sharpetronics/PostgreSQL
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-04 00:02:26 -04:00
Code Issues Projects Releases Wiki Activity

Fix intermittent BF failures in 035_conflicts.

Browse Source 
This commit addresses two sources of instability in the 035_conflicts
test:

Unstable VACUUM usage:
The test previously relied on VACUUM to remove a deleted column, which can
be unreliable due to concurrent background writer or checkpoint activity
that may lock the page containing the deleted tuple. Since the test
already verifies that replication_slot.xmin has advanced sufficiently to
confirm the feature's correctness, so, the VACUUM step is removed to
improve test stability.

Timing-sensitive retention resumption check:
The test includes a check to confirm that retention of conflict-relevant
information resumes after setting max_retention_duration to 0. However, in
some cases, the apply worker resumes retention immediately after the
inactive slot is removed from synchronized_standby_slots, even before
max_retention_duration is updated. This can happen if remote changes are
applied in under 1ms, causing the test to timeout while waiting for a
later log position. To ensure consistent behavior, this commit delays the
removal of synchronized_standby_slots until after max_retention_duration
is set to 0.

Author: Zhijie Hou <houzj.fnst@fujitsu.com>
Reviewed-by: shveta malik <shveta.malik@gmail.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Discussion: https://postgr.es/m/TY4PR01MB16907805DE4816E53C54708159414A@TY4PR01MB16907.jpnprd01.prod.outlook.com
This commit is contained in:
Amit Kapila 2025-09-16 06:16:23 +00:00
parent bce18ef3c6
commit 0f42206531
1 changed files with 10 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
src/test/subscription/t/035_conflicts.pl
View File

@ -342,15 +342,6 @@ ok( $node_A->poll_query_until(
),
"the xmin value of slot 'pg_conflict_detection' is updated on Node A");
# Confirm that the dead tuple can be removed now
($cmdret, $stdout, $stderr) = $node_A->psql(
'postgres', qq(VACUUM (verbose) public.tab;)
);
ok( $stderr =~
qr/1 removed, 1 remain, 0 are dead but not yet removable/,
'the deleted column is removed');
###############################################################################
# Ensure that the deleted tuple needed to detect an update_deleted conflict is
# accessible via a sequential table scan.
@ -555,13 +546,6 @@ if ($injection_points_supported != 0)
"the xmin value of slot 'pg_conflict_detection' is updated on subscriber"
);
# Confirm that the dead tuple can be removed now
($cmdret, $stdout, $stderr) =
$node_A->psql('postgres', qq(VACUUM (verbose) public.tab;));
ok($stderr =~ qr/1 removed, 0 remain, 0 are dead but not yet removable/,
'the deleted column is removed');
# Get the commit timestamp for the publisher's update
my $pub_ts = $node_B->safe_psql('postgres',
"SELECT pg_xact_commit_timestamp(xmin) from tab where a=1;");
@ -625,12 +609,6 @@ $result = $node_A->safe_psql('postgres',
"SELECT subretentionactive FROM pg_subscription WHERE subname='$subname_AB';");
is($result, qq(f), 'retention is inactive');
# Drop the physical slot and reset the synchronized_standby_slots setting
$node_B->safe_psql('postgres',
"SELECT * FROM pg_drop_replication_slot('blocker');");
$node_B->adjust_conf('postgresql.conf', 'synchronized_standby_slots', "''");
$node_B->reload;
###############################################################################
# Check that dead tuple retention resumes when the max_retention_duration is set
# 0.
@ -642,6 +620,16 @@ $log_offset = -s $node_A->logfile;
$node_A->safe_psql('postgres',
"ALTER SUBSCRIPTION $subname_AB SET (max_retention_duration = 0);");
# Drop the physical slot and reset the synchronized_standby_slots setting. We
# change this after setting max_retention_duration to 0, ensuring consistent
# results in the test as the resumption becomes possible immediately after
# resetting synchronized_standby_slots, due to the smaller max_retention_duration
# value of 1ms.
$node_B->safe_psql('postgres',
"SELECT * FROM pg_drop_replication_slot('blocker');");
$node_B->adjust_conf('postgresql.conf', 'synchronized_standby_slots', "''");
$node_B->reload;
# Confirm that the retention resumes
$node_A->wait_for_log(
qr/logical replication worker for subscription "tap_sub_a_b" will resume retaining the information for detecting conflicts