diff --git a/contrib/Makefile b/contrib/Makefile index 6967767..bcb9465 100644 --- a/contrib/Makefile +++ b/contrib/Makefile @@ -7,7 +7,6 @@ include $(top_builddir)/src/Makefile.global SUBDIRS = \ adminpack \ auth_delay \ - auto_explain \ btree_gin \ btree_gist \ chkpass \ @@ -27,21 +26,15 @@ SUBDIRS = \ lo \ ltree \ oid2name \ - pageinspect \ passwordcheck \ pg_archivecleanup \ - pg_buffercache \ - pg_freespacemap \ pg_standby \ - pg_stat_statements \ pg_test_fsync \ pg_trgm \ pg_upgrade \ pg_upgrade_support \ pgbench \ pgcrypto \ - pgrowlocks \ - pgstattuple \ seg \ spi \ tablefunc \ diff --git a/contrib/auto_explain/Makefile b/contrib/auto_explain/Makefile deleted file mode 100644 index 2d1443f..0000000 --- a/contrib/auto_explain/Makefile +++ /dev/null @@ -1,15 +0,0 @@ -# contrib/auto_explain/Makefile - -MODULE_big = auto_explain -OBJS = auto_explain.o - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/auto_explain -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/auto_explain/auto_explain.c b/contrib/auto_explain/auto_explain.c deleted file mode 100644 index b320698..0000000 --- a/contrib/auto_explain/auto_explain.c +++ /dev/null @@ -1,304 +0,0 @@ -/*------------------------------------------------------------------------- - * - * auto_explain.c - * - * - * Copyright (c) 2008-2011, PostgreSQL Global Development Group - * - * IDENTIFICATION - * contrib/auto_explain/auto_explain.c - * - *------------------------------------------------------------------------- - */ -#include "postgres.h" - -#include "commands/explain.h" -#include "executor/instrument.h" -#include "utils/guc.h" - -PG_MODULE_MAGIC; - -/* GUC variables */ -static int auto_explain_log_min_duration = -1; /* msec or -1 */ -static bool auto_explain_log_analyze = false; -static bool auto_explain_log_verbose = false; -static bool auto_explain_log_buffers = false; -static int auto_explain_log_format = EXPLAIN_FORMAT_TEXT; -static bool auto_explain_log_nested_statements = false; - -static const struct config_enum_entry format_options[] = { - {"text", EXPLAIN_FORMAT_TEXT, false}, - {"xml", EXPLAIN_FORMAT_XML, false}, - {"json", EXPLAIN_FORMAT_JSON, false}, - {"yaml", EXPLAIN_FORMAT_YAML, false}, - {NULL, 0, false} -}; - -/* Current nesting depth of ExecutorRun calls */ -static int nesting_level = 0; - -/* Saved hook values in case of unload */ -static ExecutorStart_hook_type prev_ExecutorStart = NULL; -static ExecutorRun_hook_type prev_ExecutorRun = NULL; -static ExecutorFinish_hook_type prev_ExecutorFinish = NULL; -static ExecutorEnd_hook_type prev_ExecutorEnd = NULL; - -#define auto_explain_enabled() \ - (auto_explain_log_min_duration >= 0 && \ - (nesting_level == 0 || auto_explain_log_nested_statements)) - -void _PG_init(void); -void _PG_fini(void); - -static void explain_ExecutorStart(QueryDesc *queryDesc, int eflags); -static void explain_ExecutorRun(QueryDesc *queryDesc, - ScanDirection direction, - long count); -static void explain_ExecutorFinish(QueryDesc *queryDesc); -static void explain_ExecutorEnd(QueryDesc *queryDesc); - - -/* - * Module load callback - */ -void -_PG_init(void) -{ - /* Define custom GUC variables. */ - DefineCustomIntVariable("auto_explain.log_min_duration", - "Sets the minimum execution time above which plans will be logged.", - "Zero prints all plans. -1 turns this feature off.", - &auto_explain_log_min_duration, - -1, - -1, INT_MAX / 1000, - PGC_SUSET, - GUC_UNIT_MS, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("auto_explain.log_analyze", - "Use EXPLAIN ANALYZE for plan logging.", - NULL, - &auto_explain_log_analyze, - false, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("auto_explain.log_verbose", - "Use EXPLAIN VERBOSE for plan logging.", - NULL, - &auto_explain_log_verbose, - false, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("auto_explain.log_buffers", - "Log buffers usage.", - NULL, - &auto_explain_log_buffers, - false, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomEnumVariable("auto_explain.log_format", - "EXPLAIN format to be used for plan logging.", - NULL, - &auto_explain_log_format, - EXPLAIN_FORMAT_TEXT, - format_options, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("auto_explain.log_nested_statements", - "Log nested statements.", - NULL, - &auto_explain_log_nested_statements, - false, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - EmitWarningsOnPlaceholders("auto_explain"); - - /* Install hooks. */ - prev_ExecutorStart = ExecutorStart_hook; - ExecutorStart_hook = explain_ExecutorStart; - prev_ExecutorRun = ExecutorRun_hook; - ExecutorRun_hook = explain_ExecutorRun; - prev_ExecutorFinish = ExecutorFinish_hook; - ExecutorFinish_hook = explain_ExecutorFinish; - prev_ExecutorEnd = ExecutorEnd_hook; - ExecutorEnd_hook = explain_ExecutorEnd; -} - -/* - * Module unload callback - */ -void -_PG_fini(void) -{ - /* Uninstall hooks. */ - ExecutorStart_hook = prev_ExecutorStart; - ExecutorRun_hook = prev_ExecutorRun; - ExecutorFinish_hook = prev_ExecutorFinish; - ExecutorEnd_hook = prev_ExecutorEnd; -} - -/* - * ExecutorStart hook: start up logging if needed - */ -static void -explain_ExecutorStart(QueryDesc *queryDesc, int eflags) -{ - if (auto_explain_enabled()) - { - /* Enable per-node instrumentation iff log_analyze is required. */ - if (auto_explain_log_analyze && (eflags & EXEC_FLAG_EXPLAIN_ONLY) == 0) - { - queryDesc->instrument_options |= INSTRUMENT_TIMER; - if (auto_explain_log_buffers) - queryDesc->instrument_options |= INSTRUMENT_BUFFERS; - } - } - - if (prev_ExecutorStart) - prev_ExecutorStart(queryDesc, eflags); - else - standard_ExecutorStart(queryDesc, eflags); - - if (auto_explain_enabled()) - { - /* - * Set up to track total elapsed time in ExecutorRun. Make sure the - * space is allocated in the per-query context so it will go away at - * ExecutorEnd. - */ - if (queryDesc->totaltime == NULL) - { - MemoryContext oldcxt; - - oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt); - queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL); - MemoryContextSwitchTo(oldcxt); - } - } -} - -/* - * ExecutorRun hook: all we need do is track nesting depth - */ -static void -explain_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, long count) -{ - nesting_level++; - PG_TRY(); - { - if (prev_ExecutorRun) - prev_ExecutorRun(queryDesc, direction, count); - else - standard_ExecutorRun(queryDesc, direction, count); - nesting_level--; - } - PG_CATCH(); - { - nesting_level--; - PG_RE_THROW(); - } - PG_END_TRY(); -} - -/* - * ExecutorFinish hook: all we need do is track nesting depth - */ -static void -explain_ExecutorFinish(QueryDesc *queryDesc) -{ - nesting_level++; - PG_TRY(); - { - if (prev_ExecutorFinish) - prev_ExecutorFinish(queryDesc); - else - standard_ExecutorFinish(queryDesc); - nesting_level--; - } - PG_CATCH(); - { - nesting_level--; - PG_RE_THROW(); - } - PG_END_TRY(); -} - -/* - * ExecutorEnd hook: log results if needed - */ -static void -explain_ExecutorEnd(QueryDesc *queryDesc) -{ - if (queryDesc->totaltime && auto_explain_enabled()) - { - double msec; - - /* - * Make sure stats accumulation is done. (Note: it's okay if several - * levels of hook all do this.) - */ - InstrEndLoop(queryDesc->totaltime); - - /* Log plan if duration is exceeded. */ - msec = queryDesc->totaltime->total * 1000.0; - if (msec >= auto_explain_log_min_duration) - { - ExplainState es; - - ExplainInitState(&es); - es.analyze = (queryDesc->instrument_options && auto_explain_log_analyze); - es.verbose = auto_explain_log_verbose; - es.buffers = (es.analyze && auto_explain_log_buffers); - es.format = auto_explain_log_format; - - ExplainBeginOutput(&es); - ExplainQueryText(&es, queryDesc); - ExplainPrintPlan(&es, queryDesc); - ExplainEndOutput(&es); - - /* Remove last line break */ - if (es.str->len > 0 && es.str->data[es.str->len - 1] == '\n') - es.str->data[--es.str->len] = '\0'; - - /* - * Note: we rely on the existing logging of context or - * debug_query_string to identify just which statement is being - * reported. This isn't ideal but trying to do it here would - * often result in duplication. - */ - ereport(LOG, - (errmsg("duration: %.3f ms plan:\n%s", - msec, es.str->data), - errhidestmt(true))); - - pfree(es.str->data); - } - } - - if (prev_ExecutorEnd) - prev_ExecutorEnd(queryDesc); - else - standard_ExecutorEnd(queryDesc); -} diff --git a/contrib/pageinspect/Makefile b/contrib/pageinspect/Makefile deleted file mode 100644 index 13ba6d3..0000000 --- a/contrib/pageinspect/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pageinspect/Makefile - -MODULE_big = pageinspect -OBJS = rawpage.o heapfuncs.o btreefuncs.o fsmfuncs.o - -EXTENSION = pageinspect -DATA = pageinspect--1.0.sql pageinspect--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pageinspect -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pageinspect/btreefuncs.c b/contrib/pageinspect/btreefuncs.c deleted file mode 100644 index ef27cd4..0000000 --- a/contrib/pageinspect/btreefuncs.c +++ /dev/null @@ -1,502 +0,0 @@ -/* - * contrib/pageinspect/btreefuncs.c - * - * - * btreefuncs.c - * - * Copyright (c) 2006 Satoshi Nagayasu - * - * Permission to use, copy, modify, and distribute this software and - * its documentation for any purpose, without fee, and without a - * written agreement is hereby granted, provided that the above - * copyright notice and this paragraph and the following two - * paragraphs appear in all copies. - * - * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, - * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING - * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS - * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - * - * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS - * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, - * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. - */ - -#include "postgres.h" - -#include "access/heapam.h" -#include "access/nbtree.h" -#include "catalog/namespace.h" -#include "catalog/pg_type.h" -#include "funcapi.h" -#include "miscadmin.h" -#include "storage/bufmgr.h" -#include "utils/builtins.h" - - -extern Datum bt_metap(PG_FUNCTION_ARGS); -extern Datum bt_page_items(PG_FUNCTION_ARGS); -extern Datum bt_page_stats(PG_FUNCTION_ARGS); - -PG_FUNCTION_INFO_V1(bt_metap); -PG_FUNCTION_INFO_V1(bt_page_items); -PG_FUNCTION_INFO_V1(bt_page_stats); - -#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX) -#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID) - -#define CHECK_PAGE_OFFSET_RANGE(pg, offnum) { \ - if ( !(FirstOffsetNumber <= (offnum) && \ - (offnum) <= PageGetMaxOffsetNumber(pg)) ) \ - elog(ERROR, "page offset number out of range"); } - -/* note: BlockNumber is unsigned, hence can't be negative */ -#define CHECK_RELATION_BLOCK_RANGE(rel, blkno) { \ - if ( RelationGetNumberOfBlocks(rel) <= (BlockNumber) (blkno) ) \ - elog(ERROR, "block number out of range"); } - -/* ------------------------------------------------ - * structure for single btree page statistics - * ------------------------------------------------ - */ -typedef struct BTPageStat -{ - uint32 blkno; - uint32 live_items; - uint32 dead_items; - uint32 page_size; - uint32 max_avail; - uint32 free_size; - uint32 avg_item_size; - char type; - - /* opaque data */ - BlockNumber btpo_prev; - BlockNumber btpo_next; - union - { - uint32 level; - TransactionId xact; - } btpo; - uint16 btpo_flags; - BTCycleId btpo_cycleid; -} BTPageStat; - - -/* ------------------------------------------------- - * GetBTPageStatistics() - * - * Collect statistics of single b-tree page - * ------------------------------------------------- - */ -static void -GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat) -{ - Page page = BufferGetPage(buffer); - PageHeader phdr = (PageHeader) page; - OffsetNumber maxoff = PageGetMaxOffsetNumber(page); - BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page); - int item_size = 0; - int off; - - stat->blkno = blkno; - - stat->max_avail = BLCKSZ - (BLCKSZ - phdr->pd_special + SizeOfPageHeaderData); - - stat->dead_items = stat->live_items = 0; - - stat->page_size = PageGetPageSize(page); - - /* page type (flags) */ - if (P_ISDELETED(opaque)) - { - stat->type = 'd'; - stat->btpo.xact = opaque->btpo.xact; - return; - } - else if (P_IGNORE(opaque)) - stat->type = 'e'; - else if (P_ISLEAF(opaque)) - stat->type = 'l'; - else if (P_ISROOT(opaque)) - stat->type = 'r'; - else - stat->type = 'i'; - - /* btpage opaque data */ - stat->btpo_prev = opaque->btpo_prev; - stat->btpo_next = opaque->btpo_next; - stat->btpo.level = opaque->btpo.level; - stat->btpo_flags = opaque->btpo_flags; - stat->btpo_cycleid = opaque->btpo_cycleid; - - /* count live and dead tuples, and free space */ - for (off = FirstOffsetNumber; off <= maxoff; off++) - { - IndexTuple itup; - - ItemId id = PageGetItemId(page, off); - - itup = (IndexTuple) PageGetItem(page, id); - - item_size += IndexTupleSize(itup); - - if (!ItemIdIsDead(id)) - stat->live_items++; - else - stat->dead_items++; - } - stat->free_size = PageGetFreeSpace(page); - - if ((stat->live_items + stat->dead_items) > 0) - stat->avg_item_size = item_size / (stat->live_items + stat->dead_items); - else - stat->avg_item_size = 0; -} - -/* ----------------------------------------------- - * bt_page() - * - * Usage: SELECT * FROM bt_page('t1_pkey', 1); - * ----------------------------------------------- - */ -Datum -bt_page_stats(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - uint32 blkno = PG_GETARG_UINT32(1); - Buffer buffer; - Relation rel; - RangeVar *relrv; - Datum result; - HeapTuple tuple; - TupleDesc tupleDesc; - int j; - char *values[11]; - BTPageStat stat; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pageinspect functions")))); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - if (!IS_INDEX(rel) || !IS_BTREE(rel)) - elog(ERROR, "relation \"%s\" is not a btree index", - RelationGetRelationName(rel)); - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the owning - * session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - if (blkno == 0) - elog(ERROR, "block 0 is a meta page"); - - CHECK_RELATION_BLOCK_RANGE(rel, blkno); - - buffer = ReadBuffer(rel, blkno); - - /* keep compiler quiet */ - stat.btpo_prev = stat.btpo_next = InvalidBlockNumber; - stat.btpo_flags = stat.free_size = stat.avg_item_size = 0; - - GetBTPageStatistics(blkno, buffer, &stat); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - j = 0; - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.blkno); - values[j] = palloc(32); - snprintf(values[j++], 32, "%c", stat.type); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.live_items); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.dead_items); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.avg_item_size); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.page_size); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.free_size); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.btpo_prev); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.btpo_next); - values[j] = palloc(32); - if (stat.type == 'd') - snprintf(values[j++], 32, "%d", stat.btpo.xact); - else - snprintf(values[j++], 32, "%d", stat.btpo.level); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", stat.btpo_flags); - - tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), - values); - - result = HeapTupleGetDatum(tuple); - - ReleaseBuffer(buffer); - - relation_close(rel, AccessShareLock); - - PG_RETURN_DATUM(result); -} - -/*------------------------------------------------------- - * bt_page_items() - * - * Get IndexTupleData set in a btree page - * - * Usage: SELECT * FROM bt_page_items('t1_pkey', 1); - *------------------------------------------------------- - */ - -/* - * cross-call data structure for SRF - */ -struct user_args -{ - Page page; - OffsetNumber offset; -}; - -Datum -bt_page_items(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - uint32 blkno = PG_GETARG_UINT32(1); - Datum result; - char *values[6]; - HeapTuple tuple; - FuncCallContext *fctx; - MemoryContext mctx; - struct user_args *uargs; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pageinspect functions")))); - - if (SRF_IS_FIRSTCALL()) - { - RangeVar *relrv; - Relation rel; - Buffer buffer; - BTPageOpaque opaque; - TupleDesc tupleDesc; - - fctx = SRF_FIRSTCALL_INIT(); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - if (!IS_INDEX(rel) || !IS_BTREE(rel)) - elog(ERROR, "relation \"%s\" is not a btree index", - RelationGetRelationName(rel)); - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the - * owning session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - if (blkno == 0) - elog(ERROR, "block 0 is a meta page"); - - CHECK_RELATION_BLOCK_RANGE(rel, blkno); - - buffer = ReadBuffer(rel, blkno); - - /* - * We copy the page into local storage to avoid holding pin on the - * buffer longer than we must, and possibly failing to release it at - * all if the calling query doesn't fetch all rows. - */ - mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); - - uargs = palloc(sizeof(struct user_args)); - - uargs->page = palloc(BLCKSZ); - memcpy(uargs->page, BufferGetPage(buffer), BLCKSZ); - - ReleaseBuffer(buffer); - relation_close(rel, AccessShareLock); - - uargs->offset = FirstOffsetNumber; - - opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page); - - if (P_ISDELETED(opaque)) - elog(NOTICE, "page is deleted"); - - fctx->max_calls = PageGetMaxOffsetNumber(uargs->page); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc); - - fctx->user_fctx = uargs; - - MemoryContextSwitchTo(mctx); - } - - fctx = SRF_PERCALL_SETUP(); - uargs = fctx->user_fctx; - - if (fctx->call_cntr < fctx->max_calls) - { - ItemId id; - IndexTuple itup; - int j; - int off; - int dlen; - char *dump; - char *ptr; - - id = PageGetItemId(uargs->page, uargs->offset); - - if (!ItemIdIsValid(id)) - elog(ERROR, "invalid ItemId"); - - itup = (IndexTuple) PageGetItem(uargs->page, id); - - j = 0; - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", uargs->offset); - values[j] = palloc(32); - snprintf(values[j++], 32, "(%u,%u)", - BlockIdGetBlockNumber(&(itup->t_tid.ip_blkid)), - itup->t_tid.ip_posid); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", (int) IndexTupleSize(itup)); - values[j] = palloc(32); - snprintf(values[j++], 32, "%c", IndexTupleHasNulls(itup) ? 't' : 'f'); - values[j] = palloc(32); - snprintf(values[j++], 32, "%c", IndexTupleHasVarwidths(itup) ? 't' : 'f'); - - ptr = (char *) itup + IndexInfoFindDataOffset(itup->t_info); - dlen = IndexTupleSize(itup) - IndexInfoFindDataOffset(itup->t_info); - dump = palloc0(dlen * 3 + 1); - values[j] = dump; - for (off = 0; off < dlen; off++) - { - if (off > 0) - *dump++ = ' '; - sprintf(dump, "%02x", *(ptr + off) & 0xff); - dump += 2; - } - - tuple = BuildTupleFromCStrings(fctx->attinmeta, values); - result = HeapTupleGetDatum(tuple); - - uargs->offset = uargs->offset + 1; - - SRF_RETURN_NEXT(fctx, result); - } - else - { - pfree(uargs->page); - pfree(uargs); - SRF_RETURN_DONE(fctx); - } -} - - -/* ------------------------------------------------ - * bt_metap() - * - * Get a btree's meta-page information - * - * Usage: SELECT * FROM bt_metap('t1_pkey') - * ------------------------------------------------ - */ -Datum -bt_metap(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - Datum result; - Relation rel; - RangeVar *relrv; - BTMetaPageData *metad; - TupleDesc tupleDesc; - int j; - char *values[6]; - Buffer buffer; - Page page; - HeapTuple tuple; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pageinspect functions")))); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - if (!IS_INDEX(rel) || !IS_BTREE(rel)) - elog(ERROR, "relation \"%s\" is not a btree index", - RelationGetRelationName(rel)); - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the owning - * session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - buffer = ReadBuffer(rel, 0); - page = BufferGetPage(buffer); - metad = BTPageGetMeta(page); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - j = 0; - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_magic); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_version); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_root); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_level); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_fastroot); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", metad->btm_fastlevel); - - tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), - values); - - result = HeapTupleGetDatum(tuple); - - ReleaseBuffer(buffer); - - relation_close(rel, AccessShareLock); - - PG_RETURN_DATUM(result); -} diff --git a/contrib/pageinspect/fsmfuncs.c b/contrib/pageinspect/fsmfuncs.c deleted file mode 100644 index 38c4e23..0000000 --- a/contrib/pageinspect/fsmfuncs.c +++ /dev/null @@ -1,59 +0,0 @@ -/*------------------------------------------------------------------------- - * - * fsmfuncs.c - * Functions to investigate FSM pages - * - * These functions are restricted to superusers for the fear of introducing - * security holes if the input checking isn't as water-tight as it should. - * You'd need to be superuser to obtain a raw page image anyway, so - * there's hardly any use case for using these without superuser-rights - * anyway. - * - * Copyright (c) 2007-2011, PostgreSQL Global Development Group - * - * IDENTIFICATION - * contrib/pageinspect/fsmfuncs.c - * - *------------------------------------------------------------------------- - */ - -#include "postgres.h" -#include "lib/stringinfo.h" -#include "storage/fsm_internals.h" -#include "utils/builtins.h" -#include "miscadmin.h" -#include "funcapi.h" - -Datum fsm_page_contents(PG_FUNCTION_ARGS); - -/* - * Dumps the contents of a FSM page. - */ -PG_FUNCTION_INFO_V1(fsm_page_contents); - -Datum -fsm_page_contents(PG_FUNCTION_ARGS) -{ - bytea *raw_page = PG_GETARG_BYTEA_P(0); - StringInfoData sinfo; - FSMPage fsmpage; - int i; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use raw page functions")))); - - fsmpage = (FSMPage) PageGetContents(VARDATA(raw_page)); - - initStringInfo(&sinfo); - - for (i = 0; i < NodesPerPage; i++) - { - if (fsmpage->fp_nodes[i] != 0) - appendStringInfo(&sinfo, "%d: %d\n", i, fsmpage->fp_nodes[i]); - } - appendStringInfo(&sinfo, "fp_next_slot: %d\n", fsmpage->fp_next_slot); - - PG_RETURN_TEXT_P(cstring_to_text(sinfo.data)); -} diff --git a/contrib/pageinspect/heapfuncs.c b/contrib/pageinspect/heapfuncs.c deleted file mode 100644 index 20bca0d..0000000 --- a/contrib/pageinspect/heapfuncs.c +++ /dev/null @@ -1,230 +0,0 @@ -/*------------------------------------------------------------------------- - * - * heapfuncs.c - * Functions to investigate heap pages - * - * We check the input to these functions for corrupt pointers etc. that - * might cause crashes, but at the same time we try to print out as much - * information as possible, even if it's nonsense. That's because if a - * page is corrupt, we don't know why and how exactly it is corrupt, so we - * let the user judge it. - * - * These functions are restricted to superusers for the fear of introducing - * security holes if the input checking isn't as water-tight as it should be. - * You'd need to be superuser to obtain a raw page image anyway, so - * there's hardly any use case for using these without superuser-rights - * anyway. - * - * Copyright (c) 2007-2011, PostgreSQL Global Development Group - * - * IDENTIFICATION - * contrib/pageinspect/heapfuncs.c - * - *------------------------------------------------------------------------- - */ - -#include "postgres.h" - -#include "fmgr.h" -#include "funcapi.h" -#include "access/heapam.h" -#include "access/transam.h" -#include "catalog/namespace.h" -#include "catalog/pg_type.h" -#include "utils/builtins.h" -#include "miscadmin.h" - -Datum heap_page_items(PG_FUNCTION_ARGS); - - -/* - * bits_to_text - * - * Converts a bits8-array of 'len' bits to a human-readable - * c-string representation. - */ -static char * -bits_to_text(bits8 *bits, int len) -{ - int i; - char *str; - - str = palloc(len + 1); - - for (i = 0; i < len; i++) - str[i] = (bits[(i / 8)] & (1 << (i % 8))) ? '1' : '0'; - - str[i] = '\0'; - - return str; -} - - -/* - * heap_page_items - * - * Allows inspection of line pointers and tuple headers of a heap page. - */ -PG_FUNCTION_INFO_V1(heap_page_items); - -typedef struct heap_page_items_state -{ - TupleDesc tupd; - Page page; - uint16 offset; -} heap_page_items_state; - -Datum -heap_page_items(PG_FUNCTION_ARGS) -{ - bytea *raw_page = PG_GETARG_BYTEA_P(0); - heap_page_items_state *inter_call_data = NULL; - FuncCallContext *fctx; - int raw_page_size; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use raw page functions")))); - - raw_page_size = VARSIZE(raw_page) - VARHDRSZ; - - if (SRF_IS_FIRSTCALL()) - { - TupleDesc tupdesc; - MemoryContext mctx; - - if (raw_page_size < SizeOfPageHeaderData) - ereport(ERROR, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("input page too small (%d bytes)", raw_page_size))); - - fctx = SRF_FIRSTCALL_INIT(); - mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); - - inter_call_data = palloc(sizeof(heap_page_items_state)); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - inter_call_data->tupd = tupdesc; - - inter_call_data->offset = FirstOffsetNumber; - inter_call_data->page = VARDATA(raw_page); - - fctx->max_calls = PageGetMaxOffsetNumber(inter_call_data->page); - fctx->user_fctx = inter_call_data; - - MemoryContextSwitchTo(mctx); - } - - fctx = SRF_PERCALL_SETUP(); - inter_call_data = fctx->user_fctx; - - if (fctx->call_cntr < fctx->max_calls) - { - Page page = inter_call_data->page; - HeapTuple resultTuple; - Datum result; - ItemId id; - Datum values[13]; - bool nulls[13]; - uint16 lp_offset; - uint16 lp_flags; - uint16 lp_len; - - memset(nulls, 0, sizeof(nulls)); - - /* Extract information from the line pointer */ - - id = PageGetItemId(page, inter_call_data->offset); - - lp_offset = ItemIdGetOffset(id); - lp_flags = ItemIdGetFlags(id); - lp_len = ItemIdGetLength(id); - - values[0] = UInt16GetDatum(inter_call_data->offset); - values[1] = UInt16GetDatum(lp_offset); - values[2] = UInt16GetDatum(lp_flags); - values[3] = UInt16GetDatum(lp_len); - - /* - * We do just enough validity checking to make sure we don't reference - * data outside the page passed to us. The page could be corrupt in - * many other ways, but at least we won't crash. - */ - if (ItemIdHasStorage(id) && - lp_len >= sizeof(HeapTupleHeader) && - lp_offset == MAXALIGN(lp_offset) && - lp_offset + lp_len <= raw_page_size) - { - HeapTupleHeader tuphdr; - int bits_len; - - /* Extract information from the tuple header */ - - tuphdr = (HeapTupleHeader) PageGetItem(page, id); - - values[4] = UInt32GetDatum(HeapTupleHeaderGetXmin(tuphdr)); - values[5] = UInt32GetDatum(HeapTupleHeaderGetXmax(tuphdr)); - values[6] = UInt32GetDatum(HeapTupleHeaderGetRawCommandId(tuphdr)); /* shared with xvac */ - values[7] = PointerGetDatum(&tuphdr->t_ctid); - values[8] = UInt32GetDatum(tuphdr->t_infomask2); - values[9] = UInt32GetDatum(tuphdr->t_infomask); - values[10] = UInt8GetDatum(tuphdr->t_hoff); - - /* - * We already checked that the item as is completely within the - * raw page passed to us, with the length given in the line - * pointer.. Let's check that t_hoff doesn't point over lp_len, - * before using it to access t_bits and oid. - */ - if (tuphdr->t_hoff >= sizeof(HeapTupleHeader) && - tuphdr->t_hoff <= lp_len) - { - if (tuphdr->t_infomask & HEAP_HASNULL) - { - bits_len = tuphdr->t_hoff - - (((char *) tuphdr->t_bits) -((char *) tuphdr)); - - values[11] = CStringGetTextDatum( - bits_to_text(tuphdr->t_bits, bits_len * 8)); - } - else - nulls[11] = true; - - if (tuphdr->t_infomask & HEAP_HASOID) - values[12] = HeapTupleHeaderGetOid(tuphdr); - else - nulls[12] = true; - } - else - { - nulls[11] = true; - nulls[12] = true; - } - } - else - { - /* - * The line pointer is not used, or it's invalid. Set the rest of - * the fields to NULL - */ - int i; - - for (i = 4; i <= 12; i++) - nulls[i] = true; - } - - /* Build and return the result tuple. */ - resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls); - result = HeapTupleGetDatum(resultTuple); - - inter_call_data->offset++; - - SRF_RETURN_NEXT(fctx, result); - } - else - SRF_RETURN_DONE(fctx); -} diff --git a/contrib/pageinspect/pageinspect--1.0.sql b/contrib/pageinspect/pageinspect--1.0.sql deleted file mode 100644 index a711f58..0000000 --- a/contrib/pageinspect/pageinspect--1.0.sql +++ /dev/null @@ -1,104 +0,0 @@ -/* contrib/pageinspect/pageinspect--1.0.sql */ - --- --- get_raw_page() --- -CREATE FUNCTION get_raw_page(text, int4) -RETURNS bytea -AS 'MODULE_PATHNAME', 'get_raw_page' -LANGUAGE C STRICT; - -CREATE FUNCTION get_raw_page(text, text, int4) -RETURNS bytea -AS 'MODULE_PATHNAME', 'get_raw_page_fork' -LANGUAGE C STRICT; - --- --- page_header() --- -CREATE FUNCTION page_header(IN page bytea, - OUT lsn text, - OUT tli smallint, - OUT flags smallint, - OUT lower smallint, - OUT upper smallint, - OUT special smallint, - OUT pagesize smallint, - OUT version smallint, - OUT prune_xid xid) -AS 'MODULE_PATHNAME', 'page_header' -LANGUAGE C STRICT; - --- --- heap_page_items() --- -CREATE FUNCTION heap_page_items(IN page bytea, - OUT lp smallint, - OUT lp_off smallint, - OUT lp_flags smallint, - OUT lp_len smallint, - OUT t_xmin xid, - OUT t_xmax xid, - OUT t_field3 int4, - OUT t_ctid tid, - OUT t_infomask2 integer, - OUT t_infomask integer, - OUT t_hoff smallint, - OUT t_bits text, - OUT t_oid oid) -RETURNS SETOF record -AS 'MODULE_PATHNAME', 'heap_page_items' -LANGUAGE C STRICT; - --- --- bt_metap() --- -CREATE FUNCTION bt_metap(IN relname text, - OUT magic int4, - OUT version int4, - OUT root int4, - OUT level int4, - OUT fastroot int4, - OUT fastlevel int4) -AS 'MODULE_PATHNAME', 'bt_metap' -LANGUAGE C STRICT; - --- --- bt_page_stats() --- -CREATE FUNCTION bt_page_stats(IN relname text, IN blkno int4, - OUT blkno int4, - OUT type "char", - OUT live_items int4, - OUT dead_items int4, - OUT avg_item_size int4, - OUT page_size int4, - OUT free_size int4, - OUT btpo_prev int4, - OUT btpo_next int4, - OUT btpo int4, - OUT btpo_flags int4) -AS 'MODULE_PATHNAME', 'bt_page_stats' -LANGUAGE C STRICT; - --- --- bt_page_items() --- -CREATE FUNCTION bt_page_items(IN relname text, IN blkno int4, - OUT itemoffset smallint, - OUT ctid tid, - OUT itemlen smallint, - OUT nulls bool, - OUT vars bool, - OUT data text) -RETURNS SETOF record -AS 'MODULE_PATHNAME', 'bt_page_items' -LANGUAGE C STRICT; - --- --- fsm_page_contents() --- -CREATE FUNCTION fsm_page_contents(IN page bytea) -RETURNS text -AS 'MODULE_PATHNAME', 'fsm_page_contents' -LANGUAGE C STRICT; diff --git a/contrib/pageinspect/pageinspect--unpackaged--1.0.sql b/contrib/pageinspect/pageinspect--unpackaged--1.0.sql deleted file mode 100644 index 7d4feaf..0000000 --- a/contrib/pageinspect/pageinspect--unpackaged--1.0.sql +++ /dev/null @@ -1,28 +0,0 @@ -/* contrib/pageinspect/pageinspect--unpackaged--1.0.sql */ - -DROP FUNCTION heap_page_items(bytea); -CREATE FUNCTION heap_page_items(IN page bytea, - OUT lp smallint, - OUT lp_off smallint, - OUT lp_flags smallint, - OUT lp_len smallint, - OUT t_xmin xid, - OUT t_xmax xid, - OUT t_field3 int4, - OUT t_ctid tid, - OUT t_infomask2 integer, - OUT t_infomask integer, - OUT t_hoff smallint, - OUT t_bits text, - OUT t_oid oid) -RETURNS SETOF record -AS 'MODULE_PATHNAME', 'heap_page_items' -LANGUAGE C STRICT; - -ALTER EXTENSION pageinspect ADD function get_raw_page(text,integer); -ALTER EXTENSION pageinspect ADD function get_raw_page(text,text,integer); -ALTER EXTENSION pageinspect ADD function page_header(bytea); -ALTER EXTENSION pageinspect ADD function bt_metap(text); -ALTER EXTENSION pageinspect ADD function bt_page_stats(text,integer); -ALTER EXTENSION pageinspect ADD function bt_page_items(text,integer); -ALTER EXTENSION pageinspect ADD function fsm_page_contents(bytea); diff --git a/contrib/pageinspect/pageinspect.control b/contrib/pageinspect/pageinspect.control deleted file mode 100644 index f9da0e8..0000000 --- a/contrib/pageinspect/pageinspect.control +++ /dev/null @@ -1,5 +0,0 @@ -# pageinspect extension -comment = 'inspect the contents of database pages at a low level' -default_version = '1.0' -module_pathname = '$libdir/pageinspect' -relocatable = true diff --git a/contrib/pageinspect/rawpage.c b/contrib/pageinspect/rawpage.c deleted file mode 100644 index 2607576..0000000 --- a/contrib/pageinspect/rawpage.c +++ /dev/null @@ -1,232 +0,0 @@ -/*------------------------------------------------------------------------- - * - * rawpage.c - * Functions to extract a raw page as bytea and inspect it - * - * Access-method specific inspection functions are in separate files. - * - * Copyright (c) 2007-2011, PostgreSQL Global Development Group - * - * IDENTIFICATION - * contrib/pageinspect/rawpage.c - * - *------------------------------------------------------------------------- - */ - -#include "postgres.h" - -#include "access/heapam.h" -#include "access/transam.h" -#include "catalog/catalog.h" -#include "catalog/namespace.h" -#include "catalog/pg_type.h" -#include "fmgr.h" -#include "funcapi.h" -#include "miscadmin.h" -#include "storage/bufmgr.h" -#include "utils/builtins.h" - -PG_MODULE_MAGIC; - -Datum get_raw_page(PG_FUNCTION_ARGS); -Datum get_raw_page_fork(PG_FUNCTION_ARGS); -Datum page_header(PG_FUNCTION_ARGS); - -static bytea *get_raw_page_internal(text *relname, ForkNumber forknum, - BlockNumber blkno); - - -/* - * get_raw_page - * - * Returns a copy of a page from shared buffers as a bytea - */ -PG_FUNCTION_INFO_V1(get_raw_page); - -Datum -get_raw_page(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - uint32 blkno = PG_GETARG_UINT32(1); - bytea *raw_page; - - /* - * We don't normally bother to check the number of arguments to a C - * function, but here it's needed for safety because early 8.4 beta - * releases mistakenly redefined get_raw_page() as taking three arguments. - */ - if (PG_NARGS() != 2) - ereport(ERROR, - (errmsg("wrong number of arguments to get_raw_page()"), - errhint("Run the updated pageinspect.sql script."))); - - raw_page = get_raw_page_internal(relname, MAIN_FORKNUM, blkno); - - PG_RETURN_BYTEA_P(raw_page); -} - -/* - * get_raw_page_fork - * - * Same, for any fork - */ -PG_FUNCTION_INFO_V1(get_raw_page_fork); - -Datum -get_raw_page_fork(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - text *forkname = PG_GETARG_TEXT_P(1); - uint32 blkno = PG_GETARG_UINT32(2); - bytea *raw_page; - ForkNumber forknum; - - forknum = forkname_to_number(text_to_cstring(forkname)); - - raw_page = get_raw_page_internal(relname, forknum, blkno); - - PG_RETURN_BYTEA_P(raw_page); -} - -/* - * workhorse - */ -static bytea * -get_raw_page_internal(text *relname, ForkNumber forknum, BlockNumber blkno) -{ - bytea *raw_page; - RangeVar *relrv; - Relation rel; - char *raw_page_data; - Buffer buf; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use raw functions")))); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - /* Check that this relation has storage */ - if (rel->rd_rel->relkind == RELKIND_VIEW) - ereport(ERROR, - (errcode(ERRCODE_WRONG_OBJECT_TYPE), - errmsg("cannot get raw page from view \"%s\"", - RelationGetRelationName(rel)))); - if (rel->rd_rel->relkind == RELKIND_COMPOSITE_TYPE) - ereport(ERROR, - (errcode(ERRCODE_WRONG_OBJECT_TYPE), - errmsg("cannot get raw page from composite type \"%s\"", - RelationGetRelationName(rel)))); - if (rel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) - ereport(ERROR, - (errcode(ERRCODE_WRONG_OBJECT_TYPE), - errmsg("cannot get raw page from foreign table \"%s\"", - RelationGetRelationName(rel)))); - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the owning - * session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - if (blkno >= RelationGetNumberOfBlocks(rel)) - elog(ERROR, "block number %u is out of range for relation \"%s\"", - blkno, RelationGetRelationName(rel)); - - /* Initialize buffer to copy to */ - raw_page = (bytea *) palloc(BLCKSZ + VARHDRSZ); - SET_VARSIZE(raw_page, BLCKSZ + VARHDRSZ); - raw_page_data = VARDATA(raw_page); - - /* Take a verbatim copy of the page */ - - buf = ReadBufferExtended(rel, forknum, blkno, RBM_NORMAL, NULL); - LockBuffer(buf, BUFFER_LOCK_SHARE); - - memcpy(raw_page_data, BufferGetPage(buf), BLCKSZ); - - LockBuffer(buf, BUFFER_LOCK_UNLOCK); - ReleaseBuffer(buf); - - relation_close(rel, AccessShareLock); - - return raw_page; -} - -/* - * page_header - * - * Allows inspection of page header fields of a raw page - */ - -PG_FUNCTION_INFO_V1(page_header); - -Datum -page_header(PG_FUNCTION_ARGS) -{ - bytea *raw_page = PG_GETARG_BYTEA_P(0); - int raw_page_size; - - TupleDesc tupdesc; - - Datum result; - HeapTuple tuple; - Datum values[9]; - bool nulls[9]; - - PageHeader page; - XLogRecPtr lsn; - char lsnchar[64]; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use raw page functions")))); - - raw_page_size = VARSIZE(raw_page) - VARHDRSZ; - - /* - * Check that enough data was supplied, so that we don't try to access - * fields outside the supplied buffer. - */ - if (raw_page_size < sizeof(PageHeaderData)) - ereport(ERROR, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("input page too small (%d bytes)", raw_page_size))); - - page = (PageHeader) VARDATA(raw_page); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - /* Extract information from the page header */ - - lsn = PageGetLSN(page); - snprintf(lsnchar, sizeof(lsnchar), "%X/%X", lsn.xlogid, lsn.xrecoff); - - values[0] = CStringGetTextDatum(lsnchar); - values[1] = UInt16GetDatum(PageGetTLI(page)); - values[2] = UInt16GetDatum(page->pd_flags); - values[3] = UInt16GetDatum(page->pd_lower); - values[4] = UInt16GetDatum(page->pd_upper); - values[5] = UInt16GetDatum(page->pd_special); - values[6] = UInt16GetDatum(PageGetPageSize(page)); - values[7] = UInt16GetDatum(PageGetPageLayoutVersion(page)); - values[8] = TransactionIdGetDatum(page->pd_prune_xid); - - /* Build and return the tuple. */ - - memset(nulls, 0, sizeof(nulls)); - - tuple = heap_form_tuple(tupdesc, values, nulls); - result = HeapTupleGetDatum(tuple); - - PG_RETURN_DATUM(result); -} diff --git a/contrib/pg_buffercache/Makefile b/contrib/pg_buffercache/Makefile deleted file mode 100644 index 323c0ac..0000000 --- a/contrib/pg_buffercache/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pg_buffercache/Makefile - -MODULE_big = pg_buffercache -OBJS = pg_buffercache_pages.o - -EXTENSION = pg_buffercache -DATA = pg_buffercache--1.0.sql pg_buffercache--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pg_buffercache -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pg_buffercache/pg_buffercache--1.0.sql b/contrib/pg_buffercache/pg_buffercache--1.0.sql deleted file mode 100644 index 9407d21..0000000 --- a/contrib/pg_buffercache/pg_buffercache--1.0.sql +++ /dev/null @@ -1,17 +0,0 @@ -/* contrib/pg_buffercache/pg_buffercache--1.0.sql */ - --- Register the function. -CREATE FUNCTION pg_buffercache_pages() -RETURNS SETOF RECORD -AS 'MODULE_PATHNAME', 'pg_buffercache_pages' -LANGUAGE C; - --- Create a view for convenient access. -CREATE VIEW pg_buffercache AS - SELECT P.* FROM pg_buffercache_pages() AS P - (bufferid integer, relfilenode oid, reltablespace oid, reldatabase oid, - relforknumber int2, relblocknumber int8, isdirty bool, usagecount int2); - --- Don't want these to be available to public. -REVOKE ALL ON FUNCTION pg_buffercache_pages() FROM PUBLIC; -REVOKE ALL ON pg_buffercache FROM PUBLIC; diff --git a/contrib/pg_buffercache/pg_buffercache--unpackaged--1.0.sql b/contrib/pg_buffercache/pg_buffercache--unpackaged--1.0.sql deleted file mode 100644 index f00a954..0000000 --- a/contrib/pg_buffercache/pg_buffercache--unpackaged--1.0.sql +++ /dev/null @@ -1,4 +0,0 @@ -/* contrib/pg_buffercache/pg_buffercache--unpackaged--1.0.sql */ - -ALTER EXTENSION pg_buffercache ADD function pg_buffercache_pages(); -ALTER EXTENSION pg_buffercache ADD view pg_buffercache; diff --git a/contrib/pg_buffercache/pg_buffercache.control b/contrib/pg_buffercache/pg_buffercache.control deleted file mode 100644 index 709513c..0000000 --- a/contrib/pg_buffercache/pg_buffercache.control +++ /dev/null @@ -1,5 +0,0 @@ -# pg_buffercache extension -comment = 'examine the shared buffer cache' -default_version = '1.0' -module_pathname = '$libdir/pg_buffercache' -relocatable = true diff --git a/contrib/pg_buffercache/pg_buffercache_pages.c b/contrib/pg_buffercache/pg_buffercache_pages.c deleted file mode 100644 index ed88288..0000000 --- a/contrib/pg_buffercache/pg_buffercache_pages.c +++ /dev/null @@ -1,219 +0,0 @@ -/*------------------------------------------------------------------------- - * - * pg_buffercache_pages.c - * display some contents of the buffer cache - * - * contrib/pg_buffercache/pg_buffercache_pages.c - *------------------------------------------------------------------------- - */ -#include "postgres.h" - -#include "access/heapam.h" -#include "catalog/pg_type.h" -#include "funcapi.h" -#include "storage/buf_internals.h" -#include "storage/bufmgr.h" -#include "utils/relcache.h" - - -#define NUM_BUFFERCACHE_PAGES_ELEM 8 - -PG_MODULE_MAGIC; - -Datum pg_buffercache_pages(PG_FUNCTION_ARGS); - - -/* - * Record structure holding the to be exposed cache data. - */ -typedef struct -{ - uint32 bufferid; - Oid relfilenode; - Oid reltablespace; - Oid reldatabase; - ForkNumber forknum; - BlockNumber blocknum; - bool isvalid; - bool isdirty; - uint16 usagecount; -} BufferCachePagesRec; - - -/* - * Function context for data persisting over repeated calls. - */ -typedef struct -{ - TupleDesc tupdesc; - BufferCachePagesRec *record; -} BufferCachePagesContext; - - -/* - * Function returning data from the shared buffer cache - buffer number, - * relation node/tablespace/database/blocknum and dirty indicator. - */ -PG_FUNCTION_INFO_V1(pg_buffercache_pages); - -Datum -pg_buffercache_pages(PG_FUNCTION_ARGS) -{ - FuncCallContext *funcctx; - Datum result; - MemoryContext oldcontext; - BufferCachePagesContext *fctx; /* User function context. */ - TupleDesc tupledesc; - HeapTuple tuple; - - if (SRF_IS_FIRSTCALL()) - { - int i; - volatile BufferDesc *bufHdr; - - funcctx = SRF_FIRSTCALL_INIT(); - - /* Switch context when allocating stuff to be used in later calls */ - oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx); - - /* Create a user function context for cross-call persistence */ - fctx = (BufferCachePagesContext *) palloc(sizeof(BufferCachePagesContext)); - - /* Construct a tuple descriptor for the result rows. */ - tupledesc = CreateTemplateTupleDesc(NUM_BUFFERCACHE_PAGES_ELEM, false); - TupleDescInitEntry(tupledesc, (AttrNumber) 1, "bufferid", - INT4OID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 2, "relfilenode", - OIDOID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 3, "reltablespace", - OIDOID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 4, "reldatabase", - OIDOID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 5, "relforknumber", - INT2OID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 6, "relblocknumber", - INT8OID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 7, "isdirty", - BOOLOID, -1, 0); - TupleDescInitEntry(tupledesc, (AttrNumber) 8, "usage_count", - INT2OID, -1, 0); - - fctx->tupdesc = BlessTupleDesc(tupledesc); - - /* Allocate NBuffers worth of BufferCachePagesRec records. */ - fctx->record = (BufferCachePagesRec *) palloc(sizeof(BufferCachePagesRec) * NBuffers); - - /* Set max calls and remember the user function context. */ - funcctx->max_calls = NBuffers; - funcctx->user_fctx = fctx; - - /* Return to original context when allocating transient memory */ - MemoryContextSwitchTo(oldcontext); - - /* - * To get a consistent picture of the buffer state, we must lock all - * partitions of the buffer map. Needless to say, this is horrible - * for concurrency. Must grab locks in increasing order to avoid - * possible deadlocks. - */ - for (i = 0; i < NUM_BUFFER_PARTITIONS; i++) - LWLockAcquire(FirstBufMappingLock + i, LW_SHARED); - - /* - * Scan though all the buffers, saving the relevant fields in the - * fctx->record structure. - */ - for (i = 0, bufHdr = BufferDescriptors; i < NBuffers; i++, bufHdr++) - { - /* Lock each buffer header before inspecting. */ - LockBufHdr(bufHdr); - - fctx->record[i].bufferid = BufferDescriptorGetBuffer(bufHdr); - fctx->record[i].relfilenode = bufHdr->tag.rnode.relNode; - fctx->record[i].reltablespace = bufHdr->tag.rnode.spcNode; - fctx->record[i].reldatabase = bufHdr->tag.rnode.dbNode; - fctx->record[i].forknum = bufHdr->tag.forkNum; - fctx->record[i].blocknum = bufHdr->tag.blockNum; - fctx->record[i].usagecount = bufHdr->usage_count; - - if (bufHdr->flags & BM_DIRTY) - fctx->record[i].isdirty = true; - else - fctx->record[i].isdirty = false; - - /* Note if the buffer is valid, and has storage created */ - if ((bufHdr->flags & BM_VALID) && (bufHdr->flags & BM_TAG_VALID)) - fctx->record[i].isvalid = true; - else - fctx->record[i].isvalid = false; - - UnlockBufHdr(bufHdr); - } - - /* - * And release locks. We do this in reverse order for two reasons: - * (1) Anyone else who needs more than one of the locks will be trying - * to lock them in increasing order; we don't want to release the - * other process until it can get all the locks it needs. (2) This - * avoids O(N^2) behavior inside LWLockRelease. - */ - for (i = NUM_BUFFER_PARTITIONS; --i >= 0;) - LWLockRelease(FirstBufMappingLock + i); - } - - funcctx = SRF_PERCALL_SETUP(); - - /* Get the saved state */ - fctx = funcctx->user_fctx; - - if (funcctx->call_cntr < funcctx->max_calls) - { - uint32 i = funcctx->call_cntr; - Datum values[NUM_BUFFERCACHE_PAGES_ELEM]; - bool nulls[NUM_BUFFERCACHE_PAGES_ELEM]; - - values[0] = Int32GetDatum(fctx->record[i].bufferid); - nulls[0] = false; - - /* - * Set all fields except the bufferid to null if the buffer is unused - * or not valid. - */ - if (fctx->record[i].blocknum == InvalidBlockNumber || - fctx->record[i].isvalid == false) - { - nulls[1] = true; - nulls[2] = true; - nulls[3] = true; - nulls[4] = true; - nulls[5] = true; - nulls[6] = true; - nulls[7] = true; - } - else - { - values[1] = ObjectIdGetDatum(fctx->record[i].relfilenode); - nulls[1] = false; - values[2] = ObjectIdGetDatum(fctx->record[i].reltablespace); - nulls[2] = false; - values[3] = ObjectIdGetDatum(fctx->record[i].reldatabase); - nulls[3] = false; - values[4] = ObjectIdGetDatum(fctx->record[i].forknum); - nulls[4] = false; - values[5] = Int64GetDatum((int64) fctx->record[i].blocknum); - nulls[5] = false; - values[6] = BoolGetDatum(fctx->record[i].isdirty); - nulls[6] = false; - values[7] = Int16GetDatum(fctx->record[i].usagecount); - nulls[7] = false; - } - - /* Build and return the tuple. */ - tuple = heap_form_tuple(fctx->tupdesc, values, nulls); - result = HeapTupleGetDatum(tuple); - - SRF_RETURN_NEXT(funcctx, result); - } - else - SRF_RETURN_DONE(funcctx); -} diff --git a/contrib/pg_freespacemap/Makefile b/contrib/pg_freespacemap/Makefile deleted file mode 100644 index b2e3ba3..0000000 --- a/contrib/pg_freespacemap/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pg_freespacemap/Makefile - -MODULE_big = pg_freespacemap -OBJS = pg_freespacemap.o - -EXTENSION = pg_freespacemap -DATA = pg_freespacemap--1.0.sql pg_freespacemap--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pg_freespacemap -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pg_freespacemap/pg_freespacemap--1.0.sql b/contrib/pg_freespacemap/pg_freespacemap--1.0.sql deleted file mode 100644 index d63420e..0000000 --- a/contrib/pg_freespacemap/pg_freespacemap--1.0.sql +++ /dev/null @@ -1,22 +0,0 @@ -/* contrib/pg_freespacemap/pg_freespacemap--1.0.sql */ - --- Register the C function. -CREATE FUNCTION pg_freespace(regclass, bigint) -RETURNS int2 -AS 'MODULE_PATHNAME', 'pg_freespace' -LANGUAGE C STRICT; - --- pg_freespace shows the recorded space avail at each block in a relation -CREATE FUNCTION - pg_freespace(rel regclass, blkno OUT bigint, avail OUT int2) -RETURNS SETOF RECORD -AS $$ - SELECT blkno, pg_freespace($1, blkno) AS avail - FROM generate_series(0, pg_relation_size($1) / current_setting('block_size')::bigint - 1) AS blkno; -$$ -LANGUAGE SQL; - - --- Don't want these to be available to public. -REVOKE ALL ON FUNCTION pg_freespace(regclass, bigint) FROM PUBLIC; -REVOKE ALL ON FUNCTION pg_freespace(regclass) FROM PUBLIC; diff --git a/contrib/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql b/contrib/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql deleted file mode 100644 index 4c7487f..0000000 --- a/contrib/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql +++ /dev/null @@ -1,4 +0,0 @@ -/* contrib/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql */ - -ALTER EXTENSION pg_freespacemap ADD function pg_freespace(regclass,bigint); -ALTER EXTENSION pg_freespacemap ADD function pg_freespace(regclass); diff --git a/contrib/pg_freespacemap/pg_freespacemap.c b/contrib/pg_freespacemap/pg_freespacemap.c deleted file mode 100644 index bf6b0df..0000000 --- a/contrib/pg_freespacemap/pg_freespacemap.c +++ /dev/null @@ -1,46 +0,0 @@ -/*------------------------------------------------------------------------- - * - * pg_freespacemap.c - * display contents of a free space map - * - * contrib/pg_freespacemap/pg_freespacemap.c - *------------------------------------------------------------------------- - */ -#include "postgres.h" - -#include "access/heapam.h" -#include "funcapi.h" -#include "storage/block.h" -#include "storage/freespace.h" - - -PG_MODULE_MAGIC; - -Datum pg_freespace(PG_FUNCTION_ARGS); - -/* - * Returns the amount of free space on a given page, according to the - * free space map. - */ -PG_FUNCTION_INFO_V1(pg_freespace); - -Datum -pg_freespace(PG_FUNCTION_ARGS) -{ - Oid relid = PG_GETARG_OID(0); - int64 blkno = PG_GETARG_INT64(1); - int16 freespace; - Relation rel; - - rel = relation_open(relid, AccessShareLock); - - if (blkno < 0 || blkno > MaxBlockNumber) - ereport(ERROR, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("invalid block number"))); - - freespace = GetRecordedFreeSpace(rel, blkno); - - relation_close(rel, AccessShareLock); - PG_RETURN_INT16(freespace); -} diff --git a/contrib/pg_freespacemap/pg_freespacemap.control b/contrib/pg_freespacemap/pg_freespacemap.control deleted file mode 100644 index 34b695f..0000000 --- a/contrib/pg_freespacemap/pg_freespacemap.control +++ /dev/null @@ -1,5 +0,0 @@ -# pg_freespacemap extension -comment = 'examine the free space map (FSM)' -default_version = '1.0' -module_pathname = '$libdir/pg_freespacemap' -relocatable = true diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile deleted file mode 100644 index e086fd8..0000000 --- a/contrib/pg_stat_statements/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pg_stat_statements/Makefile - -MODULE_big = pg_stat_statements -OBJS = pg_stat_statements.o - -EXTENSION = pg_stat_statements -DATA = pg_stat_statements--1.0.sql pg_stat_statements--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pg_stat_statements -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pg_stat_statements/pg_stat_statements--1.0.sql b/contrib/pg_stat_statements/pg_stat_statements--1.0.sql deleted file mode 100644 index e17b82c..0000000 --- a/contrib/pg_stat_statements/pg_stat_statements--1.0.sql +++ /dev/null @@ -1,36 +0,0 @@ -/* contrib/pg_stat_statements/pg_stat_statements--1.0.sql */ - --- Register functions. -CREATE FUNCTION pg_stat_statements_reset() -RETURNS void -AS 'MODULE_PATHNAME' -LANGUAGE C; - -CREATE FUNCTION pg_stat_statements( - OUT userid oid, - OUT dbid oid, - OUT query text, - OUT calls int8, - OUT total_time float8, - OUT rows int8, - OUT shared_blks_hit int8, - OUT shared_blks_read int8, - OUT shared_blks_written int8, - OUT local_blks_hit int8, - OUT local_blks_read int8, - OUT local_blks_written int8, - OUT temp_blks_read int8, - OUT temp_blks_written int8 -) -RETURNS SETOF record -AS 'MODULE_PATHNAME' -LANGUAGE C; - --- Register a view on the function for ease of use. -CREATE VIEW pg_stat_statements AS - SELECT * FROM pg_stat_statements(); - -GRANT SELECT ON pg_stat_statements TO PUBLIC; - --- Don't want this to be available to non-superusers. -REVOKE ALL ON FUNCTION pg_stat_statements_reset() FROM PUBLIC; diff --git a/contrib/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql b/contrib/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql deleted file mode 100644 index 9dda85c..0000000 --- a/contrib/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql +++ /dev/null @@ -1,5 +0,0 @@ -/* contrib/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql */ - -ALTER EXTENSION pg_stat_statements ADD function pg_stat_statements_reset(); -ALTER EXTENSION pg_stat_statements ADD function pg_stat_statements(); -ALTER EXTENSION pg_stat_statements ADD view pg_stat_statements; diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c deleted file mode 100644 index 0236b87..0000000 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ /dev/null @@ -1,1046 +0,0 @@ -/*------------------------------------------------------------------------- - * - * pg_stat_statements.c - * Track statement execution times across a whole database cluster. - * - * Note about locking issues: to create or delete an entry in the shared - * hashtable, one must hold pgss->lock exclusively. Modifying any field - * in an entry except the counters requires the same. To look up an entry, - * one must hold the lock shared. To read or update the counters within - * an entry, one must hold the lock shared or exclusive (so the entry doesn't - * disappear!) and also take the entry's mutex spinlock. - * - * - * Copyright (c) 2008-2011, PostgreSQL Global Development Group - * - * IDENTIFICATION - * contrib/pg_stat_statements/pg_stat_statements.c - * - *------------------------------------------------------------------------- - */ -#include "postgres.h" - -#include - -#include "access/hash.h" -#include "catalog/pg_type.h" -#include "executor/executor.h" -#include "executor/instrument.h" -#include "funcapi.h" -#include "mb/pg_wchar.h" -#include "miscadmin.h" -#include "pgstat.h" -#include "storage/fd.h" -#include "storage/ipc.h" -#include "storage/spin.h" -#include "tcop/utility.h" -#include "utils/builtins.h" -#include "utils/hsearch.h" -#include "utils/guc.h" - - -PG_MODULE_MAGIC; - -/* Location of stats file */ -#define PGSS_DUMP_FILE "global/pg_stat_statements.stat" - -/* This constant defines the magic number in the stats file header */ -static const uint32 PGSS_FILE_HEADER = 0x20100108; - -/* XXX: Should USAGE_EXEC reflect execution time and/or buffer usage? */ -#define USAGE_EXEC(duration) (1.0) -#define USAGE_INIT (1.0) /* including initial planning */ -#define USAGE_DECREASE_FACTOR (0.99) /* decreased every entry_dealloc */ -#define USAGE_DEALLOC_PERCENT 5 /* free this % of entries at once */ - -/* - * Hashtable key that defines the identity of a hashtable entry. The - * hash comparators do not assume that the query string is null-terminated; - * this lets us search for an mbcliplen'd string without copying it first. - * - * Presently, the query encoding is fully determined by the source database - * and so we don't really need it to be in the key. But that might not always - * be true. Anyway it's notationally convenient to pass it as part of the key. - */ -typedef struct pgssHashKey -{ - Oid userid; /* user OID */ - Oid dbid; /* database OID */ - int encoding; /* query encoding */ - int query_len; /* # of valid bytes in query string */ - const char *query_ptr; /* query string proper */ -} pgssHashKey; - -/* - * The actual stats counters kept within pgssEntry. - */ -typedef struct Counters -{ - int64 calls; /* # of times executed */ - double total_time; /* total execution time in seconds */ - int64 rows; /* total # of retrieved or affected rows */ - int64 shared_blks_hit; /* # of shared buffer hits */ - int64 shared_blks_read; /* # of shared disk blocks read */ - int64 shared_blks_written; /* # of shared disk blocks written */ - int64 local_blks_hit; /* # of local buffer hits */ - int64 local_blks_read; /* # of local disk blocks read */ - int64 local_blks_written; /* # of local disk blocks written */ - int64 temp_blks_read; /* # of temp blocks read */ - int64 temp_blks_written; /* # of temp blocks written */ - double usage; /* usage factor */ -} Counters; - -/* - * Statistics per statement - * - * NB: see the file read/write code before changing field order here. - */ -typedef struct pgssEntry -{ - pgssHashKey key; /* hash key of entry - MUST BE FIRST */ - Counters counters; /* the statistics for this query */ - slock_t mutex; /* protects the counters only */ - char query[1]; /* VARIABLE LENGTH ARRAY - MUST BE LAST */ - /* Note: the allocated length of query[] is actually pgss->query_size */ -} pgssEntry; - -/* - * Global shared state - */ -typedef struct pgssSharedState -{ - LWLockId lock; /* protects hashtable search/modification */ - int query_size; /* max query length in bytes */ -} pgssSharedState; - -/*---- Local