity/pgstat_backend.c  | 188 +++++++++++++++++++
 src/backend/utils/activity/pgstat_io.c       |  25 ++-
 src/backend/utils/activity/pgstat_relation.c |   2 +
 src/backend/utils/adt/pgstatfuncs.c          |  97 +++++++++-
 src/include/catalog/pg_proc.dat              |  13 ++
 src/include/pgstat.h                         |  34 +++-
 src/include/utils/pgstat_internal.h          |  14 ++
 src/test/regress/expected/stats.out          |  82 +++++++-
 src/test/regress/sql/stats.sql               |  42 ++++-
 src/tools/pgindent/typedefs.list             |   3 +
 17 files changed, 549 insertions(+), 27 deletions(-)
  10.3% doc/src/sgml/
  34.1% src/backend/utils/activity/
  14.7% src/backend/utils/adt/
   4.7% src/include/catalog/
   8.1% src/include/
  14.6% src/test/regress/expected/
  12.4% src/test/regress/sql/

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 24bd504c21..fbdd6ce574 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8403,9 +8403,11 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
         displayed in <link linkend="monitoring-pg-stat-database-view">
         <structname>pg_stat_database</structname></link>,
         <link linkend="monitoring-pg-stat-io-view">
-        <structname>pg_stat_io</structname></link>, in the output of
-        <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal> option
-        is used, in the output of <xref linkend="sql-vacuum"/> when
+        <structname>pg_stat_io</structname></link>, in the output of the
+        <link linkend="pg-stat-get-backend-io">
+        <function>pg_stat_get_backend_io()</function></link> function, in the
+        output of <xref linkend="sql-explain"/> when the <literal>BUFFERS</literal>
+        option is used, in the output of <xref linkend="sql-vacuum"/> when
         the <literal>VERBOSE</literal> option is used, by autovacuum
         for auto-vacuums and auto-analyzes, when <xref
         linkend="guc-log-autovacuum-min-duration"/> is set and by
diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 840d7f8161..d0d176cc54 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -4790,6 +4790,27 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry id="pg-stat-get-backend-io" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_get_backend_io</primary>
+        </indexterm>
+        <function>pg_stat_get_backend_io</function> ( <type>integer</type> )
+        <returnvalue>setof record</returnvalue>
+       </para>
+       <para>
+        Returns I/O statistics about the backend with the specified
+        process ID. The output fields are exactly the same as the ones in the
+        <structname>pg_stat_io</structname> view.
+       </para>
+       <para>
+        The function does not return I/O statistics for the checkpointer,
+        the background writer, the startup process and the autovacuum launcher
+        as they are already visible in the <structname>pg_stat_io</structname>
+        view and there is only one of each.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
@@ -4971,6 +4992,24 @@ description | Waiting for a newly initialized WAL file to reach durable storage
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_stat_reset_backend_stats</primary>
+        </indexterm>
+        <function>pg_stat_reset_backend_stats</function> ( <type>integer</type> )
+        <returnvalue>void</returnvalue>
+       </para>
+       <para>
+        Resets statistics for a single backend with the specified process ID
+        to zero.
+       </para>
+       <para>
+        This function is restricted to superusers by default, but other users
+        can be granted EXECUTE to run the function.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql
index c51dfca802..14eb99cd47 100644
--- a/src/backend/catalog/system_functions.sql
+++ b/src/backend/catalog/system_functions.sql
@@ -711,6 +711,8 @@ REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_table_counters(oid) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_single_function_counters(oid) FROM public;
 
+REVOKE EXECUTE ON FUNCTION pg_stat_reset_backend_stats(integer) FROM public;
+
 REVOKE EXECUTE ON FUNCTION pg_stat_reset_replication_slot(text) FROM public;
 
 REVOKE EXECUTE ON FUNCTION pg_stat_have_stats(text, oid, int8) FROM public;
diff --git a/src/backend/utils/activity/Makefile b/src/backend/utils/activity/Makefile
index b9fd66ea17..24b64a2742 100644
--- a/src/backend/utils/activity/Makefile
+++ b/src/backend/utils/activity/Makefile
@@ -20,6 +20,7 @@ OBJS = \
 	backend_status.o \
 	pgstat.o \
 	pgstat_archiver.o \
+	pgstat_backend.o \
 	pgstat_bgwriter.o \
 	pgstat_checkpointer.o \
 	pgstat_database.o \
diff --git a/src/backend/utils/activity/backend_status.c b/src/backend/utils/activity/backend_status.c
index 22c6dc378c..bf33e33a4e 100644
--- a/src/backend/utils/activity/backend_status.c
+++ b/src/backend/utils/activity/backend_status.c
@@ -426,6 +426,10 @@ pgstat_bestart(void)
 
 	PGSTAT_END_WRITE_ACTIVITY(vbeentry);
 
+	/* Create the backend statistics entry */
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+		pgstat_create_backend(MyProcNumber);
+
 	/* Update app name to current GUC setting */
 	if (application_name)
 		pgstat_report_appname(application_name);
diff --git a/src/backend/utils/activity/meson.build b/src/backend/utils/activity/meson.build
index f73c22905c..380d3dd70c 100644
--- a/src/backend/utils/activity/meson.build
+++ b/src/backend/utils/activity/meson.build
@@ -5,6 +5,7 @@ backend_sources += files(
   'backend_status.c',
   'pgstat.c',
   'pgstat_archiver.c',
+  'pgstat_backend.c',
   'pgstat_bgwriter.c',
   'pgstat_checkpointer.c',
   'pgstat_database.c',
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index b4e357c8a4..b72c779b2c 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -77,6 +77,7 @@
  *
  * Each statistics kind is handled in a dedicated file:
  * - pgstat_archiver.c
+ * - pgstat_backend.c
  * - pgstat_bgwriter.c
  * - pgstat_checkpointer.c
  * - pgstat_database.c
@@ -358,6 +359,22 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
+	[PGSTAT_KIND_BACKEND] = {
+		.name = "backend",
+
+		.fixed_amount = false,
+		.write_to_file = false,
+
+		.accessed_across_databases = true,
+
+		.shared_size = sizeof(PgStatShared_Backend),
+		.shared_data_off = offsetof(PgStatShared_Backend, stats),
+		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
+		.pending_size = sizeof(PgStat_BackendPendingIO),
+
+		.flush_pending_cb = pgstat_backend_flush_cb,
+		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
+	},
 
 	/* stats for fixed-numbered (mostly 1) objects */
 
@@ -602,6 +619,10 @@ pgstat_shutdown_hook(int code, Datum arg)
 	Assert(dlist_is_empty(&pgStatPending));
 	dlist_init(&pgStatPending);
 
+	/* drop the backend stats entry */
+	if (!pgstat_drop_entry(PGSTAT_KIND_BACKEND, InvalidOid, MyProcNumber))
+		pgstat_request_entry_refs_gc();
+
 	pgstat_detach_shmem();
 
 #ifdef USE_ASSERT_CHECKING
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
new file mode 100644
index 0000000000..6b2c9baa8c
--- /dev/null
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -0,0 +1,188 @@
+/* -------------------------------------------------------------------------
+ *
+ * pgstat_backend.c
+ *	  Implementation of backend statistics.
+ *
+ * This file contains the implementation of backend statistics.  It is kept
+ * separate from pgstat.c to enforce the line between the statistics access /
+ * storage implementation and the details about individual types of
+ * statistics.
+ *
+ * This statistics kind uses a proc number as object ID for the hash table
+ * of pgstats.  Entries are created each time a process is spawned, and are
+ * dropped when the process exits.  These are not written to the pgstats file
+ * on disk.
+ *
+ * Copyright (c) 2001-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/activity/pgstat_backend.c
+ * -------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "utils/pgstat_internal.h"
+
+/*
+ * Returns statistics of a backend by proc number.
+ */
+PgStat_Backend *
+pgstat_fetch_stat_backend(ProcNumber procNumber)
+{
+	PgStat_Backend *backend_entry;
+
+	backend_entry = (PgStat_Backend *) pgstat_fetch_entry(PGSTAT_KIND_BACKEND,
+														  InvalidOid, procNumber);
+
+	return backend_entry;
+}
+
+/*
+ * Flush out locally pending backend statistics
+ *
+ * If no stats have been recorded, this function returns false.
+ */
+bool
+pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+{
+	PgStatShared_Backend *shbackendioent;
+	PgStat_BackendPendingIO *pendingent;
+	PgStat_BktypeIO *bktype_shstats;
+
+	if (!pgstat_lock_entry(entry_ref, nowait))
+		return false;
+
+	shbackendioent = (PgStatShared_Backend *) entry_ref->shared_stats;
+	bktype_shstats = &shbackendioent->stats.stats;
+	pendingent = (PgStat_BackendPendingIO *) entry_ref->pending;
+
+	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
+	{
+		for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++)
+		{
+			for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++)
+			{
+				instr_time	time;
+
+				bktype_shstats->counts[io_object][io_context][io_op] +=
+					pendingent->counts[io_object][io_context][io_op];
+
+				time = pendingent->pending_times[io_object][io_context][io_op];
+
+				bktype_shstats->times[io_object][io_context][io_op] +=
+					INSTR_TIME_GET_MICROSEC(time);
+			}
+		}
+	}
+
+	pgstat_unlock_entry(entry_ref);
+
+	return true;
+}
+
+/*
+ * Simpler wrapper of pgstat_backend_flush_cb()
+ */
+void
+pgstat_flush_backend(bool nowait)
+{
+	PgStat_EntryRef *entry_ref;
+
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+									 MyProcNumber, false, NULL);
+	(void) pgstat_backend_flush_cb(entry_ref, nowait);
+}
+
+/*
+ * Create backend statistics entry for proc number.
+ */
+void
+pgstat_create_backend(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+	PgStatShared_Backend *shstatent;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
+
+	/*
+	 * NB: need to accept that there might be stats from an older backend,
+	 * e.g. if we previously used this proc number.
+	 */
+	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
+}
+
+/*
+ * Find or create a local PgStat_BackendPendingIO entry for proc number.
+ */
+PgStat_BackendPendingIO *
+pgstat_prep_backend_pending(ProcNumber procnum)
+{
+	PgStat_EntryRef *entry_ref;
+
+	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
+										  procnum, NULL);
+
+	return entry_ref->pending;
+}
+
+/*
+ * Backend statistics are not collected for all BackendTypes.
+ *
+ * The following BackendTypes do not participate in the backend stats
+ * subsystem:
+ * - The same and for the same reasons as in pgstat_tracks_io_bktype().
+ * - B_BG_WRITER, B_CHECKPOINTER, B_STARTUP and B_AUTOVAC_LAUNCHER because their
+ * I/O stats are already visible in pg_stat_io and there is only one of those.
+ *
+ * Function returns true if BackendType participates in the backend stats
+ * subsystem and false if it does not.
+ *
+ * When adding a new BackendType, also consider adding relevant restrictions to
+ * pgstat_tracks_io_object() and pgstat_tracks_io_op().
+ */
+bool
+pgstat_tracks_backend_bktype(BackendType bktype)
+{
+	/*
+	 * List every type so that new backend types trigger a warning about
+	 * needing to adjust this switch.
+	 */
+	switch (bktype)
+	{
+		case B_INVALID:
+		case B_AUTOVAC_LAUNCHER:
+		case B_DEAD_END_BACKEND:
+		case B_ARCHIVER:
+		case B_LOGGER:
+		case B_WAL_RECEIVER:
+		case B_WAL_WRITER:
+		case B_WAL_SUMMARIZER:
+		case B_BG_WRITER:
+		case B_CHECKPOINTER:
+		case B_STARTUP:
+			return false;
+
+		case B_AUTOVAC_WORKER:
+		case B_BACKEND:
+		case B_BG_WORKER:
+		case B_STANDALONE_BACKEND:
+		case B_SLOTSYNC_WORKER:
+		case B_WAL_SENDER:
+			return true;
+	}
+
+	return false;
+}
+
+void
+pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
+{
+	((PgStatShared_Backend *) header)->stats.stat_reset_timestamp = ts;
+}
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index f9883af2b3..011a3326da 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -20,14 +20,6 @@
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
 
