Hi Yura,
Thanks for the numbers, backing the series and for the
rebase.
Both code suggestions are great.
v3, on top of your v2, against 9e17d25e79d:
0001
- SyncRepInitWakeList() asserts the list is empty. Nothing between
filling it and draining it can throw today, so this only states
the invariant.
- Latches set front to back. Draining from the end reversed the
release order. Harmless either way; my sense of beauty insisted.
0004
- Accessors renamed SyncRepGetLSN() and SyncRepSetLSN(). The setter
asserts the lock.
- Assert(MyProc->syncRepState == SYNC_REP_NOT_WAITING) moved above the
lock-free exit, which skipped it.
- Comment on lsn[] rewritten: 64-bit atomic read is not a plain
load everywhere. Every access to lsn[] goes through the atomics API
now, including the ones under the lock.
0005 has one real problem. 'standby_1,standby_2' parses as FIRST 1,
so remote_apply waits for standby_1 alone. The test dumps both
standbys and compares them against the primary, taking no wait of its
own. The setval() over pg_sequence right before the dumps is such a
write. Put recovery_min_apply_delay = '10s' on standby_2 and it fails:
ok 10 - compare primary and standby_1 dumps
not ok 11 - compare primary and standby_2 dumps
changed to ANY 2 (standby_1, standby_2) in v3 - remote_apply covers both.
It also exercises the quorum path through SyncRepGetNthLatestSyncRecPtr(),
which 0002 moves out from under the lock
One question in 0005: it runs the whole regression schedule a second
time. Maybe would be behind PG_TEST_EXTRA?
Regards,
Vadim Ponomarev
From 5ecc2111579c103857f6c318ef6f46c6f39a82dd Mon Sep 17 00:00:00 2001
From: Vadim Ponomarev <[email protected]>
Date: Sat, 15 Aug 2026 12:08:13 +0300
Subject: [PATCH v3 1/5] Wake the released sync-rep waiters after the queue
lock is down
SyncRepWakeQueue() sets each released backend's latch while holding
SyncRepLock exclusively. A latch is a kill() syscall whenever its proc is
asleep, and at a high commit rate the walsender runs one of them per
released commit inside the very section every committer lines up on.
ProcArrayGroupClearXid() already wakes its batch only after ProcArrayLock
is down, for the same reason.
Collect the released procs into a list instead, and set their latches once
the lock is released. The unlink, the write barrier and the state store
stay under the lock: a waiter reads syncRepState without the lock and must
never find itself completed while still on the queue. Nothing in the
deferred loop can error out, so a released proc cannot be left completed
but unlatched short of the process dying outright -- a window the in-lock
SetLatch had as well. A proc that noticed its state on its own and moved
on, even into a new wait, gets a spurious latch set, which every latch
sleeper tolerates.
The list is sized to MaxBackends and allocated once per releasing process.
A proc waits in at most one queue, so one list of that size bounds a walk
over all three.
---
src/backend/replication/syncrep.c | 78 +++++++++++++++++++++++++++----
1 file changed, 70 insertions(+), 8 deletions(-)
diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c
index d870f09e0a0..d3b19904cea 100644
--- a/src/backend/replication/syncrep.c
+++ b/src/backend/replication/syncrep.c
@@ -84,6 +84,7 @@
#include "storage/proc.h"
#include "tcop/tcopprot.h"
#include "utils/guc_hooks.h"
+#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/wait_event.h"
@@ -98,8 +99,16 @@ static bool announce_next_takeover = true;
SyncRepConfigData *SyncRepConfig = NULL;
static int SyncRepWaitMode = SYNC_REP_NO_WAIT;
+static struct
+{
+ Latch **arr;
+ int n;
+} SyncRepWakeList = {NULL, 0};
+
static void SyncRepQueueInsert(int mode);
static void SyncRepCancelWait(void);
+static void SyncRepInitWakeList(void);
+static void SyncRepWakeFromList(void);
static int SyncRepWakeQueue(bool all, int mode);
static bool SyncRepGetSyncRecPtr(XLogRecPtr *writePtr,
@@ -512,6 +521,8 @@ SyncRepReleaseWaiters(void)
* We're a potential sync standby. Release waiters if there are enough
* sync standbys and we are considered as sync.
*/
+ SyncRepInitWakeList();
+
LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
/*
@@ -575,6 +586,9 @@ SyncRepReleaseWaiters(void)
LWLockRelease(SyncRepLock);
+ /* wake the released backends now that the lock is down */
+ SyncRepWakeFromList();
+
elog(DEBUG3, "released %d procs up to write %X/%08X, %d procs up to flush %X/%08X, %d procs up to apply %X/%08X",
numwrite, LSN_FORMAT_ARGS(writePtr),
numflush, LSN_FORMAT_ARGS(flushPtr),
@@ -902,13 +916,57 @@ SyncRepGetStandbyPriority(void)
return (SyncRepConfig->syncrep_method == SYNC_REP_PRIORITY) ? priority : 1;
}
+/*
+ * Make the list a release collects the latches to set into ready for use,
+ * allocating it the first time this process releases anybody. It is sized
+ * for every backend to be waiting at once; a proc waits in at most one queue,
+ * so one list of that size is enough for a pass over all three.
