From a8693c3003df7f9850af0be5284bb6f0e7a82fa6 Mon Sep 17 00:00:00 2001 From: Vitaly Davydov Date: Wed, 30 Apr 2025 12:48:27 +0300 Subject: [PATCH 3/5] Add TAP test to check physical repl slot advance during checkpoint The test verifies that the physical replication slot is still valid after immediate restart on checkpoint completion in case when the slot was advanced during checkpoint. Discussion: https://www.postgresql.org/message-id/flat/1d12d2-67235980-35-19a406a0%4063439497 --- .../test_replslot_required_lsn/meson.build | 3 +- .../t/002_physical_slot.pl | 126 ++++++++++++++++++ 2 files changed, 128 insertions(+), 1 deletion(-) create mode 100644 src/test/modules/test_replslot_required_lsn/t/002_physical_slot.pl diff --git a/src/test/modules/test_replslot_required_lsn/meson.build b/src/test/modules/test_replslot_required_lsn/meson.build index 999c16201fb..44d2546632b 100644 --- a/src/test/modules/test_replslot_required_lsn/meson.build +++ b/src/test/modules/test_replslot_required_lsn/meson.build @@ -9,7 +9,8 @@ tests += { 'enable_injection_points': get_option('injection_points') ? 'yes' : 'no', }, 'tests': [ - 't/001_logical_slot.pl' + 't/001_logical_slot.pl', + 't/002_physical_slot.pl' ], }, } diff --git a/src/test/modules/test_replslot_required_lsn/t/002_physical_slot.pl b/src/test/modules/test_replslot_required_lsn/t/002_physical_slot.pl new file mode 100644 index 00000000000..f89aec1da32 --- /dev/null +++ b/src/test/modules/test_replslot_required_lsn/t/002_physical_slot.pl @@ -0,0 +1,126 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group +# +# This test verifies the case when the physical slot is advanced during +# checkpoint. The test checks that the physical slot's restart_lsn still refers +# to an existed WAL segment after immediate restart. +# +# Discussion: +# https://www.postgresql.org/message-id/flat/1d12d2-67235980-35-19a406a0%4063439497 +# +use strict; +use warnings FATAL => 'all'; + +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; + +use Test::More; + +if ($ENV{enable_injection_points} ne 'yes') +{ + plan skip_all => 'Injection points not supported by this build'; +} + +my ($node, $result); + +$node = PostgreSQL::Test::Cluster->new('mike'); +$node->init(); +$node->append_conf('postgresql.conf', + "shared_preload_libraries = 'injection_points'"); +$node->append_conf('postgresql.conf', + "wal_level = 'replica'"); +$node->start(); +$node->safe_psql('postgres', q(CREATE EXTENSION injection_points)); + +# create a simple table to generate data into +$node->safe_psql('postgres', + q{create table t (id serial primary key, b text)}); + +# create a physical replication slot +$node->safe_psql('postgres', + q{select pg_create_physical_replication_slot('slot_physical', true)}); + +# advance slot to current position, just to have everything "valid" +$node->safe_psql('postgres', + q{select pg_replication_slot_advance('slot_physical', pg_current_wal_lsn())}); + +# run checkpoint, to flush current state to disk and set a baseline +$node->safe_psql('postgres', q{checkpoint}); + +# insert 2M rows, that's about 260MB (~20 segments) worth of WAL +$node->safe_psql('postgres', + q{insert into t (b) select md5(i::text) from generate_series(1,100000) s(i)}); + +# advance slot to current position, just to have everything "valid" +$node->safe_psql('postgres', + q{select pg_replication_slot_advance('slot_physical', pg_current_wal_lsn())}); + +# run another checkpoint, to set a new restore LSN +$node->safe_psql('postgres', q{checkpoint}); + +# another 2M rows, that's about 260MB (~20 segments) worth of WAL +$node->safe_psql('postgres', + q{insert into t (b) select md5(i::text) from generate_series(1,1000000) s(i)}); + +my $restart_lsn_init = $node->safe_psql('postgres', + q{select restart_lsn from pg_replication_slots where slot_name = 'slot_physical'}); +chomp($restart_lsn_init); +note("restart lsn before checkpoint: $restart_lsn_init"); + +# run another checkpoint, this time in the background, and make it wait +# on the injection point), so that the checkpoint stops right before +# removing old WAL segments +note('starting checkpoint'); + +my $checkpoint = $node->background_psql('postgres'); +$checkpoint->query_safe( + q{select injection_points_attach('checkpoint-before-old-wal-removal','wait')}); +$checkpoint->query_until(qr/starting_checkpoint/, +q(\echo starting_checkpoint +checkpoint; +\q +)); + +# wait until the checkpoint stops right before removing WAL segments +note('waiting for injection_point'); +$node->wait_for_event('checkpointer', 'checkpoint-before-old-wal-removal'); +note('injection_point is reached'); + +# OK, we're in the right situation, time to advance the physical slot, +# which recalculates the required LSN, and then unblock the checkpoint, +# which removes the WAL still needed by the logical slot +$node->safe_psql('postgres', + q{select pg_replication_slot_advance('slot_physical', pg_current_wal_lsn())}); + +# Continue checkpoint +$node->safe_psql('postgres', + q{select injection_points_wakeup('checkpoint-before-old-wal-removal')}); + +my $restart_lsn_old = $node->safe_psql('postgres', + q{select restart_lsn from pg_replication_slots where slot_name = 'slot_physical'}); +chomp($restart_lsn_old); +note("restart lsn before stop: $restart_lsn_old"); + +# abruptly stop the server (1 second should be enough for the checkpoint +# to finish, would be better ) +$node->stop('immediate'); + +$node->start; + +# Get the restart_lsn of the slot right after restarting +my $restart_lsn = $node->safe_psql('postgres', + q{select restart_lsn from pg_replication_slots where slot_name = 'slot_physical'}); +chomp($restart_lsn); +note("restart lsn: $restart_lsn"); + +# Get wal segment name for slot's restart_lsn +my $restart_lsn_segment = $node->safe_psql('postgres', + "SELECT pg_walfile_name('$restart_lsn'::pg_lsn)"); +chomp($restart_lsn_segment); + +# Check if the required wal segment exists +note("required by slot segment name: $restart_lsn_segment"); +my $datadir = $node->data_dir; +ok(-f "$datadir/pg_wal/$restart_lsn_segment", + "WAL segment $restart_lsn_segment for physical slot's restart_lsn $restart_lsn exists"); + +done_testing(); -- 2.34.1