variables ----*/ - -/* Current nesting depth of ExecutorRun calls */ -static int nested_level = 0; - -/* Saved hook values in case of unload */ -static shmem_startup_hook_type prev_shmem_startup_hook = NULL; -static ExecutorStart_hook_type prev_ExecutorStart = NULL; -static ExecutorRun_hook_type prev_ExecutorRun = NULL; -static ExecutorFinish_hook_type prev_ExecutorFinish = NULL; -static ExecutorEnd_hook_type prev_ExecutorEnd = NULL; -static ProcessUtility_hook_type prev_ProcessUtility = NULL; - -/* Links to shared memory state */ -static pgssSharedState *pgss = NULL; -static HTAB *pgss_hash = NULL; - -/*---- GUC variables ----*/ - -typedef enum -{ - PGSS_TRACK_NONE, /* track no statements */ - PGSS_TRACK_TOP, /* only top level statements */ - PGSS_TRACK_ALL /* all statements, including nested ones */ -} PGSSTrackLevel; - -static const struct config_enum_entry track_options[] = -{ - {"none", PGSS_TRACK_NONE, false}, - {"top", PGSS_TRACK_TOP, false}, - {"all", PGSS_TRACK_ALL, false}, - {NULL, 0, false} -}; - -static int pgss_max; /* max # statements to track */ -static int pgss_track; /* tracking level */ -static bool pgss_track_utility; /* whether to track utility commands */ -static bool pgss_save; /* whether to save stats across shutdown */ - - -#define pgss_enabled() \ - (pgss_track == PGSS_TRACK_ALL || \ - (pgss_track == PGSS_TRACK_TOP && nested_level == 0)) - -/*---- Function declarations ----*/ - -void _PG_init(void); -void _PG_fini(void); - -Datum pg_stat_statements_reset(PG_FUNCTION_ARGS); -Datum pg_stat_statements(PG_FUNCTION_ARGS); - -PG_FUNCTION_INFO_V1(pg_stat_statements_reset); -PG_FUNCTION_INFO_V1(pg_stat_statements); - -static void pgss_shmem_startup(void); -static void pgss_shmem_shutdown(int code, Datum arg); -static void pgss_ExecutorStart(QueryDesc *queryDesc, int eflags); -static void pgss_ExecutorRun(QueryDesc *queryDesc, - ScanDirection direction, - long count); -static void pgss_ExecutorFinish(QueryDesc *queryDesc); -static void pgss_ExecutorEnd(QueryDesc *queryDesc); -static void pgss_ProcessUtility(Node *parsetree, - const char *queryString, ParamListInfo params, bool isTopLevel, - DestReceiver *dest, char *completionTag); -static uint32 pgss_hash_fn(const void *key, Size keysize); -static int pgss_match_fn(const void *key1, const void *key2, Size keysize); -static void pgss_store(const char *query, double total_time, uint64 rows, - const BufferUsage *bufusage); -static Size pgss_memsize(void); -static pgssEntry *entry_alloc(pgssHashKey *key); -static void entry_dealloc(void); -static void entry_reset(void); - - -/* - * Module load callback - */ -void -_PG_init(void) -{ - /* - * In order to create our shared memory area, we have to be loaded via - * shared_preload_libraries. If not, fall out without hooking into any of - * the main system. (We don't throw error here because it seems useful to - * allow the pg_stat_statements functions to be created even when the - * module isn't active. The functions must protect themselves against - * being called then, however.) - */ - if (!process_shared_preload_libraries_in_progress) - return; - - /* - * Define (or redefine) custom GUC variables. - */ - DefineCustomIntVariable("pg_stat_statements.max", - "Sets the maximum number of statements tracked by pg_stat_statements.", - NULL, - &pgss_max, - 1000, - 100, - INT_MAX, - PGC_POSTMASTER, - 0, - NULL, - NULL, - NULL); - - DefineCustomEnumVariable("pg_stat_statements.track", - "Selects which statements are tracked by pg_stat_statements.", - NULL, - &pgss_track, - PGSS_TRACK_TOP, - track_options, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("pg_stat_statements.track_utility", - "Selects whether utility commands are tracked by pg_stat_statements.", - NULL, - &pgss_track_utility, - true, - PGC_SUSET, - 0, - NULL, - NULL, - NULL); - - DefineCustomBoolVariable("pg_stat_statements.save", - "Save pg_stat_statements statistics across server shutdowns.", - NULL, - &pgss_save, - true, - PGC_SIGHUP, - 0, - NULL, - NULL, - NULL); - - EmitWarningsOnPlaceholders("pg_stat_statements"); - - /* - * Request additional shared resources. (These are no-ops if we're not in - * the postmaster process.) We'll allocate or attach to the shared - * resources in pgss_shmem_startup(). - */ - RequestAddinShmemSpace(pgss_memsize()); - RequestAddinLWLocks(1); - - /* - * Install hooks. - */ - prev_shmem_startup_hook = shmem_startup_hook; - shmem_startup_hook = pgss_shmem_startup; - prev_ExecutorStart = ExecutorStart_hook; - ExecutorStart_hook = pgss_ExecutorStart; - prev_ExecutorRun = ExecutorRun_hook; - ExecutorRun_hook = pgss_ExecutorRun; - prev_ExecutorFinish = ExecutorFinish_hook; - ExecutorFinish_hook = pgss_ExecutorFinish; - prev_ExecutorEnd = ExecutorEnd_hook; - ExecutorEnd_hook = pgss_ExecutorEnd; - prev_ProcessUtility = ProcessUtility_hook; - ProcessUtility_hook = pgss_ProcessUtility; -} - -/* - * Module unload callback - */ -void -_PG_fini(void) -{ - /* Uninstall hooks. */ - shmem_startup_hook = prev_shmem_startup_hook; - ExecutorStart_hook = prev_ExecutorStart; - ExecutorRun_hook = prev_ExecutorRun; - ExecutorFinish_hook = prev_ExecutorFinish; - ExecutorEnd_hook = prev_ExecutorEnd; - ProcessUtility_hook = prev_ProcessUtility; -} - -/* - * shmem_startup hook: allocate or attach to shared memory, - * then load any pre-existing statistics from file. - */ -static void -pgss_shmem_startup(void) -{ - bool found; - HASHCTL info; - FILE *file; - uint32 header; - int32 num; - int32 i; - int query_size; - int buffer_size; - char *buffer = NULL; - - if (prev_shmem_startup_hook) - prev_shmem_startup_hook(); - - /* reset in case this is a restart within the postmaster */ - pgss = NULL; - pgss_hash = NULL; - - /* - * Create or attach to the shared memory state, including hash table - */ - LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE); - - pgss = ShmemInitStruct("pg_stat_statements", - sizeof(pgssSharedState), - &found); - - if (!found) - { - /* First time through ... */ - pgss->lock = LWLockAssign(); - pgss->query_size = pgstat_track_activity_query_size; - } - - /* Be sure everyone agrees on the hash table entry size */ - query_size = pgss->query_size; - - memset(&info, 0, sizeof(info)); - info.keysize = sizeof(pgssHashKey); - info.entrysize = offsetof(pgssEntry, query) +query_size; - info.hash = pgss_hash_fn; - info.match = pgss_match_fn; - pgss_hash = ShmemInitHash("pg_stat_statements hash", - pgss_max, pgss_max, - &info, - HASH_ELEM | HASH_FUNCTION | HASH_COMPARE); - - LWLockRelease(AddinShmemInitLock); - - /* - * If we're in the postmaster (or a standalone backend...), set up a shmem - * exit hook to dump the statistics to disk. - */ - if (!IsUnderPostmaster) - on_shmem_exit(pgss_shmem_shutdown, (Datum) 0); - - /* - * Attempt to load old statistics from the dump file, if this is the first - * time through and we weren't told not to. - */ - if (found || !pgss_save) - return; - - /* - * Note: we don't bother with locks here, because there should be no other - * processes running when this code is reached. - */ - file = AllocateFile(PGSS_DUMP_FILE, PG_BINARY_R); - if (file == NULL) - { - if (errno == ENOENT) - return; /* ignore not-found error */ - goto error; - } - - buffer_size = query_size; - buffer = (char *) palloc(buffer_size); - - if (fread(&header, sizeof(uint32), 1, file) != 1 || - header != PGSS_FILE_HEADER || - fread(&num, sizeof(int32), 1, file) != 1) - goto error; - - for (i = 0; i < num; i++) - { - pgssEntry temp; - pgssEntry *entry; - - if (fread(&temp, offsetof(pgssEntry, mutex), 1, file) != 1) - goto error; - - /* Encoding is the only field we can easily sanity-check */ - if (!PG_VALID_BE_ENCODING(temp.key.encoding)) - goto error; - - /* Previous incarnation might have had a larger query_size */ - if (temp.key.query_len >= buffer_size) - { - buffer = (char *) repalloc(buffer, temp.key.query_len + 1); - buffer_size = temp.key.query_len + 1; - } - - if (fread(buffer, 1, temp.key.query_len, file) != temp.key.query_len) - goto error; - buffer[temp.key.query_len] = '\0'; - - /* Clip to available length if needed */ - if (temp.key.query_len >= query_size) - temp.key.query_len = pg_encoding_mbcliplen(temp.key.encoding, - buffer, - temp.key.query_len, - query_size - 1); - temp.key.query_ptr = buffer; - - /* make the hashtable entry (discards old entries if too many) */ - entry = entry_alloc(&temp.key); - - /* copy in the actual stats */ - entry->counters = temp.counters; - } - - pfree(buffer); - FreeFile(file); - return; - -error: - ereport(LOG, - (errcode_for_file_access(), - errmsg("could not read pg_stat_statement file \"%s\": %m", - PGSS_DUMP_FILE))); - if (buffer) - pfree(buffer); - if (file) - FreeFile(file); - /* If possible, throw away the bogus file; ignore any error */ - unlink(PGSS_DUMP_FILE); -} - -/* - * shmem_shutdown hook: Dump statistics into file. - * - * Note: we don't bother with acquiring lock, because there should be no - * other processes running when this is called. - */ -static void -pgss_shmem_shutdown(int code, Datum arg) -{ - FILE *file; - HASH_SEQ_STATUS hash_seq; - int32 num_entries; - pgssEntry *entry; - - /* Don't try to dump during a crash. */ - if (code) - return; - - /* Safety check ... shouldn't get here unless shmem is set up. */ - if (!pgss || !pgss_hash) - return; - - /* Don't dump if told not to. */ - if (!pgss_save) - return; - - file = AllocateFile(PGSS_DUMP_FILE, PG_BINARY_W); - if (file == NULL) - goto error; - - if (fwrite(&PGSS_FILE_HEADER, sizeof(uint32), 1, file) != 1) - goto error; - num_entries = hash_get_num_entries(pgss_hash); - if (fwrite(&num_entries, sizeof(int32), 1, file) != 1) - goto error; - - hash_seq_init(&hash_seq, pgss_hash); - while ((entry = hash_seq_search(&hash_seq)) != NULL) - { - int len = entry->key.query_len; - - if (fwrite(entry, offsetof(pgssEntry, mutex), 1, file) != 1 || - fwrite(entry->query, 1, len, file) != len) - goto error; - } - - if (FreeFile(file)) - { - file = NULL; - goto error; - } - - return; - -error: - ereport(LOG, - (errcode_for_file_access(), - errmsg("could not write pg_stat_statement file \"%s\": %m", - PGSS_DUMP_FILE))); - if (file) - FreeFile(file); - unlink(PGSS_DUMP_FILE); -} - -/* - * ExecutorStart hook: start up tracking if needed - */ -static void -pgss_ExecutorStart(QueryDesc *queryDesc, int eflags) -{ - if (prev_ExecutorStart) - prev_ExecutorStart(queryDesc, eflags); - else - standard_ExecutorStart(queryDesc, eflags); - - if (pgss_enabled()) - { - /* - * Set up to track total elapsed time in ExecutorRun. Make sure the - * space is allocated in the per-query context so it will go away at - * ExecutorEnd. - */ - if (queryDesc->totaltime == NULL) - { - MemoryContext oldcxt; - - oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt); - queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL); - MemoryContextSwitchTo(oldcxt); - } - } -} - -/* - * ExecutorRun hook: all we need do is track nesting depth - */ -static void -pgss_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, long count) -{ - nested_level++; - PG_TRY(); - { - if (prev_ExecutorRun) - prev_ExecutorRun(queryDesc, direction, count); - else - standard_ExecutorRun(queryDesc, direction, count); - nested_level--; - } - PG_CATCH(); - { - nested_level--; - PG_RE_THROW(); - } - PG_END_TRY(); -} - -/* - * ExecutorFinish hook: all we need do is track nesting depth - */ -static void -pgss_ExecutorFinish(QueryDesc *queryDesc) -{ - nested_level++; - PG_TRY(); - { - if (prev_ExecutorFinish) - prev_ExecutorFinish(queryDesc); - else - standard_ExecutorFinish(queryDesc); - nested_level--; - } - PG_CATCH(); - { - nested_level--; - PG_RE_THROW(); - } - PG_END_TRY(); -} - -/* - * ExecutorEnd hook: store results if needed - */ -static void -pgss_ExecutorEnd(QueryDesc *queryDesc) -{ - if (queryDesc->totaltime && pgss_enabled()) - { - /* - * Make sure stats accumulation is done. (Note: it's okay if several - * levels of hook all do this.) - */ - InstrEndLoop(queryDesc->totaltime); - - pgss_store(queryDesc->sourceText, - queryDesc->totaltime->total, - queryDesc->estate->es_processed, - &queryDesc->totaltime->bufusage); - } - - if (prev_ExecutorEnd) - prev_ExecutorEnd(queryDesc); - else - standard_ExecutorEnd(queryDesc); -} - -/* - * ProcessUtility hook - */ -static void -pgss_ProcessUtility(Node *parsetree, const char *queryString, - ParamListInfo params, bool isTopLevel, - DestReceiver *dest, char *completionTag) -{ - if (pgss_track_utility && pgss_enabled()) - { - instr_time start; - instr_time duration; - uint64 rows = 0; - BufferUsage bufusage; - - bufusage = pgBufferUsage; - INSTR_TIME_SET_CURRENT(start); - - nested_level++; - PG_TRY(); - { - if (prev_ProcessUtility) - prev_ProcessUtility(parsetree, queryString, params, - isTopLevel, dest, completionTag); - else - standard_ProcessUtility(parsetree, queryString, params, - isTopLevel, dest, completionTag); - nested_level--; - } - PG_CATCH(); - { - nested_level--; - PG_RE_THROW(); - } - PG_END_TRY(); - - INSTR_TIME_SET_CURRENT(duration); - INSTR_TIME_SUBTRACT(duration, start); - - /* parse command tag to retrieve the number of affected rows. */ - if (completionTag && - sscanf(completionTag, "COPY " UINT64_FORMAT, &rows) != 1) - rows = 0; - - /* calc differences of buffer counters. */ - bufusage.shared_blks_hit = - pgBufferUsage.shared_blks_hit - bufusage.shared_blks_hit; - bufusage.shared_blks_read = - pgBufferUsage.shared_blks_read - bufusage.shared_blks_read; - bufusage.shared_blks_written = - pgBufferUsage.shared_blks_written - bufusage.shared_blks_written; - bufusage.local_blks_hit = - pgBufferUsage.local_blks_hit - bufusage.local_blks_hit; - bufusage.local_blks_read = - pgBufferUsage.local_blks_read - bufusage.local_blks_read; - bufusage.local_blks_written = - pgBufferUsage.local_blks_written - bufusage.local_blks_written; - bufusage.temp_blks_read = - pgBufferUsage.temp_blks_read - bufusage.temp_blks_read; - bufusage.temp_blks_written = - pgBufferUsage.temp_blks_written - bufusage.temp_blks_written; - - pgss_store(queryString, INSTR_TIME_GET_DOUBLE(duration), rows, - &bufusage); - } - else - { - if (prev_ProcessUtility) - prev_ProcessUtility(parsetree, queryString, params, - isTopLevel, dest, completionTag); - else - standard_ProcessUtility(parsetree, queryString, params, - isTopLevel, dest, completionTag); - } -} - -/* - * Calculate hash value for a key - */ -static uint32 -pgss_hash_fn(const void *key, Size keysize) -{ - const pgssHashKey *k = (const pgssHashKey *) key; - - /* we don't bother to include encoding in the hash */ - return hash_uint32((uint32) k->userid) ^ - hash_uint32((uint32) k->dbid) ^ - DatumGetUInt32(hash_any((const unsigned char *) k->query_ptr, - k->query_len)); -} - -/* - * Compare two keys - zero means match - */ -static int -pgss_match_fn(const void *key1, const void *key2, Size keysize) -{ - const pgssHashKey *k1 = (const pgssHashKey *) key1; - const pgssHashKey *k2 = (const pgssHashKey *) key2; - - if (k1->userid == k2->userid && - k1->dbid == k2->dbid && - k1->encoding == k2->encoding && - k1->query_len == k2->query_len && - memcmp(k1->query_ptr, k2->query_ptr, k1->query_len) == 0) - return 0; - else - return 1; -} - -/* - * Store some statistics for a statement. - */ -static void -pgss_store(const char *query, double total_time, uint64 rows, - const BufferUsage *bufusage) -{ - pgssHashKey key; - double usage; - pgssEntry *entry; - - Assert(query != NULL); - - /* Safety check... */ - if (!pgss || !pgss_hash) - return; - - /* Set up key for hashtable search */ - key.userid = GetUserId(); - key.dbid = MyDatabaseId; - key.encoding = GetDatabaseEncoding(); - key.query_len = strlen(query); - if (key.query_len >= pgss->query_size) - key.query_len = pg_encoding_mbcliplen(key.encoding, - query, - key.query_len, - pgss->query_size - 1); - key.query_ptr = query; - - usage = USAGE_EXEC(duration); - - /* Lookup the hash table entry with shared lock. */ - LWLockAcquire(pgss->lock, LW_SHARED); - - entry = (pgssEntry *) hash_search(pgss_hash, &key, HASH_FIND, NULL); - if (!entry) - { - /* Must acquire exclusive lock to add a new entry. */ - LWLockRelease(pgss->lock); - LWLockAcquire(pgss->lock, LW_EXCLUSIVE); - entry = entry_alloc(&key); - } - - /* Grab the spinlock while updating the counters. */ - { - volatile pgssEntry *e = (volatile pgssEntry *) entry; - - SpinLockAcquire(&e->mutex); - e->counters.calls += 1; - e->counters.total_time += total_time; - e->counters.rows += rows; - e->counters.shared_blks_hit += bufusage->shared_blks_hit; - e->counters.shared_blks_read += bufusage->shared_blks_read; - e->counters.shared_blks_written += bufusage->shared_blks_written; - e->counters.local_blks_hit += bufusage->local_blks_hit; - e->counters.local_blks_read += bufusage->local_blks_read; - e->counters.local_blks_written += bufusage->local_blks_written; - e->counters.temp_blks_read += bufusage->temp_blks_read; - e->counters.temp_blks_written += bufusage->temp_blks_written; - e->counters.usage += usage; - SpinLockRelease(&e->mutex); - } - - LWLockRelease(pgss->lock); -} - -/* - * Reset all statement statistics. - */ -Datum -pg_stat_statements_reset(PG_FUNCTION_ARGS) -{ - if (!pgss || !pgss_hash) - ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("pg_stat_statements must be loaded via shared_preload_libraries"))); - entry_reset(); - PG_RETURN_VOID(); -} - -#define PG_STAT_STATEMENTS_COLS 14 - -/* - * Retrieve statement statistics. - */ -Datum -pg_stat_statements(PG_FUNCTION_ARGS) -{ - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - MemoryContext per_query_ctx; - MemoryContext oldcontext; - Oid userid = GetUserId(); - bool is_superuser = superuser(); - HASH_SEQ_STATUS hash_seq; - pgssEntry *entry; - - if (!pgss || !pgss_hash) - ereport(ERROR, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("pg_stat_statements must be loaded via shared_preload_libraries"))); - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("materialize mode required, but it is not " \ - "allowed in this context"))); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - per_query_ctx = rsinfo->econtext->ecxt_per_query_memory; - oldcontext = MemoryContextSwitchTo(per_query_ctx); - - tupstore = tuplestore_begin_heap(true, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - LWLockAcquire(pgss->lock, LW_SHARED); - - hash_seq_init(&hash_seq, pgss_hash); - while ((entry = hash_seq_search(&hash_seq)) != NULL) - { - Datum values[PG_STAT_STATEMENTS_COLS]; - bool nulls[PG_STAT_STATEMENTS_COLS]; - int i = 0; - Counters tmp; - - memset(values, 0, sizeof(values)); - memset(nulls, 0, sizeof(nulls)); - - values[i++] = ObjectIdGetDatum(entry->key.userid); - values[i++] = ObjectIdGetDatum(entry->key.dbid); - - if (is_superuser || entry->key.userid == userid) - { - char *qstr; - - qstr = (char *) - pg_do_encoding_conversion((unsigned char *) entry->query, - entry->key.query_len, - entry->key.encoding, - GetDatabaseEncoding()); - values[i++] = CStringGetTextDatum(qstr); - if (qstr != entry->query) - pfree(qstr); - } - else - values[i++] = CStringGetTextDatum(""); - - /* copy counters to a local variable to keep locking time short */ - { - volatile pgssEntry *e = (volatile pgssEntry *) entry; - - SpinLockAcquire(&e->mutex); - tmp = e->counters; - SpinLockRelease(&e->mutex); - } - - values[i++] = Int64GetDatumFast(tmp.calls); - values[i++] = Float8GetDatumFast(tmp.total_time); - values[i++] = Int64GetDatumFast(tmp.rows); - values[i++] = Int64GetDatumFast(tmp.shared_blks_hit); - values[i++] = Int64GetDatumFast(tmp.shared_blks_read); - values[i++] = Int64GetDatumFast(tmp.shared_blks_written); - values[i++] = Int64GetDatumFast(tmp.local_blks_hit); - values[i++] = Int64GetDatumFast(tmp.local_blks_read); - values[i++] = Int64GetDatumFast(tmp.local_blks_written); - values[i++] = Int64GetDatumFast(tmp.temp_blks_read); - values[i++] = Int64GetDatumFast(tmp.temp_blks_written); - - Assert(i == PG_STAT_STATEMENTS_COLS); - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - LWLockRelease(pgss->lock); - - /* clean up and return the tuplestore */ - tuplestore_donestoring(tupstore); - - return (Datum) 0; -} - -/* - * Estimate shared memory space needed. - */ -static Size -pgss_memsize(void) -{ - Size size; - Size entrysize; - - size = MAXALIGN(sizeof(pgssSharedState)); - entrysize = offsetof(pgssEntry, query) +pgstat_track_activity_query_size; - size = add_size(size, hash_estimate_size(pgss_max, entrysize)); - - return size; -} - -/* - * Allocate a new hashtable entry. - * caller must hold an exclusive lock on pgss->lock - * - * Note: despite needing exclusive lock, it's not an error for the target - * entry to already exist. This is because pgss_store releases and - * reacquires lock after failing to find a match; so someone else could - * have made the entry while we waited to get exclusive lock. - */ -static pgssEntry * -entry_alloc(pgssHashKey *key) -{ - pgssEntry *entry; - bool found; - - /* Caller must have clipped query properly */ - Assert(key->query_len < pgss->query_size); - - /* Make space if needed */ - while (hash_get_num_entries(pgss_hash) >= pgss_max) - entry_dealloc(); - - /* Find or create an entry with desired hash code */ - entry = (pgssEntry *) hash_search(pgss_hash, key, HASH_ENTER, &found); - - if (!found) - { - /* New entry, initialize it */ - - /* dynahash tried to copy the key for us, but must fix query_ptr */ - entry->key.query_ptr = entry->query; - /* reset the statistics */ - memset(&entry->counters, 0, sizeof(Counters)); - entry->counters.usage = USAGE_INIT; - /* re-initialize the mutex each time ... we assume no one using it */ - SpinLockInit(&entry->mutex); - /* ... and don't forget the query text */ - memcpy(entry->query, key->query_ptr, key->query_len); - entry->query[key->query_len] = '\0'; - } - - return entry; -} - -/* - * qsort comparator for sorting into increasing usage order - */ -static int -entry_cmp(const void *lhs, const void *rhs) -{ - double l_usage = (*(const pgssEntry **) lhs)->counters.usage; - double r_usage = (*(const pgssEntry **) rhs)->counters.usage; - - if (l_usage < r_usage) - return -1; - else if (l_usage > r_usage) - return +1; - else - return 0; -} - -/* - * Deallocate least used entries. - * Caller must hold an exclusive lock on pgss->lock. - */ -static void -entry_dealloc(void) -{ - HASH_SEQ_STATUS hash_seq; - pgssEntry **entries; - pgssEntry *entry; - int nvictims; - int i; - - /* Sort entries by usage and deallocate USAGE_DEALLOC_PERCENT of them. */ - - entries = palloc(hash_get_num_entries(pgss_hash) * sizeof(pgssEntry *)); - - i = 0; - hash_seq_init(&hash_seq, pgss_hash); - while ((entry = hash_seq_search(&hash_seq)) != NULL) - { - entries[i++] = entry; - entry->counters.usage *= USAGE_DECREASE_FACTOR; - } - - qsort(entries, i, sizeof(pgssEntry *), entry_cmp); - nvictims = Max(10, i * USAGE_DEALLOC_PERCENT / 100); - nvictims = Min(nvictims, i); - - for (i = 0; i < nvictims; i++) - { - hash_search(pgss_hash, &entries[i]->key, HASH_REMOVE, NULL); - } - - pfree(entries); -} - -/* - * Release all entries. - */ -static void -entry_reset(void) -{ - HASH_SEQ_STATUS hash_seq; - pgssEntry *entry; - - LWLockAcquire(pgss->lock, LW_EXCLUSIVE); - - hash_seq_init(&hash_seq, pgss_hash); - while ((entry = hash_seq_search(&hash_seq)) != NULL) - { - hash_search(pgss_hash, &entry->key, HASH_REMOVE, NULL); - } - - LWLockRelease(pgss->lock); -} diff --git a/contrib/pg_stat_statements/pg_stat_statements.control b/contrib/pg_stat_statements/pg_stat_statements.control deleted file mode 100644 index 6f9a947..0000000 --- a/contrib/pg_stat_statements/pg_stat_statements.control +++ /dev/null @@ -1,5 +0,0 @@ -# pg_stat_statements extension -comment = 'track execution statistics of all SQL statements executed' -default_version = '1.0' -module_pathname = '$libdir/pg_stat_statements' -relocatable = true diff --git a/contrib/pgrowlocks/Makefile b/contrib/pgrowlocks/Makefile deleted file mode 100644 index f56389b..0000000 --- a/contrib/pgrowlocks/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pgrowlocks/Makefile - -MODULE_big = pgrowlocks -OBJS = pgrowlocks.o - -EXTENSION = pgrowlocks -DATA = pgrowlocks--1.0.sql pgrowlocks--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pgrowlocks -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pgrowlocks/pgrowlocks--1.0.sql b/contrib/pgrowlocks/pgrowlocks--1.0.sql deleted file mode 100644 index 0b60fdc..0000000 --- a/contrib/pgrowlocks/pgrowlocks--1.0.sql +++ /dev/null @@ -1,12 +0,0 @@ -/* contrib/pgrowlocks/pgrowlocks--1.0.sql */ - -CREATE FUNCTION pgrowlocks(IN relname text, - OUT locked_row TID, -- row TID - OUT lock_type TEXT, -- lock type - OUT locker XID, -- locking XID - OUT multi bool, -- multi XID? - OUT xids xid[], -- multi XIDs - OUT pids INTEGER[]) -- locker's process id -RETURNS SETOF record -AS 'MODULE_PATHNAME', 'pgrowlocks' -LANGUAGE C STRICT; diff --git a/contrib/pgrowlocks/pgrowlocks--unpackaged--1.0.sql b/contrib/pgrowlocks/pgrowlocks--unpackaged--1.0.sql deleted file mode 100644 index 2d9d1ee..0000000 --- a/contrib/pgrowlocks/pgrowlocks--unpackaged--1.0.sql +++ /dev/null @@ -1,3 +0,0 @@ -/* contrib/pgrowlocks/pgrowlocks--unpackaged--1.0.sql */ - -ALTER EXTENSION pgrowlocks ADD function pgrowlocks(text); diff --git a/contrib/pgrowlocks/pgrowlocks.c b/contrib/pgrowlocks/pgrowlocks.c deleted file mode 100644 index 302bb5c..0000000 --- a/contrib/pgrowlocks/pgrowlocks.c +++ /dev/null @@ -1,220 +0,0 @@ -/* - * contrib/pgrowlocks/pgrowlocks.c - * - * Copyright (c) 2005-2006 Tatsuo Ishii - * - * Permission to use, copy, modify, and distribute this software and - * its documentation for any purpose, without fee, and without a - * written agreement is hereby granted, provided that the above - * copyright notice and this paragraph and the following two - * paragraphs appear in all copies. - * - * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, - * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING - * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS - * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - * - * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS - * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, - * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. - */ - -#include "postgres.h" - -#include "access/heapam.h" -#include "access/multixact.h" -#include "access/relscan.h" -#include "access/xact.h" -#include "catalog/namespace.h" -#include "funcapi.h" -#include "miscadmin.h" -#include "storage/bufmgr.h" -#include "storage/procarray.h" -#include "utils/acl.h" -#include "utils/builtins.h" -#include "utils/tqual.h" - - -PG_MODULE_MAGIC; - -PG_FUNCTION_INFO_V1(pgrowlocks); - -extern Datum pgrowlocks(PG_FUNCTION_ARGS); - -/* ---------- - * pgrowlocks: - * returns tids of rows being locked - * ---------- - */ - -#define NCHARS 32 - -typedef struct -{ - Relation rel; - HeapScanDesc scan; - int ncolumns; -} MyData; - -Datum -pgrowlocks(PG_FUNCTION_ARGS) -{ - FuncCallContext *funcctx; - HeapScanDesc scan; - HeapTuple tuple; - TupleDesc tupdesc; - AttInMetadata *attinmeta; - Datum result; - MyData *mydata; - Relation rel; - - if (SRF_IS_FIRSTCALL()) - { - text *relname; - RangeVar *relrv; - MemoryContext oldcontext; - AclResult aclresult; - - funcctx = SRF_FIRSTCALL_INIT(); - oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx); - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - attinmeta = TupleDescGetAttInMetadata(tupdesc); - funcctx->attinmeta = attinmeta; - - relname = PG_GETARG_TEXT_P(0); - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = heap_openrv(relrv, AccessShareLock); - - /* check permissions: must have SELECT on table */ - aclresult = pg_class_aclcheck(RelationGetRelid(rel), GetUserId(), - ACL_SELECT); - if (aclresult != ACLCHECK_OK) - aclcheck_error(aclresult, ACL_KIND_CLASS, - RelationGetRelationName(rel)); - - scan = heap_beginscan(rel, SnapshotNow, 0, NULL); - mydata = palloc(sizeof(*mydata)); - mydata->rel = rel; - mydata->scan = scan; - mydata->ncolumns = tupdesc->natts; - funcctx->user_fctx = mydata; - - MemoryContextSwitchTo(oldcontext); - } - - funcctx = SRF_PERCALL_SETUP(); - attinmeta = funcctx->attinmeta; - mydata = (MyData *) funcctx->user_fctx; - scan = mydata->scan; - - /* scan the relation */ - while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) - { - /* must hold a buffer lock to call HeapTupleSatisfiesUpdate */ - LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE); - - if (HeapTupleSatisfiesUpdate(tuple->t_data, - GetCurrentCommandId(false), - scan->rs_cbuf) == HeapTupleBeingUpdated) - { - - char **values; - int i; - - values = (char **) palloc(mydata->ncolumns * sizeof(char *)); - - i = 0; - values[i++] = (char *) DirectFunctionCall1(tidout, PointerGetDatum(&tuple->t_self)); - - if (tuple->t_data->t_infomask & HEAP_XMAX_SHARED_LOCK) - values[i++] = pstrdup("Shared"); - else - values[i++] = pstrdup("Exclusive"); - values[i] = palloc(NCHARS * sizeof(char)); - snprintf(values[i++], NCHARS, "%d", HeapTupleHeaderGetXmax(tuple->t_data)); - if (tuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI) - { - TransactionId *xids; - int nxids; - int j; - int isValidXid = 0; /* any valid xid ever exists? */ - - values[i++] = pstrdup("true"); - nxids = GetMultiXactIdMembers(HeapTupleHeaderGetXmax(tuple->t_data), &xids); - if (nxids == -1) - { - elog(ERROR, "GetMultiXactIdMembers returns error"); - } - - values[i] = palloc(NCHARS * nxids); - values[i + 1] = palloc(NCHARS * nxids); - strcpy(values[i], "{"); - strcpy(values[i + 1], "{"); - - for (j = 0; j < nxids; j++) - { - char buf[NCHARS]; - - if (TransactionIdIsInProgress(xids[j])) - { - if (isValidXid) - { - strcat(values[i], ","); - strcat(values[i + 1], ","); - } - snprintf(buf, NCHARS, "%d", xids[j]); - strcat(values[i], buf); - snprintf(buf, NCHARS, "%d", BackendXidGetPid(xids[j])); - strcat(values[i + 1], buf); - - isValidXid = 1; - } - } - - strcat(values[i], "}"); - strcat(values[i + 1], "}"); - i++; - } - else - { - values[i++] = pstrdup("false"); - values[i] = palloc(NCHARS * sizeof(char)); - snprintf(values[i++], NCHARS, "{%d}", HeapTupleHeaderGetXmax(tuple->t_data)); - - values[i] = palloc(NCHARS * sizeof(char)); - snprintf(values[i++], NCHARS, "{%d}", BackendXidGetPid(HeapTupleHeaderGetXmax(tuple->t_data))); - } - - LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); - - /* build a tuple */ - tuple = BuildTupleFromCStrings(attinmeta, values); - - /* make the tuple into a datum */ - result = HeapTupleGetDatum(tuple); - - /* Clean up */ - for (i = 0; i < mydata->ncolumns; i++) - pfree(values[i]); - pfree(values); - - SRF_RETURN_NEXT(funcctx, result); - } - else - { - LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); - } - } - - heap_endscan(scan); - heap_close(mydata->rel, AccessShareLock); - - SRF_RETURN_DONE(funcctx); -} diff --git a/contrib/pgrowlocks/pgrowlocks.control b/contrib/pgrowlocks/pgrowlocks.control deleted file mode 100644 index a6ba164..0000000 --- a/contrib/pgrowlocks/pgrowlocks.control +++ /dev/null @@ -1,5 +0,0 @@ -# pgrowlocks extension -comment = 'show row-level locking information' -default_version = '1.0' -module_pathname = '$libdir/pgrowlocks' -relocatable = true diff --git a/contrib/pgstattuple/Makefile b/contrib/pgstattuple/Makefile deleted file mode 100644 index 13b8709..0000000 --- a/contrib/pgstattuple/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# contrib/pgstattuple/Makefile - -MODULE_big = pgstattuple -OBJS = pgstattuple.o pgstatindex.o - -EXTENSION = pgstattuple -DATA = pgstattuple--1.0.sql pgstattuple--unpackaged--1.0.sql - -ifdef USE_PGXS -PG_CONFIG = pg_config -PGXS := $(shell $(PG_CONFIG) --pgxs) -include $(PGXS) -else -subdir = contrib/pgstattuple -top_builddir = ../.. -include $(top_builddir)/src/Makefile.global -include $(top_srcdir)/contrib/contrib-global.mk -endif diff --git a/contrib/pgstattuple/pgstatindex.c b/contrib/pgstattuple/pgstatindex.c deleted file mode 100644 index fd2cc92..0000000 --- a/contrib/pgstattuple/pgstatindex.c +++ /dev/null @@ -1,282 +0,0 @@ -/* - * contrib/pgstattuple/pgstatindex.c - * - * - * pgstatindex - * - * Copyright (c) 2006 Satoshi Nagayasu - * - * Permission to use, copy, modify, and distribute this software and - * its documentation for any purpose, without fee, and without a - * written agreement is hereby granted, provided that the above - * copyright notice and this paragraph and the following two - * paragraphs appear in all copies. - * - * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, - * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING - * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS - * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - * - * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS - * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, - * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. - */ - -#include "postgres.h" - -#include "access/heapam.h" -#include "access/nbtree.h" -#include "catalog/namespace.h" -#include "funcapi.h" -#include "miscadmin.h" -#include "storage/bufmgr.h" -#include "utils/builtins.h" - - -extern Datum pgstatindex(PG_FUNCTION_ARGS); -extern Datum pg_relpages(PG_FUNCTION_ARGS); - -PG_FUNCTION_INFO_V1(pgstatindex); -PG_FUNCTION_INFO_V1(pg_relpages); - -#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX) -#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID) - -#define CHECK_PAGE_OFFSET_RANGE(pg, offnum) { \ - if ( !(FirstOffsetNumber <= (offnum) && \ - (offnum) <= PageGetMaxOffsetNumber(pg)) ) \ - elog(ERROR, "page offset number out of range"); } - -/* note: BlockNumber is unsigned, hence can't be negative */ -#define CHECK_RELATION_BLOCK_RANGE(rel, blkno) { \ - if ( RelationGetNumberOfBlocks(rel) <= (BlockNumber) (blkno) ) \ - elog(ERROR, "block number out of range"); } - -/* ------------------------------------------------ - * A structure for a whole btree index statistics - * used by pgstatindex(). - * ------------------------------------------------ - */ -typedef struct BTIndexStat -{ - uint32 version; - uint32 level; - BlockNumber root_blkno; - - uint64 root_pages; - uint64 internal_pages; - uint64 leaf_pages; - uint64 empty_pages; - uint64 deleted_pages; - - uint64 max_avail; - uint64 free_space; - - uint64 fragments; -} BTIndexStat; - -/* ------------------------------------------------------ - * pgstatindex() - * - * Usage: SELECT * FROM pgstatindex('t1_pkey'); - * ------------------------------------------------------ - */ -Datum -pgstatindex(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - Relation rel; - RangeVar *relrv; - Datum result; - BlockNumber nblocks; - BlockNumber blkno; - BTIndexStat indexStat; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pgstattuple functions")))); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - if (!IS_INDEX(rel) || !IS_BTREE(rel)) - elog(ERROR, "relation \"%s\" is not a btree index", - RelationGetRelationName(rel)); - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the owning - * session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - /* - * Read metapage - */ - { - Buffer buffer = ReadBuffer(rel, 0); - Page page = BufferGetPage(buffer); - BTMetaPageData *metad = BTPageGetMeta(page); - - indexStat.version = metad->btm_version; - indexStat.level = metad->btm_level; - indexStat.root_blkno = metad->btm_root; - - ReleaseBuffer(buffer); - } - - /* -- init counters -- */ - indexStat.root_pages = 0; - indexStat.internal_pages = 0; - indexStat.leaf_pages = 0; - indexStat.empty_pages = 0; - indexStat.deleted_pages = 0; - - indexStat.max_avail = 0; - indexStat.free_space = 0; - - indexStat.fragments = 0; - - /* - * Scan all blocks except the metapage - */ - nblocks = RelationGetNumberOfBlocks(rel); - - for (blkno = 1; blkno < nblocks; blkno++) - { - Buffer buffer; - Page page; - BTPageOpaque opaque; - - /* Read and lock buffer */ - buffer = ReadBuffer(rel, blkno); - LockBuffer(buffer, BUFFER_LOCK_SHARE); - - page = BufferGetPage(buffer); - opaque = (BTPageOpaque) PageGetSpecialPointer(page); - - /* Determine page type, and update totals */ - - if (P_ISLEAF(opaque)) - { - int max_avail; - - max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData); - indexStat.max_avail += max_avail; - indexStat.free_space += PageGetFreeSpace(page); - - indexStat.leaf_pages++; - - /* - * If the next leaf is on an earlier block, it means a - * fragmentation. - */ - if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno) - indexStat.fragments++; - } - else if (P_ISDELETED(opaque)) - indexStat.deleted_pages++; - else if (P_IGNORE(opaque)) - indexStat.empty_pages++; - else if (P_ISROOT(opaque)) - indexStat.root_pages++; - else - indexStat.internal_pages++; - - /* Unlock and release buffer */ - LockBuffer(buffer, BUFFER_LOCK_UNLOCK); - ReleaseBuffer(buffer); - } - - relation_close(rel, AccessShareLock); - - /*---------------------------- - * Build a result tuple - *---------------------------- - */ - { - TupleDesc tupleDesc; - int j; - char *values[10]; - HeapTuple tuple; - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - j = 0; - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", indexStat.version); - values[j] = palloc(32); - snprintf(values[j++], 32, "%d", indexStat.level); - values[j] = palloc(32); - snprintf(values[j++], 32, INT64_FORMAT, - (indexStat.root_pages + - indexStat.leaf_pages + - indexStat.internal_pages + - indexStat.deleted_pages + - indexStat.empty_pages) * BLCKSZ); - values[j] = palloc(32); - snprintf(values[j++], 32, "%u", indexStat.root_blkno); - values[j] = palloc(32); - snprintf(values[j++], 32, INT64_FORMAT, indexStat.internal_pages); - values[j] = palloc(32); - snprintf(values[j++], 32, INT64_FORMAT, indexStat.leaf_pages); - values[j] = palloc(32); - snprintf(values[j++], 32, INT64_FORMAT, indexStat.empty_pages); - values[j] = palloc(32); - snprintf(values[j++], 32, INT64_FORMAT, indexStat.deleted_pages); - values[j] = palloc(32); - snprintf(values[j++], 32, "%.2f", 100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0); - values[j] = palloc(32); - snprintf(values[j++], 32, "%.2f", (double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0); - - tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), - values); - - result = HeapTupleGetDatum(tuple); - } - - PG_RETURN_DATUM(result); -} - -/* -------------------------------------------------------- - * pg_relpages() - * - * Get the number of pages of the table/index. - * - * Usage: SELECT pg_relpages('t1'); - * SELECT pg_relpages('t1_pkey'); - * -------------------------------------------------------- - */ -Datum -pg_relpages(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - int64 relpages; - Relation rel; - RangeVar *relrv; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pgstattuple functions")))); - - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - /* note: this will work OK on non-local temp tables */ - - relpages = RelationGetNumberOfBlocks(rel); - - relation_close(rel, AccessShareLock); - - PG_RETURN_INT64(relpages); -} diff --git a/contrib/pgstattuple/pgstattuple--1.0.sql b/contrib/pgstattuple/pgstattuple--1.0.sql deleted file mode 100644 index 83445ec..0000000 --- a/contrib/pgstattuple/pgstattuple--1.0.sql +++ /dev/null @@ -1,46 +0,0 @@ -/* contrib/pgstattuple/pgstattuple--1.0.sql */ - -CREATE FUNCTION pgstattuple(IN relname text, - OUT table_len BIGINT, -- physical table length in bytes - OUT tuple_count BIGINT, -- number of live tuples - OUT tuple_len BIGINT, -- total tuples length in bytes - OUT tuple_percent FLOAT8, -- live tuples in % - OUT dead_tuple_count BIGINT, -- number of dead tuples - OUT dead_tuple_len BIGINT, -- total dead tuples length in bytes - OUT dead_tuple_percent FLOAT8, -- dead tuples in % - OUT free_space BIGINT, -- free space in bytes - OUT free_percent FLOAT8) -- free space in % -AS 'MODULE_PATHNAME', 'pgstattuple' -LANGUAGE C STRICT; - -CREATE FUNCTION pgstattuple(IN reloid oid, - OUT table_len BIGINT, -- physical table length in bytes - OUT tuple_count BIGINT, -- number of live tuples - OUT tuple_len BIGINT, -- total tuples length in bytes - OUT tuple_percent FLOAT8, -- live tuples in % - OUT dead_tuple_count BIGINT, -- number of dead tuples - OUT dead_tuple_len BIGINT, -- total dead tuples length in bytes - OUT dead_tuple_percent FLOAT8, -- dead tuples in % - OUT free_space BIGINT, -- free space in bytes - OUT free_percent FLOAT8) -- free space in % -AS 'MODULE_PATHNAME', 'pgstattuplebyid' -LANGUAGE C STRICT; - -CREATE FUNCTION pgstatindex(IN relname text, - OUT version INT, - OUT tree_level INT, - OUT index_size BIGINT, - OUT root_block_no BIGINT, - OUT internal_pages BIGINT, - OUT leaf_pages BIGINT, - OUT empty_pages BIGINT, - OUT deleted_pages BIGINT, - OUT avg_leaf_density FLOAT8, - OUT leaf_fragmentation FLOAT8) -AS 'MODULE_PATHNAME', 'pgstatindex' -LANGUAGE C STRICT; - -CREATE FUNCTION pg_relpages(IN relname text) -RETURNS BIGINT -AS 'MODULE_PATHNAME', 'pg_relpages' -LANGUAGE C STRICT; diff --git a/contrib/pgstattuple/pgstattuple--unpackaged--1.0.sql b/contrib/pgstattuple/pgstattuple--unpackaged--1.0.sql deleted file mode 100644 index 3cfb8db..0000000 --- a/contrib/pgstattuple/pgstattuple--unpackaged--1.0.sql +++ /dev/null @@ -1,6 +0,0 @@ -/* contrib/pgstattuple/pgstattuple--unpackaged--1.0.sql */ - -ALTER EXTENSION pgstattuple ADD function pgstattuple(text); -ALTER EXTENSION pgstattuple ADD function pgstattuple(oid); -ALTER EXTENSION pgstattuple ADD function pgstatindex(text); -ALTER EXTENSION pgstattuple ADD function pg_relpages(text); diff --git a/contrib/pgstattuple/pgstattuple.c b/contrib/pgstattuple/pgstattuple.c deleted file mode 100644 index e5ddd87..0000000 --- a/contrib/pgstattuple/pgstattuple.c +++ /dev/null @@ -1,518 +0,0 @@ -/* - * contrib/pgstattuple/pgstattuple.c - * - * Copyright (c) 2001,2002 Tatsuo Ishii - * - * Permission to use, copy, modify, and distribute this software and - * its documentation for any purpose, without fee, and without a - * written agreement is hereby granted, provided that the above - * copyright notice and this paragraph and the following two - * paragraphs appear in all copies. - * - * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, - * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING - * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS - * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - * - * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS - * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, - * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. - */ - -#include "postgres.h" - -#include "access/gist_private.h" -#include "access/hash.h" -#include "access/nbtree.h" -#include "access/relscan.h" -#include "catalog/namespace.h" -#include "funcapi.h" -#include "miscadmin.h" -#include "storage/bufmgr.h" -#include "storage/lmgr.h" -#include "utils/builtins.h" -#include "utils/tqual.h" - - -PG_MODULE_MAGIC; - -PG_FUNCTION_INFO_V1(pgstattuple); -PG_FUNCTION_INFO_V1(pgstattuplebyid); - -extern Datum pgstattuple(PG_FUNCTION_ARGS); -extern Datum pgstattuplebyid(PG_FUNCTION_ARGS); - -/* - * struct pgstattuple_type - * - * tuple_percent, dead_tuple_percent and free_percent are computable, - * so not defined here. - */ -typedef struct pgstattuple_type -{ - uint64 table_len; - uint64 tuple_count; - uint64 tuple_len; - uint64 dead_tuple_count; - uint64 dead_tuple_len; - uint64 free_space; /* free/reusable space in bytes */ -} pgstattuple_type; - -typedef void (*pgstat_page) (pgstattuple_type *, Relation, BlockNumber); - -static Datum build_pgstattuple_type(pgstattuple_type *stat, - FunctionCallInfo fcinfo); -static Datum pgstat_relation(Relation rel, FunctionCallInfo fcinfo); -static Datum pgstat_heap(Relation rel, FunctionCallInfo fcinfo); -static void pgstat_btree_page(pgstattuple_type *stat, - Relation rel, BlockNumber blkno); -static void pgstat_hash_page(pgstattuple_type *stat, - Relation rel, BlockNumber blkno); -static void pgstat_gist_page(pgstattuple_type *stat, - Relation rel, BlockNumber blkno); -static Datum pgstat_index(Relation rel, BlockNumber start, - pgstat_page pagefn, FunctionCallInfo fcinfo); -static void pgstat_index_page(pgstattuple_type *stat, Page page, - OffsetNumber minoff, OffsetNumber maxoff); - -/* - * build_pgstattuple_type -- build a pgstattuple_type tuple - */ -static Datum -build_pgstattuple_type(pgstattuple_type *stat, FunctionCallInfo fcinfo) -{ -#define NCOLUMNS 9 -#define NCHARS 32 - - HeapTuple tuple; - char *values[NCOLUMNS]; - char values_buf[NCOLUMNS][NCHARS]; - int i; - double tuple_percent; - double dead_tuple_percent; - double free_percent; /* free/reusable space in % */ - TupleDesc tupdesc; - AttInMetadata *attinmeta; - - /* Build a tuple descriptor for our result type */ - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); - - /* - * Generate attribute metadata needed later to produce tuples from raw C - * strings - */ - attinmeta = TupleDescGetAttInMetadata(tupdesc); - - if (stat->table_len == 0) - { - tuple_percent = 0.0; - dead_tuple_percent = 0.0; - free_percent = 0.0; - } - else - { - tuple_percent = 100.0 * stat->tuple_len / stat->table_len; - dead_tuple_percent = 100.0 * stat->dead_tuple_len / stat->table_len; - free_percent = 100.0 * stat->free_space / stat->table_len; - } - - /* - * Prepare a values array for constructing the tuple. This should be an - * array of C strings which will be processed later by the appropriate - * "in" functions. - */ - for (i = 0; i < NCOLUMNS; i++) - values[i] = values_buf[i]; - i = 0; - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->table_len); - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->tuple_count); - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->tuple_len); - snprintf(values[i++], NCHARS, "%.2f", tuple_percent); - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->dead_tuple_count); - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->dead_tuple_len); - snprintf(values[i++], NCHARS, "%.2f", dead_tuple_percent); - snprintf(values[i++], NCHARS, INT64_FORMAT, stat->free_space); - snprintf(values[i++], NCHARS, "%.2f", free_percent); - - /* build a tuple */ - tuple = BuildTupleFromCStrings(attinmeta, values); - - /* make the tuple into a datum */ - return HeapTupleGetDatum(tuple); -} - -/* ---------- - * pgstattuple: - * returns live/dead tuples info - * - * C FUNCTION definition - * pgstattuple(text) returns pgstattuple_type - * see pgstattuple.sql for pgstattuple_type - * ---------- - */ - -Datum -pgstattuple(PG_FUNCTION_ARGS) -{ - text *relname = PG_GETARG_TEXT_P(0); - RangeVar *relrv; - Relation rel; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pgstattuple functions")))); - - /* open relation */ - relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); - rel = relation_openrv(relrv, AccessShareLock); - - PG_RETURN_DATUM(pgstat_relation(rel, fcinfo)); -} - -Datum -pgstattuplebyid(PG_FUNCTION_ARGS) -{ - Oid relid = PG_GETARG_OID(0); - Relation rel; - - if (!superuser()) - ereport(ERROR, - (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), - (errmsg("must be superuser to use pgstattuple functions")))); - - /* open relation */ - rel = relation_open(relid, AccessShareLock); - - PG_RETURN_DATUM(pgstat_relation(rel, fcinfo)); -} - -/* - * pgstat_relation - */ -static Datum -pgstat_relation(Relation rel, FunctionCallInfo fcinfo) -{ - const char *err; - - /* - * Reject attempts to read non-local temporary relations; we would be - * likely to get wrong data since we have no visibility into the owning - * session's local buffers. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot access temporary tables of other sessions"))); - - switch (rel->rd_rel->relkind) - { - case RELKIND_RELATION: - case RELKIND_TOASTVALUE: - case RELKIND_UNCATALOGED: - case RELKIND_SEQUENCE: - return pgstat_heap(rel, fcinfo); - case RELKIND_INDEX: - switch (rel->rd_rel->relam) - { - case BTREE_AM_OID: - return pgstat_index(rel, BTREE_METAPAGE + 1, - pgstat_btree_page, fcinfo); - case HASH_AM_OID: - return pgstat_index(rel, HASH_METAPAGE + 1, - pgstat_hash_page, fcinfo); - case GIST_AM_OID: - return pgstat_index(rel, GIST_ROOT_BLKNO + 1, - pgstat_gist_page, fcinfo); - case GIN_AM_OID: - err = "gin index"; - break; - default: - err = "unknown index"; - break; - } - break; - case RELKIND_VIEW: - err = "view"; - break; - case RELKIND_COMPOSITE_TYPE: - err = "composite type"; - break; - case RELKIND_FOREIGN_TABLE: - err = "foreign table"; - break; - default: - err = "unknown"; - break; - } - - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("\"%s\" (%s) is not supported", - RelationGetRelationName(rel), err))); - return 0; /* should not happen */ -} - -/* - * pgstat_heap -- returns live/dead tuples info in a heap - */ -static Datum -pgstat_heap(Relation rel, FunctionCallInfo fcinfo) -{ - HeapScanDesc scan; - HeapTuple tuple; - BlockNumber nblocks; - BlockNumber block = 0; /* next block to count free space in */ - BlockNumber tupblock; - Buffer buffer; - pgstattuple_type stat = {0}; - - /* Disable syncscan because we assume we scan from block zero upwards */ - scan = heap_beginscan_strat(rel, SnapshotAny, 0, NULL, true, false); - - nblocks = scan->rs_nblocks; /* # blocks to be scanned */ - - /* scan the relation */ - while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) - { - CHECK_FOR_INTERRUPTS(); - - /* must hold a buffer lock to call HeapTupleSatisfiesVisibility */ - LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE); - - if (HeapTupleSatisfiesVisibility(tuple, SnapshotNow, scan->rs_cbuf)) - { - stat.tuple_len += tuple->t_len; - stat.tuple_count++; - } - else - { - stat.dead_tuple_len += tuple->t_len; - stat.dead_tuple_count++; - } - - LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); - - /* - * To avoid physically reading the table twice, try to do the - * free-space scan in parallel with the heap scan. However, - * heap_getnext may find no tuples on a given page, so we cannot - * simply examine the pages returned by the heap scan. - */ - tupblock = BlockIdGetBlockNumber(&tuple->t_self.ip_blkid); - - while (block <= tupblock) - { - CHECK_FOR_INTERRUPTS(); - - buffer = ReadBuffer(rel, block); - LockBuffer(buffer, BUFFER_LOCK_SHARE); - stat.free_space += PageGetHeapFreeSpace((Page) BufferGetPage(buffer)); - UnlockReleaseBuffer(buffer); - block++; - } - } - heap_endscan(scan); - - while (block < nblocks) - { - CHECK_FOR_INTERRUPTS(); - - buffer = ReadBuffer(rel, block); - LockBuffer(buffer, BUFFER_LOCK_SHARE); - stat.free_space += PageGetHeapFreeSpace((Page) BufferGetPage(buffer)); - UnlockReleaseBuffer(buffer); - block++; - } - - relation_close(rel, AccessShareLock); - - stat.table_len = (uint64) nblocks *BLCKSZ; - - return build_pgstattuple_type(&stat, fcinfo); -} - -/* - * pgstat_btree_page -- check tuples in a btree page - */ -static void -pgstat_btree_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) -{ - Buffer buf; - Page page; - - buf = ReadBuffer(rel, blkno); - LockBuffer(buf, BT_READ); - page = BufferGetPage(buf); - - /* Page is valid, see what to do with it */ - if (PageIsNew(page)) - { - /* fully empty page */ - stat->free_space += BLCKSZ; - } - else - { - BTPageOpaque opaque; - - opaque = (BTPageOpaque) PageGetSpecialPointer(page); - if (opaque->btpo_flags & (BTP_DELETED | BTP_HALF_DEAD)) - { - /* recyclable page */ - stat->free_space += BLCKSZ; - } - else if (P_ISLEAF(opaque)) - { - pgstat_index_page(stat, page, P_FIRSTDATAKEY(opaque), - PageGetMaxOffsetNumber(page)); - } - else - { - /* root or node */ - } - } - - _bt_relbuf(rel, buf); -} - -/* - * pgstat_hash_page -- check tuples in a hash page - */ -static void -pgstat_hash_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) -{ - Buffer buf; - Page page; - - _hash_getlock(rel, blkno, HASH_SHARE); - buf = _hash_getbuf(rel, blkno, HASH_READ, 0); - page = BufferGetPage(buf); - - if (PageGetSpecialSize(page) == MAXALIGN(sizeof(HashPageOpaqueData))) - { - HashPageOpaque opaque; - - opaque = (HashPageOpaque) PageGetSpecialPointer(page); - switch (opaque->hasho_flag) - { - case LH_UNUSED_PAGE: - stat->free_space += BLCKSZ; - break; - case LH_BUCKET_PAGE: - case LH_OVERFLOW_PAGE: - pgstat_index_page(stat, page, FirstOffsetNumber, - PageGetMaxOffsetNumber(page)); - break; - case LH_BITMAP_PAGE: - case LH_META_PAGE: - default: - break; - } - } - else - { - /* maybe corrupted */ - } - - _hash_relbuf(rel, buf); - _hash_droplock(rel, blkno, HASH_SHARE); -} - -/* - * pgstat_gist_page -- check tuples in a gist page - */ -static void -pgstat_gist_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) -{ - Buffer buf; - Page page; - - buf = ReadBuffer(rel, blkno); - LockBuffer(buf, GIST_SHARE); - gistcheckpage(rel, buf); - page = BufferGetPage(buf); - - if (GistPageIsLeaf(page)) - { - pgstat_index_page(stat, page, FirstOffsetNumber, - PageGetMaxOffsetNumber(page)); - } - else - { - /* root or node */ - } - - UnlockReleaseBuffer(buf); -} - -/* - * pgstat_index -- returns live/dead tuples info in a generic index - */ -static Datum -pgstat_index(Relation rel, BlockNumber start, pgstat_page pagefn, - FunctionCallInfo fcinfo) -{ - BlockNumber nblocks; - BlockNumber blkno; - pgstattuple_type stat = {0}; - - blkno = start; - for (;;) - { - /* Get the current relation length */ - LockRelationForExtension(rel, ExclusiveLock); - nblocks = RelationGetNumberOfBlocks(rel); - UnlockRelationForExtension(rel, ExclusiveLock); - - /* Quit if we've scanned the whole relation */ - if (blkno >= nblocks) - { - stat.table_len = (uint64) nblocks *BLCKSZ; - - break; - } - - for (; blkno < nblocks; blkno++) - { - CHECK_FOR_INTERRUPTS(); - - pagefn(&stat, rel, blkno); - } - } - - relation_close(rel, AccessShareLock); - - return build_pgstattuple_type(&stat, fcinfo); -} - -/* - * pgstat_index_page -- for generic index page - */ -static void -pgstat_index_page(pgstattuple_type *stat, Page page, - OffsetNumber minoff, OffsetNumber maxoff) -{ - OffsetNumber i; - - stat->free_space += PageGetFreeSpace(page); - - for (i = minoff; i <= maxoff; i = OffsetNumberNext(i)) - { - ItemId itemid = PageGetItemId(page, i); - - if (ItemIdIsDead(itemid)) - { - stat->dead_tuple_count++; - stat->dead_tuple_len += ItemIdGetLength(itemid); - } - else - { - stat->tuple_count++; - stat->tuple_len += ItemIdGetLength(itemid); - } - } -} diff --git a/contrib/pgstattuple/pgstattuple.control b/contrib/pgstattuple/pgstattuple.control deleted file mode 100644 index 7b5129b..0000000 --- a/contrib/pgstattuple/pgstattuple.control +++ /dev/null @@ -1,5 +0,0 @@ -# pgstattuple extension -comment = 'show tuple-level statistics' -default_version = '1.0' -module_pathname = '$libdir/pgstattuple' -relocatable = true diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml index adf09ca..0d16084 100644 --- a/doc/src/sgml/contrib.sgml +++ b/doc/src/sgml/contrib.sgml @@ -89,7 +89,6 @@ CREATE EXTENSION module_name FROM unpackaged; &adminpack; &auth-delay; - &auto-explain; &btree-gin; &btree-gist; &chkpass; @@ -109,17 +108,11 @@ CREATE EXTENSION module_name FROM unpackaged; &lo; <ree; &oid2name; - &pageinspect; &passwordcheck; &pgarchivecleanup; &pgbench; - &pgbuffercache; &pgcrypto; - &pgfreespacemap; - &pgrowlocks; &pgstandby; - &pgstatstatements; - &pgstattuple; &pgtestfsync; &pgtrgm; &pgupgrade; diff --git a/doc/src/sgml/extensions.sgml b/doc/src/sgml/extensions.sgml new file mode 100644 index 0000000..eea69c3 --- /dev/null +++ b/doc/src/sgml/extensions.sgml @@ -0,0 +1,77 @@ + + + + Core Extensions + + + + It is difficult to manage all of the components to + PostgreSQL without making the database core + larger than it must be. But many enhancements can be efficiently developed + using the facilites normally intended for adding external modules. + This appendix contains information regarding core extensions that are + built and included with a standard installation of PostgreSQL. These + core extensions supply useful features in areas such as database diagnostics + and performance monitoring. + + + + Some of these features could instead be made available as built-in functions. + Providing them as extension modules instead reduces the amount of code to be + maintained in the main database. It also serves as an example of how + powerful the extension features described in are. It + is possible to write your own extensions of similar utility to those listed + here, and to use these as examples for doing so. + + + + To make use of one of these extensions, you need to register the new SQL + objects in the database system. This is done by executing a + command. In a fresh database, + you can simply do + + +CREATE EXTENSION module_name; + + + This command must be run by a database superuser. This registers the + new SQL objects in the current database only, so you need to run this + command in each database that you want + the module's facilities to be available in. Alternatively, run it in + database template1 so that the extension will be copied into + subsequently-created databases by default. + + + + Many modules allow you to install their objects in a schema of your + choice. To do that, add SCHEMA + schema_name to the CREATE EXTENSION + command. By default, the objects will be placed in your current creation + target schema, typically public. + + + + If your database was brought forward by dump and reload from a pre-9.1 + version of PostgreSQL, and you had been using the pre-9.1 + version of the module in it, you should instead do + + +CREATE EXTENSION module_name FROM unpackaged; + + + This will update the pre-9.1 objects of the module into a proper + extension object. Future updates to the module will be + managed by . + For more information about extension updates, see + . + + + &auto-explain; + &pageinspect; + &pgbuffercache; + &pgfreespacemap; + &pgrowlocks; + &pgstatstatements; + &pgstattuple; + + diff --git a/doc/src/sgml/external-projects.sgml b/doc/src/sgml/external-projects.sgml index ef516b4..8b12574 100644 --- a/doc/src/sgml/external-projects.sgml +++ b/doc/src/sgml/external-projects.sgml @@ -246,9 +246,10 @@ PostgreSQL is designed to be easily extensible. For this reason, extensions loaded into the database can function - just like features that are built in. The + just like features that are built in. Some + are available in any installation. The contrib/ directory shipped with the source code - contains several extensions, which are described in + contains several optional extensions, which are described in . Other extensions are developed independently, like PostGIS. Even diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml index ed39e0b..352c6f2 100644 --- a/doc/src/sgml/filelist.sgml +++ b/doc/src/sgml/filelist.sgml @@ -91,11 +91,20 @@ + + + + + + + + + + - @@ -115,17 +124,11 @@ - - - - - - diff --git a/doc/src/sgml/postgres.sgml b/doc/src/sgml/postgres.sgml index ac1da22..1a90267 100644 --- a/doc/src/sgml/postgres.sgml +++ b/doc/src/sgml/postgres.sgml @@ -257,6 +257,7 @@ &keywords; &features; &release; + &extensions; &contrib; &external-projects; &sourcerepo; diff --git a/src/Makefile b/src/Makefile index a046034..87d6e2c 100644 --- a/src/Makefile +++ b/src/Makefile @@ -24,6 +24,7 @@ SUBDIRS = \ bin \ pl \ makefiles \ + extension \ test/regress # There are too many interdependencies between the subdirectories, so diff --git a/src/extension/Makefile b/src/extension/Makefile new file mode 100644 index 0000000..282f076 --- /dev/null +++ b/src/extension/Makefile @@ -0,0 +1,41 @@ +# $PostgreSQL: pgsql/src/extension/Makefile $ + +subdir = src/extension +top_builddir = ../.. +include $(top_builddir)/src/Makefile.global + +SUBDIRS = \ + auto_explain \ + pageinspect \ + pg_buffercache \ + pgrowlocks \ + pg_stat_statements \ + pgstattuple + +ifeq ($(with_openssl),yes) +SUBDIRS += sslinfo +endif + +ifeq ($(with_ossp_uuid),yes) +SUBDIRS += uuid-ossp +endif + +ifeq ($(with_libxml),yes) +SUBDIRS += xml2 +endif + +# Missing: +# start-scripts \ (does not have a makefile) + + +all install installdirs uninstall distprep clean distclean maintainer-clean: + @for dir in $(SUBDIRS); do \ + $(MAKE) -C $$dir $@ || exit; \ + done + +# We'd like check operations to run all the subtests before failing. +check installcheck: + @CHECKERR=0; for dir in $(SUBDIRS); do \ + $(MAKE) -C $$dir $@ || CHECKERR=$$?; \ + done; \ + exit $$CHECKERR diff --git a/src/extension/auto_explain/Makefile b/src/extension/auto_explain/Makefile new file mode 100644 index 0000000..023e59a --- /dev/null +++ b/src/extension/auto_explain/Makefile @@ -0,0 +1,16 @@ +# src/extension/auto_explain/Makefile + +MODULE_big = auto_explain +OBJS = auto_explain.o +MODULEDIR=extension + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/auto_explain +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/auto_explain/auto_explain.c b/src/extension/auto_explain/auto_explain.c new file mode 100644 index 0000000..647f6d0 --- /dev/null +++ b/src/extension/auto_explain/auto_explain.c @@ -0,0 +1,304 @@ +/*------------------------------------------------------------------------- + * + * auto_explain.c + * + * + * Copyright (c) 2008-2011, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/extension/auto_explain/auto_explain.