+ *
+ * Every pass empties the list again, so it starts out empty here.
+ */
+static void
+SyncRepInitWakeList(void)
+{
+ Assert(SyncRepWakeList.n == 0);
+
+ if (SyncRepWakeList.arr == NULL)
+ SyncRepWakeList.arr = (Latch **)
+ MemoryContextAlloc(TopMemoryContext,
+ MaxBackends * sizeof(Latch *));
+}
+
+/*
+ * Set the latches the pass under the lock collected, and empty the list.
+ *
+ * Each latch is a kill() for a sleeping proc, and running one per released
+ * commit inside the exclusive section makes every committer wait for those
+ * syscalls. The procs here are off the queue with their state already
+ * complete, so nothing below needs the lock's protection. Nothing here can
+ * error out either: only this process dying outright could leave a released
+ * proc completed but unlatched, and the in-lock SetLatch had that same
+ * window. A proc that noticed its state on its own and moved on, even into
+ * a new wait, gets a spurious latch set, which every latch sleeper tolerates.
+ */
+static void
+SyncRepWakeFromList(void)
+{
+ for (int i = 0; i < SyncRepWakeList.n; i++)
+ SetLatch(SyncRepWakeList.arr[i]);
+
+ SyncRepWakeList.n = 0;
+}
+
/*
* Walk the specified queue from head. Set the state of any backends that
- * need to be woken, remove them from the queue, and then wake them.
- * Pass all = true to wake whole queue; otherwise, just wake up to
- * the walsender's LSN.
+ * need to be woken and remove them from the queue; their latches are
+ * appended to the wake list for SyncRepWakeFromList to set once the lock is
+ * down. Pass all = true to release the whole queue; otherwise, just release
+ * up to the walsender's LSN.
*
- * The caller must hold SyncRepLock in exclusive mode.
+ * The caller must hold SyncRepLock in exclusive mode, and must set the
+ * latches with SyncRepWakeFromList after releasing it. Unlink, barrier and
+ * state stay together in here: a waiter reads syncRepState without the lock
+ * and must never find itself completed while still on the queue.
*/
static int
SyncRepWakeQueue(bool all, int mode)
@@ -948,10 +1006,9 @@ SyncRepWakeQueue(bool all, int mode)
*/
proc->syncRepState = SYNC_REP_WAIT_COMPLETE;
- /*
- * Wake only when we have set state and removed from queue.
- */
- SetLatch(&(proc->procLatch));
+ /* the list is sized to every process that can ever queue here */
+ Assert(SyncRepWakeList.n < MaxBackends);
+ SyncRepWakeList.arr[SyncRepWakeList.n++] = &proc->procLatch;
numprocs++;
}
@@ -974,6 +1031,8 @@ SyncRepUpdateSyncStandbysDefined(void)
if (sync_standbys_defined !=
((WalSndCtl->sync_standbys_status & SYNC_STANDBY_DEFINED) != 0))
{
+ SyncRepInitWakeList();
+
LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
/*
@@ -1000,6 +1059,9 @@ SyncRepUpdateSyncStandbysDefined(void)
(sync_standbys_defined ? SYNC_STANDBY_DEFINED : 0);
LWLockRelease(SyncRepLock);
+
+ /* wake the released backends now that the lock is down */
+ SyncRepWakeFromList();
}
else if ((WalSndCtl->sync_standbys_status & SYNC_STANDBY_INIT) == 0)
{
base-commit: 9e17d25e79d4756be08b4a5521b4b58450217137
--
2.34.1
From 84de8e25774ce9d32ea4f73bd1b4026a4bd92d64 Mon Sep 17 00:00:00 2001
From: Vadim Ponomarev <[email protected]>
Date: Sat, 15 Aug 2026 12:08:53 +0300
Subject: [PATCH v3 2/5] Compute the synced positions before taking the
sync-rep queue lock
SyncRepReleaseWaiters() takes SyncRepLock and only then walks the
walsender slots to work out the synced write, flush and apply positions.
That walk takes a spinlock per slot, allocates, and for a quorum set sorts
the result, and every cycle of it is spent in the section every committer
lines up on. The comment there conceded the work does not need the lock
and kept it inside anyway, to guarantee the positions are newer than any
previous execution of the routine used.
That guarantee is not needed. The three sites that consume the positions
each move lsn[] forward only when the new reading is ahead of the stored
one, so positions gone stale while the lock was being taken release nobody
and change nothing; a concurrent walsender that got further has already
stored its own.
Compute them before taking the lock, and leave without taking it at all
when this walsender turns out not to be a sync standby.
---
src/backend/replication/syncrep.c | 28 +++++++++++++---------------
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c
index d3b19904cea..176f5d2935a 100644
--- a/src/backend/replication/syncrep.c
+++ b/src/backend/replication/syncrep.c
@@ -518,20 +518,15 @@ SyncRepReleaseWaiters(void)
}
/*
- * We're a potential sync standby. Release waiters if there are enough
- * sync standbys and we are considered as sync.
- */
- SyncRepInitWakeList();
-
- LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
-
- /*
- * Check whether we are a sync standby or not, and calculate the synced
- * positions among all sync standbys. (Note: although this step does not
- * of itself require holding SyncRepLock, it seems like a good idea to do
- * it after acquiring the lock. This ensures that the WAL pointers we use
- * to release waiters are newer than any previous execution of this
- * routine used.)
