From 81f47cfcf146dd2a99c3d6b2e1f74de3dcdc5b85 Mon Sep 17 00:00:00 2001 From: Hou Zhijie Date: Thu, 27 Feb 2025 10:49:32 +0800 Subject: [PATCH v1 1/3] Tap test to reproduce the issue This patch set fixes a bug for slot synchronization with logical replication slots that enabled two_phase decoding. As it stands, transactions prepared before two-phase decoding is enabled may fail to replicate to the subscriber after being committed on a promoted standby following a failover. The issue arises because the two_phase_at field of a slot, which tracks the LSN from which two-phase decoding starts, is not synchronized to standby servers. Without this field, the logical decoding might incorrectly identify prepared transaction as already replicated to the subscriber, causing them to be skipped. To address the issue, this patch set makes the two_phase_at field of the slot visible in the pg_replication_slots view and enables the slot synchronization to copy this value to the corresponding synced slot on the standby server. --- .../t/040_standby_failover_slots_sync.pl | 68 ++++++++++++++++++- 1 file changed, 66 insertions(+), 2 deletions(-) diff --git a/src/test/recovery/t/040_standby_failover_slots_sync.pl b/src/test/recovery/t/040_standby_failover_slots_sync.pl index 50388a494d6..692b746ccd9 100644 --- a/src/test/recovery/t/040_standby_failover_slots_sync.pl +++ b/src/test/recovery/t/040_standby_failover_slots_sync.pl @@ -22,7 +22,11 @@ $publisher->init( # Disable autovacuum to avoid generating xid during stats update as otherwise # the new XID could then be replicated to standby at some random point making # slots at primary lag behind standby during slot sync. -$publisher->append_conf('postgresql.conf', 'autovacuum = off'); +$publisher->append_conf( + 'postgresql.conf', qq{ +autovacuum = off +max_prepared_transactions = 1 +}); $publisher->start; $publisher->safe_psql('postgres', @@ -33,6 +37,7 @@ my $publisher_connstr = $publisher->connstr . ' dbname=postgres'; # Create a subscriber node, wait for sync to complete my $subscriber1 = PostgreSQL::Test::Cluster->new('subscriber1'); $subscriber1->init; +$subscriber1->append_conf('postgresql.conf', 'max_prepared_transactions = 1'); $subscriber1->start; # Capture the time before the logical failover slot is created on the @@ -830,13 +835,63 @@ $primary->adjust_conf('postgresql.conf', 'synchronized_standby_slots', "'sb1_slot'"); $primary->reload; +################################################## +# Test the synchronization of the two_phase setting for a subscription with the +# standby. Additionally, prepare a transaction before enabling the two_phase +# option; subsequent tests will verify if it can be correctly replicated to the +# subscriber after committing it on the promoted standby. +################################################## + +$standby1->start; + +# Prepare a transaction +$primary->safe_psql( + 'postgres', qq[ + BEGIN; + INSERT INTO tab_int values(0); + PREPARE TRANSACTION 'test_twophase_slotsync'; +]); + +$primary->wait_for_replay_catchup($standby1); +$primary->wait_for_catchup('regress_mysub1'); + +# Disable the subscription to allow changing the two_phase option. +$subscriber1->safe_psql('postgres', + "ALTER SUBSCRIPTION regress_mysub1 DISABLE"); + +# Wait for the replication slot to become inactive on the publisher +$primary->poll_query_until( + 'postgres', + "SELECT COUNT(*) FROM pg_catalog.pg_replication_slots WHERE slot_name = 'lsub1_slot' AND active='f'", + 1); + +# Set two_phase to true and enable the subscription +$subscriber1->safe_psql( + 'postgres', qq[ + ALTER SUBSCRIPTION regress_mysub1 SET (two_phase = true); + ALTER SUBSCRIPTION regress_mysub1 ENABLE; +]); + +# Confirm that two_phase setting of lsub1_slot slot is synced to the standby +ok( $standby1->poll_query_until( + 'postgres', + "SELECT two_phase from pg_replication_slots WHERE slot_name = 'lsub1_slot' AND synced AND NOT temporary;" + ), + 'two_phase setting of slot lsub1_slot synced to standby'); + +# Confirm that the prepared transaction is not yet replicated to the +# subscriber. +$result = $subscriber1->safe_psql('postgres', + "SELECT count(*) = 0 FROM pg_prepared_xacts;"); +is($result, 't', + "the prepared transaction is not replicated to the subscriber"); + ################################################## # Promote the standby1 to primary. Confirm that: # a) the slot 'lsub1_slot' and 'snap_test_slot' are retained on the new primary # b) logical replication for regress_mysub1 is resumed successfully after failover # c) changes can be consumed from the synced slot 'snap_test_slot' ################################################## -$standby1->start; $primary->wait_for_replay_catchup($standby1); # Capture the time before the standby is promoted @@ -885,6 +940,15 @@ $standby1->wait_for_catchup('regress_mysub1'); is($subscriber1->safe_psql('postgres', q{SELECT count(*) FROM tab_int;}), "20", 'data replicated from the new primary'); +# Commit the prepared transaction +$standby1->safe_psql('postgres', + "COMMIT PREPARED 'test_twophase_slotsync';"); +$standby1->wait_for_catchup('regress_mysub1'); + +# Confirm that the prepared transaction is replicated to the subscriber +is($subscriber1->safe_psql('postgres', q{SELECT count(*) FROM tab_int;}), + "21", 'prepared data replicated from the new primary'); + # Consume the data from the snap_test_slot. The synced slot should reach a # consistent point by restoring the snapshot at the restart_lsn serialized # during slot synchronization. -- 2.30.0.windows.2