-
-typedef struct PgStat_PendingIO
-{
-	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
-} PgStat_PendingIO;
-
-
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
 
@@ -87,6 +79,14 @@ pgstat_count_io_op_n(IOObject io_object, IOContext io_context, IOOp io_op, uint3
 	Assert((unsigned int) io_op < IOOP_NUM_TYPES);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
+	if (pgstat_tracks_backend_bktype(MyBackendType))
+	{
+		PgStat_PendingIO *entry_ref;
+
+		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+		entry_ref->counts[io_object][io_context][io_op] += cnt;
+	}
+
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 
 	have_iostats = true;
@@ -148,6 +148,15 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
+
+		if (pgstat_tracks_backend_bktype(MyBackendType))
+		{
+			PgStat_PendingIO *entry_ref;
+
+			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
+			INSTR_TIME_ADD(entry_ref->pending_times[io_object][io_context][io_op],
+						   io_time);
+		}
 	}
 
 	pgstat_count_io_op_n(io_object, io_context, io_op, cnt);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index faba8b64d2..85e65557bb 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,6 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
@@ -350,6 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
+	pgstat_flush_backend(false);
 }
 
 /*
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index efd35f700a..8387e11a93 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -1274,8 +1274,9 @@ pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
 }
 
 /*
-* When adding a new column to the pg_stat_io view, add a new enum value
-* here above IO_NUM_COLUMNS.
+* When adding a new column to the pg_stat_io view and the
+* pg_stat_get_backend_io() function, add a new enum value here above
+* IO_NUM_COLUMNS.
 */
 typedef enum io_stat_col
 {
@@ -1368,9 +1369,9 @@ pg_stat_us_to_ms(PgStat_Counter val_ms)
 /*
  * pg_stat_io_build_tuples
  *
- * Helper routine for pg_stat_get_io() filling in a result tuplestore with one
- * tuple for each object and each context supported by the caller, based on the
- * contents of bktype_stats.
+ * Helper routine for pg_stat_get_io() and pg_stat_get_backend_io(),
+ * filling in a result tuplestore with one tuple for each object and each
+ * context supported by the caller, based on the contents of bktype_stats.
  */
 static void
 pg_stat_io_build_tuples(ReturnSetInfo *rsinfo,
@@ -1494,6 +1495,68 @@ pg_stat_get_io(PG_FUNCTION_ARGS)
 	return (Datum) 0;
 }
 
+/*
+ * Returns I/O statistics for a backend with given PID.
+ */
+Datum
+pg_stat_get_backend_io(PG_FUNCTION_ARGS)
+{
+	ReturnSetInfo *rsinfo;
+	BackendType bktype;
+	int			pid;
+	PGPROC	   *proc;
+	ProcNumber	procNumber;
+	PgStat_Backend *backend_stats;
+	PgStat_BktypeIO *bktype_stats;
+	PgBackendStatus *beentry;
+
+	InitMaterializedSRF(fcinfo, 0);
+	rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+
+	pid = PG_GETARG_INT32(0);
+	proc = BackendPidGetProc(pid);
+
+	/*
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		return (Datum) 0;
+
+	procNumber = GetNumberFromPGProc(proc);
+
+	backend_stats = pgstat_fetch_stat_backend(procNumber);
+
+	if (!backend_stats)
+		return (Datum) 0;
+
+	beentry = pgstat_get_beentry_by_proc_number(procNumber);
+	bktype = beentry->st_backendType;
+
+	/* if PID does not match, leave */
+	if (beentry->st_procpid != pid)
+		return (Datum) 0;
+
+	/* backend may be gone, so recheck in case */
+	if (bktype == B_INVALID)
+		return (Datum) 0;
+
+	bktype_stats = &backend_stats->stats;
+
+	/*
+	 * In Assert builds, we can afford an extra loop through all of the
+	 * counters (in pg_stat_io_build_tuples()), checking that only expected
+	 * stats are non-zero, since it keeps the non-Assert code cleaner.
+	 */
+	Assert(pgstat_bktype_io_stats_valid(bktype_stats, bktype));
+
+	/* save tuples with data from this PgStat_BktypeIO */
+	pg_stat_io_build_tuples(rsinfo, bktype_stats, bktype,
+							backend_stats->stat_reset_timestamp);
+	return (Datum) 0;
+}
+
 /*
  * Returns statistics of WAL activity
  */
@@ -1799,6 +1862,30 @@ pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * Reset statistics of backend with given PID.
+ */
+Datum
+pg_stat_reset_backend_stats(PG_FUNCTION_ARGS)
+{
+	PGPROC	   *proc;
+	int			backend_pid = PG_GETARG_INT32(0);
+
+	proc = BackendPidGetProc(backend_pid);
+
+	/*
+	 * This could be an auxiliary process but these do not report backend
+	 * statistics due to pgstat_tracks_backend_bktype(), so there is no need
+	 * for an extra call to AuxiliaryPidGetProc().
+	 */
+	if (!proc)
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_BACKEND, InvalidOid, GetNumberFromPGProc(proc));
+
+	PG_RETURN_VOID();
+}
+
 /* Reset SLRU counters (a specific one or all of them). */
 Datum
 pg_stat_reset_slru(PG_FUNCTION_ARGS)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 0f22c21723..2dcc2d42da 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -5913,6 +5913,15 @@
   proargnames => '{backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
   prosrc => 'pg_stat_get_io' },
 
+{ oid => '8806', descr => 'statistics: backend IO statistics',
+  proname => 'pg_stat_get_backend_io', prorows => '5', proretset => 't',
+  provolatile => 'v', proparallel => 'r', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,text,text,text,int8,float8,int8,float8,int8,float8,int8,float8,int8,int8,int8,int8,int8,float8,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{backend_pid,backend_type,object,context,reads,read_time,writes,write_time,writebacks,writeback_time,extends,extend_time,op_bytes,hits,evictions,reuses,fsyncs,fsync_time,stats_reset}',
+  prosrc => 'pg_stat_get_backend_io' },
+
 { oid => '1136', descr => 'statistics: information about WAL activity',
   proname => 'pg_stat_get_wal', proisstrict => 'f', provolatile => 's',
   proparallel => 'r', prorettype => 'record', proargtypes => '',
@@ -6052,6 +6061,10 @@
   proname => 'pg_stat_reset_single_function_counters', provolatile => 'v',
   prorettype => 'void', proargtypes => 'oid',
   prosrc => 'pg_stat_reset_single_function_counters' },
+{ oid => '8807', descr => 'statistics: reset statistics for a single backend',
+  proname => 'pg_stat_reset_backend_stats', provolatile => 'v',
+  prorettype => 'void', proargtypes => 'int4',
+  prosrc => 'pg_stat_reset_backend_stats' },
 { oid => '2307',
   descr => 'statistics: reset collected statistics for a single SLRU',
   proname => 'pg_stat_reset_slru', proisstrict => 'f', provolatile => 'v',
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index ebfeef2f46..56ed1b8bb3 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -49,14 +49,15 @@
 #define PGSTAT_KIND_FUNCTION	3	/* per-function statistics */
 #define PGSTAT_KIND_REPLSLOT	4	/* per-slot statistics */
 #define PGSTAT_KIND_SUBSCRIPTION	5	/* per-subscription statistics */
+#define PGSTAT_KIND_BACKEND	6	/* per-backend statistics */
 
 /* stats for fixed-numbered objects */
-#define PGSTAT_KIND_ARCHIVER	6
-#define PGSTAT_KIND_BGWRITER	7
-#define PGSTAT_KIND_CHECKPOINTER	8
-#define PGSTAT_KIND_IO	9
-#define PGSTAT_KIND_SLRU	10
-#define PGSTAT_KIND_WAL	11
+#define PGSTAT_KIND_ARCHIVER	7
+#define PGSTAT_KIND_BGWRITER	8
+#define PGSTAT_KIND_CHECKPOINTER	9
+#define PGSTAT_KIND_IO	10
+#define PGSTAT_KIND_SLRU	11
+#define PGSTAT_KIND_WAL	12
 
 #define PGSTAT_KIND_BUILTIN_MIN PGSTAT_KIND_DATABASE
 #define PGSTAT_KIND_BUILTIN_MAX PGSTAT_KIND_WAL
@@ -362,12 +363,26 @@ typedef struct PgStat_BktypeIO
 	PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
 } PgStat_BktypeIO;
 
+typedef struct PgStat_PendingIO
+{
+	PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+	instr_time	pending_times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES];
+} PgStat_PendingIO;
+
 typedef struct PgStat_IO
 {
 	TimestampTz stat_reset_timestamp;
 	PgStat_BktypeIO stats[BACKEND_NUM_TYPES];
 } PgStat_IO;
 
+/* Backend statistics store the same amount of IO data as PGSTAT_KIND_IO */
+typedef PgStat_PendingIO PgStat_BackendPendingIO;
+
+typedef struct PgStat_Backend
+{
+	TimestampTz stat_reset_timestamp;
+	PgStat_BktypeIO stats;
+} PgStat_Backend;
 
 typedef struct PgStat_StatDBEntry
 {
@@ -549,6 +564,13 @@ extern bool pgstat_have_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_report_archiver(const char *xlog, bool failed);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
+extern bool pgstat_tracks_backend_bktype(BackendType bktype);
+extern void pgstat_create_backend(ProcNumber procnum);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 7338bc1e28..811ed9b005 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -450,6 +450,11 @@ typedef struct PgStatShared_ReplSlot
 	PgStat_StatReplSlotEntry stats;
 } PgStatShared_ReplSlot;
 
+typedef struct PgStatShared_Backend
+{
+	PgStatShared_Common header;
+	PgStat_Backend stats;
+} PgStatShared_Backend;
 
 /*
  * Central shared memory entry for the cumulative stats system.
@@ -604,6 +609,15 @@ extern void pgstat_archiver_init_shmem_cb(void *stats);
 extern void pgstat_archiver_reset_all_cb(TimestampTz ts);
 extern void pgstat_archiver_snapshot_cb(void);
 
+/*
+ * Functions in pgstat_backend.c
+ */
+
+extern void pgstat_flush_backend(bool nowait);
+
+extern PgStat_BackendPendingIO *pgstat_prep_backend_pending(ProcNumber procnum);
+extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 56771f83ed..150b6dcf74 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1249,7 +1249,8 @@ SELECT pg_stat_get_subscription_stats(NULL);
  
 (1 row)
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -1259,11 +1260,19 @@ SELECT pg_stat_get_subscription_stats(NULL);
 -- be sure of the state of shared buffers at the point the test is run.
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
@@ -1280,8 +1289,17 @@ SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
  t
 (1 row)
 
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
+ ?column? 
+----------
+ t
+(1 row)
+
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -1301,6 +1319,23 @@ SELECT current_setting('fsync') = 'off'
  t
 (1 row)
 
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
+ ?column? 
+----------
+ t
+(1 row)
+
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
 SELECT sum(reads) AS io_sum_shared_before_reads
@@ -1521,6 +1556,8 @@ SELECT pg_stat_have_stats('io', 0, 0);
 
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
  pg_stat_reset_shared 
 ----------------------
@@ -1535,6 +1572,47 @@ SELECT :io_stats_post_reset < :io_stats_pre_reset;
  t
 (1 row)
 
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+ pg_stat_reset_backend_stats 
+-----------------------------
+ 
+(1 row)
+
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+ ?column? 
+----------
+ t
+(1 row)
+
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+SELECT pg_stat_get_backend_io(0);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
+ pg_stat_get_backend_io 
+------------------------
+(0 rows)
+
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
   id  integer PRIMARY KEY,
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 7147cc2f89..1e7d0ff665 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -595,7 +595,8 @@ SELECT pg_stat_get_replication_slot(NULL);
 SELECT pg_stat_get_subscription_stats(NULL);
 
 
--- Test that the following operations are tracked in pg_stat_io:
+-- Test that the following operations are tracked in pg_stat_io and in
+-- backend stats:
 -- - reads of target blocks into shared buffers
 -- - writes of shared buffers to permanent storage
 -- - extends of relations using shared buffers
@@ -607,20 +608,32 @@ SELECT pg_stat_get_subscription_stats(NULL);
 