+ * We're a potential sync standby. Check whether we are a sync standby
+ * and calculate the synced positions among all sync standbys before
+ * taking the lock: the walk over the walsender slots takes their
+ * spinlocks, allocates, and possibly sorts, and doing all of it under
+ * SyncRepLock delays every committer.
+ *
+ * Positions gone stale by the time the lock is held cost nothing. The
+ * guards further down only ever move lsn[] forward, so a reading older
+ * than a concurrent walsender's simply releases nobody.
*/
got_recptr = SyncRepGetSyncRecPtr(&writePtr, &flushPtr, &applyPtr, &am_sync);
@@ -559,11 +554,14 @@ SyncRepReleaseWaiters(void)
*/
if (!got_recptr || !am_sync)
{
- LWLockRelease(SyncRepLock);
announce_next_takeover = !am_sync;
return;
}
+ SyncRepInitWakeList();
+
+ LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
+
/*
* Set the lsn first so that when we wake backends they will release up to
* this location.
--
2.34.1
From 67739a9d0cf31ebbc9f70a55519b7d90b5262ca0 Mon Sep 17 00:00:00 2001
From: Vadim Ponomarev <[email protected]>
Date: Sat, 15 Aug 2026 12:12:19 +0300
Subject: [PATCH v3 3/5] Release the sync-rep waiters once per drained batch of
standby replies
ProcessStandbyReplyMessage() calls SyncRepReleaseWaiters() for every reply
it processes, and several replies routinely sit in the walsender's socket
together. Each of those calls takes SyncRepLock exclusively, so a batch of
replies costs the committers one period of that lock apiece -- computed,
for all but the last reply, from positions the next message in the same
batch immediately makes stale.
Have a reply only mark a release as pending, and run one release at the end
of the drain. The positions in shared memory are the newest of the batch
by then, so the single pass releases everything the individual passes would
have.
A deferred release must survive every way out of the drain, because the
positions the reply already stored are valid whatever follows and the
committers it acknowledged have no other process to wake them:
- the standby's goodbye, an EOF, an invalid message type and an unexpected
message type each run the pending release before leaving. A clean
standby shutdown sends its final reply and the goodbye back to back,
which makes that exit the routine one rather than the exotic one.
- an error thrown while a later message in the same drain is parsed -- a
torn message above all -- leaves through WalSndErrorCleanup(), which runs
the pending release after the locks are dropped.
The test makes both coincidences certain instead of likely. For the first,
a paused standby holds a remote_apply committer in the queue, the walsender
is held with SIGSTOP while the standby applies past the commit and shuts
down, and the released walsender drains the final reply and the goodbye in
one pass. For the second, an injection point right after a drained reply
stands in for the torn message; it fires on every reply, so the walreceiver
is held with SIGSTOP while replay proceeds from WAL already on standby
disk, which makes the first reply after release the one carrying the apply
position the committer waits for. Both halves fail without their fix.
---
src/backend/replication/walsender.c | 59 +++++-
src/test/recovery/meson.build | 1 +
src/test/recovery/t/057_syncrep_release.pl | 206 +++++++++++++++++++++
3 files changed, 264 insertions(+), 2 deletions(-)
create mode 100644 src/test/recovery/t/057_syncrep_release.pl
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index e9331de3df5..89fed06f851 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,6 +94,7 @@
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/guc.h"
+#include "utils/injection_point.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/pg_lsn.h"
@@ -206,6 +207,13 @@ static TimestampTz last_reply_timestamp = 0;
/* Have we sent a heartbeat message asking for reply, since last reply? */
static bool waiting_for_ping_response = false;
+/*
+ * Set when a standby reply has updated this walsender's positions and the
+ * waiters those positions release have not been released yet. Raised per
+ * reply, acted on once per drain of the socket.
+ */
+static bool syncrep_release_pending = false;
+
/* Timestamp when walsender received the shutdown request */
static TimestampTz shutdown_request_timestamp = 0;
@@ -300,6 +308,7 @@ static void CreateReplicationSlot(CreateReplicationSlotCmd *cmd);
static void DropReplicationSlot(DropReplicationSlotCmd *cmd);
static void StartReplication(StartReplicationCmd *cmd);
static void StartLogicalReplication(StartReplicationCmd *cmd);
+static void SyncRepFlushPendingRelease(void);
static void ProcessStandbyMessage(void);
static void ProcessStandbyReplyMessage(void);
static void ProcessStandbyHSFeedbackMessage(void);
@@ -381,6 +390,15 @@ WalSndErrorCleanup(void)
pgstat_report_wait_end();
pgaio_error_cleanup();
+ /*
+ * A release deferred by the reply drain survives an error thrown while a
+ * later message in the same drain was being parsed. The positions the
+ * drained reply put in shared memory are valid whatever came after it,
+ * and the committers it acknowledged have no other process to wake them.
+ * The locks are released above, so the queue lock is free to take.
