database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-12-19 17:02:53 +03:00
Code Activity

Add slotsync skip statistics.

Browse Source 
This patch adds two new columns to the pg_stat_replication_slots view:
slotsync_skip_count - the total number of times a slotsync operation was
skipped.
slotsync_skip_at - the timestamp of the most recent skip.

These additions provide better visibility into replication slot
synchronization behavior.

A future patch will introduce the slotsync_skip_reason column in
pg_replication_slots to capture the reason for skip.

Author: Shlok Kyal <shlok.kyal.oss@gmail.com>
Reviewed-by: shveta malik <shveta.malik@gmail.com>
Reviewed-by: Hayato Kuroda <kuroda.hayato@fujitsu.com>
Reviewed-by: Ashutosh Sharma <ashu.coek88@gmail.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Discussion: https://postgr.es/m/CAE9k0PkhfKrTEAsGz4DjOhEj1nQ+hbQVfvWUxNacD38ibW3a1g@mail.gmail.com
This commit is contained in:
Amit Kapila
2025-11-25 06:47:49 +00:00
parent c581c9a7ac
commit 76b78721ca
11 changed files with 212 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
src/test/recovery/t/040_standby_failover_slots_sync.pl
View File

@@ -213,19 +213,75 @@ is( $standby1->safe_psql(
##################################################
# Test that the synchronized slot will be dropped if the corresponding remote
# slot on the primary server has been dropped.
#
# Note: Both slots need to be dropped for the next test to work
##################################################
$primary->psql('postgres', "SELECT pg_drop_replication_slot('lsub2_slot');");
$primary->psql('postgres', "SELECT pg_drop_replication_slot('lsub1_slot');");
$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();");
is( $standby1->safe_psql(
'postgres',
q{SELECT count(*) = 0 FROM pg_replication_slots WHERE slot_name = 'lsub2_slot';}
q{SELECT count(*) = 0 FROM pg_replication_slots WHERE slot_name IN ('lsub1_slot', 'lsub2_slot');}
),
"t",
'synchronized slot has been dropped');
##################################################
# Verify that slotsync skip statistics are correctly updated when the
# slotsync operation is skipped.
##################################################
# Create a logical replication slot and create some DDL on the primary so
# that the slot lags behind the standby.
$primary->safe_psql(
'postgres', qq(
SELECT pg_create_logical_replication_slot('lsub1_slot', 'pgoutput', false, false, true);
CREATE TABLE wal_push(a int);
));
$primary->wait_for_replay_catchup($standby1);
my $log_offset = -s $standby1->logfile;
# Enable slot sync worker.
$standby1->append_conf('postgresql.conf', qq(sync_replication_slots = on));
$standby1->reload;
# Confirm that the slot sync worker is able to start.
$standby1->wait_for_log(qr/slot sync worker started/, $log_offset);
# Confirm that the slot sync is skipped due to the remote slot lagging behind
$standby1->wait_for_log(
qr/could not synchronize replication slot \"lsub1_slot\"/, $log_offset);
# Confirm that the slotsync skip statistics is updated
$result = $standby1->safe_psql('postgres',
"SELECT slotsync_skip_count > 0 FROM pg_stat_replication_slots WHERE slot_name = 'lsub1_slot'"
);
is($result, 't', "check slot sync skip count increments");
# Clean the table
$primary->safe_psql(
'postgres', qq(
DROP TABLE wal_push;
));
$primary->wait_for_replay_catchup($standby1);
# Re-create the logical replication slot and sync it to standby for further tests
$primary->safe_psql(
'postgres', qq(
SELECT pg_drop_replication_slot('lsub1_slot');
SELECT pg_create_logical_replication_slot('lsub1_slot', 'pgoutput', false, false, true);
));
$standby1->wait_for_log(
qr/newly created replication slot \"lsub1_slot\" is sync-ready now/,
$log_offset);
$standby1->append_conf('postgresql.conf', qq(sync_replication_slots = off));
$standby1->reload;
##################################################
# Test that if the synchronized slot is invalidated while the remote slot is
# still valid, the slot will be dropped and re-created on the standby by
@@ -281,7 +337,7 @@ $inactive_since_on_primary =
# the failover slots.
$primary->wait_for_replay_catchup($standby1);
my $log_offset = -s $standby1->logfile;
$log_offset = -s $standby1->logfile;
# Synchronize the primary server slots to the standby.
$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();");

4
src/test/regress/expected/rules.out
View File

@@ -2151,9 +2151,11 @@ pg_stat_replication_slots| SELECT s.slot_name,
s.mem_exceeded_count,
s.total_txns,
s.total_bytes,
s.slotsync_skip_count,
s.slotsync_skip_at,
s.stats_reset
FROM pg_replication_slots r,
LATERAL pg_stat_get_replication_slot((r.slot_name)::text) s(slot_name, spill_txns, spill_count, spill_bytes, stream_txns, stream_count, stream_bytes, mem_exceeded_count, total_txns, total_bytes, stats_reset)
LATERAL pg_stat_get_replication_slot((r.slot_name)::text) s(slot_name, spill_txns, spill_count, spill_bytes, stream_txns, stream_count, stream_bytes, mem_exceeded_count, total_txns, total_bytes, slotsync_skip_count, slotsync_skip_at, stats_reset)
WHERE (r.datoid IS NOT NULL);
pg_stat_slru| SELECT name,
blks_zeroed,