 -- Create a regular table and insert some data to generate IOCONTEXT_NORMAL
 -- extends.
+SELECT pid AS checkpointer_pid FROM pg_stat_activity
+  WHERE backend_type = 'checkpointer' \gset
 SELECT sum(extends) AS io_sum_shared_before_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
+SELECT sum(extends) AS my_io_sum_shared_before_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
 SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   FROM pg_stat_io
   WHERE object = 'relation' \gset io_sum_shared_before_
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_before_
 CREATE TABLE test_io_shared(a int);
 INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i;
 SELECT pg_stat_force_next_flush();
 SELECT sum(extends) AS io_sum_shared_after_extends
   FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset
 SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends;
+SELECT sum(extends) AS my_io_sum_shared_after_extends
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE context = 'normal' AND object = 'relation' \gset
+SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends;
 
 -- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes
--- and fsyncs.
+-- and fsyncs in the global stats (not for the backend).
 -- See comment above for rationale for two explicit CHECKPOINTs.
 CHECKPOINT;
 CHECKPOINT;
@@ -630,6 +643,13 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
 SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
   OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs;
+SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
+  FROM pg_stat_get_backend_io(pg_backend_pid())
+  WHERE object = 'relation' \gset my_io_sum_shared_after_
+SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
+SELECT current_setting('fsync') = 'off'
+  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
+      AND :my_io_sum_shared_after_fsyncs= 0);
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
@@ -762,11 +782,27 @@ SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_ext
 SELECT pg_stat_have_stats('io', 0, 0);
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset
   FROM pg_stat_io \gset
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
 SELECT pg_stat_reset_shared('io');
 SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset
   FROM pg_stat_io \gset
 SELECT :io_stats_post_reset < :io_stats_pre_reset;
-
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+-- pg_stat_reset_shared() did not reset backend IO stats
+SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset;
+-- but pg_stat_reset_backend_stats() does
+SELECT pg_stat_reset_backend_stats(pg_backend_pid());
+SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset
+  FROM pg_stat_get_backend_io(pg_backend_pid()) \gset
+SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset;
+
+-- Check invalid input for pg_stat_get_backend_io()
+SELECT pg_stat_get_backend_io(NULL);
+SELECT pg_stat_get_backend_io(0);
+-- Auxiliary processes return no data.
+SELECT pg_stat_get_backend_io(:checkpointer_pid);
 
 -- test BRIN index doesn't block HOT update
 CREATE TABLE brin_hot (
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ce33e55bf1..398dd92527 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2121,6 +2121,7 @@ PgFdwSamplingMethod
 PgFdwScanState
 PgIfAddrCallback
 PgStatShared_Archiver
+PgStatShared_Backend
 PgStatShared_BgWriter
 PgStatShared_Checkpointer
 PgStatShared_Common
@@ -2136,6 +2137,8 @@ PgStatShared_SLRU
 PgStatShared_Subscription
 PgStatShared_Wal
 PgStat_ArchiverStats
+PgStat_Backend
+PgStat_BackendPendingIO
 PgStat_BackendSubEntry
 PgStat_BgWriterStats
 PgStat_BktypeIO
-- 
2.34.1

From a83def4ca95c154e824378452cb15f100887a56c Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Fri, 20 Dec 2024 08:59:53 +0000
Subject: [PATCH v1] Fix per-backend IO stats regression test

The tests added in 9aea73fc61 did not take into account that the backend can
fsync in some circumstances.
---
 src/test/regress/expected/stats.out | 3 +--
 src/test/regress/sql/stats.sql      | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)
  50.0% src/test/regress/expected/
  50.0% src/test/regress/sql/

diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 150b6dcf74..d18fc7c081 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1329,8 +1329,7 @@ SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
 (1 row)
 
 SELECT current_setting('fsync') = 'off'
-  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
-      AND :my_io_sum_shared_after_fsyncs= 0);
+  OR :my_io_sum_shared_after_fsyncs >= :my_io_sum_shared_before_fsyncs;
  ?column? 
 ----------
  t
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 1e7d0ff665..fc0d2fde31 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -648,8 +648,7 @@ SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
   WHERE object = 'relation' \gset my_io_sum_shared_after_
 SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes;
 SELECT current_setting('fsync') = 'off'
-  OR (:my_io_sum_shared_after_fsyncs = :my_io_sum_shared_before_fsyncs
-      AND :my_io_sum_shared_after_fsyncs= 0);
+  OR :my_io_sum_shared_after_fsyncs >= :my_io_sum_shared_before_fsyncs;
 
 -- Change the tablespace so that the table is rewritten directly, then SELECT
 -- from it to cause it to be read back into shared buffers.
-- 
2.34.1

From 48d715a4a8b667628bb8ccf573e0003eb8f54633 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Fri, 17 Jan 2025 06:44:47 +0000
Subject: [PATCH v1] Rework per backend pending stats

9aea73fc61d added per backend pending statistics but not all of them are well
suited to memory allocation and have to be outside of critical sections.

For those (the only current one is I/O statistics but WAL statistics is under
discussion), let's rely on a new PendingBackendStats instead.
---
 src/backend/utils/activity/pgstat.c         | 27 ++++++++++++++++++-
 src/backend/utils/activity/pgstat_backend.c | 29 +++++++++++++++------
 src/backend/utils/activity/pgstat_io.c      | 14 +++-------
 src/include/pgstat.h                        | 12 +++++++++
 4 files changed, 62 insertions(+), 20 deletions(-)
  89.0% src/backend/utils/activity/
  10.9% src/include/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 34520535d54..27aa0491001 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -1369,6 +1369,7 @@ static bool
 pgstat_flush_pending_entries(bool nowait)
 {
 	bool		have_pending = false;
+	bool		backend_have_pending = false;
 	dlist_node *cur = NULL;
 
 	/*
@@ -1416,9 +1417,33 @@ pgstat_flush_pending_entries(bool nowait)
 		cur = next;
 	}
 
+	/*
+	 * There is a special case for some pending stats that are tracked in
+	 * PendingBackendStats. It's possible that those have not been flushed
+	 * above, hence the extra check here.
+	 */
+	if (!pg_memory_is_all_zeros(&PendingBackendStats,
+								sizeof(struct PgStat_BackendPending)))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+
+		if (entry_ref)
+		{
+			PgStat_HashKey key = entry_ref->shared_entry->key;
+			PgStat_Kind kind = key.kind;
+			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+
+			if (!kind_info->flush_pending_cb(entry_ref, nowait))
+				backend_have_pending = true;
+		}
+	}
+
 	Assert(dlist_is_empty(&pgStatPending) == !have_pending);
 
-	return have_pending;
+	return (have_pending || backend_have_pending);
 }
 
 
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 79e4d0a3053..ca5cec348b2 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -22,8 +22,11 @@
 
 #include "postgres.h"
 
+#include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 
+PgStat_BackendPending PendingBackendStats = {0};
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -46,14 +49,20 @@ static void
 pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 {
 	PgStatShared_Backend *shbackendent;
-	PgStat_BackendPending *pendingent;
 	PgStat_BktypeIO *bktype_shstats;
-	PgStat_PendingIO *pending_io;
+	PgStat_PendingIO pending_io;
+
+	/*
+	 * This function can be called even if nothing at all has happened. In
+	 * this case, avoid unnecessarily modifying the stats entry.
+	 */
+	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
+							   sizeof(struct PgStat_PendingIO)))
+		return;
 
 	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
-	pendingent = (PgStat_BackendPending *) entry_ref->pending;
 	bktype_shstats = &shbackendent->stats.io_stats;
-	pending_io = &pendingent->pending_io;
+	pending_io = PendingBackendStats.pending_io;
 
 	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
 	{
@@ -64,17 +73,21 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 				instr_time	time;
 
 				bktype_shstats->counts[io_object][io_context][io_op] +=
-					pending_io->counts[io_object][io_context][io_op];
+					pending_io.counts[io_object][io_context][io_op];
 				bktype_shstats->bytes[io_object][io_context][io_op] +=
-					pending_io->bytes[io_object][io_context][io_op];
-
-				time = pending_io->pending_times[io_object][io_context][io_op];
+					pending_io.bytes[io_object][io_context][io_op];
+				time = pending_io.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 027aad8b24e..b8f19515ae1 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -75,11 +75,8 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 
 	if (pgstat_tracks_backend_bktype(MyBackendType))
 	{
-		PgStat_BackendPending *entry_ref;
-
-		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-		entry_ref->pending_io.counts[io_object][io_context][io_op] += cnt;
-		entry_ref->pending_io.bytes[io_object][io_context][io_op] += bytes;
+		PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
+		PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 	}
 
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
@@ -146,13 +143,8 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 					   io_time);
 
 		if (pgstat_tracks_backend_bktype(MyBackendType))
-		{
-			PgStat_BackendPending *entry_ref;
-
-			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-			INSTR_TIME_ADD(entry_ref->pending_io.pending_times[io_object][io_context][io_op],
+			INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 						   io_time);
-		}
 	}
 
 	pgstat_count_io_op(io_object, io_context, io_op, cnt, bytes);
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2d40fe3e70f..3eb7b6614fe 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -826,5 +826,17 @@ extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 /* updated directly by backends and background processes */
 extern PGDLLIMPORT PgStat_PendingWalStats PendingWalStats;
 
+/*
+ * Variables in pgstat_backend.c
+ */
+
+/* updated directly by backends */
+
+/*
+ * Some pending statistics are not well suited to memory allocation and have
+ * to be outside of critical sections. For those, let's rely on this variable
+ * instead.
+ */
+extern PGDLLIMPORT PgStat_BackendPending PendingBackendStats;
 
 #endif							/* PGSTAT_H */
-- 
2.34.1

From 90ffa6d32a9cd0034a2fd97c31991199f2089698 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Fri, 17 Jan 2025 06:44:47 +0000
Subject: [PATCH v2 1/2] Rework per backend pending stats

9aea73fc61d added per backend pending statistics but not all of them are well
suited to memory allocation and have to be outside of critical sections.

For those (the only current one is I/O statistics but WAL statistics is under
discussion), let's rely on a new PendingBackendStats instead.
---
 src/include/pgstat.h                        | 12 +++++++++
 src/backend/utils/activity/pgstat.c         | 27 ++++++++++++++++++-
 src/backend/utils/activity/pgstat_backend.c | 29 +++++++++++++++------
 src/backend/utils/activity/pgstat_io.c      | 14 +++-------
 4 files changed, 62 insertions(+), 20 deletions(-)

diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2d40fe3e70..3eb7b6614f 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -826,5 +826,17 @@ extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 /* updated directly by backends and background processes */
 extern PGDLLIMPORT PgStat_PendingWalStats PendingWalStats;
 
+/*
+ * Variables in pgstat_backend.c
+ */
+
+/* updated directly by backends */
+
+/*
+ * Some pending statistics are not well suited to memory allocation and have
+ * to be outside of critical sections. For those, let's rely on this variable
+ * instead.
+ */
+extern PGDLLIMPORT PgStat_BackendPending PendingBackendStats;
 
 #endif							/* PGSTAT_H */
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 34520535d5..27aa049100 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -1369,6 +1369,7 @@ static bool
 pgstat_flush_pending_entries(bool nowait)
 {
 	bool		have_pending = false;
+	bool		backend_have_pending = false;
 	dlist_node *cur = NULL;
 
 	/*
@@ -1416,9 +1417,33 @@ pgstat_flush_pending_entries(bool nowait)
 		cur = next;
 	}
 
+	/*
+	 * There is a special case for some pending stats that are tracked in
+	 * PendingBackendStats. It's possible that those have not been flushed
+	 * above, hence the extra check here.
+	 */
+	if (!pg_memory_is_all_zeros(&PendingBackendStats,
+								sizeof(struct PgStat_BackendPending)))
+	{
+		PgStat_EntryRef *entry_ref;
+
+		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
+										 MyProcNumber, false, NULL);
+
+		if (entry_ref)
+		{
+			PgStat_HashKey key = entry_ref->shared_entry->key;
+			PgStat_Kind kind = key.kind;
+			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+
+			if (!kind_info->flush_pending_cb(entry_ref, nowait))
+				backend_have_pending = true;
+		}
+	}
+
 	Assert(dlist_is_empty(&pgStatPending) == !have_pending);
 