+ */
+ SyncRepFlushPendingRelease();
+
if (xlogreader != NULL && xlogreader->seg.ws_file >= 0)
wal_segment_close(xlogreader);
@@ -2353,6 +2371,22 @@ exec_replication_command(const char *cmd_string)
return true;
}
+/*
+ * Run the release a drained reply deferred. A reply already processed has
+ * put its positions in shared memory, and the committers it acknowledged
+ * have nothing but this process to wake them, so every exit out of the reply
+ * drain runs through here before leaving. The standby's goodbye is the
+ * common one.
+ */
+static void
+SyncRepFlushPendingRelease(void)
+{
+ if (!syncrep_release_pending)
+ return;
+ syncrep_release_pending = false;
+ SyncRepReleaseWaiters();
+}
+
/*
* Process any incoming messages while streaming. Also checks if the remote
* end has closed the connection.
@@ -2379,6 +2413,7 @@ ProcessRepliesIfAny(void)
if (r < 0)
{
/* unexpected error or EOF */
+ SyncRepFlushPendingRelease();
ereport(COMMERROR,
(errcode(ERRCODE_PROTOCOL_VIOLATION),
errmsg("unexpected EOF on standby connection")));
@@ -2402,6 +2437,7 @@ ProcessRepliesIfAny(void)
maxmsglen = PQ_SMALL_MESSAGE_LIMIT;
break;
default:
+ SyncRepFlushPendingRelease();
ereport(FATAL,
(errcode(ERRCODE_PROTOCOL_VIOLATION),
errmsg("invalid standby message type \"%c\"",
@@ -2414,6 +2450,7 @@ ProcessRepliesIfAny(void)
resetStringInfo(&reply_message);
if (pq_getmessage(&reply_message, maxmsglen))
{
+ SyncRepFlushPendingRelease();
ereport(COMMERROR,
(errcode(ERRCODE_PROTOCOL_VIOLATION),
errmsg("unexpected EOF on standby connection")));
@@ -2429,6 +2466,7 @@ ProcessRepliesIfAny(void)
*/
case PqMsg_CopyData:
ProcessStandbyMessage();
+ INJECTION_POINT("walsender-reply-drained", NULL);
received = true;
break;
@@ -2450,9 +2488,12 @@ ProcessRepliesIfAny(void)
/*
* PqMsg_Terminate means that the standby is closing down the
- * socket.
+ * socket. The last reply it sent is drained already, and
+ * what that reply acknowledged must not leave with this
+ * process.
*/
case PqMsg_Terminate:
+ SyncRepFlushPendingRelease();
proc_exit(0);
default:
@@ -2468,6 +2509,13 @@ ProcessRepliesIfAny(void)
last_reply_timestamp = last_processing;
waiting_for_ping_response = false;
}
+
+ /*
+ * One release covers every reply drained above: the positions in shared
+ * memory are already the newest ones, and each release takes SyncRepLock
+ * exclusively.
+ */
+ SyncRepFlushPendingRelease();
}
/*
@@ -2498,6 +2546,7 @@ ProcessStandbyMessage(void)
break;
default:
+ SyncRepFlushPendingRelease();
ereport(COMMERROR,
(errcode(ERRCODE_PROTOCOL_VIOLATION),
errmsg("unexpected message type \"%c\"", msgtype)));
@@ -2633,8 +2682,14 @@ ProcessStandbyReplyMessage(void)
SpinLockRelease(&walsnd->mutex);
}
+ /*
+ * The release is left for ProcessRepliesIfAny() to run once per drain of
+ * the socket: several replies routinely sit in the buffer together, and
+ * every release takes SyncRepLock exclusively to compute positions this
+ * message has just made stale anyway.
+ */
if (!am_cascading_walsender)
- SyncRepReleaseWaiters();
+ syncrep_release_pending = true;
/*
* Advance our local xmin horizon when the client confirmed a flush.
diff --git a/src/test/recovery/meson.build b/src/test/recovery/meson.build
index 72113c5ac6e..1e9f37ddcd2 100644
--- a/src/test/recovery/meson.build
+++ b/src/test/recovery/meson.build
@@ -65,6 +65,7 @@ tests += {
't/054_unlogged_sequence_promotion.pl',
't/055_cascade_reconnect.pl',
't/056_standby_snapshot_export.pl',
+ 't/057_syncrep_release.pl',
],
},
}
diff --git a/src/test/recovery/t/057_syncrep_release.pl b/src/test/recovery/t/057_syncrep_release.pl
new file mode 100644
index 00000000000..bc205356fe0
--- /dev/null
+++ b/src/test/recovery/t/057_syncrep_release.pl
@@ -0,0 +1,206 @@
+# Copyright (c) 2026, PostgreSQL Global Development Group
+
+# A walsender coalesces the releases a drained batch of standby replies
+# asks for into one pass at the end of the drain. The drain has early
+# exits, the standby's goodbye being the common one, and a release owed
+# by a reply processed in the same drain must survive them: the positions are
+# in shared memory already, and a committer acknowledged by that reply has
+# nothing else to wake it. What this file proves is that a commit whose
+# ack arrives in the same drain as the standby's goodbye comes back.
+#
+# The choreography makes that coincidence certain instead of likely. A
+# paused standby holds a remote_apply committer in the queue while the
+# flush acks flow; the walsender is then held with SIGSTOP, the standby
+# is resumed, allowed to apply past the commit, and shut down, so its
+# final reply, the one carrying the apply position the committer waits
+# for, lands in the walsender's socket right next to the goodbye. The
+# walsender, released, drains both in one pass.