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "commands/explain.h" +#include "executor/instrument.h" +#include "utils/guc.h" + +PG_MODULE_MAGIC; + +/* GUC variables */ +static int auto_explain_log_min_duration = -1; /* msec or -1 */ +static bool auto_explain_log_analyze = false; +static bool auto_explain_log_verbose = false; +static bool auto_explain_log_buffers = false; +static int auto_explain_log_format = EXPLAIN_FORMAT_TEXT; +static bool auto_explain_log_nested_statements = false; + +static const struct config_enum_entry format_options[] = { + {"text", EXPLAIN_FORMAT_TEXT, false}, + {"xml", EXPLAIN_FORMAT_XML, false}, + {"json", EXPLAIN_FORMAT_JSON, false}, + {"yaml", EXPLAIN_FORMAT_YAML, false}, + {NULL, 0, false} +}; + +/* Current nesting depth of ExecutorRun calls */ +static int nesting_level = 0; + +/* Saved hook values in case of unload */ +static ExecutorStart_hook_type prev_ExecutorStart = NULL; +static ExecutorRun_hook_type prev_ExecutorRun = NULL; +static ExecutorFinish_hook_type prev_ExecutorFinish = NULL; +static ExecutorEnd_hook_type prev_ExecutorEnd = NULL; + +#define auto_explain_enabled() \ + (auto_explain_log_min_duration >= 0 && \ + (nesting_level == 0 || auto_explain_log_nested_statements)) + +void _PG_init(void); +void _PG_fini(void); + +static void explain_ExecutorStart(QueryDesc *queryDesc, int eflags); +static void explain_ExecutorRun(QueryDesc *queryDesc, + ScanDirection direction, + long count); +static void explain_ExecutorFinish(QueryDesc *queryDesc); +static void explain_ExecutorEnd(QueryDesc *queryDesc); + + +/* + * Module load callback + */ +void +_PG_init(void) +{ + /* Define custom GUC variables. */ + DefineCustomIntVariable("auto_explain.log_min_duration", + "Sets the minimum execution time above which plans will be logged.", + "Zero prints all plans. -1 turns this feature off.", + &auto_explain_log_min_duration, + -1, + -1, INT_MAX / 1000, + PGC_SUSET, + GUC_UNIT_MS, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("auto_explain.log_analyze", + "Use EXPLAIN ANALYZE for plan logging.", + NULL, + &auto_explain_log_analyze, + false, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("auto_explain.log_verbose", + "Use EXPLAIN VERBOSE for plan logging.", + NULL, + &auto_explain_log_verbose, + false, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("auto_explain.log_buffers", + "Log buffers usage.", + NULL, + &auto_explain_log_buffers, + false, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomEnumVariable("auto_explain.log_format", + "EXPLAIN format to be used for plan logging.", + NULL, + &auto_explain_log_format, + EXPLAIN_FORMAT_TEXT, + format_options, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("auto_explain.log_nested_statements", + "Log nested statements.", + NULL, + &auto_explain_log_nested_statements, + false, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + EmitWarningsOnPlaceholders("auto_explain"); + + /* Install hooks. */ + prev_ExecutorStart = ExecutorStart_hook; + ExecutorStart_hook = explain_ExecutorStart; + prev_ExecutorRun = ExecutorRun_hook; + ExecutorRun_hook = explain_ExecutorRun; + prev_ExecutorFinish = ExecutorFinish_hook; + ExecutorFinish_hook = explain_ExecutorFinish; + prev_ExecutorEnd = ExecutorEnd_hook; + ExecutorEnd_hook = explain_ExecutorEnd; +} + +/* + * Module unload callback + */ +void +_PG_fini(void) +{ + /* Uninstall hooks. */ + ExecutorStart_hook = prev_ExecutorStart; + ExecutorRun_hook = prev_ExecutorRun; + ExecutorFinish_hook = prev_ExecutorFinish; + ExecutorEnd_hook = prev_ExecutorEnd; +} + +/* + * ExecutorStart hook: start up logging if needed + */ +static void +explain_ExecutorStart(QueryDesc *queryDesc, int eflags) +{ + if (auto_explain_enabled()) + { + /* Enable per-node instrumentation iff log_analyze is required. */ + if (auto_explain_log_analyze && (eflags & EXEC_FLAG_EXPLAIN_ONLY) == 0) + { + queryDesc->instrument_options |= INSTRUMENT_TIMER; + if (auto_explain_log_buffers) + queryDesc->instrument_options |= INSTRUMENT_BUFFERS; + } + } + + if (prev_ExecutorStart) + prev_ExecutorStart(queryDesc, eflags); + else + standard_ExecutorStart(queryDesc, eflags); + + if (auto_explain_enabled()) + { + /* + * Set up to track total elapsed time in ExecutorRun. Make sure the + * space is allocated in the per-query context so it will go away at + * ExecutorEnd. + */ + if (queryDesc->totaltime == NULL) + { + MemoryContext oldcxt; + + oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt); + queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL); + MemoryContextSwitchTo(oldcxt); + } + } +} + +/* + * ExecutorRun hook: all we need do is track nesting depth + */ +static void +explain_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, long count) +{ + nesting_level++; + PG_TRY(); + { + if (prev_ExecutorRun) + prev_ExecutorRun(queryDesc, direction, count); + else + standard_ExecutorRun(queryDesc, direction, count); + nesting_level--; + } + PG_CATCH(); + { + nesting_level--; + PG_RE_THROW(); + } + PG_END_TRY(); +} + +/* + * ExecutorFinish hook: all we need do is track nesting depth + */ +static void +explain_ExecutorFinish(QueryDesc *queryDesc) +{ + nesting_level++; + PG_TRY(); + { + if (prev_ExecutorFinish) + prev_ExecutorFinish(queryDesc); + else + standard_ExecutorFinish(queryDesc); + nesting_level--; + } + PG_CATCH(); + { + nesting_level--; + PG_RE_THROW(); + } + PG_END_TRY(); +} + +/* + * ExecutorEnd hook: log results if needed + */ +static void +explain_ExecutorEnd(QueryDesc *queryDesc) +{ + if (queryDesc->totaltime && auto_explain_enabled()) + { + double msec; + + /* + * Make sure stats accumulation is done. (Note: it's okay if several + * levels of hook all do this.) + */ + InstrEndLoop(queryDesc->totaltime); + + /* Log plan if duration is exceeded. */ + msec = queryDesc->totaltime->total * 1000.0; + if (msec >= auto_explain_log_min_duration) + { + ExplainState es; + + ExplainInitState(&es); + es.analyze = (queryDesc->instrument_options && auto_explain_log_analyze); + es.verbose = auto_explain_log_verbose; + es.buffers = (es.analyze && auto_explain_log_buffers); + es.format = auto_explain_log_format; + + ExplainBeginOutput(&es); + ExplainQueryText(&es, queryDesc); + ExplainPrintPlan(&es, queryDesc); + ExplainEndOutput(&es); + + /* Remove last line break */ + if (es.str->len > 0 && es.str->data[es.str->len - 1] == '\n') + es.str->data[--es.str->len] = '\0'; + + /* + * Note: we rely on the existing logging of context or + * debug_query_string to identify just which statement is being + * reported. This isn't ideal but trying to do it here would + * often result in duplication. + */ + ereport(LOG, + (errmsg("duration: %.3f ms plan:\n%s", + msec, es.str->data), + errhidestmt(true))); + + pfree(es.str->data); + } + } + + if (prev_ExecutorEnd) + prev_ExecutorEnd(queryDesc); + else + standard_ExecutorEnd(queryDesc); +} diff --git a/src/extension/extension-global.mk b/src/extension/extension-global.mk new file mode 100644 index 0000000..cc7643b --- /dev/null +++ b/src/extension/extension-global.mk @@ -0,0 +1,5 @@ +# $PostgreSQL: pgsql/extension/extension-global.mk,v 1.10 2005/09/27 17:43:31 tgl Exp $ + +NO_PGXS = 1 +MODULEDIR=extension +include $(top_srcdir)/src/makefiles/pgxs.mk diff --git a/src/extension/pageinspect/Makefile b/src/extension/pageinspect/Makefile new file mode 100644 index 0000000..c6940b8 --- /dev/null +++ b/src/extension/pageinspect/Makefile @@ -0,0 +1,19 @@ +# src/extension/pageinspect/Makefile + +MODULE_big = pageinspect +OBJS = rawpage.o heapfuncs.o btreefuncs.o fsmfuncs.o +MODULEDIR = extension + +EXTENSION = pageinspect +DATA = pageinspect--1.0.sql pageinspect--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pageinspect +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pageinspect/btreefuncs.c b/src/extension/pageinspect/btreefuncs.c new file mode 100644 index 0000000..e378560 --- /dev/null +++ b/src/extension/pageinspect/btreefuncs.c @@ -0,0 +1,502 @@ +/* + * src/extension/pageinspect/btreefuncs.c + * + * + * btreefuncs.c + * + * Copyright (c) 2006 Satoshi Nagayasu + * + * Permission to use, copy, modify, and distribute this software and + * its documentation for any purpose, without fee, and without a + * written agreement is hereby granted, provided that the above + * copyright notice and this paragraph and the following two + * paragraphs appear in all copies. + * + * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, + * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING + * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS + * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + * + * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS + * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, + * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. + */ + +#include "postgres.h" + +#include "access/heapam.h" +#include "access/nbtree.h" +#include "catalog/namespace.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "storage/bufmgr.h" +#include "utils/builtins.h" + + +extern Datum bt_metap(PG_FUNCTION_ARGS); +extern Datum bt_page_items(PG_FUNCTION_ARGS); +extern Datum bt_page_stats(PG_FUNCTION_ARGS); + +PG_FUNCTION_INFO_V1(bt_metap); +PG_FUNCTION_INFO_V1(bt_page_items); +PG_FUNCTION_INFO_V1(bt_page_stats); + +#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX) +#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID) + +#define CHECK_PAGE_OFFSET_RANGE(pg, offnum) { \ + if ( !(FirstOffsetNumber <= (offnum) && \ + (offnum) <= PageGetMaxOffsetNumber(pg)) ) \ + elog(ERROR, "page offset number out of range"); } + +/* note: BlockNumber is unsigned, hence can't be negative */ +#define CHECK_RELATION_BLOCK_RANGE(rel, blkno) { \ + if ( RelationGetNumberOfBlocks(rel) <= (BlockNumber) (blkno) ) \ + elog(ERROR, "block number out of range"); } + +/* ------------------------------------------------ + * structure for single btree page statistics + * ------------------------------------------------ + */ +typedef struct BTPageStat +{ + uint32 blkno; + uint32 live_items; + uint32 dead_items; + uint32 page_size; + uint32 max_avail; + uint32 free_size; + uint32 avg_item_size; + char type; + + /* opaque data */ + BlockNumber btpo_prev; + BlockNumber btpo_next; + union + { + uint32 level; + TransactionId xact; + } btpo; + uint16 btpo_flags; + BTCycleId btpo_cycleid; +} BTPageStat; + + +/* ------------------------------------------------- + * GetBTPageStatistics() + * + * Collect statistics of single b-tree page + * ------------------------------------------------- + */ +static void +GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat) +{ + Page page = BufferGetPage(buffer); + PageHeader phdr = (PageHeader) page; + OffsetNumber maxoff = PageGetMaxOffsetNumber(page); + BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page); + int item_size = 0; + int off; + + stat->blkno = blkno; + + stat->max_avail = BLCKSZ - (BLCKSZ - phdr->pd_special + SizeOfPageHeaderData); + + stat->dead_items = stat->live_items = 0; + + stat->page_size = PageGetPageSize(page); + + /* page type (flags) */ + if (P_ISDELETED(opaque)) + { + stat->type = 'd'; + stat->btpo.xact = opaque->btpo.xact; + return; + } + else if (P_IGNORE(opaque)) + stat->type = 'e'; + else if (P_ISLEAF(opaque)) + stat->type = 'l'; + else if (P_ISROOT(opaque)) + stat->type = 'r'; + else + stat->type = 'i'; + + /* btpage opaque data */ + stat->btpo_prev = opaque->btpo_prev; + stat->btpo_next = opaque->btpo_next; + stat->btpo.level = opaque->btpo.level; + stat->btpo_flags = opaque->btpo_flags; + stat->btpo_cycleid = opaque->btpo_cycleid; + + /* count live and dead tuples, and free space */ + for (off = FirstOffsetNumber; off <= maxoff; off++) + { + IndexTuple itup; + + ItemId id = PageGetItemId(page, off); + + itup = (IndexTuple) PageGetItem(page, id); + + item_size += IndexTupleSize(itup); + + if (!ItemIdIsDead(id)) + stat->live_items++; + else + stat->dead_items++; + } + stat->free_size = PageGetFreeSpace(page); + + if ((stat->live_items + stat->dead_items) > 0) + stat->avg_item_size = item_size / (stat->live_items + stat->dead_items); + else + stat->avg_item_size = 0; +} + +/* ----------------------------------------------- + * bt_page() + * + * Usage: SELECT * FROM bt_page('t1_pkey', 1); + * ----------------------------------------------- + */ +Datum +bt_page_stats(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + uint32 blkno = PG_GETARG_UINT32(1); + Buffer buffer; + Relation rel; + RangeVar *relrv; + Datum result; + HeapTuple tuple; + TupleDesc tupleDesc; + int j; + char *values[11]; + BTPageStat stat; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pageinspect functions")))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + elog(ERROR, "relation \"%s\" is not a btree index", + RelationGetRelationName(rel)); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno == 0) + elog(ERROR, "block 0 is a meta page"); + + CHECK_RELATION_BLOCK_RANGE(rel, blkno); + + buffer = ReadBuffer(rel, blkno); + + /* keep compiler quiet */ + stat.btpo_prev = stat.btpo_next = InvalidBlockNumber; + stat.btpo_flags = stat.free_size = stat.avg_item_size = 0; + + GetBTPageStatistics(blkno, buffer, &stat); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + j = 0; + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.blkno); + values[j] = palloc(32); + snprintf(values[j++], 32, "%c", stat.type); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.live_items); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.dead_items); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.avg_item_size); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.page_size); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.free_size); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.btpo_prev); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.btpo_next); + values[j] = palloc(32); + if (stat.type == 'd') + snprintf(values[j++], 32, "%d", stat.btpo.xact); + else + snprintf(values[j++], 32, "%d", stat.btpo.level); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", stat.btpo_flags); + + tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), + values); + + result = HeapTupleGetDatum(tuple); + + ReleaseBuffer(buffer); + + relation_close(rel, AccessShareLock); + + PG_RETURN_DATUM(result); +} + +/*------------------------------------------------------- + * bt_page_items() + * + * Get IndexTupleData set in a btree page + * + * Usage: SELECT * FROM bt_page_items('t1_pkey', 1); + *------------------------------------------------------- + */ + +/* + * cross-call data structure for SRF + */ +struct user_args +{ + Page page; + OffsetNumber offset; +}; + +Datum +bt_page_items(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + uint32 blkno = PG_GETARG_UINT32(1); + Datum result; + char *values[6]; + HeapTuple tuple; + FuncCallContext *fctx; + MemoryContext mctx; + struct user_args *uargs; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pageinspect functions")))); + + if (SRF_IS_FIRSTCALL()) + { + RangeVar *relrv; + Relation rel; + Buffer buffer; + BTPageOpaque opaque; + TupleDesc tupleDesc; + + fctx = SRF_FIRSTCALL_INIT(); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + elog(ERROR, "relation \"%s\" is not a btree index", + RelationGetRelationName(rel)); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the + * owning session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno == 0) + elog(ERROR, "block 0 is a meta page"); + + CHECK_RELATION_BLOCK_RANGE(rel, blkno); + + buffer = ReadBuffer(rel, blkno); + + /* + * We copy the page into local storage to avoid holding pin on the + * buffer longer than we must, and possibly failing to release it at + * all if the calling query doesn't fetch all rows. + */ + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + uargs = palloc(sizeof(struct user_args)); + + uargs->page = palloc(BLCKSZ); + memcpy(uargs->page, BufferGetPage(buffer), BLCKSZ); + + ReleaseBuffer(buffer); + relation_close(rel, AccessShareLock); + + uargs->offset = FirstOffsetNumber; + + opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page); + + if (P_ISDELETED(opaque)) + elog(NOTICE, "page is deleted"); + + fctx->max_calls = PageGetMaxOffsetNumber(uargs->page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc); + + fctx->user_fctx = uargs; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + uargs = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + ItemId id; + IndexTuple itup; + int j; + int off; + int dlen; + char *dump; + char *ptr; + + id = PageGetItemId(uargs->page, uargs->offset); + + if (!ItemIdIsValid(id)) + elog(ERROR, "invalid ItemId"); + + itup = (IndexTuple) PageGetItem(uargs->page, id); + + j = 0; + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", uargs->offset); + values[j] = palloc(32); + snprintf(values[j++], 32, "(%u,%u)", + BlockIdGetBlockNumber(&(itup->t_tid.ip_blkid)), + itup->t_tid.ip_posid); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", (int) IndexTupleSize(itup)); + values[j] = palloc(32); + snprintf(values[j++], 32, "%c", IndexTupleHasNulls(itup) ? 't' : 'f'); + values[j] = palloc(32); + snprintf(values[j++], 32, "%c", IndexTupleHasVarwidths(itup) ? 't' : 'f'); + + ptr = (char *) itup + IndexInfoFindDataOffset(itup->t_info); + dlen = IndexTupleSize(itup) - IndexInfoFindDataOffset(itup->t_info); + dump = palloc0(dlen * 3 + 1); + values[j] = dump; + for (off = 0; off < dlen; off++) + { + if (off > 0) + *dump++ = ' '; + sprintf(dump, "%02x", *(ptr + off) & 0xff); + dump += 2; + } + + tuple = BuildTupleFromCStrings(fctx->attinmeta, values); + result = HeapTupleGetDatum(tuple); + + uargs->offset = uargs->offset + 1; + + SRF_RETURN_NEXT(fctx, result); + } + else + { + pfree(uargs->page); + pfree(uargs); + SRF_RETURN_DONE(fctx); + } +} + + +/* ------------------------------------------------ + * bt_metap() + * + * Get a btree's meta-page information + * + * Usage: SELECT * FROM bt_metap('t1_pkey') + * ------------------------------------------------ + */ +Datum +bt_metap(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + Datum result; + Relation rel; + RangeVar *relrv; + BTMetaPageData *metad; + TupleDesc tupleDesc; + int j; + char *values[6]; + Buffer buffer; + Page page; + HeapTuple tuple; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pageinspect functions")))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + elog(ERROR, "relation \"%s\" is not a btree index", + RelationGetRelationName(rel)); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + buffer = ReadBuffer(rel, 0); + page = BufferGetPage(buffer); + metad = BTPageGetMeta(page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + j = 0; + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_magic); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_version); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_root); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_level); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_fastroot); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", metad->btm_fastlevel); + + tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), + values); + + result = HeapTupleGetDatum(tuple); + + ReleaseBuffer(buffer); + + relation_close(rel, AccessShareLock); + + PG_RETURN_DATUM(result); +} diff --git a/src/extension/pageinspect/fsmfuncs.c b/src/extension/pageinspect/fsmfuncs.c new file mode 100644 index 0000000..45b2b9d --- /dev/null +++ b/src/extension/pageinspect/fsmfuncs.c @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * fsmfuncs.c + * Functions to investigate FSM pages + * + * These functions are restricted to superusers for the fear of introducing + * security holes if the input checking isn't as water-tight as it should. + * You'd need to be superuser to obtain a raw page image anyway, so + * there's hardly any use case for using these without superuser-rights + * anyway. + * + * Copyright (c) 2007-2011, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/extension/pageinspect/fsmfuncs.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" +#include "lib/stringinfo.h" +#include "storage/fsm_internals.h" +#include "utils/builtins.h" +#include "miscadmin.h" +#include "funcapi.h" + +Datum fsm_page_contents(PG_FUNCTION_ARGS); + +/* + * Dumps the contents of a FSM page. + */ +PG_FUNCTION_INFO_V1(fsm_page_contents); + +Datum +fsm_page_contents(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + StringInfoData sinfo; + FSMPage fsmpage; + int i; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use raw page functions")))); + + fsmpage = (FSMPage) PageGetContents(VARDATA(raw_page)); + + initStringInfo(&sinfo); + + for (i = 0; i < NodesPerPage; i++) + { + if (fsmpage->fp_nodes[i] != 0) + appendStringInfo(&sinfo, "%d: %d\n", i, fsmpage->fp_nodes[i]); + } + appendStringInfo(&sinfo, "fp_next_slot: %d\n", fsmpage->fp_next_slot); + + PG_RETURN_TEXT_P(cstring_to_text(sinfo.data)); +} diff --git a/src/extension/pageinspect/heapfuncs.c b/src/extension/pageinspect/heapfuncs.c new file mode 100644 index 0000000..a9f95b4 --- /dev/null +++ b/src/extension/pageinspect/heapfuncs.c @@ -0,0 +1,230 @@ +/*------------------------------------------------------------------------- + * + * heapfuncs.c + * Functions to investigate heap pages + * + * We check the input to these functions for corrupt pointers etc. that + * might cause crashes, but at the same time we try to print out as much + * information as possible, even if it's nonsense. That's because if a + * page is corrupt, we don't know why and how exactly it is corrupt, so we + * let the user judge it. + * + * These functions are restricted to superusers for the fear of introducing + * security holes if the input checking isn't as water-tight as it should be. + * You'd need to be superuser to obtain a raw page image anyway, so + * there's hardly any use case for using these without superuser-rights + * anyway. + * + * Copyright (c) 2007-2011, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/extension/pageinspect/heapfuncs.