-	return have_pending;
+	return (have_pending || backend_have_pending);
 }
 
 
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 79e4d0a305..ca5cec348b 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -22,8 +22,11 @@
 
 #include "postgres.h"
 
+#include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 
+PgStat_BackendPending PendingBackendStats = {0};
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -46,14 +49,20 @@ static void
 pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 {
 	PgStatShared_Backend *shbackendent;
-	PgStat_BackendPending *pendingent;
 	PgStat_BktypeIO *bktype_shstats;
-	PgStat_PendingIO *pending_io;
+	PgStat_PendingIO pending_io;
+
+	/*
+	 * This function can be called even if nothing at all has happened. In
+	 * this case, avoid unnecessarily modifying the stats entry.
+	 */
+	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
+							   sizeof(struct PgStat_PendingIO)))
+		return;
 
 	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
-	pendingent = (PgStat_BackendPending *) entry_ref->pending;
 	bktype_shstats = &shbackendent->stats.io_stats;
-	pending_io = &pendingent->pending_io;
+	pending_io = PendingBackendStats.pending_io;
 
 	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
 	{
@@ -64,17 +73,21 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 				instr_time	time;
 
 				bktype_shstats->counts[io_object][io_context][io_op] +=
-					pending_io->counts[io_object][io_context][io_op];
+					pending_io.counts[io_object][io_context][io_op];
 				bktype_shstats->bytes[io_object][io_context][io_op] +=
-					pending_io->bytes[io_object][io_context][io_op];
-
-				time = pending_io->pending_times[io_object][io_context][io_op];
+					pending_io.bytes[io_object][io_context][io_op];
+				time = pending_io.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 027aad8b24..b8f19515ae 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -75,11 +75,8 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 
 	if (pgstat_tracks_backend_bktype(MyBackendType))
 	{
-		PgStat_BackendPending *entry_ref;
-
-		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-		entry_ref->pending_io.counts[io_object][io_context][io_op] += cnt;
-		entry_ref->pending_io.bytes[io_object][io_context][io_op] += bytes;
+		PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
+		PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 	}
 
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
@@ -146,13 +143,8 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 					   io_time);
 
 		if (pgstat_tracks_backend_bktype(MyBackendType))
-		{
-			PgStat_BackendPending *entry_ref;
-
-			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-			INSTR_TIME_ADD(entry_ref->pending_io.pending_times[io_object][io_context][io_op],
+			INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 						   io_time);
-		}
 	}
 
 	pgstat_count_io_op(io_object, io_context, io_op, cnt, bytes);
-- 
2.47.1

From 99561e65c3e266157ac21588097c8222a1df1d28 Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Mon, 20 Jan 2025 15:31:57 +0900
Subject: [PATCH v2 2/2] More work to allow backend statistics in critical
 sections

Callbacks are refactored so as variable-numbered stats can use them if
they don't want to use pending data, like the backend stats.
---
 src/include/pgstat.h                         |  21 ++-
 src/include/utils/pgstat_internal.h          |  29 ++--
 src/backend/utils/activity/pgstat.c          |  67 +++------
 src/backend/utils/activity/pgstat_backend.c  | 142 ++++++++++++-------
 src/backend/utils/activity/pgstat_io.c       |  15 +-
 src/backend/utils/activity/pgstat_relation.c |   4 +-
 6 files changed, 140 insertions(+), 138 deletions(-)

diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 3eb7b6614f..d0d4515097 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -540,6 +540,15 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
  * Functions in pgstat_backend.c
  */
 
+/* used by pgstat_io.c for I/O stats tracked in backends */
+extern void pgstat_count_backend_io_op_time(IOObject io_object,
+											IOContext io_context,
+											IOOp io_op,
+											instr_time io_time);
+extern void pgstat_count_backend_io_op(IOObject io_object,
+									   IOContext io_context,
+									   IOOp io_op, uint32 cnt,
+									   uint64 bytes);
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern bool pgstat_tracks_backend_bktype(BackendType bktype);
 extern void pgstat_create_backend(ProcNumber procnum);
@@ -826,17 +835,5 @@ extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 /* updated directly by backends and background processes */
 extern PGDLLIMPORT PgStat_PendingWalStats PendingWalStats;
 
-/*
- * Variables in pgstat_backend.c
- */
-
-/* updated directly by backends */
-
-/*
- * Some pending statistics are not well suited to memory allocation and have
- * to be outside of critical sections. For those, let's rely on this variable
- * instead.
- */
-extern PGDLLIMPORT PgStat_BackendPending PendingBackendStats;
 
 #endif							/* PGSTAT_H */
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 4bb8e5c53a..000ed5b36f 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -259,8 +259,8 @@ typedef struct PgStat_KindInfo
 	void		(*init_backend_cb) (void);
 
 	/*
-	 * For variable-numbered stats: flush pending stats. Required if pending
-	 * data is used.  See flush_fixed_cb for fixed-numbered stats.
+	 * For variable-numbered stats: flush pending stats within the dshash.
+	 * Required if pending data interacts with the pgstats dshash.
 	 */
 	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
 
@@ -289,17 +289,19 @@ typedef struct PgStat_KindInfo
 	void		(*init_shmem_cb) (void *stats);
 
 	/*
-	 * For fixed-numbered statistics: Flush pending stats. Returns true if
-	 * some of the stats could not be flushed, due to lock contention for
-	 * example. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Check for pending
+	 * stats in need of flush, when these do not use the pgstats dshash.
+	 * Returns true if there are any stats pending for flush, triggering
+	 * flush_cb. Optional.
 	 */
-	bool		(*flush_fixed_cb) (bool nowait);
+	bool		(*have_pending_cb) (void);
 
 	/*
-	 * For fixed-numbered statistics: Check for pending stats in need of
-	 * flush. Returns true if there are any stats pending for flush. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Flush pending
+	 * stats. Returns true if some of the stats could not be flushed, due
+	 * to lock contention for example. Optional.
 	 */
-	bool		(*have_fixed_pending_cb) (void);
+	bool		(*flush_cb) (bool nowait);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -617,10 +619,11 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL	(PGSTAT_BACKEND_FLUSH_IO)
 
-extern void pgstat_flush_backend(bool nowait, bits32 flags);
-extern PgStat_BackendPending *pgstat_prep_backend_pending(ProcNumber procnum);
-extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
-extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags);
+extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_backend_have_pending_cb(void);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
+											  TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 27aa049100..bd1ffad6f4 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -372,7 +372,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
 		.pending_size = sizeof(PgStat_BackendPending),
 
-		.flush_pending_cb = pgstat_backend_flush_cb,
+		.have_pending_cb = pgstat_backend_have_pending_cb,
+		.flush_cb = pgstat_backend_flush_cb,
 		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
 	},
 
@@ -437,8 +438,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_IO, stats),
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_io_flush_cb,
-		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
+		.flush_cb = pgstat_io_flush_cb,
+		.have_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
 		.snapshot_cb = pgstat_io_snapshot_cb,
@@ -455,8 +456,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_SLRU, stats),
 		.shared_data_len = sizeof(((PgStatShared_SLRU *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_slru_flush_cb,
-		.have_fixed_pending_cb = pgstat_slru_have_pending_cb,
+		.flush_cb = pgstat_slru_flush_cb,
+		.have_pending_cb = pgstat_slru_have_pending_cb,
 		.init_shmem_cb = pgstat_slru_init_shmem_cb,
 		.reset_all_cb = pgstat_slru_reset_all_cb,
 		.snapshot_cb = pgstat_slru_snapshot_cb,
@@ -474,8 +475,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Wal *) 0)->stats),
 
 		.init_backend_cb = pgstat_wal_init_backend_cb,
-		.flush_fixed_cb = pgstat_wal_flush_cb,
-		.have_fixed_pending_cb = pgstat_wal_have_pending_cb,
+		.flush_cb = pgstat_wal_flush_cb,
+		.have_pending_cb = pgstat_wal_have_pending_cb,
 		.init_shmem_cb = pgstat_wal_init_shmem_cb,
 		.reset_all_cb = pgstat_wal_reset_all_cb,
 		.snapshot_cb = pgstat_wal_snapshot_cb,
@@ -713,22 +714,17 @@ pgstat_report_stat(bool force)
 	{
 		bool		do_flush = false;
 
-		/* Check for pending fixed-numbered stats */
+		/* Check for pending stats */
 		for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 		{
 			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 			if (!kind_info)
 				continue;
-			if (!kind_info->fixed_amount)
-			{
-				Assert(kind_info->have_fixed_pending_cb == NULL);
-				continue;
-			}
-			if (!kind_info->have_fixed_pending_cb)
+			if (!kind_info->have_pending_cb)
 				continue;
 
-			if (kind_info->have_fixed_pending_cb())
+			if (kind_info->have_pending_cb())
 			{
 				do_flush = true;
 				break;
@@ -792,22 +788,20 @@ pgstat_report_stat(bool force)
 	/* flush of variable-numbered stats */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
-	/* flush of fixed-numbered stats */
+	/*
+	 * Flush of other stats, which could be variable-numbered or
+	 * fixed-numbered.
+	 */
 	for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 	{
 		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 		if (!kind_info)
 			continue;
-		if (!kind_info->fixed_amount)
-		{
-			Assert(kind_info->flush_fixed_cb == NULL);
-			continue;
-		}
-		if (!kind_info->flush_fixed_cb)
+		if (!kind_info->flush_cb)
 			continue;
 
-		partial_flush |= kind_info->flush_fixed_cb(nowait);
+		partial_flush |= kind_info->flush_cb(nowait);
 	}
 
 	last_flush = now;
@@ -1369,7 +1363,6 @@ static bool
 pgstat_flush_pending_entries(bool nowait)
 {
 	bool		have_pending = false;
-	bool		backend_have_pending = false;
 	dlist_node *cur = NULL;
 
 	/*
@@ -1417,33 +1410,9 @@ pgstat_flush_pending_entries(bool nowait)
 		cur = next;
 	}
 
-	/*
-	 * There is a special case for some pending stats that are tracked in
-	 * PendingBackendStats. It's possible that those have not been flushed
-	 * above, hence the extra check here.
-	 */
-	if (!pg_memory_is_all_zeros(&PendingBackendStats,
-								sizeof(struct PgStat_BackendPending)))
-	{
-		PgStat_EntryRef *entry_ref;
-
-		entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-										 MyProcNumber, false, NULL);
-
-		if (entry_ref)
-		{
-			PgStat_HashKey key = entry_ref->shared_entry->key;
-			PgStat_Kind kind = key.kind;
-			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
-
-			if (!kind_info->flush_pending_cb(entry_ref, nowait))
-				backend_have_pending = true;
-		}
-	}
-
 	Assert(dlist_is_empty(&pgStatPending) == !have_pending);
 
-	return (have_pending || backend_have_pending);
+	return have_pending;
 }
 
 
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index ca5cec348b..fb7abf64a0 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -11,7 +11,9 @@
  * This statistics kind uses a proc number as object ID for the hash table
  * of pgstats.  Entries are created each time a process is spawned, and are
  * dropped when the process exits.  These are not written to the pgstats file
- * on disk.
+ * on disk.  Pending statistics are managed without direct interactions with
+ * the pgstats dshash, relying on PendingBackendStats instead so as it is
+ * possible to report data within critical sections.
  *
  * Copyright (c) 2001-2025, PostgreSQL Global Development Group
  *
@@ -22,10 +24,53 @@
 
 #include "postgres.h"
 
+#include "storage/bufmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 
-PgStat_BackendPending PendingBackendStats = {0};
+/*
+ * Backend statistics counts waiting to be flushed out.  We assume this variable
+ * inits to zeroes.  These counters may be reported within critical sections so
+ * we use static memory in order to avoid memory allocation.
+ */
+static PgStat_BackendPending PendingBackendStats = {0};
+static bool have_backendstats = false;
+
+/*
+ * Utility routines to report I/O stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
+								IOOp io_op, instr_time io_time)
+{
+	Assert(track_io_timing);
+
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
+				   io_time);
+
+	have_backendstats = true;
+}
+
+void
+pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
+						   IOOp io_op, uint32 cnt, uint64 bytes)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
+	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
+
+	have_backendstats = true;
+}
 