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Time::HiRes qw(usleep time);
+use Test::More;
+
+my $primary = PostgreSQL::Test::Cluster->new('rel_primary');
+$primary->init(allows_streaming => 1);
+$primary->append_conf(
+ 'postgresql.conf', q(
+autovacuum = off
+checkpoint_timeout = 1h
+));
+$primary->start;
+$primary->safe_psql('postgres', 'CREATE TABLE t (id int)');
+$primary->backup('bkp');
+
+# A node streaming from a backup reports its own name as its
+# application_name, which is what the synchronous set goes by.
+my $standby = PostgreSQL::Test::Cluster->new('rel_standby');
+$standby->init_from_backup($primary, 'bkp', has_streaming => 1);
+$standby->start;
+$primary->wait_for_catchup($standby, 'replay');
+
+$primary->safe_psql('postgres',
+ "ALTER SYSTEM SET synchronous_standby_names = 'rel_standby'");
+$primary->reload;
+$primary->poll_query_until('postgres',
+ "SELECT sync_state = 'sync' FROM pg_stat_replication WHERE application_name = 'rel_standby'"
+) or die "standby never became synchronous";
+
+# Hold replay: the flush acks keep flowing, the apply position does not,
+# so a remote_apply commit queues and stays queued.
+$standby->safe_psql('postgres', 'SELECT pg_wal_replay_pause()');
+
+my $committer = $primary->background_psql('postgres');
+$committer->query_until(
+ qr/inserting/, q(
+\echo inserting
+SET synchronous_commit = remote_apply;
+INSERT INTO t VALUES (1);
+));
+
+$primary->poll_query_until('postgres',
+ "SELECT count(*) > 0 FROM pg_stat_activity WHERE wait_event = 'SyncRep'")
+ or die "committer never reached the sync-rep queue";
+my $commit_lsn =
+ $primary->safe_psql('postgres', 'SELECT pg_current_wal_lsn()');
+
+# Hold the walsender, so everything the standby says from here on is
+# drained in one pass.
+my $walsender = $primary->safe_psql('postgres',
+ "SELECT pid FROM pg_stat_replication WHERE application_name = 'rel_standby'"
+);
+die "no walsender pid" unless $walsender =~ /^\d+$/;
+kill 'STOP', $walsender or die "SIGSTOP walsender: $!";
+
+# Let the standby apply past the commit, then say goodbye.
+$standby->safe_psql('postgres', 'SELECT pg_wal_replay_resume()');
+my $deadline = time() + 30;
+while (time() < $deadline)
+{
+ my $replayed = $standby->safe_psql('postgres',
+ "SELECT pg_last_wal_replay_lsn() >= '$commit_lsn'::pg_lsn");
+ last if $replayed eq 't';
+ usleep(100_000);
+}
+$standby->stop('fast');
+
+# The final reply and the goodbye are now side by side in the held
+# walsender's socket. Release it: the drain must not drop the release
+# the reply asks for on its way out.
+kill 'CONT', $walsender or die "SIGCONT walsender: $!";
+
+$deadline = time() + 10;
+my $released = 0;
+while (time() < $deadline)
+{
+ my $waiting = $primary->safe_psql('postgres',
+ "SELECT count(*) FROM pg_stat_activity WHERE wait_event = 'SyncRep'");
+ if ($waiting eq '0')
+ {
+ $released = 1;
+ last;
+ }
+ usleep(200_000);
+}
+ok($released,
+ 'a commit acknowledged in the drain the standby left in is released');
+
+# Free the committer session whatever state it is in.
+$primary->safe_psql('postgres',
+ "SELECT pg_cancel_backend(pid) FROM pg_stat_activity WHERE wait_event = 'SyncRep'"
+) if !$released;
+$committer->quit;
+
+# The other way out of the drain: an error thrown while parsing a later
+# message in the same pass. A reply processed just before it has already
+# asked for a release, and the walsender's error cleanup must run that
+# release on the way out. The connection is lost either way; the
+# committers the reply acknowledged are not. An injection point right
+# after a drained reply stands in for the torn message.
+#
+# The reply the error lands on has to be the one that carries the apply
+# position the committer waits for, and the injection point fires on
+# every drained reply, so no reply may reach the walsender between arming
+# it and the apply position passing the commit. Holding the
+# walreceiver with SIGSTOP is what guarantees that: replay proceeds from
+# WAL already on standby disk, and the receiver's first words on release
+# are the positions as they stand then.
+if (($ENV{enable_injection_points} // 'no') eq 'yes')
+{
+ $standby->start;
+ $primary->wait_for_catchup($standby, 'replay');
+ $primary->safe_psql('postgres', 'CREATE EXTENSION injection_points');
+
+ $standby->safe_psql('postgres', 'SELECT pg_wal_replay_pause()');
+
+ my $committer2 = $primary->background_psql('postgres');
+ $committer2->query_until(
+ qr/inserting2/, q(
+\echo inserting2
+SET synchronous_commit = remote_apply;
+INSERT INTO t VALUES (3);
+));
+ $primary->poll_query_until('postgres',
+ "SELECT count(*) > 0 FROM pg_stat_activity WHERE wait_event = 'SyncRep'"
+ ) or die "second committer never reached the sync-rep queue";
+ my $lsn2 = $primary->safe_psql('postgres', 'SELECT pg_current_wal_lsn()');
+
+ # The commit's WAL must be on standby disk before the receiver is
+ # held, or replay below has nothing to apply.