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "fmgr.h" +#include "funcapi.h" +#include "access/heapam.h" +#include "access/transam.h" +#include "catalog/namespace.h" +#include "catalog/pg_type.h" +#include "utils/builtins.h" +#include "miscadmin.h" + +Datum heap_page_items(PG_FUNCTION_ARGS); + + +/* + * bits_to_text + * + * Converts a bits8-array of 'len' bits to a human-readable + * c-string representation. + */ +static char * +bits_to_text(bits8 *bits, int len) +{ + int i; + char *str; + + str = palloc(len + 1); + + for (i = 0; i < len; i++) + str[i] = (bits[(i / 8)] & (1 << (i % 8))) ? '1' : '0'; + + str[i] = '\0'; + + return str; +} + + +/* + * heap_page_items + * + * Allows inspection of line pointers and tuple headers of a heap page. + */ +PG_FUNCTION_INFO_V1(heap_page_items); + +typedef struct heap_page_items_state +{ + TupleDesc tupd; + Page page; + uint16 offset; +} heap_page_items_state; + +Datum +heap_page_items(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + heap_page_items_state *inter_call_data = NULL; + FuncCallContext *fctx; + int raw_page_size; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use raw page functions")))); + + raw_page_size = VARSIZE(raw_page) - VARHDRSZ; + + if (SRF_IS_FIRSTCALL()) + { + TupleDesc tupdesc; + MemoryContext mctx; + + if (raw_page_size < SizeOfPageHeaderData) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page too small (%d bytes)", raw_page_size))); + + fctx = SRF_FIRSTCALL_INIT(); + mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx); + + inter_call_data = palloc(sizeof(heap_page_items_state)); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + inter_call_data->tupd = tupdesc; + + inter_call_data->offset = FirstOffsetNumber; + inter_call_data->page = VARDATA(raw_page); + + fctx->max_calls = PageGetMaxOffsetNumber(inter_call_data->page); + fctx->user_fctx = inter_call_data; + + MemoryContextSwitchTo(mctx); + } + + fctx = SRF_PERCALL_SETUP(); + inter_call_data = fctx->user_fctx; + + if (fctx->call_cntr < fctx->max_calls) + { + Page page = inter_call_data->page; + HeapTuple resultTuple; + Datum result; + ItemId id; + Datum values[13]; + bool nulls[13]; + uint16 lp_offset; + uint16 lp_flags; + uint16 lp_len; + + memset(nulls, 0, sizeof(nulls)); + + /* Extract information from the line pointer */ + + id = PageGetItemId(page, inter_call_data->offset); + + lp_offset = ItemIdGetOffset(id); + lp_flags = ItemIdGetFlags(id); + lp_len = ItemIdGetLength(id); + + values[0] = UInt16GetDatum(inter_call_data->offset); + values[1] = UInt16GetDatum(lp_offset); + values[2] = UInt16GetDatum(lp_flags); + values[3] = UInt16GetDatum(lp_len); + + /* + * We do just enough validity checking to make sure we don't reference + * data outside the page passed to us. The page could be corrupt in + * many other ways, but at least we won't crash. + */ + if (ItemIdHasStorage(id) && + lp_len >= sizeof(HeapTupleHeader) && + lp_offset == MAXALIGN(lp_offset) && + lp_offset + lp_len <= raw_page_size) + { + HeapTupleHeader tuphdr; + int bits_len; + + /* Extract information from the tuple header */ + + tuphdr = (HeapTupleHeader) PageGetItem(page, id); + + values[4] = UInt32GetDatum(HeapTupleHeaderGetXmin(tuphdr)); + values[5] = UInt32GetDatum(HeapTupleHeaderGetXmax(tuphdr)); + values[6] = UInt32GetDatum(HeapTupleHeaderGetRawCommandId(tuphdr)); /* shared with xvac */ + values[7] = PointerGetDatum(&tuphdr->t_ctid); + values[8] = UInt32GetDatum(tuphdr->t_infomask2); + values[9] = UInt32GetDatum(tuphdr->t_infomask); + values[10] = UInt8GetDatum(tuphdr->t_hoff); + + /* + * We already checked that the item as is completely within the + * raw page passed to us, with the length given in the line + * pointer.. Let's check that t_hoff doesn't point over lp_len, + * before using it to access t_bits and oid. + */ + if (tuphdr->t_hoff >= sizeof(HeapTupleHeader) && + tuphdr->t_hoff <= lp_len) + { + if (tuphdr->t_infomask & HEAP_HASNULL) + { + bits_len = tuphdr->t_hoff - + (((char *) tuphdr->t_bits) -((char *) tuphdr)); + + values[11] = CStringGetTextDatum( + bits_to_text(tuphdr->t_bits, bits_len * 8)); + } + else + nulls[11] = true; + + if (tuphdr->t_infomask & HEAP_HASOID) + values[12] = HeapTupleHeaderGetOid(tuphdr); + else + nulls[12] = true; + } + else + { + nulls[11] = true; + nulls[12] = true; + } + } + else + { + /* + * The line pointer is not used, or it's invalid. Set the rest of + * the fields to NULL + */ + int i; + + for (i = 4; i <= 12; i++) + nulls[i] = true; + } + + /* Build and return the result tuple. */ + resultTuple = heap_form_tuple(inter_call_data->tupd, values, nulls); + result = HeapTupleGetDatum(resultTuple); + + inter_call_data->offset++; + + SRF_RETURN_NEXT(fctx, result); + } + else + SRF_RETURN_DONE(fctx); +} diff --git a/src/extension/pageinspect/pageinspect--1.0.sql b/src/extension/pageinspect/pageinspect--1.0.sql new file mode 100644 index 0000000..cadcb4a --- /dev/null +++ b/src/extension/pageinspect/pageinspect--1.0.sql @@ -0,0 +1,104 @@ +/* src/extension/pageinspect/pageinspect--1.0.sql */ + +-- +-- get_raw_page() +-- +CREATE FUNCTION get_raw_page(text, int4) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page' +LANGUAGE C STRICT; + +CREATE FUNCTION get_raw_page(text, text, int4) +RETURNS bytea +AS 'MODULE_PATHNAME', 'get_raw_page_fork' +LANGUAGE C STRICT; + +-- +-- page_header() +-- +CREATE FUNCTION page_header(IN page bytea, + OUT lsn text, + OUT tli smallint, + OUT flags smallint, + OUT lower smallint, + OUT upper smallint, + OUT special smallint, + OUT pagesize smallint, + OUT version smallint, + OUT prune_xid xid) +AS 'MODULE_PATHNAME', 'page_header' +LANGUAGE C STRICT; + +-- +-- heap_page_items() +-- +CREATE FUNCTION heap_page_items(IN page bytea, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'heap_page_items' +LANGUAGE C STRICT; + +-- +-- bt_metap() +-- +CREATE FUNCTION bt_metap(IN relname text, + OUT magic int4, + OUT version int4, + OUT root int4, + OUT level int4, + OUT fastroot int4, + OUT fastlevel int4) +AS 'MODULE_PATHNAME', 'bt_metap' +LANGUAGE C STRICT; + +-- +-- bt_page_stats() +-- +CREATE FUNCTION bt_page_stats(IN relname text, IN blkno int4, + OUT blkno int4, + OUT type "char", + OUT live_items int4, + OUT dead_items int4, + OUT avg_item_size int4, + OUT page_size int4, + OUT free_size int4, + OUT btpo_prev int4, + OUT btpo_next int4, + OUT btpo int4, + OUT btpo_flags int4) +AS 'MODULE_PATHNAME', 'bt_page_stats' +LANGUAGE C STRICT; + +-- +-- bt_page_items() +-- +CREATE FUNCTION bt_page_items(IN relname text, IN blkno int4, + OUT itemoffset smallint, + OUT ctid tid, + OUT itemlen smallint, + OUT nulls bool, + OUT vars bool, + OUT data text) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'bt_page_items' +LANGUAGE C STRICT; + +-- +-- fsm_page_contents() +-- +CREATE FUNCTION fsm_page_contents(IN page bytea) +RETURNS text +AS 'MODULE_PATHNAME', 'fsm_page_contents' +LANGUAGE C STRICT; diff --git a/src/extension/pageinspect/pageinspect--unpackaged--1.0.sql b/src/extension/pageinspect/pageinspect--unpackaged--1.0.sql new file mode 100644 index 0000000..9e9d8cf --- /dev/null +++ b/src/extension/pageinspect/pageinspect--unpackaged--1.0.sql @@ -0,0 +1,28 @@ +/* src/extension/pageinspect/pageinspect--unpackaged--1.0.sql */ + +DROP FUNCTION heap_page_items(bytea); +CREATE FUNCTION heap_page_items(IN page bytea, + OUT lp smallint, + OUT lp_off smallint, + OUT lp_flags smallint, + OUT lp_len smallint, + OUT t_xmin xid, + OUT t_xmax xid, + OUT t_field3 int4, + OUT t_ctid tid, + OUT t_infomask2 integer, + OUT t_infomask integer, + OUT t_hoff smallint, + OUT t_bits text, + OUT t_oid oid) +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'heap_page_items' +LANGUAGE C STRICT; + +ALTER EXTENSION pageinspect ADD function get_raw_page(text,integer); +ALTER EXTENSION pageinspect ADD function get_raw_page(text,text,integer); +ALTER EXTENSION pageinspect ADD function page_header(bytea); +ALTER EXTENSION pageinspect ADD function bt_metap(text); +ALTER EXTENSION pageinspect ADD function bt_page_stats(text,integer); +ALTER EXTENSION pageinspect ADD function bt_page_items(text,integer); +ALTER EXTENSION pageinspect ADD function fsm_page_contents(bytea); diff --git a/src/extension/pageinspect/pageinspect.control b/src/extension/pageinspect/pageinspect.control new file mode 100644 index 0000000..f9da0e8 --- /dev/null +++ b/src/extension/pageinspect/pageinspect.control @@ -0,0 +1,5 @@ +# pageinspect extension +comment = 'inspect the contents of database pages at a low level' +default_version = '1.0' +module_pathname = '$libdir/pageinspect' +relocatable = true diff --git a/src/extension/pageinspect/rawpage.c b/src/extension/pageinspect/rawpage.c new file mode 100644 index 0000000..87a029f --- /dev/null +++ b/src/extension/pageinspect/rawpage.c @@ -0,0 +1,232 @@ +/*------------------------------------------------------------------------- + * + * rawpage.c + * Functions to extract a raw page as bytea and inspect it + * + * Access-method specific inspection functions are in separate files. + * + * Copyright (c) 2007-2011, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/extension/pageinspect/rawpage.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "access/heapam.h" +#include "access/transam.h" +#include "catalog/catalog.h" +#include "catalog/namespace.h" +#include "catalog/pg_type.h" +#include "fmgr.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "storage/bufmgr.h" +#include "utils/builtins.h" + +PG_MODULE_MAGIC; + +Datum get_raw_page(PG_FUNCTION_ARGS); +Datum get_raw_page_fork(PG_FUNCTION_ARGS); +Datum page_header(PG_FUNCTION_ARGS); + +static bytea *get_raw_page_internal(text *relname, ForkNumber forknum, + BlockNumber blkno); + + +/* + * get_raw_page + * + * Returns a copy of a page from shared buffers as a bytea + */ +PG_FUNCTION_INFO_V1(get_raw_page); + +Datum +get_raw_page(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + uint32 blkno = PG_GETARG_UINT32(1); + bytea *raw_page; + + /* + * We don't normally bother to check the number of arguments to a C + * function, but here it's needed for safety because early 8.4 beta + * releases mistakenly redefined get_raw_page() as taking three arguments. + */ + if (PG_NARGS() != 2) + ereport(ERROR, + (errmsg("wrong number of arguments to get_raw_page()"), + errhint("Run the updated pageinspect.sql script."))); + + raw_page = get_raw_page_internal(relname, MAIN_FORKNUM, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * get_raw_page_fork + * + * Same, for any fork + */ +PG_FUNCTION_INFO_V1(get_raw_page_fork); + +Datum +get_raw_page_fork(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + text *forkname = PG_GETARG_TEXT_P(1); + uint32 blkno = PG_GETARG_UINT32(2); + bytea *raw_page; + ForkNumber forknum; + + forknum = forkname_to_number(text_to_cstring(forkname)); + + raw_page = get_raw_page_internal(relname, forknum, blkno); + + PG_RETURN_BYTEA_P(raw_page); +} + +/* + * workhorse + */ +static bytea * +get_raw_page_internal(text *relname, ForkNumber forknum, BlockNumber blkno) +{ + bytea *raw_page; + RangeVar *relrv; + Relation rel; + char *raw_page_data; + Buffer buf; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use raw functions")))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + /* Check that this relation has storage */ + if (rel->rd_rel->relkind == RELKIND_VIEW) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from view \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_COMPOSITE_TYPE) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from composite type \"%s\"", + RelationGetRelationName(rel)))); + if (rel->rd_rel->relkind == RELKIND_FOREIGN_TABLE) + ereport(ERROR, + (errcode(ERRCODE_WRONG_OBJECT_TYPE), + errmsg("cannot get raw page from foreign table \"%s\"", + RelationGetRelationName(rel)))); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + if (blkno >= RelationGetNumberOfBlocks(rel)) + elog(ERROR, "block number %u is out of range for relation \"%s\"", + blkno, RelationGetRelationName(rel)); + + /* Initialize buffer to copy to */ + raw_page = (bytea *) palloc(BLCKSZ + VARHDRSZ); + SET_VARSIZE(raw_page, BLCKSZ + VARHDRSZ); + raw_page_data = VARDATA(raw_page); + + /* Take a verbatim copy of the page */ + + buf = ReadBufferExtended(rel, forknum, blkno, RBM_NORMAL, NULL); + LockBuffer(buf, BUFFER_LOCK_SHARE); + + memcpy(raw_page_data, BufferGetPage(buf), BLCKSZ); + + LockBuffer(buf, BUFFER_LOCK_UNLOCK); + ReleaseBuffer(buf); + + relation_close(rel, AccessShareLock); + + return raw_page; +} + +/* + * page_header + * + * Allows inspection of page header fields of a raw page + */ + +PG_FUNCTION_INFO_V1(page_header); + +Datum +page_header(PG_FUNCTION_ARGS) +{ + bytea *raw_page = PG_GETARG_BYTEA_P(0); + int raw_page_size; + + TupleDesc tupdesc; + + Datum result; + HeapTuple tuple; + Datum values[9]; + bool nulls[9]; + + PageHeader page; + XLogRecPtr lsn; + char lsnchar[64]; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use raw page functions")))); + + raw_page_size = VARSIZE(raw_page) - VARHDRSZ; + + /* + * Check that enough data was supplied, so that we don't try to access + * fields outside the supplied buffer. + */ + if (raw_page_size < sizeof(PageHeaderData)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("input page too small (%d bytes)", raw_page_size))); + + page = (PageHeader) VARDATA(raw_page); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + /* Extract information from the page header */ + + lsn = PageGetLSN(page); + snprintf(lsnchar, sizeof(lsnchar), "%X/%X", lsn.xlogid, lsn.xrecoff); + + values[0] = CStringGetTextDatum(lsnchar); + values[1] = UInt16GetDatum(PageGetTLI(page)); + values[2] = UInt16GetDatum(page->pd_flags); + values[3] = UInt16GetDatum(page->pd_lower); + values[4] = UInt16GetDatum(page->pd_upper); + values[5] = UInt16GetDatum(page->pd_special); + values[6] = UInt16GetDatum(PageGetPageSize(page)); + values[7] = UInt16GetDatum(PageGetPageLayoutVersion(page)); + values[8] = TransactionIdGetDatum(page->pd_prune_xid); + + /* Build and return the tuple. */ + + memset(nulls, 0, sizeof(nulls)); + + tuple = heap_form_tuple(tupdesc, values, nulls); + result = HeapTupleGetDatum(tuple); + + PG_RETURN_DATUM(result); +} diff --git a/src/extension/pg_buffercache/Makefile b/src/extension/pg_buffercache/Makefile new file mode 100644 index 0000000..e361592 --- /dev/null +++ b/src/extension/pg_buffercache/Makefile @@ -0,0 +1,19 @@ +# src/extension/pg_buffercache/Makefile + +MODULE_big = pg_buffercache +OBJS = pg_buffercache_pages.o +MODULEDIR = extension + +EXTENSION = pg_buffercache +DATA = pg_buffercache--1.0.sql pg_buffercache--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pg_buffercache +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pg_buffercache/pg_buffercache--1.0.sql b/src/extension/pg_buffercache/pg_buffercache--1.0.sql new file mode 100644 index 0000000..ceca6ae --- /dev/null +++ b/src/extension/pg_buffercache/pg_buffercache--1.0.sql @@ -0,0 +1,17 @@ +/* src/extension/pg_buffercache/pg_buffercache--1.0.sql */ + +-- Register the function. +CREATE FUNCTION pg_buffercache_pages() +RETURNS SETOF RECORD +AS 'MODULE_PATHNAME', 'pg_buffercache_pages' +LANGUAGE C; + +-- Create a view for convenient access. +CREATE VIEW pg_buffercache AS + SELECT P.* FROM pg_buffercache_pages() AS P + (bufferid integer, relfilenode oid, reltablespace oid, reldatabase oid, + relforknumber int2, relblocknumber int8, isdirty bool, usagecount int2); + +-- Don't want these to be available to public. +REVOKE ALL ON FUNCTION pg_buffercache_pages() FROM PUBLIC; +REVOKE ALL ON pg_buffercache FROM PUBLIC; diff --git a/src/extension/pg_buffercache/pg_buffercache--unpackaged--1.0.sql b/src/extension/pg_buffercache/pg_buffercache--unpackaged--1.0.sql new file mode 100644 index 0000000..0cfa317 --- /dev/null +++ b/src/extension/pg_buffercache/pg_buffercache--unpackaged--1.0.sql @@ -0,0 +1,4 @@ +/* src/extension/pg_buffercache/pg_buffercache--unpackaged--1.0.sql */ + +ALTER EXTENSION pg_buffercache ADD function pg_buffercache_pages(); +ALTER EXTENSION pg_buffercache ADD view pg_buffercache; diff --git a/src/extension/pg_buffercache/pg_buffercache.control b/src/extension/pg_buffercache/pg_buffercache.control new file mode 100644 index 0000000..709513c --- /dev/null +++ b/src/extension/pg_buffercache/pg_buffercache.control @@ -0,0 +1,5 @@ +# pg_buffercache extension +comment = 'examine the shared buffer cache' +default_version = '1.0' +module_pathname = '$libdir/pg_buffercache' +relocatable = true diff --git a/src/extension/pg_buffercache/pg_buffercache_pages.c b/src/extension/pg_buffercache/pg_buffercache_pages.c new file mode 100644 index 0000000..a44610f --- /dev/null +++ b/src/extension/pg_buffercache/pg_buffercache_pages.c @@ -0,0 +1,219 @@ +/*------------------------------------------------------------------------- + * + * pg_buffercache_pages.c + * display some contents of the buffer cache + * + * src/extension/pg_buffercache/pg_buffercache_pages.c + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "access/heapam.h" +#include "catalog/pg_type.h" +#include "funcapi.h" +#include "storage/buf_internals.h" +#include "storage/bufmgr.h" +#include "utils/relcache.h" + + +#define NUM_BUFFERCACHE_PAGES_ELEM 8 + +PG_MODULE_MAGIC; + +Datum pg_buffercache_pages(PG_FUNCTION_ARGS); + + +/* + * Record structure holding the to be exposed cache data. + */ +typedef struct +{ + uint32 bufferid; + Oid relfilenode; + Oid reltablespace; + Oid reldatabase; + ForkNumber forknum; + BlockNumber blocknum; + bool isvalid; + bool isdirty; + uint16 usagecount; +} BufferCachePagesRec; + + +/* + * Function context for data persisting over repeated calls. + */ +typedef struct +{ + TupleDesc tupdesc; + BufferCachePagesRec *record; +} BufferCachePagesContext; + + +/* + * Function returning data from the shared buffer cache - buffer number, + * relation node/tablespace/database/blocknum and dirty indicator. + */ +PG_FUNCTION_INFO_V1(pg_buffercache_pages); + +Datum +pg_buffercache_pages(PG_FUNCTION_ARGS) +{ + FuncCallContext *funcctx; + Datum result; + MemoryContext oldcontext; + BufferCachePagesContext *fctx; /* User function context. */ + TupleDesc tupledesc; + HeapTuple tuple; + + if (SRF_IS_FIRSTCALL()) + { + int i; + volatile BufferDesc *bufHdr; + + funcctx = SRF_FIRSTCALL_INIT(); + + /* Switch context when allocating stuff to be used in later calls */ + oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx); + + /* Create a user function context for cross-call persistence */ + fctx = (BufferCachePagesContext *) palloc(sizeof(BufferCachePagesContext)); + + /* Construct a tuple descriptor for the result rows. */ + tupledesc = CreateTemplateTupleDesc(NUM_BUFFERCACHE_PAGES_ELEM, false); + TupleDescInitEntry(tupledesc, (AttrNumber) 1, "bufferid", + INT4OID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 2, "relfilenode", + OIDOID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 3, "reltablespace", + OIDOID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 4, "reldatabase", + OIDOID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 5, "relforknumber", + INT2OID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 6, "relblocknumber", + INT8OID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 7, "isdirty", + BOOLOID, -1, 0); + TupleDescInitEntry(tupledesc, (AttrNumber) 8, "usage_count", + INT2OID, -1, 0); + + fctx->tupdesc = BlessTupleDesc(tupledesc); + + /* Allocate NBuffers worth of BufferCachePagesRec records. */ + fctx->record = (BufferCachePagesRec *) palloc(sizeof(BufferCachePagesRec) * NBuffers); + + /* Set max calls and remember the user function context. */ + funcctx->max_calls = NBuffers; + funcctx->user_fctx = fctx; + + /* Return to original context when allocating transient memory */ + MemoryContextSwitchTo(oldcontext); + + /* + * To get a consistent picture of the buffer state, we must lock all + * partitions of the buffer map. Needless to say, this is horrible + * for concurrency. Must grab locks in increasing order to avoid + * possible deadlocks. + */ + for (i = 0; i < NUM_BUFFER_PARTITIONS; i++) + LWLockAcquire(FirstBufMappingLock + i, LW_SHARED); + + /* + * Scan though all the buffers, saving the relevant fields in the + * fctx->record structure. + */ + for (i = 0, bufHdr = BufferDescriptors; i < NBuffers; i++, bufHdr++) + { + /* Lock each buffer header before inspecting. */ + LockBufHdr(bufHdr); + + fctx->record[i].bufferid = BufferDescriptorGetBuffer(bufHdr); + fctx->record[i].relfilenode = bufHdr->tag.rnode.relNode; + fctx->record[i].reltablespace = bufHdr->tag.rnode.spcNode; + fctx->record[i].reldatabase = bufHdr->tag.rnode.dbNode; + fctx->record[i].forknum = bufHdr->tag.forkNum; + fctx->record[i].blocknum = bufHdr->tag.blockNum; + fctx->record[i].usagecount = bufHdr->usage_count; + + if (bufHdr->flags & BM_DIRTY) + fctx->record[i].isdirty = true; + else + fctx->record[i].isdirty = false; + + /* Note if the buffer is valid, and has storage created */ + if ((bufHdr->flags & BM_VALID) && (bufHdr->flags & BM_TAG_VALID)) + fctx->record[i].isvalid = true; + else + fctx->record[i].isvalid = false; + + UnlockBufHdr(bufHdr); + } + + /* + * And release locks. We do this in reverse order for two reasons: + * (1) Anyone else who needs more than one of the locks will be trying + * to lock them in increasing order; we don't want to release the + * other process until it can get all the locks it needs. (2) This + * avoids O(N^2) behavior inside LWLockRelease. + */ + for (i = NUM_BUFFER_PARTITIONS; --i >= 0;) + LWLockRelease(FirstBufMappingLock + i); + } + + funcctx = SRF_PERCALL_SETUP(); + + /* Get the saved state */ + fctx = funcctx->user_fctx; + + if (funcctx->call_cntr < funcctx->max_calls) + { + uint32 i = funcctx->call_cntr; + Datum values[NUM_BUFFERCACHE_PAGES_ELEM]; + bool nulls[NUM_BUFFERCACHE_PAGES_ELEM]; + + values[0] = Int32GetDatum(fctx->record[i].bufferid); + nulls[0] = false; + + /* + * Set all fields except the bufferid to null if the buffer is unused + * or not valid. + */ + if (fctx->record[i].blocknum == InvalidBlockNumber || + fctx->record[i].isvalid == false) + { + nulls[1] = true; + nulls[2] = true; + nulls[3] = true; + nulls[4] = true; + nulls[5] = true; + nulls[6] = true; + nulls[7] = true; + } + else + { + values[1] = ObjectIdGetDatum(fctx->record[i].relfilenode); + nulls[1] = false; + values[2] = ObjectIdGetDatum(fctx->record[i].reltablespace); + nulls[2] = false; + values[3] = ObjectIdGetDatum(fctx->record[i].reldatabase); + nulls[3] = false; + values[4] = ObjectIdGetDatum(fctx->record[i].forknum); + nulls[4] = false; + values[5] = Int64GetDatum((int64) fctx->record[i].blocknum); + nulls[5] = false; + values[6] = BoolGetDatum(fctx->record[i].isdirty); + nulls[6] = false; + values[7] = Int16GetDatum(fctx->record[i].usagecount); + nulls[7] = false; + } + + /* Build and return the tuple. */ + tuple = heap_form_tuple(fctx->tupdesc, values, nulls); + result = HeapTupleGetDatum(tuple); + + SRF_RETURN_NEXT(funcctx, result); + } + else + SRF_RETURN_DONE(funcctx); +} diff --git a/src/extension/pg_freespacemap/Makefile b/src/extension/pg_freespacemap/Makefile new file mode 100644 index 0000000..0ffe226 --- /dev/null +++ b/src/extension/pg_freespacemap/Makefile @@ -0,0 +1,19 @@ +# src/extensions/pg_freespacemap/Makefile + +MODULE_big = pg_freespacemap +OBJS = pg_freespacemap.o +MODULEDIR = extension + +EXTENSION = pg_freespacemap +DATA = pg_freespacemap--1.0.sql pg_freespacemap--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pg_freespacemap +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pg_freespacemap/pg_freespacemap--1.0.sql b/src/extension/pg_freespacemap/pg_freespacemap--1.0.sql new file mode 100644 index 0000000..8188786 --- /dev/null +++ b/src/extension/pg_freespacemap/pg_freespacemap--1.0.sql @@ -0,0 +1,22 @@ +/* src/extensions/pg_freespacemap/pg_freespacemap--1.0.sql */ + +-- Register the C function. +CREATE FUNCTION pg_freespace(regclass, bigint) +RETURNS int2 +AS 'MODULE_PATHNAME', 'pg_freespace' +LANGUAGE C STRICT; + +-- pg_freespace shows the recorded space avail at each block in a relation +CREATE FUNCTION + pg_freespace(rel regclass, blkno OUT bigint, avail OUT int2) +RETURNS SETOF RECORD +AS $$ + SELECT blkno, pg_freespace($1, blkno) AS avail + FROM generate_series(0, pg_relation_size($1) / current_setting('block_size')::bigint - 1) AS blkno; +$$ +LANGUAGE SQL; + + +-- Don't want these to be available to public. +REVOKE ALL ON FUNCTION pg_freespace(regclass, bigint) FROM PUBLIC; +REVOKE ALL ON FUNCTION pg_freespace(regclass) FROM PUBLIC; diff --git a/src/extension/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql b/src/extension/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql new file mode 100644 index 0000000..d2231ef --- /dev/null +++ b/src/extension/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql @@ -0,0 +1,4 @@ +/* src/extensions/pg_freespacemap/pg_freespacemap--unpackaged--1.0.sql */ + +ALTER EXTENSION pg_freespacemap ADD function pg_freespace(regclass,bigint); +ALTER EXTENSION pg_freespacemap ADD function pg_freespace(regclass); diff --git a/src/extension/pg_freespacemap/pg_freespacemap.c b/src/extension/pg_freespacemap/pg_freespacemap.c new file mode 100644 index 0000000..501da04 --- /dev/null +++ b/src/extension/pg_freespacemap/pg_freespacemap.c @@ -0,0 +1,46 @@ +/*------------------------------------------------------------------------- + * + * pg_freespacemap.c + * display contents of a free space map + * + * src/extensions/pg_freespacemap/pg_freespacemap.c + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "access/heapam.h" +#include "funcapi.h" +#include "storage/block.h" +#include "storage/freespace.h" + + +PG_MODULE_MAGIC; + +Datum pg_freespace(PG_FUNCTION_ARGS); + +/* + * Returns the amount of free space on a given page, according to the + * free space map. + */ +PG_FUNCTION_INFO_V1(pg_freespace); + +Datum +pg_freespace(PG_FUNCTION_ARGS) +{ + Oid relid = PG_GETARG_OID(0); + int64 blkno = PG_GETARG_INT64(1); + int16 freespace; + Relation rel; + + rel = relation_open(relid, AccessShareLock); + + if (blkno < 0 || blkno > MaxBlockNumber) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("invalid block number"))); + + freespace = GetRecordedFreeSpace(rel, blkno); + + relation_close(rel, AccessShareLock); + PG_RETURN_INT16(freespace); +} diff --git a/src/extension/pg_freespacemap/pg_freespacemap.control b/src/extension/pg_freespacemap/pg_freespacemap.control new file mode 100644 index 0000000..34b695f --- /dev/null +++ b/src/extension/pg_freespacemap/pg_freespacemap.control @@ -0,0 +1,5 @@ +# pg_freespacemap extension +comment = 'examine the free space map (FSM)' +default_version = '1.0' +module_pathname = '$libdir/pg_freespacemap' +relocatable = true diff --git a/src/extension/pg_stat_statements/Makefile b/src/extension/pg_stat_statements/Makefile new file mode 100644 index 0000000..9cf3f99 --- /dev/null +++ b/src/extension/pg_stat_statements/Makefile @@ -0,0 +1,19 @@ +# src/extension/pg_stat_statements/Makefile + +MODULE_big = pg_stat_statements +OBJS = pg_stat_statements.o +MODULEDIR = extension + +EXTENSION = pg_stat_statements +DATA = pg_stat_statements--1.0.sql pg_stat_statements--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pg_stat_statements +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pg_stat_statements/pg_stat_statements--1.0.sql b/src/extension/pg_stat_statements/pg_stat_statements--1.0.sql new file mode 100644 index 0000000..41145e7 --- /dev/null +++ b/src/extension/pg_stat_statements/pg_stat_statements--1.0.sql @@ -0,0 +1,36 @@ +/* src/extension/pg_stat_statements/pg_stat_statements--1.0.sql */ + +-- Register functions. +CREATE FUNCTION pg_stat_statements_reset() +RETURNS void +AS 'MODULE_PATHNAME' +LANGUAGE C; + +CREATE FUNCTION pg_stat_statements( + OUT userid oid, + OUT dbid oid, + OUT query text, + OUT calls int8, + OUT total_time float8, + OUT rows int8, + OUT shared_blks_hit int8, + OUT shared_blks_read int8, + OUT shared_blks_written int8, + OUT local_blks_hit int8, + OUT local_blks_read int8, + OUT local_blks_written int8, + OUT temp_blks_read int8, + OUT temp_blks_written int8 +) +RETURNS SETOF record +AS 'MODULE_PATHNAME' +LANGUAGE C; + +-- Register a view on the function for ease of use. +CREATE VIEW pg_stat_statements AS + SELECT * FROM pg_stat_statements(); + +GRANT SELECT ON pg_stat_statements TO PUBLIC; + +-- Don't want this to be available to non-superusers. +REVOKE ALL ON FUNCTION pg_stat_statements_reset() FROM PUBLIC; diff --git a/src/extension/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql b/src/extension/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql new file mode 100644 index 0000000..c8993b5 --- /dev/null +++ b/src/extension/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql @@ -0,0 +1,5 @@ +/* src/extension/pg_stat_statements/pg_stat_statements--unpackaged--1.0.sql */ + +ALTER EXTENSION pg_stat_statements ADD function pg_stat_statements_reset(); +ALTER EXTENSION pg_stat_statements ADD function pg_stat_statements(); +ALTER EXTENSION pg_stat_statements ADD view pg_stat_statements; diff --git a/src/extension/pg_stat_statements/pg_stat_statements.c b/src/extension/pg_stat_statements/pg_stat_statements.c new file mode 100644 index 0000000..4ecd445 --- /dev/null +++ b/src/extension/pg_stat_statements/pg_stat_statements.c @@ -0,0 +1,1046 @@ +/*------------------------------------------------------------------------- + * + * pg_stat_statements.c + * Track statement execution times across a whole database cluster. + * + * Note about locking issues: to create or delete an entry in the shared + * hashtable, one must hold pgss->lock exclusively. Modifying any field + * in an entry except the counters requires the same. To look up an entry, + * one must hold the lock shared. To read or update the counters within + * an entry, one must hold the lock shared or exclusive (so the entry doesn't + * disappear!) and also take the entry's mutex spinlock. + * + * + * Copyright (c) 2008-2011, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/test/pg_stat_statements/pg_stat_statements.