 /*
  * Returns statistics of a backend by proc number.
@@ -53,8 +98,9 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 	PgStat_PendingIO pending_io;
 
 	/*
-	 * This function can be called even if nothing at all has happened. In
-	 * this case, avoid unnecessarily modifying the stats entry.
+	 * This function can be called even if nothing at all has happened for
+	 * IO statistics.  In this case, avoid unnecessarily modifying the stats
+	 * entry.
 	 */
 	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
 							   sizeof(struct PgStat_PendingIO)))
@@ -83,25 +129,29 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 			}
 		}
 	}
-
-	/*
-	 * Clear out the statistics buffer, so it can be re-used.
-	 */
-	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
- * Wrapper routine to flush backend statistics.
+ * Flush out locally pending backend statistics
+ *
+ * "flags" parameter controls which statistics to flush.  Returns true
+ * if some statistics could not be flushed.
  */
-static bool
-pgstat_flush_backend_entry(PgStat_EntryRef *entry_ref, bool nowait,
-						   bits32 flags)
+bool
+pgstat_flush_backend(bool nowait, bits32 flags)
 {
+	PgStat_EntryRef *entry_ref;
+
+	if (!have_backendstats)
+		return false;
+
 	if (!pgstat_tracks_backend_bktype(MyBackendType))
 		return false;
 
-	if (!pgstat_lock_entry(entry_ref, nowait))
-		return false;
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, nowait);
+	if (!entry_ref)
+		return true;
 
 	/* Flush requested statistics */
 	if (flags & PGSTAT_BACKEND_FLUSH_IO)
@@ -109,36 +159,33 @@ pgstat_flush_backend_entry(PgStat_EntryRef *entry_ref, bool nowait,
 
 	pgstat_unlock_entry(entry_ref);
 
-	return true;
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
+
+	have_backendstats = false;
+	return false;
+}
+
+/*
+ * Check if there are any backend stats waiting for flush.
+ */
+bool
+pgstat_backend_have_pending_cb(void)
+{
+	return have_backendstats;
 }
 
 /*
  * Callback to flush out locally pending backend statistics.
  *
- * If no stats have been recorded, this function returns false.
+ * If some stats could not be flushed, return true.
  */
 bool
-pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_backend_flush_cb(bool nowait)
 {
-	return pgstat_flush_backend_entry(entry_ref, nowait, PGSTAT_BACKEND_FLUSH_ALL);
-}
-
-/*
- * Flush out locally pending backend statistics
- *
- * "flags" parameter controls which statistics to flush.
- */
-void
-pgstat_flush_backend(bool nowait, bits32 flags)
-{
-	PgStat_EntryRef *entry_ref;
-
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
-		return;
-
-	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-									 MyProcNumber, false, NULL);
-	(void) pgstat_flush_backend_entry(entry_ref, nowait, flags);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
 }
 
 /*
@@ -150,9 +197,8 @@ pgstat_create_backend(ProcNumber procnum)
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Backend *shstatent;
 
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
-
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, false);
 	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
 
 	/*
@@ -160,20 +206,10 @@ pgstat_create_backend(ProcNumber procnum)
 	 * e.g. if we previously used this proc number.
 	 */
 	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
-}
+	pgstat_unlock_entry(entry_ref);
 
-/*
- * Find or create a local PgStat_BackendPending entry for proc number.
- */
-PgStat_BackendPending *
-pgstat_prep_backend_pending(ProcNumber procnum)
-{
-	PgStat_EntryRef *entry_ref;
-
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
-
-	return entry_ref->pending;
+	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
+	have_backendstats = false;
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index b8f19515ae..6ff5d9e96a 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -73,15 +73,12 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	Assert(pgstat_is_ioop_tracked_in_bytes(io_op) || bytes == 0);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
-	if (pgstat_tracks_backend_bktype(MyBackendType))
-	{
-		PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
-		PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
-	}
-
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 	PendingIOStats.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Add the per-backend counts */
+	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
+
 	have_iostats = true;
 }
 
@@ -142,9 +139,9 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
 
-		if (pgstat_tracks_backend_bktype(MyBackendType))
-			INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
-						   io_time);
+		/* Add the per-backend count */
+		pgstat_count_backend_io_op_time(io_object, io_context, io_op,
+										io_time);
 	}
 
 	pgstat_count_io_op(io_object, io_context, io_op, cnt, bytes);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 09247ba097..965a7fe2c6 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
@@ -351,7 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
-- 
2.47.1

From c945a5800554ec90f42091d8175ed50e00ead45f Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Fri, 17 Jan 2025 06:44:47 +0000
Subject: [PATCH v3 1/2] Rework per backend pending stats

9aea73fc61d added per backend pending statistics but not all of them are well
suited to memory allocation and have to be outside of critical sections.

For those (the only current one is I/O statistics but WAL statistics is under
discussion), let's rely on a new PendingBackendStats instead.
---
 src/backend/utils/activity/pgstat.c           |  53 +++----
 src/backend/utils/activity/pgstat_backend.c   | 142 ++++++++++++------
 src/backend/utils/activity/pgstat_io.c        |  23 +--
 src/backend/utils/activity/pgstat_relation.c  |   4 +-
 src/include/pgstat.h                          |   9 ++
 src/include/utils/pgstat_internal.h           |  36 +++--
 .../injection_points/injection_stats.c        |   2 +-
 7 files changed, 153 insertions(+), 116 deletions(-)
  75.8% src/backend/utils/activity/
  19.6% src/include/utils/
   3.6% src/include/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 34520535d54..0a4b687f045 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -292,7 +292,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Database *) 0)->stats),
 		.pending_size = sizeof(PgStat_StatDBEntry),
 
-		.flush_pending_cb = pgstat_database_flush_cb,
+		.flush_dynamic_cb = pgstat_database_flush_cb,
 		.reset_timestamp_cb = pgstat_database_reset_timestamp_cb,
 	},
 
@@ -307,7 +307,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Relation *) 0)->stats),
 		.pending_size = sizeof(PgStat_TableStatus),
 
-		.flush_pending_cb = pgstat_relation_flush_cb,
+		.flush_dynamic_cb = pgstat_relation_flush_cb,
 		.delete_pending_cb = pgstat_relation_delete_pending_cb,
 	},
 
@@ -322,7 +322,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Function *) 0)->stats),
 		.pending_size = sizeof(PgStat_FunctionCounts),
 
-		.flush_pending_cb = pgstat_function_flush_cb,
+		.flush_dynamic_cb = pgstat_function_flush_cb,
 	},
 
 	[PGSTAT_KIND_REPLSLOT] = {
@@ -355,7 +355,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Subscription *) 0)->stats),
 		.pending_size = sizeof(PgStat_BackendSubEntry),
 
-		.flush_pending_cb = pgstat_subscription_flush_cb,
+		.flush_dynamic_cb = pgstat_subscription_flush_cb,
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
@@ -372,7 +372,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
 		.pending_size = sizeof(PgStat_BackendPending),
 
-		.flush_pending_cb = pgstat_backend_flush_cb,
+		.have_pending_cb = pgstat_backend_have_pending_cb,
+		.flush_static_cb = pgstat_backend_flush_cb,
 		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
 	},
 
@@ -437,8 +438,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_IO, stats),
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_io_flush_cb,
-		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
+		.flush_static_cb = pgstat_io_flush_cb,
+		.have_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
 		.snapshot_cb = pgstat_io_snapshot_cb,
@@ -455,8 +456,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_SLRU, stats),
 		.shared_data_len = sizeof(((PgStatShared_SLRU *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_slru_flush_cb,
-		.have_fixed_pending_cb = pgstat_slru_have_pending_cb,
+		.flush_static_cb = pgstat_slru_flush_cb,
+		.have_pending_cb = pgstat_slru_have_pending_cb,
 		.init_shmem_cb = pgstat_slru_init_shmem_cb,
 		.reset_all_cb = pgstat_slru_reset_all_cb,
 		.snapshot_cb = pgstat_slru_snapshot_cb,
@@ -474,8 +475,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Wal *) 0)->stats),
 
 		.init_backend_cb = pgstat_wal_init_backend_cb,
-		.flush_fixed_cb = pgstat_wal_flush_cb,
-		.have_fixed_pending_cb = pgstat_wal_have_pending_cb,
+		.flush_static_cb = pgstat_wal_flush_cb,
+		.have_pending_cb = pgstat_wal_have_pending_cb,
 		.init_shmem_cb = pgstat_wal_init_shmem_cb,
 		.reset_all_cb = pgstat_wal_reset_all_cb,
 		.snapshot_cb = pgstat_wal_snapshot_cb,
@@ -713,22 +714,17 @@ pgstat_report_stat(bool force)
 	{
 		bool		do_flush = false;
 
-		/* Check for pending fixed-numbered stats */
+		/* Check for pending stats */
 		for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 		{
 			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 			if (!kind_info)
 				continue;
-			if (!kind_info->fixed_amount)
-			{
-				Assert(kind_info->have_fixed_pending_cb == NULL);
-				continue;
-			}
-			if (!kind_info->have_fixed_pending_cb)
+			if (!kind_info->have_pending_cb)
 				continue;
 
-			if (kind_info->have_fixed_pending_cb())
+			if (kind_info->have_pending_cb())
 			{
 				do_flush = true;
 				break;
@@ -789,25 +785,20 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush of variable-numbered stats */
+	/* flush of variable-numbered stats tracked in pending entries list */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
-	/* flush of fixed-numbered stats */
+	/* flush stats for each registered kind that has a flush static callback */
 	for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 	{
 		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 		if (!kind_info)
 			continue;
-		if (!kind_info->fixed_amount)
-		{
-			Assert(kind_info->flush_fixed_cb == NULL);
-			continue;
-		}
-		if (!kind_info->flush_fixed_cb)
+		if (!kind_info->flush_static_cb)
 			continue;
 
-		partial_flush |= kind_info->flush_fixed_cb(nowait);
+		partial_flush |= kind_info->flush_static_cb(nowait);
 	}
 
 	last_flush = now;
@@ -1297,7 +1288,7 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 	PgStat_EntryRef *entry_ref;
 
 	/* need to be able to flush out */
-	Assert(pgstat_get_kind_info(kind)->flush_pending_cb != NULL);
+	Assert(pgstat_get_kind_info(kind)->flush_dynamic_cb != NULL);
 
 	if (unlikely(!pgStatPendingContext))
 	{
@@ -1394,10 +1385,10 @@ pgstat_flush_pending_entries(bool nowait)
 		dlist_node *next;
 
 		Assert(!kind_info->fixed_amount);
-		Assert(kind_info->flush_pending_cb != NULL);
+		Assert(kind_info->flush_dynamic_cb != NULL);
 
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_dynamic_cb(entry_ref, nowait);
 
 		Assert(did_flush || nowait);
 
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 79e4d0a3053..bcae6a78169 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -11,7 +11,9 @@
  * This statistics kind uses a proc number as object ID for the hash table
  * of pgstats.  Entries are created each time a process is spawned, and are
  * dropped when the process exits.  These are not written to the pgstats file
- * on disk.
+ * on disk.  Pending statistics are managed without direct interactions with
+ * the pgstats dshash, relying on PendingBackendStats instead so as it is
+ * possible to report data within critical sections.
  *
  * Copyright (c) 2001-2025, PostgreSQL Global Development Group
  *
@@ -22,8 +24,49 @@
 
 #include "postgres.h"
 