+ $standby->poll_query_until('postgres',
+ "SELECT pg_last_wal_receive_lsn() >= '$lsn2'::pg_lsn")
+ or die "standby never flushed the commit's WAL";
+
+ my $walreceiver =
+ $standby->safe_psql('postgres', 'SELECT pid FROM pg_stat_wal_receiver');
+ die "no walreceiver pid" unless $walreceiver =~ /^\d+$/;
+ kill 'STOP', $walreceiver or die "SIGSTOP walreceiver: $!";
+
+ # A reply already in flight when the receiver stopped is drained --
+ # and released, long before the injection point is armed.
+ usleep(300_000);
+ $primary->safe_psql('postgres',
+ "SELECT injection_points_attach('walsender-reply-drained', 'error')");
+
+ $standby->safe_psql('postgres', 'SELECT pg_wal_replay_resume()');
+ $deadline = time() + 30;
+ while (time() < $deadline)
+ {
+ my $replayed = $standby->safe_psql('postgres',
+ "SELECT pg_last_wal_replay_lsn() >= '$lsn2'::pg_lsn");
+ last if $replayed eq 't';
+ usleep(100_000);
+ }
+
+ # The receiver's first reply now carries an apply position past the
+ # commit, and the injection point tears the drain right after it.
+ kill 'CONT', $walreceiver or die "SIGCONT walreceiver: $!";
+
+ $deadline = time() + 15;
+ my $released2 = 0;
+ while (time() < $deadline)
+ {
+ my $waiting = $primary->safe_psql('postgres',
+ "SELECT count(*) FROM pg_stat_activity WHERE wait_event = 'SyncRep'"
+ );
+ if ($waiting eq '0')
+ {
+ $released2 = 1;
+ last;
+ }
+ usleep(200_000);
+ }
+ ok($released2,
+ 'a commit acknowledged right before a torn message is released');
+
+ $primary->safe_psql('postgres',
+ "SELECT injection_points_detach('walsender-reply-drained')");
+ $primary->safe_psql('postgres',
+ "SELECT pg_cancel_backend(pid) FROM pg_stat_activity WHERE wait_event = 'SyncRep'"
+ ) if !$released2;
+ $committer2->quit;
+}
+
+done_testing();
--
2.34.1
From dd26244920233f6618eab35ccabfb5845fb59ba8 Mon Sep 17 00:00:00 2001
From: Vadim Ponomarev <[email protected]>
Date: Sat, 15 Aug 2026 12:14:40 +0300
Subject: [PATCH v3 4/5] Let a committer whose acknowledgement already arrived
skip the queue lock
SyncRepWaitForLSN() runs on every commit that wrote WAL, and it takes
SyncRepLock exclusively before it can find out whether there is anything to
wait for. On a busy primary a large share of those commits find their LSN
already acknowledged and queue for nothing, so the answer costs them a
period of the lock every other committer is lining up on.
Turn lsn[] into an atomic watermark, and read it before taking the lock.
A watermark that already covers the commit's LSN says a valid quorum
acknowledged it, which is exactly the answer the check under the lock
gives. It is only ever moved forward, so a read gone stale can send a
committer to the slow path that would have exited, but never past a wait
it owes.
On platforms where pg_atomic_read_u64() is not a plain load the read is
itself a compare-and-exchange, or a spinlock acquisition where 64-bit
atomics are emulated. Whether the exit still pays for itself there is
untested.
---
src/backend/replication/syncrep.c | 80 ++++++++++++++-------
src/backend/replication/walsender.c | 3 +
src/include/replication/walsender_private.h | 13 +++-
3 files changed, 67 insertions(+), 29 deletions(-)
diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c
index 176f5d2935a..db89161739f 100644
--- a/src/backend/replication/syncrep.c
+++ b/src/backend/replication/syncrep.c
@@ -134,6 +134,25 @@ static int cmp_lsn(const void *a, const void *b);
static bool SyncRepQueueIsOrderedByLSN(int mode);
#endif
+/*
+ * Accessors for the position a queue's waiters have been released up to.
+ *
+ * Writers hold SyncRepLock and only ever move it forward, so a reader
+ * without the lock can be behind, never ahead.
+ */
+static inline XLogRecPtr
+SyncRepGetLSN(int mode)
+{
+ return pg_atomic_read_u64(&WalSndCtl->lsn[mode]);
+}
+
+static inline void
+SyncRepSetLSN(int mode, XLogRecPtr lsn)
+{
+ Assert(LWLockHeldByMeInMode(SyncRepLock, LW_EXCLUSIVE));
+ pg_atomic_write_u64(&WalSndCtl->lsn[mode], lsn);
+}
+
/*
* ===========================================================
* Synchronous Replication functions for normal user backends
@@ -198,42 +217,48 @@ SyncRepWaitForLSN(XLogRecPtr lsn, bool commit)
Assert(dlist_node_is_detached(&MyProc->syncRepLinks));
Assert(WalSndCtl != NULL);
+ Assert(MyProc->syncRepState == SYNC_REP_NOT_WAITING);
+
+ /*
+ * A released position that already covers this LSN says a valid quorum
+ * acknowledged it, which is the same answer the check below the lock
+ * would give. It only ever moves forward, so a stale read can only send
+ * us to take the lock for nothing, never past a wait we owe. How often
+ * this exit fires depends on the wait mode: it needs the acknowledgement
+ * to have arrived before the committer got here.