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include + +#include "access/hash.h" +#include "catalog/pg_type.h" +#include "executor/executor.h" +#include "executor/instrument.h" +#include "funcapi.h" +#include "mb/pg_wchar.h" +#include "miscadmin.h" +#include "pgstat.h" +#include "storage/fd.h" +#include "storage/ipc.h" +#include "storage/spin.h" +#include "tcop/utility.h" +#include "utils/builtins.h" +#include "utils/hsearch.h" +#include "utils/guc.h" + + +PG_MODULE_MAGIC; + +/* Location of stats file */ +#define PGSS_DUMP_FILE "global/pg_stat_statements.stat" + +/* This constant defines the magic number in the stats file header */ +static const uint32 PGSS_FILE_HEADER = 0x20100108; + +/* XXX: Should USAGE_EXEC reflect execution time and/or buffer usage? */ +#define USAGE_EXEC(duration) (1.0) +#define USAGE_INIT (1.0) /* including initial planning */ +#define USAGE_DECREASE_FACTOR (0.99) /* decreased every entry_dealloc */ +#define USAGE_DEALLOC_PERCENT 5 /* free this % of entries at once */ + +/* + * Hashtable key that defines the identity of a hashtable entry. The + * hash comparators do not assume that the query string is null-terminated; + * this lets us search for an mbcliplen'd string without copying it first. + * + * Presently, the query encoding is fully determined by the source database + * and so we don't really need it to be in the key. But that might not always + * be true. Anyway it's notationally convenient to pass it as part of the key. + */ +typedef struct pgssHashKey +{ + Oid userid; /* user OID */ + Oid dbid; /* database OID */ + int encoding; /* query encoding */ + int query_len; /* # of valid bytes in query string */ + const char *query_ptr; /* query string proper */ +} pgssHashKey; + +/* + * The actual stats counters kept within pgssEntry. + */ +typedef struct Counters +{ + int64 calls; /* # of times executed */ + double total_time; /* total execution time in seconds */ + int64 rows; /* total # of retrieved or affected rows */ + int64 shared_blks_hit; /* # of shared buffer hits */ + int64 shared_blks_read; /* # of shared disk blocks read */ + int64 shared_blks_written; /* # of shared disk blocks written */ + int64 local_blks_hit; /* # of local buffer hits */ + int64 local_blks_read; /* # of local disk blocks read */ + int64 local_blks_written; /* # of local disk blocks written */ + int64 temp_blks_read; /* # of temp blocks read */ + int64 temp_blks_written; /* # of temp blocks written */ + double usage; /* usage factor */ +} Counters; + +/* + * Statistics per statement + * + * NB: see the file read/write code before changing field order here. + */ +typedef struct pgssEntry +{ + pgssHashKey key; /* hash key of entry - MUST BE FIRST */ + Counters counters; /* the statistics for this query */ + slock_t mutex; /* protects the counters only */ + char query[1]; /* VARIABLE LENGTH ARRAY - MUST BE LAST */ + /* Note: the allocated length of query[] is actually pgss->query_size */ +} pgssEntry; + +/* + * Global shared state + */ +typedef struct pgssSharedState +{ + LWLockId lock; /* protects hashtable search/modification */ + int query_size; /* max query length in bytes */ +} pgssSharedState; + +/*---- Local variables ----*/ + +/* Current nesting depth of ExecutorRun calls */ +static int nested_level = 0; + +/* Saved hook values in case of unload */ +static shmem_startup_hook_type prev_shmem_startup_hook = NULL; +static ExecutorStart_hook_type prev_ExecutorStart = NULL; +static ExecutorRun_hook_type prev_ExecutorRun = NULL; +static ExecutorFinish_hook_type prev_ExecutorFinish = NULL; +static ExecutorEnd_hook_type prev_ExecutorEnd = NULL; +static ProcessUtility_hook_type prev_ProcessUtility = NULL; + +/* Links to shared memory state */ +static pgssSharedState *pgss = NULL; +static HTAB *pgss_hash = NULL; + +/*---- GUC variables ----*/ + +typedef enum +{ + PGSS_TRACK_NONE, /* track no statements */ + PGSS_TRACK_TOP, /* only top level statements */ + PGSS_TRACK_ALL /* all statements, including nested ones */ +} PGSSTrackLevel; + +static const struct config_enum_entry track_options[] = +{ + {"none", PGSS_TRACK_NONE, false}, + {"top", PGSS_TRACK_TOP, false}, + {"all", PGSS_TRACK_ALL, false}, + {NULL, 0, false} +}; + +static int pgss_max; /* max # statements to track */ +static int pgss_track; /* tracking level */ +static bool pgss_track_utility; /* whether to track utility commands */ +static bool pgss_save; /* whether to save stats across shutdown */ + + +#define pgss_enabled() \ + (pgss_track == PGSS_TRACK_ALL || \ + (pgss_track == PGSS_TRACK_TOP && nested_level == 0)) + +/*---- Function declarations ----*/ + +void _PG_init(void); +void _PG_fini(void); + +Datum pg_stat_statements_reset(PG_FUNCTION_ARGS); +Datum pg_stat_statements(PG_FUNCTION_ARGS); + +PG_FUNCTION_INFO_V1(pg_stat_statements_reset); +PG_FUNCTION_INFO_V1(pg_stat_statements); + +static void pgss_shmem_startup(void); +static void pgss_shmem_shutdown(int code, Datum arg); +static void pgss_ExecutorStart(QueryDesc *queryDesc, int eflags); +static void pgss_ExecutorRun(QueryDesc *queryDesc, + ScanDirection direction, + long count); +static void pgss_ExecutorFinish(QueryDesc *queryDesc); +static void pgss_ExecutorEnd(QueryDesc *queryDesc); +static void pgss_ProcessUtility(Node *parsetree, + const char *queryString, ParamListInfo params, bool isTopLevel, + DestReceiver *dest, char *completionTag); +static uint32 pgss_hash_fn(const void *key, Size keysize); +static int pgss_match_fn(const void *key1, const void *key2, Size keysize); +static void pgss_store(const char *query, double total_time, uint64 rows, + const BufferUsage *bufusage); +static Size pgss_memsize(void); +static pgssEntry *entry_alloc(pgssHashKey *key); +static void entry_dealloc(void); +static void entry_reset(void); + + +/* + * Module load callback + */ +void +_PG_init(void) +{ + /* + * In order to create our shared memory area, we have to be loaded via + * shared_preload_libraries. If not, fall out without hooking into any of + * the main system. (We don't throw error here because it seems useful to + * allow the pg_stat_statements functions to be created even when the + * module isn't active. The functions must protect themselves against + * being called then, however.) + */ + if (!process_shared_preload_libraries_in_progress) + return; + + /* + * Define (or redefine) custom GUC variables. + */ + DefineCustomIntVariable("pg_stat_statements.max", + "Sets the maximum number of statements tracked by pg_stat_statements.", + NULL, + &pgss_max, + 1000, + 100, + INT_MAX, + PGC_POSTMASTER, + 0, + NULL, + NULL, + NULL); + + DefineCustomEnumVariable("pg_stat_statements.track", + "Selects which statements are tracked by pg_stat_statements.", + NULL, + &pgss_track, + PGSS_TRACK_TOP, + track_options, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("pg_stat_statements.track_utility", + "Selects whether utility commands are tracked by pg_stat_statements.", + NULL, + &pgss_track_utility, + true, + PGC_SUSET, + 0, + NULL, + NULL, + NULL); + + DefineCustomBoolVariable("pg_stat_statements.save", + "Save pg_stat_statements statistics across server shutdowns.", + NULL, + &pgss_save, + true, + PGC_SIGHUP, + 0, + NULL, + NULL, + NULL); + + EmitWarningsOnPlaceholders("pg_stat_statements"); + + /* + * Request additional shared resources. (These are no-ops if we're not in + * the postmaster process.) We'll allocate or attach to the shared + * resources in pgss_shmem_startup(). + */ + RequestAddinShmemSpace(pgss_memsize()); + RequestAddinLWLocks(1); + + /* + * Install hooks. + */ + prev_shmem_startup_hook = shmem_startup_hook; + shmem_startup_hook = pgss_shmem_startup; + prev_ExecutorStart = ExecutorStart_hook; + ExecutorStart_hook = pgss_ExecutorStart; + prev_ExecutorRun = ExecutorRun_hook; + ExecutorRun_hook = pgss_ExecutorRun; + prev_ExecutorFinish = ExecutorFinish_hook; + ExecutorFinish_hook = pgss_ExecutorFinish; + prev_ExecutorEnd = ExecutorEnd_hook; + ExecutorEnd_hook = pgss_ExecutorEnd; + prev_ProcessUtility = ProcessUtility_hook; + ProcessUtility_hook = pgss_ProcessUtility; +} + +/* + * Module unload callback + */ +void +_PG_fini(void) +{ + /* Uninstall hooks. */ + shmem_startup_hook = prev_shmem_startup_hook; + ExecutorStart_hook = prev_ExecutorStart; + ExecutorRun_hook = prev_ExecutorRun; + ExecutorFinish_hook = prev_ExecutorFinish; + ExecutorEnd_hook = prev_ExecutorEnd; + ProcessUtility_hook = prev_ProcessUtility; +} + +/* + * shmem_startup hook: allocate or attach to shared memory, + * then load any pre-existing statistics from file. + */ +static void +pgss_shmem_startup(void) +{ + bool found; + HASHCTL info; + FILE *file; + uint32 header; + int32 num; + int32 i; + int query_size; + int buffer_size; + char *buffer = NULL; + + if (prev_shmem_startup_hook) + prev_shmem_startup_hook(); + + /* reset in case this is a restart within the postmaster */ + pgss = NULL; + pgss_hash = NULL; + + /* + * Create or attach to the shared memory state, including hash table + */ + LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE); + + pgss = ShmemInitStruct("pg_stat_statements", + sizeof(pgssSharedState), + &found); + + if (!found) + { + /* First time through ... */ + pgss->lock = LWLockAssign(); + pgss->query_size = pgstat_track_activity_query_size; + } + + /* Be sure everyone agrees on the hash table entry size */ + query_size = pgss->query_size; + + memset(&info, 0, sizeof(info)); + info.keysize = sizeof(pgssHashKey); + info.entrysize = offsetof(pgssEntry, query) +query_size; + info.hash = pgss_hash_fn; + info.match = pgss_match_fn; + pgss_hash = ShmemInitHash("pg_stat_statements hash", + pgss_max, pgss_max, + &info, + HASH_ELEM | HASH_FUNCTION | HASH_COMPARE); + + LWLockRelease(AddinShmemInitLock); + + /* + * If we're in the postmaster (or a standalone backend...), set up a shmem + * exit hook to dump the statistics to disk. + */ + if (!IsUnderPostmaster) + on_shmem_exit(pgss_shmem_shutdown, (Datum) 0); + + /* + * Attempt to load old statistics from the dump file, if this is the first + * time through and we weren't told not to. + */ + if (found || !pgss_save) + return; + + /* + * Note: we don't bother with locks here, because there should be no other + * processes running when this code is reached. + */ + file = AllocateFile(PGSS_DUMP_FILE, PG_BINARY_R); + if (file == NULL) + { + if (errno == ENOENT) + return; /* ignore not-found error */ + goto error; + } + + buffer_size = query_size; + buffer = (char *) palloc(buffer_size); + + if (fread(&header, sizeof(uint32), 1, file) != 1 || + header != PGSS_FILE_HEADER || + fread(&num, sizeof(int32), 1, file) != 1) + goto error; + + for (i = 0; i < num; i++) + { + pgssEntry temp; + pgssEntry *entry; + + if (fread(&temp, offsetof(pgssEntry, mutex), 1, file) != 1) + goto error; + + /* Encoding is the only field we can easily sanity-check */ + if (!PG_VALID_BE_ENCODING(temp.key.encoding)) + goto error; + + /* Previous incarnation might have had a larger query_size */ + if (temp.key.query_len >= buffer_size) + { + buffer = (char *) repalloc(buffer, temp.key.query_len + 1); + buffer_size = temp.key.query_len + 1; + } + + if (fread(buffer, 1, temp.key.query_len, file) != temp.key.query_len) + goto error; + buffer[temp.key.query_len] = '\0'; + + /* Clip to available length if needed */ + if (temp.key.query_len >= query_size) + temp.key.query_len = pg_encoding_mbcliplen(temp.key.encoding, + buffer, + temp.key.query_len, + query_size - 1); + temp.key.query_ptr = buffer; + + /* make the hashtable entry (discards old entries if too many) */ + entry = entry_alloc(&temp.key); + + /* copy in the actual stats */ + entry->counters = temp.counters; + } + + pfree(buffer); + FreeFile(file); + return; + +error: + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not read pg_stat_statement file \"%s\": %m", + PGSS_DUMP_FILE))); + if (buffer) + pfree(buffer); + if (file) + FreeFile(file); + /* If possible, throw away the bogus file; ignore any error */ + unlink(PGSS_DUMP_FILE); +} + +/* + * shmem_shutdown hook: Dump statistics into file. + * + * Note: we don't bother with acquiring lock, because there should be no + * other processes running when this is called. + */ +static void +pgss_shmem_shutdown(int code, Datum arg) +{ + FILE *file; + HASH_SEQ_STATUS hash_seq; + int32 num_entries; + pgssEntry *entry; + + /* Don't try to dump during a crash. */ + if (code) + return; + + /* Safety check ... shouldn't get here unless shmem is set up. */ + if (!pgss || !pgss_hash) + return; + + /* Don't dump if told not to. */ + if (!pgss_save) + return; + + file = AllocateFile(PGSS_DUMP_FILE, PG_BINARY_W); + if (file == NULL) + goto error; + + if (fwrite(&PGSS_FILE_HEADER, sizeof(uint32), 1, file) != 1) + goto error; + num_entries = hash_get_num_entries(pgss_hash); + if (fwrite(&num_entries, sizeof(int32), 1, file) != 1) + goto error; + + hash_seq_init(&hash_seq, pgss_hash); + while ((entry = hash_seq_search(&hash_seq)) != NULL) + { + int len = entry->key.query_len; + + if (fwrite(entry, offsetof(pgssEntry, mutex), 1, file) != 1 || + fwrite(entry->query, 1, len, file) != len) + goto error; + } + + if (FreeFile(file)) + { + file = NULL; + goto error; + } + + return; + +error: + ereport(LOG, + (errcode_for_file_access(), + errmsg("could not write pg_stat_statement file \"%s\": %m", + PGSS_DUMP_FILE))); + if (file) + FreeFile(file); + unlink(PGSS_DUMP_FILE); +} + +/* + * ExecutorStart hook: start up tracking if needed + */ +static void +pgss_ExecutorStart(QueryDesc *queryDesc, int eflags) +{ + if (prev_ExecutorStart) + prev_ExecutorStart(queryDesc, eflags); + else + standard_ExecutorStart(queryDesc, eflags); + + if (pgss_enabled()) + { + /* + * Set up to track total elapsed time in ExecutorRun. Make sure the + * space is allocated in the per-query context so it will go away at + * ExecutorEnd. + */ + if (queryDesc->totaltime == NULL) + { + MemoryContext oldcxt; + + oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt); + queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL); + MemoryContextSwitchTo(oldcxt); + } + } +} + +/* + * ExecutorRun hook: all we need do is track nesting depth + */ +static void +pgss_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, long count) +{ + nested_level++; + PG_TRY(); + { + if (prev_ExecutorRun) + prev_ExecutorRun(queryDesc, direction, count); + else + standard_ExecutorRun(queryDesc, direction, count); + nested_level--; + } + PG_CATCH(); + { + nested_level--; + PG_RE_THROW(); + } + PG_END_TRY(); +} + +/* + * ExecutorFinish hook: all we need do is track nesting depth + */ +static void +pgss_ExecutorFinish(QueryDesc *queryDesc) +{ + nested_level++; + PG_TRY(); + { + if (prev_ExecutorFinish) + prev_ExecutorFinish(queryDesc); + else + standard_ExecutorFinish(queryDesc); + nested_level--; + } + PG_CATCH(); + { + nested_level--; + PG_RE_THROW(); + } + PG_END_TRY(); +} + +/* + * ExecutorEnd hook: store results if needed + */ +static void +pgss_ExecutorEnd(QueryDesc *queryDesc) +{ + if (queryDesc->totaltime && pgss_enabled()) + { + /* + * Make sure stats accumulation is done. (Note: it's okay if several + * levels of hook all do this.) + */ + InstrEndLoop(queryDesc->totaltime); + + pgss_store(queryDesc->sourceText, + queryDesc->totaltime->total, + queryDesc->estate->es_processed, + &queryDesc->totaltime->bufusage); + } + + if (prev_ExecutorEnd) + prev_ExecutorEnd(queryDesc); + else + standard_ExecutorEnd(queryDesc); +} + +/* + * ProcessUtility hook + */ +static void +pgss_ProcessUtility(Node *parsetree, const char *queryString, + ParamListInfo params, bool isTopLevel, + DestReceiver *dest, char *completionTag) +{ + if (pgss_track_utility && pgss_enabled()) + { + instr_time start; + instr_time duration; + uint64 rows = 0; + BufferUsage bufusage; + + bufusage = pgBufferUsage; + INSTR_TIME_SET_CURRENT(start); + + nested_level++; + PG_TRY(); + { + if (prev_ProcessUtility) + prev_ProcessUtility(parsetree, queryString, params, + isTopLevel, dest, completionTag); + else + standard_ProcessUtility(parsetree, queryString, params, + isTopLevel, dest, completionTag); + nested_level--; + } + PG_CATCH(); + { + nested_level--; + PG_RE_THROW(); + } + PG_END_TRY(); + + INSTR_TIME_SET_CURRENT(duration); + INSTR_TIME_SUBTRACT(duration, start); + + /* parse command tag to retrieve the number of affected rows. */ + if (completionTag && + sscanf(completionTag, "COPY " UINT64_FORMAT, &rows) != 1) + rows = 0; + + /* calc differences of buffer counters. */ + bufusage.shared_blks_hit = + pgBufferUsage.shared_blks_hit - bufusage.shared_blks_hit; + bufusage.shared_blks_read = + pgBufferUsage.shared_blks_read - bufusage.shared_blks_read; + bufusage.shared_blks_written = + pgBufferUsage.shared_blks_written - bufusage.shared_blks_written; + bufusage.local_blks_hit = + pgBufferUsage.local_blks_hit - bufusage.local_blks_hit; + bufusage.local_blks_read = + pgBufferUsage.local_blks_read - bufusage.local_blks_read; + bufusage.local_blks_written = + pgBufferUsage.local_blks_written - bufusage.local_blks_written; + bufusage.temp_blks_read = + pgBufferUsage.temp_blks_read - bufusage.temp_blks_read; + bufusage.temp_blks_written = + pgBufferUsage.temp_blks_written - bufusage.temp_blks_written; + + pgss_store(queryString, INSTR_TIME_GET_DOUBLE(duration), rows, + &bufusage); + } + else + { + if (prev_ProcessUtility) + prev_ProcessUtility(parsetree, queryString, params, + isTopLevel, dest, completionTag); + else + standard_ProcessUtility(parsetree, queryString, params, + isTopLevel, dest, completionTag); + } +} + +/* + * Calculate hash value for a key + */ +static uint32 +pgss_hash_fn(const void *key, Size keysize) +{ + const pgssHashKey *k = (const pgssHashKey *) key; + + /* we don't bother to include encoding in the hash */ + return hash_uint32((uint32) k->userid) ^ + hash_uint32((uint32) k->dbid) ^ + DatumGetUInt32(hash_any((const unsigned char *) k->query_ptr, + k->query_len)); +} + +/* + * Compare two keys - zero means match + */ +static int +pgss_match_fn(const void *key1, const void *key2, Size keysize) +{ + const pgssHashKey *k1 = (const pgssHashKey *) key1; + const pgssHashKey *k2 = (const pgssHashKey *) key2; + + if (k1->userid == k2->userid && + k1->dbid == k2->dbid && + k1->encoding == k2->encoding && + k1->query_len == k2->query_len && + memcmp(k1->query_ptr, k2->query_ptr, k1->query_len) == 0) + return 0; + else + return 1; +} + +/* + * Store some statistics for a statement. + */ +static void +pgss_store(const char *query, double total_time, uint64 rows, + const BufferUsage *bufusage) +{ + pgssHashKey key; + double usage; + pgssEntry *entry; + + Assert(query != NULL); + + /* Safety check... */ + if (!pgss || !pgss_hash) + return; + + /* Set up key for hashtable search */ + key.userid = GetUserId(); + key.dbid = MyDatabaseId; + key.encoding = GetDatabaseEncoding(); + key.query_len = strlen(query); + if (key.query_len >= pgss->query_size) + key.query_len = pg_encoding_mbcliplen(key.encoding, + query, + key.query_len, + pgss->query_size - 1); + key.query_ptr = query; + + usage = USAGE_EXEC(duration); + + /* Lookup the hash table entry with shared lock. */ + LWLockAcquire(pgss->lock, LW_SHARED); + + entry = (pgssEntry *) hash_search(pgss_hash, &key, HASH_FIND, NULL); + if (!entry) + { + /* Must acquire exclusive lock to add a new entry. */ + LWLockRelease(pgss->lock); + LWLockAcquire(pgss->lock, LW_EXCLUSIVE); + entry = entry_alloc(&key); + } + + /* Grab the spinlock while updating the counters. */ + { + volatile pgssEntry *e = (volatile pgssEntry *) entry; + + SpinLockAcquire(&e->mutex); + e->counters.calls += 1; + e->counters.total_time += total_time; + e->counters.rows += rows; + e->counters.shared_blks_hit += bufusage->shared_blks_hit; + e->counters.shared_blks_read += bufusage->shared_blks_read; + e->counters.shared_blks_written += bufusage->shared_blks_written; + e->counters.local_blks_hit += bufusage->local_blks_hit; + e->counters.local_blks_read += bufusage->local_blks_read; + e->counters.local_blks_written += bufusage->local_blks_written; + e->counters.temp_blks_read += bufusage->temp_blks_read; + e->counters.temp_blks_written += bufusage->temp_blks_written; + e->counters.usage += usage; + SpinLockRelease(&e->mutex); + } + + LWLockRelease(pgss->lock); +} + +/* + * Reset all statement statistics. + */ +Datum +pg_stat_statements_reset(PG_FUNCTION_ARGS) +{ + if (!pgss || !pgss_hash) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("pg_stat_statements must be loaded via shared_preload_libraries"))); + entry_reset(); + PG_RETURN_VOID(); +} + +#define PG_STAT_STATEMENTS_COLS 14 + +/* + * Retrieve statement statistics. + */ +Datum +pg_stat_statements(PG_FUNCTION_ARGS) +{ + ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; + TupleDesc tupdesc; + Tuplestorestate *tupstore; + MemoryContext per_query_ctx; + MemoryContext oldcontext; + Oid userid = GetUserId(); + bool is_superuser = superuser(); + HASH_SEQ_STATUS hash_seq; + pgssEntry *entry; + + if (!pgss || !pgss_hash) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("pg_stat_statements must be loaded via shared_preload_libraries"))); + + /* check to see if caller supports us returning a tuplestore */ + if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("set-valued function called in context that cannot accept a set"))); + if (!(rsinfo->allowedModes & SFRM_Materialize)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("materialize mode required, but it is not " \ + "allowed in this context"))); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + per_query_ctx = rsinfo->econtext->ecxt_per_query_memory; + oldcontext = MemoryContextSwitchTo(per_query_ctx); + + tupstore = tuplestore_begin_heap(true, false, work_mem); + rsinfo->returnMode = SFRM_Materialize; + rsinfo->setResult = tupstore; + rsinfo->setDesc = tupdesc; + + MemoryContextSwitchTo(oldcontext); + + LWLockAcquire(pgss->lock, LW_SHARED); + + hash_seq_init(&hash_seq, pgss_hash); + while ((entry = hash_seq_search(&hash_seq)) != NULL) + { + Datum values[PG_STAT_STATEMENTS_COLS]; + bool nulls[PG_STAT_STATEMENTS_COLS]; + int i = 0; + Counters tmp; + + memset(values, 0, sizeof(values)); + memset(nulls, 0, sizeof(nulls)); + + values[i++] = ObjectIdGetDatum(entry->key.userid); + values[i++] = ObjectIdGetDatum(entry->key.dbid); + + if (is_superuser || entry->key.userid == userid) + { + char *qstr; + + qstr = (char *) + pg_do_encoding_conversion((unsigned char *) entry->query, + entry->key.query_len, + entry->key.encoding, + GetDatabaseEncoding()); + values[i++] = CStringGetTextDatum(qstr); + if (qstr != entry->query) + pfree(qstr); + } + else + values[i++] = CStringGetTextDatum(""); + + /* copy counters to a local variable to keep locking time short */ + { + volatile pgssEntry *e = (volatile pgssEntry *) entry; + + SpinLockAcquire(&e->mutex); + tmp = e->counters; + SpinLockRelease(&e->mutex); + } + + values[i++] = Int64GetDatumFast(tmp.calls); + values[i++] = Float8GetDatumFast(tmp.total_time); + values[i++] = Int64GetDatumFast(tmp.rows); + values[i++] = Int64GetDatumFast(tmp.shared_blks_hit); + values[i++] = Int64GetDatumFast(tmp.shared_blks_read); + values[i++] = Int64GetDatumFast(tmp.shared_blks_written); + values[i++] = Int64GetDatumFast(tmp.local_blks_hit); + values[i++] = Int64GetDatumFast(tmp.local_blks_read); + values[i++] = Int64GetDatumFast(tmp.local_blks_written); + values[i++] = Int64GetDatumFast(tmp.temp_blks_read); + values[i++] = Int64GetDatumFast(tmp.temp_blks_written); + + Assert(i == PG_STAT_STATEMENTS_COLS); + + tuplestore_putvalues(tupstore, tupdesc, values, nulls); + } + + LWLockRelease(pgss->lock); + + /* clean up and return the tuplestore */ + tuplestore_donestoring(tupstore); + + return (Datum) 0; +} + +/* + * Estimate shared memory space needed. + */ +static Size +pgss_memsize(void) +{ + Size size; + Size entrysize; + + size = MAXALIGN(sizeof(pgssSharedState)); + entrysize = offsetof(pgssEntry, query) +pgstat_track_activity_query_size; + size = add_size(size, hash_estimate_size(pgss_max, entrysize)); + + return size; +} + +/* + * Allocate a new hashtable entry. + * caller must hold an exclusive lock on pgss->lock + * + * Note: despite needing exclusive lock, it's not an error for the target + * entry to already exist. This is because pgss_store releases and + * reacquires lock after failing to find a match; so someone else could + * have made the entry while we waited to get exclusive lock. + */ +static pgssEntry * +entry_alloc(pgssHashKey *key) +{ + pgssEntry *entry; + bool found; + + /* Caller must have clipped query properly */ + Assert(key->query_len < pgss->query_size); + + /* Make space if needed */ + while (hash_get_num_entries(pgss_hash) >= pgss_max) + entry_dealloc(); + + /* Find or create an entry with desired hash code */ + entry = (pgssEntry *) hash_search(pgss_hash, key, HASH_ENTER, &found); + + if (!found) + { + /* New entry, initialize it */ + + /* dynahash tried to copy the key for us, but must fix query_ptr */ + entry->key.query_ptr = entry->query; + /* reset the statistics */ + memset(&entry->counters, 0, sizeof(Counters)); + entry->counters.usage = USAGE_INIT; + /* re-initialize the mutex each time ... we assume no one using it */ + SpinLockInit(&entry->mutex); + /* ... and don't forget the query text */ + memcpy(entry->query, key->query_ptr, key->query_len); + entry->query[key->query_len] = '\0'; + } + + return entry; +} + +/* + * qsort comparator for sorting into increasing usage order + */ +static int +entry_cmp(const void *lhs, const void *rhs) +{ + double l_usage = (*(const pgssEntry **) lhs)->counters.usage; + double r_usage = (*(const pgssEntry **) rhs)->counters.usage; + + if (l_usage < r_usage) + return -1; + else if (l_usage > r_usage) + return +1; + else + return 0; +} + +/* + * Deallocate least used entries. + * Caller must hold an exclusive lock on pgss->lock. + */ +static void +entry_dealloc(void) +{ + HASH_SEQ_STATUS hash_seq; + pgssEntry **entries; + pgssEntry *entry; + int nvictims; + int i; + + /* Sort entries by usage and deallocate USAGE_DEALLOC_PERCENT of them. */ + + entries = palloc(hash_get_num_entries(pgss_hash) * sizeof(pgssEntry *)); + + i = 0; + hash_seq_init(&hash_seq, pgss_hash); + while ((entry = hash_seq_search(&hash_seq)) != NULL) + { + entries[i++] = entry; + entry->counters.usage *= USAGE_DECREASE_FACTOR; + } + + qsort(entries, i, sizeof(pgssEntry *), entry_cmp); + nvictims = Max(10, i * USAGE_DEALLOC_PERCENT / 100); + nvictims = Min(nvictims, i); + + for (i = 0; i < nvictims; i++) + { + hash_search(pgss_hash, &entries[i]->key, HASH_REMOVE, NULL); + } + + pfree(entries); +} + +/* + * Release all entries. + */ +static void +entry_reset(void) +{ + HASH_SEQ_STATUS hash_seq; + pgssEntry *entry; + + LWLockAcquire(pgss->lock, LW_EXCLUSIVE); + + hash_seq_init(&hash_seq, pgss_hash); + while ((entry = hash_seq_search(&hash_seq)) != NULL) + { + hash_search(pgss_hash, &entry->key, HASH_REMOVE, NULL); + } + + LWLockRelease(pgss->lock); +} diff --git a/src/extension/pg_stat_statements/pg_stat_statements.control b/src/extension/pg_stat_statements/pg_stat_statements.control new file mode 100644 index 0000000..6f9a947 --- /dev/null +++ b/src/extension/pg_stat_statements/pg_stat_statements.control @@ -0,0 +1,5 @@ +# pg_stat_statements extension +comment = 'track execution statistics of all SQL statements executed' +default_version = '1.0' +module_pathname = '$libdir/pg_stat_statements' +relocatable = true diff --git a/src/extension/pgrowlocks/Makefile b/src/extension/pgrowlocks/Makefile new file mode 100644 index 0000000..a4191fb --- /dev/null +++ b/src/extension/pgrowlocks/Makefile @@ -0,0 +1,19 @@ +# contrib/pgrowlocks/Makefile + +MODULE_big = pgrowlocks +OBJS = pgrowlocks.o +MODULEDIR = extension + +EXTENSION = pgrowlocks +DATA = pgrowlocks--1.0.sql pgrowlocks--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pgrowlocks +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pgrowlocks/pgrowlocks--1.0.sql b/src/extension/pgrowlocks/pgrowlocks--1.0.sql new file mode 100644 index 0000000..0b60fdc --- /dev/null +++ b/src/extension/pgrowlocks/pgrowlocks--1.0.sql @@ -0,0 +1,12 @@ +/* contrib/pgrowlocks/pgrowlocks--1.0.sql */ + +CREATE FUNCTION pgrowlocks(IN relname text, + OUT locked_row TID, -- row TID + OUT lock_type TEXT, -- lock type + OUT locker XID, -- locking XID + OUT multi bool, -- multi XID? + OUT xids xid[], -- multi XIDs + OUT pids INTEGER[]) -- locker's process id +RETURNS SETOF record +AS 'MODULE_PATHNAME', 'pgrowlocks' +LANGUAGE C STRICT; diff --git a/src/extension/pgrowlocks/pgrowlocks--unpackaged--1.0.sql b/src/extension/pgrowlocks/pgrowlocks--unpackaged--1.0.sql new file mode 100644 index 0000000..90d7088 --- /dev/null +++ b/src/extension/pgrowlocks/pgrowlocks--unpackaged--1.0.sql @@ -0,0 +1,3 @@ +/* src/extension/pgrowlocks/pgrowlocks--unpackaged--1.0.sql */ + +ALTER EXTENSION pgrowlocks ADD function pgrowlocks(text); diff --git a/src/extension/pgrowlocks/pgrowlocks.c b/src/extension/pgrowlocks/pgrowlocks.c new file mode 100644 index 0000000..aa41491 --- /dev/null +++ b/src/extension/pgrowlocks/pgrowlocks.c @@ -0,0 +1,220 @@ +/* + * src/extension/pgrowlocks/pgrowlocks.c + * + * Copyright (c) 2005-2006 Tatsuo Ishii + * + * Permission to use, copy, modify, and distribute this software and + * its documentation for any purpose, without fee, and without a + * written agreement is hereby granted, provided that the above + * copyright notice and this paragraph and the following two + * paragraphs appear in all copies. + * + * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, + * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING + * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS + * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + * + * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS + * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, + * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. + */ + +#include "postgres.h" + +#include "access/heapam.h" +#include "access/multixact.h" +#include "access/relscan.h" +#include "access/xact.h" +#include "catalog/namespace.