+#include "storage/bufmgr.h"
+#include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 
+/*
+ * Backend statistics counts waiting to be flushed out. These counters may be
+ * reported within critical sections so we use static memory in order to avoid
+ * memory allocation.
+ */
+static PgStat_BackendPending PendingBackendStats;
+
+/*
+ * Utility routines to report I/O stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
+								IOOp io_op, instr_time io_time)
+{
+	Assert(track_io_timing);
+
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
+				   io_time);
+}
+
+void
+pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
+						   IOOp io_op, uint32 cnt, uint64 bytes)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
+	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -46,14 +89,21 @@ static void
 pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 {
 	PgStatShared_Backend *shbackendent;
-	PgStat_BackendPending *pendingent;
 	PgStat_BktypeIO *bktype_shstats;
-	PgStat_PendingIO *pending_io;
+	PgStat_PendingIO pending_io;
+
+	/*
+	 * This function can be called even if nothing at all has happened for IO
+	 * statistics.  In this case, avoid unnecessarily modifying the stats
+	 * entry.
+	 */
+	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
+							   sizeof(struct PgStat_PendingIO)))
+		return;
 
 	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
-	pendingent = (PgStat_BackendPending *) entry_ref->pending;
 	bktype_shstats = &shbackendent->stats.io_stats;
-	pending_io = &pendingent->pending_io;
+	pending_io = PendingBackendStats.pending_io;
 
 	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
 	{
@@ -64,68 +114,74 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 				instr_time	time;
 
 				bktype_shstats->counts[io_object][io_context][io_op] +=
-					pending_io->counts[io_object][io_context][io_op];
+					pending_io.counts[io_object][io_context][io_op];
 				bktype_shstats->bytes[io_object][io_context][io_op] +=
-					pending_io->bytes[io_object][io_context][io_op];
-
-				time = pending_io->pending_times[io_object][io_context][io_op];
+					pending_io.bytes[io_object][io_context][io_op];
+				time = pending_io.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
- * Wrapper routine to flush backend statistics.
+ * Flush out locally pending backend statistics
+ *
+ * "flags" parameter controls which statistics to flush.  Returns true
+ * if some statistics could not be flushed.
  */
-static bool
-pgstat_flush_backend_entry(PgStat_EntryRef *entry_ref, bool nowait,
-						   bits32 flags)
+bool
+pgstat_flush_backend(bool nowait, bits32 flags)
 {
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
+	PgStat_EntryRef *entry_ref;
+
+	if (pg_memory_is_all_zeros(&PendingBackendStats,
+							   sizeof(struct PgStat_BackendPending)))
 		return false;
 
-	if (!pgstat_lock_entry(entry_ref, nowait))
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
 		return false;
 
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, nowait);
+	if (!entry_ref)
+		return true;
+
 	/* Flush requested statistics */
 	if (flags & PGSTAT_BACKEND_FLUSH_IO)
 		pgstat_flush_backend_entry_io(entry_ref);
 
 	pgstat_unlock_entry(entry_ref);
 
-	return true;
+	return false;
 }
 
 /*
- * Callback to flush out locally pending backend statistics.
- *
- * If no stats have been recorded, this function returns false.
+ * Check if there are any backend stats waiting for flush.
  */
 bool
-pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_backend_have_pending_cb(void)
 {
-	return pgstat_flush_backend_entry(entry_ref, nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return (!pg_memory_is_all_zeros(&PendingBackendStats,
+									sizeof(struct PgStat_BackendPending)));
 }
 
 /*
- * Flush out locally pending backend statistics
+ * Callback to flush out locally pending backend statistics.
  *
- * "flags" parameter controls which statistics to flush.
+ * If some stats could not be flushed, return true.
  */
-void
-pgstat_flush_backend(bool nowait, bits32 flags)
+bool
+pgstat_backend_flush_cb(bool nowait)
 {
-	PgStat_EntryRef *entry_ref;
-
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
-		return;
-
-	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-									 MyProcNumber, false, NULL);
-	(void) pgstat_flush_backend_entry(entry_ref, nowait, flags);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
 }
 
 /*
@@ -137,9 +193,8 @@ pgstat_create_backend(ProcNumber procnum)
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Backend *shstatent;
 
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
-
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, false);
 	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
 
 	/*
@@ -147,20 +202,9 @@ pgstat_create_backend(ProcNumber procnum)
 	 * e.g. if we previously used this proc number.
 	 */
 	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
-}
-
-/*
- * Find or create a local PgStat_BackendPending entry for proc number.
- */
-PgStat_BackendPending *
-pgstat_prep_backend_pending(ProcNumber procnum)
-{
-	PgStat_EntryRef *entry_ref;
-
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
+	pgstat_unlock_entry(entry_ref);
 
-	return entry_ref->pending;
+	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 027aad8b24e..6ff5d9e96a1 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -73,18 +73,12 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	Assert(pgstat_is_ioop_tracked_in_bytes(io_op) || bytes == 0);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
-	if (pgstat_tracks_backend_bktype(MyBackendType))
-	{
-		PgStat_BackendPending *entry_ref;
-
-		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-		entry_ref->pending_io.counts[io_object][io_context][io_op] += cnt;
-		entry_ref->pending_io.bytes[io_object][io_context][io_op] += bytes;
-	}
-
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 	PendingIOStats.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Add the per-backend counts */
+	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
+
 	have_iostats = true;
 }
 
@@ -145,14 +139,9 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
 
-		if (pgstat_tracks_backend_bktype(MyBackendType))
-		{
-			PgStat_BackendPending *entry_ref;
-
-			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-			INSTR_TIME_ADD(entry_ref->pending_io.pending_times[io_object][io_context][io_op],
-						   io_time);
-		}
+		/* Add the per-backend count */
+		pgstat_count_backend_io_op_time(io_object, io_context, io_op,
+										io_time);
 	}
 
 	pgstat_count_io_op(io_object, io_context, io_op, cnt, bytes);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 09247ba0971..965a7fe2c64 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
@@ -351,7 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2d40fe3e70f..d0d45150977 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -540,6 +540,15 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
  * Functions in pgstat_backend.c
  */
 
+/* used by pgstat_io.c for I/O stats tracked in backends */
+extern void pgstat_count_backend_io_op_time(IOObject io_object,
+											IOContext io_context,
+											IOOp io_op,
+											instr_time io_time);
+extern void pgstat_count_backend_io_op(IOObject io_object,
+									   IOContext io_context,
+									   IOOp io_op, uint32 cnt,
+									   uint64 bytes);
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern bool pgstat_tracks_backend_bktype(BackendType bktype);
 extern void pgstat_create_backend(ProcNumber procnum);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 4bb8e5c53ab..7222b414779 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -156,8 +156,8 @@ typedef struct PgStat_EntryRef
 	 * Pending statistics data that will need to be flushed to shared memory
 	 * stats eventually. Each stats kind utilizing pending data defines what
 	 * format its pending data has and needs to provide a
-	 * PgStat_KindInfo->flush_pending_cb callback to merge pending into shared
-	 * stats.
+	 * PgStat_KindInfo->flush_dynamic_cb callback to merge pending entries
+	 * that are in dynamic memory into shared stats.
 	 */
 	void	   *pending;
 	dlist_node	pending_node;	/* membership in pgStatPending list */
@@ -259,10 +259,11 @@ typedef struct PgStat_KindInfo
 	void		(*init_backend_cb) (void);
 
 	/*
-	 * For variable-numbered stats: flush pending stats. Required if pending
-	 * data is used.  See flush_fixed_cb for fixed-numbered stats.
+	 * For variable-numbered stats: flush pending stats entries in dynamic
+	 * memory within the dshash. Required if pending data interacts with the
+	 * pgstats dshash.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_dynamic_cb) (PgStat_EntryRef *sr, bool nowait);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -289,17 +290,19 @@ typedef struct PgStat_KindInfo
 	void		(*init_shmem_cb) (void *stats);
 
 	/*
-	 * For fixed-numbered statistics: Flush pending stats. Returns true if
-	 * some of the stats could not be flushed, due to lock contention for
-	 * example. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Check for pending
+	 * stats in need of flush, when these do not use the pgstats dshash.
+	 * Returns true if there are any stats pending for flush, triggering
+	 * flush_cb. Optional.
 	 */
-	bool		(*flush_fixed_cb) (bool nowait);
+	bool		(*have_pending_cb) (void);
 
 	/*
-	 * For fixed-numbered statistics: Check for pending stats in need of
-	 * flush. Returns true if there are any stats pending for flush. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Flush pending
+	 * static stats. Returns true if some of the stats could not be flushed,
+	 * due to lock contention for example. Optional.
 	 */
-	bool		(*have_fixed_pending_cb) (void);
+	bool		(*flush_static_cb) (bool nowait);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -617,10 +620,11 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL	(PGSTAT_BACKEND_FLUSH_IO)
 
-extern void pgstat_flush_backend(bool nowait, bits32 flags);
-extern PgStat_BackendPending *pgstat_prep_backend_pending(ProcNumber procnum);
-extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
-extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags);
+extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_backend_have_pending_cb(void);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
+											  TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
diff --git a/src/test/modules/injection_points/injection_stats.c b/src/test/modules/injection_points/injection_stats.c
index 5db62bca66f..4f3691c702b 100644
--- a/src/test/modules/injection_points/injection_stats.c
+++ b/src/test/modules/injection_points/injection_stats.c
@@ -48,7 +48,7 @@ static const PgStat_KindInfo injection_stats = {
 	.shared_data_off = offsetof(PgStatShared_InjectionPoint, stats),
 	.shared_data_len = sizeof(((PgStatShared_InjectionPoint *) 0)->stats),
 	.pending_size = sizeof(PgStat_StatInjEntry),
-	.flush_pending_cb = injection_stats_flush_cb,
+	.flush_dynamic_cb = injection_stats_flush_cb,
 };
 
 /*
-- 
2.34.1

From 33dbb87cd92e29a71ea2012476aca1d760c8c557 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Mon, 20 Jan 2025 10:39:50 +0000
Subject: [PATCH v3 2/2] Fixing pgstat_backend.c Copyright

The file has been introduced in 9aea73fc61d, in 2024. So fixing its Copyright
accordingly.
---
 src/backend/utils/activity/pgstat_backend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
 100.0% src/backend/utils/activity/

diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index bcae6a78169..b0184b3293e 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -15,7 +15,7 @@
  * the pgstats dshash, relying on PendingBackendStats instead so as it is
  * possible to report data within critical sections.
  *
- * Copyright (c) 2001-2025, PostgreSQL Global Development Group
+ * Copyright (c) 2024-2025, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/backend/utils/activity/pgstat_backend.c
-- 
2.34.1

commit af786645e63b34e0d4eefbef7a8dd0794d358d0f
Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date:   Mon Jan 20 09:57:26 2025 +0000

    Change flush callbacks names
    
    and the way pending backend stats are checks and set to zero.