+ */
+ if (lsn <= SyncRepGetLSN(mode))
+ return;
LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
- Assert(MyProc->syncRepState == SYNC_REP_NOT_WAITING);
+
+ /*
+ * Read it again under the lock. The standby may have replied in the
+ * window since the check above, and this is the read that decides:
+ * anything the queue is released up to needs no wait, whether or not the
+ * sync standby data has been initialized yet.
+ */
+ if (lsn <= SyncRepGetLSN(mode))
+ {
+ LWLockRelease(SyncRepLock);
+ return;
+ }
/*
* We don't wait for sync rep if SYNC_STANDBY_DEFINED is not set. See
* SyncRepUpdateSyncStandbysDefined().
*
- * Also check that the standby hasn't already replied. Unlikely race
- * condition but we'll be fetching that cache line anyway so it's likely
- * to be a low cost check.
- *
* If the sync standby data has not been initialized yet
- * (SYNC_STANDBY_INIT is not set), fall back to a check based on the LSN,
- * then do a direct GUC check.
+ * (SYNC_STANDBY_INIT is not set), fall back to a direct GUC check.
*/
if (WalSndCtl->sync_standbys_status & SYNC_STANDBY_INIT)
{
- if ((WalSndCtl->sync_standbys_status & SYNC_STANDBY_DEFINED) == 0 ||
- lsn <= WalSndCtl->lsn[mode])
+ if ((WalSndCtl->sync_standbys_status & SYNC_STANDBY_DEFINED) == 0)
{
LWLockRelease(SyncRepLock);
return;
}
}
- else if (lsn <= WalSndCtl->lsn[mode])
- {
- /*
- * The LSN is older than what we need to wait for. The sync standby
- * data has not been initialized yet, but we are OK to not wait
- * because we know that there is no point in doing so based on the
- * LSN.
- */
- LWLockRelease(SyncRepLock);
- return;
- }
else if (!SyncStandbysDefined())
{
/*
@@ -566,19 +591,19 @@ SyncRepReleaseWaiters(void)
* Set the lsn first so that when we wake backends they will release up to
* this location.
*/
- if (WalSndCtl->lsn[SYNC_REP_WAIT_WRITE] < writePtr)
+ if (SyncRepGetLSN(SYNC_REP_WAIT_WRITE) < writePtr)
{
- WalSndCtl->lsn[SYNC_REP_WAIT_WRITE] = writePtr;
+ SyncRepSetLSN(SYNC_REP_WAIT_WRITE, writePtr);
numwrite = SyncRepWakeQueue(false, SYNC_REP_WAIT_WRITE);
}
- if (WalSndCtl->lsn[SYNC_REP_WAIT_FLUSH] < flushPtr)
+ if (SyncRepGetLSN(SYNC_REP_WAIT_FLUSH) < flushPtr)
{
- WalSndCtl->lsn[SYNC_REP_WAIT_FLUSH] = flushPtr;
+ SyncRepSetLSN(SYNC_REP_WAIT_FLUSH, flushPtr);
numflush = SyncRepWakeQueue(false, SYNC_REP_WAIT_FLUSH);
}
- if (WalSndCtl->lsn[SYNC_REP_WAIT_APPLY] < applyPtr)
+ if (SyncRepGetLSN(SYNC_REP_WAIT_APPLY) < applyPtr)
{
- WalSndCtl->lsn[SYNC_REP_WAIT_APPLY] = applyPtr;
+ SyncRepSetLSN(SYNC_REP_WAIT_APPLY, applyPtr);
numapply = SyncRepWakeQueue(false, SYNC_REP_WAIT_APPLY);
}
@@ -971,6 +996,7 @@ SyncRepWakeQueue(bool all, int mode)
{
int numprocs = 0;
dlist_mutable_iter iter;
+ XLogRecPtr lsn = SyncRepGetLSN(mode);
Assert(mode >= 0 && mode < NUM_SYNC_REP_WAIT_MODE);
Assert(LWLockHeldByMeInMode(SyncRepLock, LW_EXCLUSIVE));
@@ -983,7 +1009,7 @@ SyncRepWakeQueue(bool all, int mode)
/*
* Assume the queue is ordered by LSN
*/
- if (!all && WalSndCtl->lsn[mode] < proc->waitLSN)
+ if (!all && lsn < proc->waitLSN)
return numprocs;
/*
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 89fed06f851..5afcb7d6153 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -4097,7 +4097,10 @@ static void
WalSndShmemInit(void *arg)
{
for (int i = 0; i < NUM_SYNC_REP_WAIT_MODE; i++)
+ {
dlist_init(&(WalSndCtl->SyncRepQueue[i]));
+ pg_atomic_init_u64(&(WalSndCtl->lsn[i]), 0);
+ }
for (int i = 0; i < max_wal_senders; i++)
{
diff --git a/src/include/replication/walsender_private.h b/src/include/replication/walsender_private.h
index b0c80deeb24..36e3541d020 100644
--- a/src/include/replication/walsender_private.h
+++ b/src/include/replication/walsender_private.h
@@ -16,6 +16,7 @@
#include "lib/ilist.h"
#include "nodes/nodes.h"
#include "nodes/replnodes.h"
+#include "port/atomics.h"
#include "replication/syncrep.h"
#include "storage/condition_variable.h"
#include "storage/shmem.h"
@@ -91,9 +92,17 @@ typedef struct
/*
* Current location of the head of the queue. All waiters should have a
- * waitLSN that follows this value. Protected by SyncRepLock.