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "storage/bufmgr.h" +#include "storage/procarray.h" +#include "utils/acl.h" +#include "utils/builtins.h" +#include "utils/tqual.h" + + +PG_MODULE_MAGIC; + +PG_FUNCTION_INFO_V1(pgrowlocks); + +extern Datum pgrowlocks(PG_FUNCTION_ARGS); + +/* ---------- + * pgrowlocks: + * returns tids of rows being locked + * ---------- + */ + +#define NCHARS 32 + +typedef struct +{ + Relation rel; + HeapScanDesc scan; + int ncolumns; +} MyData; + +Datum +pgrowlocks(PG_FUNCTION_ARGS) +{ + FuncCallContext *funcctx; + HeapScanDesc scan; + HeapTuple tuple; + TupleDesc tupdesc; + AttInMetadata *attinmeta; + Datum result; + MyData *mydata; + Relation rel; + + if (SRF_IS_FIRSTCALL()) + { + text *relname; + RangeVar *relrv; + MemoryContext oldcontext; + AclResult aclresult; + + funcctx = SRF_FIRSTCALL_INIT(); + oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx); + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + attinmeta = TupleDescGetAttInMetadata(tupdesc); + funcctx->attinmeta = attinmeta; + + relname = PG_GETARG_TEXT_P(0); + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = heap_openrv(relrv, AccessShareLock); + + /* check permissions: must have SELECT on table */ + aclresult = pg_class_aclcheck(RelationGetRelid(rel), GetUserId(), + ACL_SELECT); + if (aclresult != ACLCHECK_OK) + aclcheck_error(aclresult, ACL_KIND_CLASS, + RelationGetRelationName(rel)); + + scan = heap_beginscan(rel, SnapshotNow, 0, NULL); + mydata = palloc(sizeof(*mydata)); + mydata->rel = rel; + mydata->scan = scan; + mydata->ncolumns = tupdesc->natts; + funcctx->user_fctx = mydata; + + MemoryContextSwitchTo(oldcontext); + } + + funcctx = SRF_PERCALL_SETUP(); + attinmeta = funcctx->attinmeta; + mydata = (MyData *) funcctx->user_fctx; + scan = mydata->scan; + + /* scan the relation */ + while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) + { + /* must hold a buffer lock to call HeapTupleSatisfiesUpdate */ + LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE); + + if (HeapTupleSatisfiesUpdate(tuple->t_data, + GetCurrentCommandId(false), + scan->rs_cbuf) == HeapTupleBeingUpdated) + { + + char **values; + int i; + + values = (char **) palloc(mydata->ncolumns * sizeof(char *)); + + i = 0; + values[i++] = (char *) DirectFunctionCall1(tidout, PointerGetDatum(&tuple->t_self)); + + if (tuple->t_data->t_infomask & HEAP_XMAX_SHARED_LOCK) + values[i++] = pstrdup("Shared"); + else + values[i++] = pstrdup("Exclusive"); + values[i] = palloc(NCHARS * sizeof(char)); + snprintf(values[i++], NCHARS, "%d", HeapTupleHeaderGetXmax(tuple->t_data)); + if (tuple->t_data->t_infomask & HEAP_XMAX_IS_MULTI) + { + TransactionId *xids; + int nxids; + int j; + int isValidXid = 0; /* any valid xid ever exists? */ + + values[i++] = pstrdup("true"); + nxids = GetMultiXactIdMembers(HeapTupleHeaderGetXmax(tuple->t_data), &xids); + if (nxids == -1) + { + elog(ERROR, "GetMultiXactIdMembers returns error"); + } + + values[i] = palloc(NCHARS * nxids); + values[i + 1] = palloc(NCHARS * nxids); + strcpy(values[i], "{"); + strcpy(values[i + 1], "{"); + + for (j = 0; j < nxids; j++) + { + char buf[NCHARS]; + + if (TransactionIdIsInProgress(xids[j])) + { + if (isValidXid) + { + strcat(values[i], ","); + strcat(values[i + 1], ","); + } + snprintf(buf, NCHARS, "%d", xids[j]); + strcat(values[i], buf); + snprintf(buf, NCHARS, "%d", BackendXidGetPid(xids[j])); + strcat(values[i + 1], buf); + + isValidXid = 1; + } + } + + strcat(values[i], "}"); + strcat(values[i + 1], "}"); + i++; + } + else + { + values[i++] = pstrdup("false"); + values[i] = palloc(NCHARS * sizeof(char)); + snprintf(values[i++], NCHARS, "{%d}", HeapTupleHeaderGetXmax(tuple->t_data)); + + values[i] = palloc(NCHARS * sizeof(char)); + snprintf(values[i++], NCHARS, "{%d}", BackendXidGetPid(HeapTupleHeaderGetXmax(tuple->t_data))); + } + + LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); + + /* build a tuple */ + tuple = BuildTupleFromCStrings(attinmeta, values); + + /* make the tuple into a datum */ + result = HeapTupleGetDatum(tuple); + + /* Clean up */ + for (i = 0; i < mydata->ncolumns; i++) + pfree(values[i]); + pfree(values); + + SRF_RETURN_NEXT(funcctx, result); + } + else + { + LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); + } + } + + heap_endscan(scan); + heap_close(mydata->rel, AccessShareLock); + + SRF_RETURN_DONE(funcctx); +} diff --git a/src/extension/pgrowlocks/pgrowlocks.control b/src/extension/pgrowlocks/pgrowlocks.control new file mode 100644 index 0000000..a6ba164 --- /dev/null +++ b/src/extension/pgrowlocks/pgrowlocks.control @@ -0,0 +1,5 @@ +# pgrowlocks extension +comment = 'show row-level locking information' +default_version = '1.0' +module_pathname = '$libdir/pgrowlocks' +relocatable = true diff --git a/src/extension/pgstattuple/Makefile b/src/extension/pgstattuple/Makefile new file mode 100644 index 0000000..296ca57 --- /dev/null +++ b/src/extension/pgstattuple/Makefile @@ -0,0 +1,19 @@ +# src/extension/pgstattuple/Makefile + +MODULE_big = pgstattuple +OBJS = pgstattuple.o pgstatindex.o +MODULEDIR = extension + +EXTENSION = pgstattuple +DATA = pgstattuple--1.0.sql pgstattuple--unpackaged--1.0.sql + +ifdef USE_PGXS +PG_CONFIG = pg_config +PGXS := $(shell $(PG_CONFIG) --pgxs) +include $(PGXS) +else +subdir = src/extension/pgstattuple +top_builddir = ../../.. +include $(top_builddir)/src/Makefile.global +include $(top_srcdir)/src/extension/extension-global.mk +endif diff --git a/src/extension/pgstattuple/pgstatindex.c b/src/extension/pgstattuple/pgstatindex.c new file mode 100644 index 0000000..77ca208 --- /dev/null +++ b/src/extension/pgstattuple/pgstatindex.c @@ -0,0 +1,282 @@ +/* + * src/extension/pgstattuple/pgstatindex.c + * + * + * pgstatindex + * + * Copyright (c) 2006 Satoshi Nagayasu + * + * Permission to use, copy, modify, and distribute this software and + * its documentation for any purpose, without fee, and without a + * written agreement is hereby granted, provided that the above + * copyright notice and this paragraph and the following two + * paragraphs appear in all copies. + * + * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, + * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING + * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS + * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + * + * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS + * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, + * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. + */ + +#include "postgres.h" + +#include "access/heapam.h" +#include "access/nbtree.h" +#include "catalog/namespace.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "storage/bufmgr.h" +#include "utils/builtins.h" + + +extern Datum pgstatindex(PG_FUNCTION_ARGS); +extern Datum pg_relpages(PG_FUNCTION_ARGS); + +PG_FUNCTION_INFO_V1(pgstatindex); +PG_FUNCTION_INFO_V1(pg_relpages); + +#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX) +#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID) + +#define CHECK_PAGE_OFFSET_RANGE(pg, offnum) { \ + if ( !(FirstOffsetNumber <= (offnum) && \ + (offnum) <= PageGetMaxOffsetNumber(pg)) ) \ + elog(ERROR, "page offset number out of range"); } + +/* note: BlockNumber is unsigned, hence can't be negative */ +#define CHECK_RELATION_BLOCK_RANGE(rel, blkno) { \ + if ( RelationGetNumberOfBlocks(rel) <= (BlockNumber) (blkno) ) \ + elog(ERROR, "block number out of range"); } + +/* ------------------------------------------------ + * A structure for a whole btree index statistics + * used by pgstatindex(). + * ------------------------------------------------ + */ +typedef struct BTIndexStat +{ + uint32 version; + uint32 level; + BlockNumber root_blkno; + + uint64 root_pages; + uint64 internal_pages; + uint64 leaf_pages; + uint64 empty_pages; + uint64 deleted_pages; + + uint64 max_avail; + uint64 free_space; + + uint64 fragments; +} BTIndexStat; + +/* ------------------------------------------------------ + * pgstatindex() + * + * Usage: SELECT * FROM pgstatindex('t1_pkey'); + * ------------------------------------------------------ + */ +Datum +pgstatindex(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + Relation rel; + RangeVar *relrv; + Datum result; + BlockNumber nblocks; + BlockNumber blkno; + BTIndexStat indexStat; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pgstattuple functions")))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + if (!IS_INDEX(rel) || !IS_BTREE(rel)) + elog(ERROR, "relation \"%s\" is not a btree index", + RelationGetRelationName(rel)); + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + /* + * Read metapage + */ + { + Buffer buffer = ReadBuffer(rel, 0); + Page page = BufferGetPage(buffer); + BTMetaPageData *metad = BTPageGetMeta(page); + + indexStat.version = metad->btm_version; + indexStat.level = metad->btm_level; + indexStat.root_blkno = metad->btm_root; + + ReleaseBuffer(buffer); + } + + /* -- init counters -- */ + indexStat.root_pages = 0; + indexStat.internal_pages = 0; + indexStat.leaf_pages = 0; + indexStat.empty_pages = 0; + indexStat.deleted_pages = 0; + + indexStat.max_avail = 0; + indexStat.free_space = 0; + + indexStat.fragments = 0; + + /* + * Scan all blocks except the metapage + */ + nblocks = RelationGetNumberOfBlocks(rel); + + for (blkno = 1; blkno < nblocks; blkno++) + { + Buffer buffer; + Page page; + BTPageOpaque opaque; + + /* Read and lock buffer */ + buffer = ReadBuffer(rel, blkno); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + + page = BufferGetPage(buffer); + opaque = (BTPageOpaque) PageGetSpecialPointer(page); + + /* Determine page type, and update totals */ + + if (P_ISLEAF(opaque)) + { + int max_avail; + + max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData); + indexStat.max_avail += max_avail; + indexStat.free_space += PageGetFreeSpace(page); + + indexStat.leaf_pages++; + + /* + * If the next leaf is on an earlier block, it means a + * fragmentation. + */ + if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno) + indexStat.fragments++; + } + else if (P_ISDELETED(opaque)) + indexStat.deleted_pages++; + else if (P_IGNORE(opaque)) + indexStat.empty_pages++; + else if (P_ISROOT(opaque)) + indexStat.root_pages++; + else + indexStat.internal_pages++; + + /* Unlock and release buffer */ + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); + ReleaseBuffer(buffer); + } + + relation_close(rel, AccessShareLock); + + /*---------------------------- + * Build a result tuple + *---------------------------- + */ + { + TupleDesc tupleDesc; + int j; + char *values[10]; + HeapTuple tuple; + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + j = 0; + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", indexStat.version); + values[j] = palloc(32); + snprintf(values[j++], 32, "%d", indexStat.level); + values[j] = palloc(32); + snprintf(values[j++], 32, INT64_FORMAT, + (indexStat.root_pages + + indexStat.leaf_pages + + indexStat.internal_pages + + indexStat.deleted_pages + + indexStat.empty_pages) * BLCKSZ); + values[j] = palloc(32); + snprintf(values[j++], 32, "%u", indexStat.root_blkno); + values[j] = palloc(32); + snprintf(values[j++], 32, INT64_FORMAT, indexStat.internal_pages); + values[j] = palloc(32); + snprintf(values[j++], 32, INT64_FORMAT, indexStat.leaf_pages); + values[j] = palloc(32); + snprintf(values[j++], 32, INT64_FORMAT, indexStat.empty_pages); + values[j] = palloc(32); + snprintf(values[j++], 32, INT64_FORMAT, indexStat.deleted_pages); + values[j] = palloc(32); + snprintf(values[j++], 32, "%.2f", 100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0); + values[j] = palloc(32); + snprintf(values[j++], 32, "%.2f", (double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0); + + tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc), + values); + + result = HeapTupleGetDatum(tuple); + } + + PG_RETURN_DATUM(result); +} + +/* -------------------------------------------------------- + * pg_relpages() + * + * Get the number of pages of the table/index. + * + * Usage: SELECT pg_relpages('t1'); + * SELECT pg_relpages('t1_pkey'); + * -------------------------------------------------------- + */ +Datum +pg_relpages(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + int64 relpages; + Relation rel; + RangeVar *relrv; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pgstattuple functions")))); + + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + /* note: this will work OK on non-local temp tables */ + + relpages = RelationGetNumberOfBlocks(rel); + + relation_close(rel, AccessShareLock); + + PG_RETURN_INT64(relpages); +} diff --git a/src/extension/pgstattuple/pgstattuple--1.0.sql b/src/extension/pgstattuple/pgstattuple--1.0.sql new file mode 100644 index 0000000..7b78905 --- /dev/null +++ b/src/extension/pgstattuple/pgstattuple--1.0.sql @@ -0,0 +1,46 @@ +/* src/extension/pgstattuple/pgstattuple--1.0.sql */ + +CREATE FUNCTION pgstattuple(IN relname text, + OUT table_len BIGINT, -- physical table length in bytes + OUT tuple_count BIGINT, -- number of live tuples + OUT tuple_len BIGINT, -- total tuples length in bytes + OUT tuple_percent FLOAT8, -- live tuples in % + OUT dead_tuple_count BIGINT, -- number of dead tuples + OUT dead_tuple_len BIGINT, -- total dead tuples length in bytes + OUT dead_tuple_percent FLOAT8, -- dead tuples in % + OUT free_space BIGINT, -- free space in bytes + OUT free_percent FLOAT8) -- free space in % +AS 'MODULE_PATHNAME', 'pgstattuple' +LANGUAGE C STRICT; + +CREATE FUNCTION pgstattuple(IN reloid oid, + OUT table_len BIGINT, -- physical table length in bytes + OUT tuple_count BIGINT, -- number of live tuples + OUT tuple_len BIGINT, -- total tuples length in bytes + OUT tuple_percent FLOAT8, -- live tuples in % + OUT dead_tuple_count BIGINT, -- number of dead tuples + OUT dead_tuple_len BIGINT, -- total dead tuples length in bytes + OUT dead_tuple_percent FLOAT8, -- dead tuples in % + OUT free_space BIGINT, -- free space in bytes + OUT free_percent FLOAT8) -- free space in % +AS 'MODULE_PATHNAME', 'pgstattuplebyid' +LANGUAGE C STRICT; + +CREATE FUNCTION pgstatindex(IN relname text, + OUT version INT, + OUT tree_level INT, + OUT index_size BIGINT, + OUT root_block_no BIGINT, + OUT internal_pages BIGINT, + OUT leaf_pages BIGINT, + OUT empty_pages BIGINT, + OUT deleted_pages BIGINT, + OUT avg_leaf_density FLOAT8, + OUT leaf_fragmentation FLOAT8) +AS 'MODULE_PATHNAME', 'pgstatindex' +LANGUAGE C STRICT; + +CREATE FUNCTION pg_relpages(IN relname text) +RETURNS BIGINT +AS 'MODULE_PATHNAME', 'pg_relpages' +LANGUAGE C STRICT; diff --git a/src/extension/pgstattuple/pgstattuple--unpackaged--1.0.sql b/src/extension/pgstattuple/pgstattuple--unpackaged--1.0.sql new file mode 100644 index 0000000..6a1474a --- /dev/null +++ b/src/extension/pgstattuple/pgstattuple--unpackaged--1.0.sql @@ -0,0 +1,6 @@ +/* src/extension/pgstattuple/pgstattuple--unpackaged--1.0.sql */ + +ALTER EXTENSION pgstattuple ADD function pgstattuple(text); +ALTER EXTENSION pgstattuple ADD function pgstattuple(oid); +ALTER EXTENSION pgstattuple ADD function pgstatindex(text); +ALTER EXTENSION pgstattuple ADD function pg_relpages(text); diff --git a/src/extension/pgstattuple/pgstattuple.c b/src/extension/pgstattuple/pgstattuple.c new file mode 100644 index 0000000..76357ee --- /dev/null +++ b/src/extension/pgstattuple/pgstattuple.c @@ -0,0 +1,518 @@ +/* + * src/extension/pgstattuple/pgstattuple.c + * + * Copyright (c) 2001,2002 Tatsuo Ishii + * + * Permission to use, copy, modify, and distribute this software and + * its documentation for any purpose, without fee, and without a + * written agreement is hereby granted, provided that the above + * copyright notice and this paragraph and the following two + * paragraphs appear in all copies. + * + * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, + * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING + * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS + * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + * + * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS + * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE, + * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. + */ + +#include "postgres.h" + +#include "access/gist_private.h" +#include "access/hash.h" +#include "access/nbtree.h" +#include "access/relscan.h" +#include "catalog/namespace.h" +#include "funcapi.h" +#include "miscadmin.h" +#include "storage/bufmgr.h" +#include "storage/lmgr.h" +#include "utils/builtins.h" +#include "utils/tqual.h" + + +PG_MODULE_MAGIC; + +PG_FUNCTION_INFO_V1(pgstattuple); +PG_FUNCTION_INFO_V1(pgstattuplebyid); + +extern Datum pgstattuple(PG_FUNCTION_ARGS); +extern Datum pgstattuplebyid(PG_FUNCTION_ARGS); + +/* + * struct pgstattuple_type + * + * tuple_percent, dead_tuple_percent and free_percent are computable, + * so not defined here. + */ +typedef struct pgstattuple_type +{ + uint64 table_len; + uint64 tuple_count; + uint64 tuple_len; + uint64 dead_tuple_count; + uint64 dead_tuple_len; + uint64 free_space; /* free/reusable space in bytes */ +} pgstattuple_type; + +typedef void (*pgstat_page) (pgstattuple_type *, Relation, BlockNumber); + +static Datum build_pgstattuple_type(pgstattuple_type *stat, + FunctionCallInfo fcinfo); +static Datum pgstat_relation(Relation rel, FunctionCallInfo fcinfo); +static Datum pgstat_heap(Relation rel, FunctionCallInfo fcinfo); +static void pgstat_btree_page(pgstattuple_type *stat, + Relation rel, BlockNumber blkno); +static void pgstat_hash_page(pgstattuple_type *stat, + Relation rel, BlockNumber blkno); +static void pgstat_gist_page(pgstattuple_type *stat, + Relation rel, BlockNumber blkno); +static Datum pgstat_index(Relation rel, BlockNumber start, + pgstat_page pagefn, FunctionCallInfo fcinfo); +static void pgstat_index_page(pgstattuple_type *stat, Page page, + OffsetNumber minoff, OffsetNumber maxoff); + +/* + * build_pgstattuple_type -- build a pgstattuple_type tuple + */ +static Datum +build_pgstattuple_type(pgstattuple_type *stat, FunctionCallInfo fcinfo) +{ +#define NCOLUMNS 9 +#define NCHARS 32 + + HeapTuple tuple; + char *values[NCOLUMNS]; + char values_buf[NCOLUMNS][NCHARS]; + int i; + double tuple_percent; + double dead_tuple_percent; + double free_percent; /* free/reusable space in % */ + TupleDesc tupdesc; + AttInMetadata *attinmeta; + + /* Build a tuple descriptor for our result type */ + if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + + /* + * Generate attribute metadata needed later to produce tuples from raw C + * strings + */ + attinmeta = TupleDescGetAttInMetadata(tupdesc); + + if (stat->table_len == 0) + { + tuple_percent = 0.0; + dead_tuple_percent = 0.0; + free_percent = 0.0; + } + else + { + tuple_percent = 100.0 * stat->tuple_len / stat->table_len; + dead_tuple_percent = 100.0 * stat->dead_tuple_len / stat->table_len; + free_percent = 100.0 * stat->free_space / stat->table_len; + } + + /* + * Prepare a values array for constructing the tuple. This should be an + * array of C strings which will be processed later by the appropriate + * "in" functions. + */ + for (i = 0; i < NCOLUMNS; i++) + values[i] = values_buf[i]; + i = 0; + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->table_len); + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->tuple_count); + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->tuple_len); + snprintf(values[i++], NCHARS, "%.2f", tuple_percent); + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->dead_tuple_count); + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->dead_tuple_len); + snprintf(values[i++], NCHARS, "%.2f", dead_tuple_percent); + snprintf(values[i++], NCHARS, INT64_FORMAT, stat->free_space); + snprintf(values[i++], NCHARS, "%.2f", free_percent); + + /* build a tuple */ + tuple = BuildTupleFromCStrings(attinmeta, values); + + /* make the tuple into a datum */ + return HeapTupleGetDatum(tuple); +} + +/* ---------- + * pgstattuple: + * returns live/dead tuples info + * + * C FUNCTION definition + * pgstattuple(text) returns pgstattuple_type + * see pgstattuple.sql for pgstattuple_type + * ---------- + */ + +Datum +pgstattuple(PG_FUNCTION_ARGS) +{ + text *relname = PG_GETARG_TEXT_P(0); + RangeVar *relrv; + Relation rel; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pgstattuple functions")))); + + /* open relation */ + relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname)); + rel = relation_openrv(relrv, AccessShareLock); + + PG_RETURN_DATUM(pgstat_relation(rel, fcinfo)); +} + +Datum +pgstattuplebyid(PG_FUNCTION_ARGS) +{ + Oid relid = PG_GETARG_OID(0); + Relation rel; + + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + (errmsg("must be superuser to use pgstattuple functions")))); + + /* open relation */ + rel = relation_open(relid, AccessShareLock); + + PG_RETURN_DATUM(pgstat_relation(rel, fcinfo)); +} + +/* + * pgstat_relation + */ +static Datum +pgstat_relation(Relation rel, FunctionCallInfo fcinfo) +{ + const char *err; + + /* + * Reject attempts to read non-local temporary relations; we would be + * likely to get wrong data since we have no visibility into the owning + * session's local buffers. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot access temporary tables of other sessions"))); + + switch (rel->rd_rel->relkind) + { + case RELKIND_RELATION: + case RELKIND_TOASTVALUE: + case RELKIND_UNCATALOGED: + case RELKIND_SEQUENCE: + return pgstat_heap(rel, fcinfo); + case RELKIND_INDEX: + switch (rel->rd_rel->relam) + { + case BTREE_AM_OID: + return pgstat_index(rel, BTREE_METAPAGE + 1, + pgstat_btree_page, fcinfo); + case HASH_AM_OID: + return pgstat_index(rel, HASH_METAPAGE + 1, + pgstat_hash_page, fcinfo); + case GIST_AM_OID: + return pgstat_index(rel, GIST_ROOT_BLKNO + 1, + pgstat_gist_page, fcinfo); + case GIN_AM_OID: + err = "gin index"; + break; + default: + err = "unknown index"; + break; + } + break; + case RELKIND_VIEW: + err = "view"; + break; + case RELKIND_COMPOSITE_TYPE: + err = "composite type"; + break; + case RELKIND_FOREIGN_TABLE: + err = "foreign table"; + break; + default: + err = "unknown"; + break; + } + + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("\"%s\" (%s) is not supported", + RelationGetRelationName(rel), err))); + return 0; /* should not happen */ +} + +/* + * pgstat_heap -- returns live/dead tuples info in a heap + */ +static Datum +pgstat_heap(Relation rel, FunctionCallInfo fcinfo) +{ + HeapScanDesc scan; + HeapTuple tuple; + BlockNumber nblocks; + BlockNumber block = 0; /* next block to count free space in */ + BlockNumber tupblock; + Buffer buffer; + pgstattuple_type stat = {0}; + + /* Disable syncscan because we assume we scan from block zero upwards */ + scan = heap_beginscan_strat(rel, SnapshotAny, 0, NULL, true, false); + + nblocks = scan->rs_nblocks; /* # blocks to be scanned */ + + /* scan the relation */ + while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) + { + CHECK_FOR_INTERRUPTS(); + + /* must hold a buffer lock to call HeapTupleSatisfiesVisibility */ + LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE); + + if (HeapTupleSatisfiesVisibility(tuple, SnapshotNow, scan->rs_cbuf)) + { + stat.tuple_len += tuple->t_len; + stat.tuple_count++; + } + else + { + stat.dead_tuple_len += tuple->t_len; + stat.dead_tuple_count++; + } + + LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK); + + /* + * To avoid physically reading the table twice, try to do the + * free-space scan in parallel with the heap scan. However, + * heap_getnext may find no tuples on a given page, so we cannot + * simply examine the pages returned by the heap scan. + */ + tupblock = BlockIdGetBlockNumber(&tuple->t_self.ip_blkid); + + while (block <= tupblock) + { + CHECK_FOR_INTERRUPTS(); + + buffer = ReadBuffer(rel, block); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + stat.free_space += PageGetHeapFreeSpace((Page) BufferGetPage(buffer)); + UnlockReleaseBuffer(buffer); + block++; + } + } + heap_endscan(scan); + + while (block < nblocks) + { + CHECK_FOR_INTERRUPTS(); + + buffer = ReadBuffer(rel, block); + LockBuffer(buffer, BUFFER_LOCK_SHARE); + stat.free_space += PageGetHeapFreeSpace((Page) BufferGetPage(buffer)); + UnlockReleaseBuffer(buffer); + block++; + } + + relation_close(rel, AccessShareLock); + + stat.table_len = (uint64) nblocks *BLCKSZ; + + return build_pgstattuple_type(&stat, fcinfo); +} + +/* + * pgstat_btree_page -- check tuples in a btree page + */ +static void +pgstat_btree_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) +{ + Buffer buf; + Page page; + + buf = ReadBuffer(rel, blkno); + LockBuffer(buf, BT_READ); + page = BufferGetPage(buf); + + /* Page is valid, see what to do with it */ + if (PageIsNew(page)) + { + /* fully empty page */ + stat->free_space += BLCKSZ; + } + else + { + BTPageOpaque opaque; + + opaque = (BTPageOpaque) PageGetSpecialPointer(page); + if (opaque->btpo_flags & (BTP_DELETED | BTP_HALF_DEAD)) + { + /* recyclable page */ + stat->free_space += BLCKSZ; + } + else if (P_ISLEAF(opaque)) + { + pgstat_index_page(stat, page, P_FIRSTDATAKEY(opaque), + PageGetMaxOffsetNumber(page)); + } + else + { + /* root or node */ + } + } + + _bt_relbuf(rel, buf); +} + +/* + * pgstat_hash_page -- check tuples in a hash page + */ +static void +pgstat_hash_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) +{ + Buffer buf; + Page page; + + _hash_getlock(rel, blkno, HASH_SHARE); + buf = _hash_getbuf(rel, blkno, HASH_READ, 0); + page = BufferGetPage(buf); + + if (PageGetSpecialSize(page) == MAXALIGN(sizeof(HashPageOpaqueData))) + { + HashPageOpaque opaque; + + opaque = (HashPageOpaque) PageGetSpecialPointer(page); + switch (opaque->hasho_flag) + { + case LH_UNUSED_PAGE: + stat->free_space += BLCKSZ; + break; + case LH_BUCKET_PAGE: + case LH_OVERFLOW_PAGE: + pgstat_index_page(stat, page, FirstOffsetNumber, + PageGetMaxOffsetNumber(page)); + break; + case LH_BITMAP_PAGE: + case LH_META_PAGE: + default: + break; + } + } + else + { + /* maybe corrupted */ + } + + _hash_relbuf(rel, buf); + _hash_droplock(rel, blkno, HASH_SHARE); +} + +/* + * pgstat_gist_page -- check tuples in a gist page + */ +static void +pgstat_gist_page(pgstattuple_type *stat, Relation rel, BlockNumber blkno) +{ + Buffer buf; + Page page; + + buf = ReadBuffer(rel, blkno); + LockBuffer(buf, GIST_SHARE); + gistcheckpage(rel, buf); + page = BufferGetPage(buf); + + if (GistPageIsLeaf(page)) + { + pgstat_index_page(stat, page, FirstOffsetNumber, + PageGetMaxOffsetNumber(page)); + } + else + { + /* root or node */ + } + + UnlockReleaseBuffer(buf); +} + +/* + * pgstat_index -- returns live/dead tuples info in a generic index + */ +static Datum +pgstat_index(Relation rel, BlockNumber start, pgstat_page pagefn, + FunctionCallInfo fcinfo) +{ + BlockNumber nblocks; + BlockNumber blkno; + pgstattuple_type stat = {0}; + + blkno = start; + for (;;) + { + /* Get the current relation length */ + LockRelationForExtension(rel, ExclusiveLock); + nblocks = RelationGetNumberOfBlocks(rel); + UnlockRelationForExtension(rel, ExclusiveLock); + + /* Quit if we've scanned the whole relation */ + if (blkno >= nblocks) + { + stat.table_len = (uint64) nblocks *BLCKSZ; + + break; + } + + for (; blkno < nblocks; blkno++) + { + CHECK_FOR_INTERRUPTS(); + + pagefn(&stat, rel, blkno); + } + } + + relation_close(rel, AccessShareLock); + + return build_pgstattuple_type(&stat, fcinfo); +} + +/* + * pgstat_index_page -- for generic index page + */ +static void +pgstat_index_page(pgstattuple_type *stat, Page page, + OffsetNumber minoff, OffsetNumber maxoff) +{ + OffsetNumber i; + + stat->free_space += PageGetFreeSpace(page); + + for (i = minoff; i <= maxoff; i = OffsetNumberNext(i)) + { + ItemId itemid = PageGetItemId(page, i); + + if (ItemIdIsDead(itemid)) + { + stat->dead_tuple_count++; + stat->dead_tuple_len += ItemIdGetLength(itemid); + } + else + { + stat->tuple_count++; + stat->tuple_len += ItemIdGetLength(itemid); + } + } +} diff --git a/src/extension/pgstattuple/pgstattuple.control b/src/extension/pgstattuple/pgstattuple.control new file mode 100644 index 0000000..7b5129b --- /dev/null +++ b/src/extension/pgstattuple/pgstattuple.control @@ -0,0 +1,5 @@ +# pgstattuple extension +comment = 'show tuple-level statistics' +default_version = '1.0' +module_pathname = '$libdir/pgstattuple' +relocatable = true