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index bd1ffad6f46..0a4b687f045 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -292,7 +292,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Database *) 0)->stats),
 		.pending_size = sizeof(PgStat_StatDBEntry),
 
-		.flush_pending_cb = pgstat_database_flush_cb,
+		.flush_dynamic_cb = pgstat_database_flush_cb,
 		.reset_timestamp_cb = pgstat_database_reset_timestamp_cb,
 	},
 
@@ -307,7 +307,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Relation *) 0)->stats),
 		.pending_size = sizeof(PgStat_TableStatus),
 
-		.flush_pending_cb = pgstat_relation_flush_cb,
+		.flush_dynamic_cb = pgstat_relation_flush_cb,
 		.delete_pending_cb = pgstat_relation_delete_pending_cb,
 	},
 
@@ -322,7 +322,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Function *) 0)->stats),
 		.pending_size = sizeof(PgStat_FunctionCounts),
 
-		.flush_pending_cb = pgstat_function_flush_cb,
+		.flush_dynamic_cb = pgstat_function_flush_cb,
 	},
 
 	[PGSTAT_KIND_REPLSLOT] = {
@@ -355,7 +355,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Subscription *) 0)->stats),
 		.pending_size = sizeof(PgStat_BackendSubEntry),
 
-		.flush_pending_cb = pgstat_subscription_flush_cb,
+		.flush_dynamic_cb = pgstat_subscription_flush_cb,
 		.reset_timestamp_cb = pgstat_subscription_reset_timestamp_cb,
 	},
 
@@ -373,7 +373,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.pending_size = sizeof(PgStat_BackendPending),
 
 		.have_pending_cb = pgstat_backend_have_pending_cb,
-		.flush_cb = pgstat_backend_flush_cb,
+		.flush_static_cb = pgstat_backend_flush_cb,
 		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
 	},
 
@@ -438,7 +438,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_IO, stats),
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
-		.flush_cb = pgstat_io_flush_cb,
+		.flush_static_cb = pgstat_io_flush_cb,
 		.have_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
@@ -456,7 +456,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_SLRU, stats),
 		.shared_data_len = sizeof(((PgStatShared_SLRU *) 0)->stats),
 
-		.flush_cb = pgstat_slru_flush_cb,
+		.flush_static_cb = pgstat_slru_flush_cb,
 		.have_pending_cb = pgstat_slru_have_pending_cb,
 		.init_shmem_cb = pgstat_slru_init_shmem_cb,
 		.reset_all_cb = pgstat_slru_reset_all_cb,
@@ -475,7 +475,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Wal *) 0)->stats),
 
 		.init_backend_cb = pgstat_wal_init_backend_cb,
-		.flush_cb = pgstat_wal_flush_cb,
+		.flush_static_cb = pgstat_wal_flush_cb,
 		.have_pending_cb = pgstat_wal_have_pending_cb,
 		.init_shmem_cb = pgstat_wal_init_shmem_cb,
 		.reset_all_cb = pgstat_wal_reset_all_cb,
@@ -785,23 +785,20 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush of variable-numbered stats */
+	/* flush of variable-numbered stats tracked in pending entries list */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
-	/*
-	 * Flush of other stats, which could be variable-numbered or
-	 * fixed-numbered.
-	 */
+	/* flush stats for each registered kind that has a flush static callback */
 	for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 	{
 		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 		if (!kind_info)
 			continue;
-		if (!kind_info->flush_cb)
+		if (!kind_info->flush_static_cb)
 			continue;
 
-		partial_flush |= kind_info->flush_cb(nowait);
+		partial_flush |= kind_info->flush_static_cb(nowait);
 	}
 
 	last_flush = now;
@@ -1291,7 +1288,7 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 	PgStat_EntryRef *entry_ref;
 
 	/* need to be able to flush out */
-	Assert(pgstat_get_kind_info(kind)->flush_pending_cb != NULL);
+	Assert(pgstat_get_kind_info(kind)->flush_dynamic_cb != NULL);
 
 	if (unlikely(!pgStatPendingContext))
 	{
@@ -1388,10 +1385,10 @@ pgstat_flush_pending_entries(bool nowait)
 		dlist_node *next;
 
 		Assert(!kind_info->fixed_amount);
-		Assert(kind_info->flush_pending_cb != NULL);
+		Assert(kind_info->flush_dynamic_cb != NULL);
 
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_dynamic_cb(entry_ref, nowait);
 
 		Assert(did_flush || nowait);
 
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index fb7abf64a0b..bcae6a78169 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -29,12 +29,11 @@
 #include "utils/pgstat_internal.h"
 
 /*
- * Backend statistics counts waiting to be flushed out.  We assume this variable
- * inits to zeroes.  These counters may be reported within critical sections so
- * we use static memory in order to avoid memory allocation.
+ * Backend statistics counts waiting to be flushed out. These counters may be
+ * reported within critical sections so we use static memory in order to avoid
+ * memory allocation.
  */
-static PgStat_BackendPending PendingBackendStats = {0};
-static bool have_backendstats = false;
+static PgStat_BackendPending PendingBackendStats;
 
 /*
  * Utility routines to report I/O stats for backends, kept here to avoid
@@ -53,8 +52,6 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
-
-	have_backendstats = true;
 }
 
 void
@@ -68,8 +65,6 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
-
-	have_backendstats = true;
 }
 
 /*
@@ -98,8 +93,8 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 	PgStat_PendingIO pending_io;
 
 	/*
-	 * This function can be called even if nothing at all has happened for
-	 * IO statistics.  In this case, avoid unnecessarily modifying the stats
+	 * This function can be called even if nothing at all has happened for IO
+	 * statistics.  In this case, avoid unnecessarily modifying the stats
 	 * entry.
 	 */
 	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
@@ -129,6 +124,11 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 			}
 		}
 	}
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
@@ -142,7 +142,8 @@ pgstat_flush_backend(bool nowait, bits32 flags)
 {
 	PgStat_EntryRef *entry_ref;
 
-	if (!have_backendstats)
+	if (pg_memory_is_all_zeros(&PendingBackendStats,
+							   sizeof(struct PgStat_BackendPending)))
 		return false;
 
 	if (!pgstat_tracks_backend_bktype(MyBackendType))
@@ -159,12 +160,6 @@ pgstat_flush_backend(bool nowait, bits32 flags)
 
 	pgstat_unlock_entry(entry_ref);
 
-	/*
-	 * Clear out the statistics buffer, so it can be re-used.
-	 */
-	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
-
-	have_backendstats = false;
 	return false;
 }
 
@@ -174,7 +169,8 @@ pgstat_flush_backend(bool nowait, bits32 flags)
 bool
 pgstat_backend_have_pending_cb(void)
 {
-	return have_backendstats;
+	return (!pg_memory_is_all_zeros(&PendingBackendStats,
+									sizeof(struct PgStat_BackendPending)));
 }
 
 /*
@@ -209,7 +205,6 @@ pgstat_create_backend(ProcNumber procnum)
 	pgstat_unlock_entry(entry_ref);
 
 	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
-	have_backendstats = false;
 }
 
 /*
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 000ed5b36f6..7222b414779 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -156,8 +156,8 @@ typedef struct PgStat_EntryRef
 	 * Pending statistics data that will need to be flushed to shared memory
 	 * stats eventually. Each stats kind utilizing pending data defines what
 	 * format its pending data has and needs to provide a
-	 * PgStat_KindInfo->flush_pending_cb callback to merge pending into shared
-	 * stats.
+	 * PgStat_KindInfo->flush_dynamic_cb callback to merge pending entries
+	 * that are in dynamic memory into shared stats.
 	 */
 	void	   *pending;
 	dlist_node	pending_node;	/* membership in pgStatPending list */
@@ -259,10 +259,11 @@ typedef struct PgStat_KindInfo
 	void		(*init_backend_cb) (void);
 
 	/*
-	 * For variable-numbered stats: flush pending stats within the dshash.
-	 * Required if pending data interacts with the pgstats dshash.
+	 * For variable-numbered stats: flush pending stats entries in dynamic
+	 * memory within the dshash. Required if pending data interacts with the
+	 * pgstats dshash.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_dynamic_cb) (PgStat_EntryRef *sr, bool nowait);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -298,10 +299,10 @@ typedef struct PgStat_KindInfo
 
 	/*
 	 * For fixed-numbered or variable-numbered statistics: Flush pending
-	 * stats. Returns true if some of the stats could not be flushed, due
-	 * to lock contention for example. Optional.
+	 * static stats. Returns true if some of the stats could not be flushed,
+	 * due to lock contention for example. Optional.
 	 */
-	bool		(*flush_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
diff --git a/src/test/modules/injection_points/injection_stats.c b/src/test/modules/injection_points/injection_stats.c
index 5db62bca66f..4f3691c702b 100644
--- a/src/test/modules/injection_points/injection_stats.c
+++ b/src/test/modules/injection_points/injection_stats.c
@@ -48,7 +48,7 @@ static const PgStat_KindInfo injection_stats = {
 	.shared_data_off = offsetof(PgStatShared_InjectionPoint, stats),
 	.shared_data_len = sizeof(((PgStatShared_InjectionPoint *) 0)->stats),
 	.pending_size = sizeof(PgStat_StatInjEntry),
-	.flush_pending_cb = injection_stats_flush_cb,
+	.flush_dynamic_cb = injection_stats_flush_cb,
 };
 
 /*

From d57755402e9a9f672d2057c7f7ffa3832d402a3b Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Fri, 17 Jan 2025 06:44:47 +0000
Subject: [PATCH v4] Rework per backend pending stats

9aea73fc61d added per backend pending statistics but not all of them are well
suited to memory allocation and have to be outside of critical sections.

For those (the only current one is I/O statistics but WAL statistics is under
discussion), let's rely on a new PendingBackendStats instead.
---
 src/backend/utils/activity/pgstat.c          |  39 ++---
 src/backend/utils/activity/pgstat_backend.c  | 142 ++++++++++++-------
 src/backend/utils/activity/pgstat_io.c       |  23 +--
 src/backend/utils/activity/pgstat_relation.c |   4 +-
 src/include/pgstat.h                         |   9 ++
 src/include/utils/pgstat_internal.h          |  34 +++--
 6 files changed, 144 insertions(+), 107 deletions(-)
  76.8% src/backend/utils/activity/
  19.1% src/include/utils/
   4.0% src/include/

diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 34520535d54..d4fc03b5d39 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -372,7 +372,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
 		.pending_size = sizeof(PgStat_BackendPending),
 
-		.flush_pending_cb = pgstat_backend_flush_cb,
+		.have_static_pending_cb = pgstat_backend_have_pending_cb,
+		.flush_static_cb = pgstat_backend_flush_cb,
 		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
 	},
 
@@ -437,8 +438,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_IO, stats),
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_io_flush_cb,
-		.have_fixed_pending_cb = pgstat_io_have_pending_cb,
+		.flush_static_cb = pgstat_io_flush_cb,
+		.have_static_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
 		.snapshot_cb = pgstat_io_snapshot_cb,
@@ -455,8 +456,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_SLRU, stats),
 		.shared_data_len = sizeof(((PgStatShared_SLRU *) 0)->stats),
 
-		.flush_fixed_cb = pgstat_slru_flush_cb,
-		.have_fixed_pending_cb = pgstat_slru_have_pending_cb,
+		.flush_static_cb = pgstat_slru_flush_cb,
+		.have_static_pending_cb = pgstat_slru_have_pending_cb,
 		.init_shmem_cb = pgstat_slru_init_shmem_cb,
 		.reset_all_cb = pgstat_slru_reset_all_cb,
 		.snapshot_cb = pgstat_slru_snapshot_cb,
@@ -474,8 +475,8 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_Wal *) 0)->stats),
 
 		.init_backend_cb = pgstat_wal_init_backend_cb,
-		.flush_fixed_cb = pgstat_wal_flush_cb,
-		.have_fixed_pending_cb = pgstat_wal_have_pending_cb,
+		.flush_static_cb = pgstat_wal_flush_cb,
+		.have_static_pending_cb = pgstat_wal_have_pending_cb,
 		.init_shmem_cb = pgstat_wal_init_shmem_cb,
 		.reset_all_cb = pgstat_wal_reset_all_cb,
 		.snapshot_cb = pgstat_wal_snapshot_cb,
@@ -713,22 +714,17 @@ pgstat_report_stat(bool force)
 	{
 		bool		do_flush = false;
 
-		/* Check for pending fixed-numbered stats */
+		/* Check for pending stats */
 		for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 		{
 			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 			if (!kind_info)
 				continue;
-			if (!kind_info->fixed_amount)
-			{
-				Assert(kind_info->have_fixed_pending_cb == NULL);
-				continue;
-			}
-			if (!kind_info->have_fixed_pending_cb)
+			if (!kind_info->have_static_pending_cb)
 				continue;
 
-			if (kind_info->have_fixed_pending_cb())
+			if (kind_info->have_static_pending_cb())
 			{
 				do_flush = true;
 				break;
@@ -789,25 +785,20 @@ pgstat_report_stat(bool force)
 
 	partial_flush = false;
 
-	/* flush of variable-numbered stats */
+	/* flush of variable-numbered stats tracked in pending entries list */
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
-	/* flush of fixed-numbered stats */
+	/* flush stats for each registered kind that has a flush static callback */
 	for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
 	{
 		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
 		if (!kind_info)
 			continue;
-		if (!kind_info->fixed_amount)
-		{
-			Assert(kind_info->flush_fixed_cb == NULL);
-			continue;
-		}
-		if (!kind_info->flush_fixed_cb)
+		if (!kind_info->flush_static_cb)
 			continue;
 
-		partial_flush |= kind_info->flush_fixed_cb(nowait);
+		partial_flush |= kind_info->flush_static_cb(nowait);
 	}
 
 	last_flush = now;
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 79e4d0a3053..bcae6a78169 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -11,7 +11,9 @@
  * This statistics kind uses a proc number as object ID for the hash table
  * of pgstats.  Entries are created each time a process is spawned, and are
  * dropped when the process exits.  These are not written to the pgstats file
- * on disk.
+ * on disk.  Pending statistics are managed without direct interactions with
+ * the pgstats dshash, relying on PendingBackendStats instead so as it is
+ * possible to report data within critical sections.
  *
  * Copyright (c) 2001-2025, PostgreSQL Global Development Group
  *
@@ -22,8 +24,49 @@
 
 #include "postgres.h"
 
+#include "storage/bufmgr.h"
+#include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 
+/*
+ * Backend statistics counts waiting to be flushed out. These counters may be
+ * reported within critical sections so we use static memory in order to avoid
+ * memory allocation.
+ */
+static PgStat_BackendPending PendingBackendStats;
+
+/*
+ * Utility routines to report I/O stats for backends, kept here to avoid
+ * exposing PendingBackendStats to the outside world.
+ */
+void
+pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
+								IOOp io_op, instr_time io_time)
+{
+	Assert(track_io_timing);
+
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
+				   io_time);
+}
+
+void
+pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
+						   IOOp io_op, uint32 cnt, uint64 bytes)
+{
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
+		return;
+
+	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
+
+	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
+	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
+}
+
 /*
  * Returns statistics of a backend by proc number.
  */
@@ -46,14 +89,21 @@ static void
 pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 {
 	PgStatShared_Backend *shbackendent;
-	PgStat_BackendPending *pendingent;
 	PgStat_BktypeIO *bktype_shstats;
-	PgStat_PendingIO *pending_io;
+	PgStat_PendingIO pending_io;
+
+	/*
+	 * This function can be called even if nothing at all has happened for IO
+	 * statistics.  In this case, avoid unnecessarily modifying the stats
+	 * entry.
+	 */
+	if (pg_memory_is_all_zeros(&PendingBackendStats.pending_io,
+							   sizeof(struct PgStat_PendingIO)))
+		return;
 
 	shbackendent = (PgStatShared_Backend *) entry_ref->shared_stats;
-	pendingent = (PgStat_BackendPending *) entry_ref->pending;
 	bktype_shstats = &shbackendent->stats.io_stats;
-	pending_io = &pendingent->pending_io;
+	pending_io = PendingBackendStats.pending_io;
 
 	for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++)
 	{
@@ -64,68 +114,74 @@ pgstat_flush_backend_entry_io(PgStat_EntryRef *entry_ref)
 				instr_time	time;
 
 				bktype_shstats->counts[io_object][io_context][io_op] +=
-					pending_io->counts[io_object][io_context][io_op];
+					pending_io.counts[io_object][io_context][io_op];
 				bktype_shstats->bytes[io_object][io_context][io_op] +=
-					pending_io->bytes[io_object][io_context][io_op];
-
-				time = pending_io->pending_times[io_object][io_context][io_op];
+					pending_io.bytes[io_object][io_context][io_op];
+				time = pending_io.pending_times[io_object][io_context][io_op];
 
 				bktype_shstats->times[io_object][io_context][io_op] +=
 					INSTR_TIME_GET_MICROSEC(time);
 			}
 		}
 	}
+
+	/*
+	 * Clear out the statistics buffer, so it can be re-used.
+	 */
+	MemSet(&PendingBackendStats.pending_io, 0, sizeof(PgStat_PendingIO));
 }
 
 /*
- * Wrapper routine to flush backend statistics.
+ * Flush out locally pending backend statistics
+ *
+ * "flags" parameter controls which statistics to flush.  Returns true
+ * if some statistics could not be flushed.
  */
-static bool
-pgstat_flush_backend_entry(PgStat_EntryRef *entry_ref, bool nowait,
-						   bits32 flags)
+bool
+pgstat_flush_backend(bool nowait, bits32 flags)
 {
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
+	PgStat_EntryRef *entry_ref;
+
+	if (pg_memory_is_all_zeros(&PendingBackendStats,
+							   sizeof(struct PgStat_BackendPending)))
 		return false;
 
-	if (!pgstat_lock_entry(entry_ref, nowait))
+	if (!pgstat_tracks_backend_bktype(MyBackendType))
 		return false;
 
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, nowait);
+	if (!entry_ref)
+		return true;
+
 	/* Flush requested statistics */
 	if (flags & PGSTAT_BACKEND_FLUSH_IO)
 		pgstat_flush_backend_entry_io(entry_ref);
 
 	pgstat_unlock_entry(entry_ref);
 
-	return true;
+	return false;
 }
 
 /*
- * Callback to flush out locally pending backend statistics.
- *
- * If no stats have been recorded, this function returns false.
+ * Check if there are any backend stats waiting for flush.
  */
 bool
-pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_backend_have_pending_cb(void)
 {
-	return pgstat_flush_backend_entry(entry_ref, nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return (!pg_memory_is_all_zeros(&PendingBackendStats,
+									sizeof(struct PgStat_BackendPending)));
 }
 
 /*
- * Flush out locally pending backend statistics
+ * Callback to flush out locally pending backend statistics.
  *
- * "flags" parameter controls which statistics to flush.
+ * If some stats could not be flushed, return true.
  */
-void
-pgstat_flush_backend(bool nowait, bits32 flags)
+bool
+pgstat_backend_flush_cb(bool nowait)
 {
-	PgStat_EntryRef *entry_ref;
-
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
-		return;
-
-	entry_ref = pgstat_get_entry_ref(PGSTAT_KIND_BACKEND, InvalidOid,
-									 MyProcNumber, false, NULL);
-	(void) pgstat_flush_backend_entry(entry_ref, nowait, flags);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
 }
 
 /*
@@ -137,9 +193,8 @@ pgstat_create_backend(ProcNumber procnum)
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Backend *shstatent;
 
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
-
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_BACKEND, InvalidOid,
+											MyProcNumber, false);
 	shstatent = (PgStatShared_Backend *) entry_ref->shared_stats;
 
 	/*
@@ -147,20 +202,9 @@ pgstat_create_backend(ProcNumber procnum)
 	 * e.g. if we previously used this proc number.
 	 */
 	memset(&shstatent->stats, 0, sizeof(shstatent->stats));
-}
-
-/*
- * Find or create a local PgStat_BackendPending entry for proc number.
- */
-PgStat_BackendPending *
-pgstat_prep_backend_pending(ProcNumber procnum)
-{
-	PgStat_EntryRef *entry_ref;
-
-	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_BACKEND, InvalidOid,
-										  procnum, NULL);
+	pgstat_unlock_entry(entry_ref);
 
-	return entry_ref->pending;
+	MemSet(&PendingBackendStats, 0, sizeof(PgStat_BackendPending));
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 027aad8b24e..6ff5d9e96a1 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -73,18 +73,12 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	Assert(pgstat_is_ioop_tracked_in_bytes(io_op) || bytes == 0);
 	Assert(pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op));
 
-	if (pgstat_tracks_backend_bktype(MyBackendType))
-	{
-		PgStat_BackendPending *entry_ref;
-
-		entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-		entry_ref->pending_io.counts[io_object][io_context][io_op] += cnt;
-		entry_ref->pending_io.bytes[io_object][io_context][io_op] += bytes;
-	}
-
 	PendingIOStats.counts[io_object][io_context][io_op] += cnt;
 	PendingIOStats.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Add the per-backend counts */
+	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
+
 	have_iostats = true;
 }
 
@@ -145,14 +139,9 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op,
 		INSTR_TIME_ADD(PendingIOStats.pending_times[io_object][io_context][io_op],
 					   io_time);
 
-		if (pgstat_tracks_backend_bktype(MyBackendType))
-		{
-			PgStat_BackendPending *entry_ref;
-
-			entry_ref = pgstat_prep_backend_pending(MyProcNumber);
-			INSTR_TIME_ADD(entry_ref->pending_io.pending_times[io_object][io_context][io_op],
-						   io_time);
-		}
+		/* Add the per-backend count */
+		pgstat_count_backend_io_op_time(io_object, io_context, io_op,
+										io_time);
 	}
 
 	pgstat_count_io_op(io_object, io_context, io_op, cnt, bytes);
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 09247ba0971..965a7fe2c64 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -264,7 +264,7 @@ pgstat_report_vacuum(Oid tableoid, bool shared,
 	 * VACUUM command has processed all tables and committed.
 	 */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
@@ -351,7 +351,7 @@ pgstat_report_analyze(Relation rel,
 
 	/* see pgstat_report_vacuum() */
 	pgstat_flush_io(false);
-	pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
 }
 
 /*
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 2d40fe3e70f..d0d45150977 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -540,6 +540,15 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
  * Functions in pgstat_backend.c
  */
 
+/* used by pgstat_io.c for I/O stats tracked in backends */
+extern void pgstat_count_backend_io_op_time(IOObject io_object,
+											IOContext io_context,
+											IOOp io_op,
+											instr_time io_time);
+extern void pgstat_count_backend_io_op(IOObject io_object,
+									   IOContext io_context,
+									   IOOp io_op, uint32 cnt,
+									   uint64 bytes);
 extern PgStat_Backend *pgstat_fetch_stat_backend(ProcNumber procNumber);
 extern bool pgstat_tracks_backend_bktype(BackendType bktype);
 extern void pgstat_create_backend(ProcNumber procnum);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 4bb8e5c53ab..c0e77488aed 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -156,8 +156,8 @@ typedef struct PgStat_EntryRef
 	 * Pending statistics data that will need to be flushed to shared memory
 	 * stats eventually. Each stats kind utilizing pending data defines what
 	 * format its pending data has and needs to provide a
-	 * PgStat_KindInfo->flush_pending_cb callback to merge pending into shared
-	 * stats.
+	 * PgStat_KindInfo->flush_pending_cb callback to merge pending entries
+	 * that are in dynamic memory into shared stats.
 	 */
 	void	   *pending;
 	dlist_node	pending_node;	/* membership in pgStatPending list */
@@ -259,8 +259,9 @@ typedef struct PgStat_KindInfo
 	void		(*init_backend_cb) (void);
 
 	/*
-	 * For variable-numbered stats: flush pending stats. Required if pending
-	 * data is used.  See flush_fixed_cb for fixed-numbered stats.
+	 * For variable-numbered stats: flush pending stats entries in dynamic
+	 * memory within the dshash. Required if pending data interacts with the
+	 * pgstats dshash.
 	 */
 	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
 
@@ -289,17 +290,19 @@ typedef struct PgStat_KindInfo
 	void		(*init_shmem_cb) (void *stats);
 
 	/*
-	 * For fixed-numbered statistics: Flush pending stats. Returns true if
-	 * some of the stats could not be flushed, due to lock contention for
-	 * example. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Check for pending
+	 * stats in need of flush, when these do not use the pgstats dshash.
+	 * Returns true if there are any stats pending for flush, triggering
+	 * flush_cb. Optional.
 	 */
-	bool		(*flush_fixed_cb) (bool nowait);
+	bool		(*have_static_pending_cb) (void);
 
 	/*
-	 * For fixed-numbered statistics: Check for pending stats in need of
-	 * flush. Returns true if there are any stats pending for flush. Optional.
+	 * For fixed-numbered or variable-numbered statistics: Flush pending
+	 * static stats. Returns true if some of the stats could not be flushed,
+	 * due to lock contention for example. Optional.
 	 */
-	bool		(*have_fixed_pending_cb) (void);
+	bool		(*flush_static_cb) (bool nowait);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -617,10 +620,11 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_IO		(1 << 0)	/* Flush I/O statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL	(PGSTAT_BACKEND_FLUSH_IO)
 
-extern void pgstat_flush_backend(bool nowait, bits32 flags);
-extern PgStat_BackendPending *pgstat_prep_backend_pending(ProcNumber procnum);
-extern bool pgstat_backend_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
-extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags);
+extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_backend_have_pending_cb(void);
+extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
+											  TimestampTz ts);
 
 /*
  * Functions in pgstat_bgwriter.c
-- 
2.34.1