+ * waitLSN that follows this value. Writers hold SyncRepLock, since
+ * moving it forward is what releases the waiters it passes, and it is
+ * only ever moved forward.
+ *
+ * It is atomic so that a committer can read it without the lock: one
+ * whose LSN this value already covers was acknowledged by a valid quorum
+ * and has nothing to wait for. On platforms where a 64-bit atomic read
+ * is not a plain load, that read is itself a compare-and-exchange, or a
+ * spinlock acquisition where 64-bit atomics are emulated.
*/
- XLogRecPtr lsn[NUM_SYNC_REP_WAIT_MODE];
+ pg_atomic_uint64 lsn[NUM_SYNC_REP_WAIT_MODE];
/*
* Status of data related to the synchronous standbys. Waiting backends
--
2.34.1
From 744c3fef0ecb4c6082c833d2b7a844a9a645b658 Mon Sep 17 00:00:00 2001
From: Yura Sokolov <[email protected]>
Date: Thu, 17 Sep 2026 20:55:01 +0300
Subject: [PATCH v3 5/5] Add stream regress test for synchronous replication
It will allow to experiment with synchronous replication code more wildly.
027_stream_regress_sync.pl is a copy of 027_stream_regress.pl with couple
of changes:
- synchronous_commit is set to remote_apply
- second standby added and checked
- both standbys are made synchronous with ANY 2, so that remote_apply
covers both of them
- rely on remote_apply for standbys to catchup.
---
src/test/recovery/meson.build | 1 +
.../recovery/t/027_stream_regress_sync.pl | 240 ++++++++++++++++++
src/test/regress/expected/stats.out | 2 +-
src/test/regress/sql/stats.sql | 2 +-
4 files changed, 243 insertions(+), 2 deletions(-)
create mode 100644 src/test/recovery/t/027_stream_regress_sync.pl
diff --git a/src/test/recovery/meson.build b/src/test/recovery/meson.build
index 1e9f37ddcd2..3d46a84c3d6 100644
--- a/src/test/recovery/meson.build
+++ b/src/test/recovery/meson.build
@@ -36,6 +36,7 @@ tests += {
't/025_stuck_on_old_timeline.pl',
't/026_overwrite_contrecord.pl',
't/027_stream_regress.pl',
+ 't/027_stream_regress_sync.pl',
't/028_pitr_timelines.pl',
't/029_stats_restart.pl',
't/030_stats_cleanup_replica.pl',
diff --git a/src/test/recovery/t/027_stream_regress_sync.pl b/src/test/recovery/t/027_stream_regress_sync.pl
new file mode 100644
index 00000000000..dfda80c6691
--- /dev/null
+++ b/src/test/recovery/t/027_stream_regress_sync.pl
@@ -0,0 +1,240 @@
+
+# Copyright (c) 2026, PostgreSQL Global Development Group
+
+# Run the standard regression tests with streaming replication
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+use File::Basename;
+
+# Initialize primary node
+my $node_primary = PostgreSQL::Test::Cluster->new('primary');
+$node_primary->init(allows_streaming => 1);
+
+# Increase some settings that Cluster->new makes too low by default.
+$node_primary->adjust_conf('postgresql.conf', 'max_connections', '25');
+$node_primary->append_conf('postgresql.conf',
+ 'max_prepared_transactions = 10');
+
+# Enable pg_stat_statements to force tests to do query jumbling.
+# pg_stat_statements.max should be large enough to hold all the entries
+# of the regression database.
+$node_primary->append_conf(
+ 'postgresql.conf',
+ qq{shared_preload_libraries = 'pg_stat_statements'
+pg_stat_statements.max = 50000
+compute_query_id = 'regress'
+});
+
+# We'll stick with Cluster->new's small default shared_buffers, but since that
+# makes synchronized seqscans more probable, it risks changing the results of
+# some test queries. Disable synchronized seqscans to prevent that.
+$node_primary->append_conf('postgresql.conf', 'synchronize_seqscans = off');
+
+# Use the strictest commit mode, so that a committed transaction is on both
+# standbys by the time COMMIT returns. The dump comparisons below rely on
+# that: they take no wait of their own.
+$node_primary->append_conf('postgresql.conf',
+ 'synchronous_commit = remote_apply');
+
+# WAL consistency checking is resource intensive so require opt-in with the
+# PG_TEST_EXTRA environment variable.
+if ( $ENV{PG_TEST_EXTRA}
+ && $ENV{PG_TEST_EXTRA} =~ m/\bwal_consistency_checking\b/)
+{
+ $node_primary->append_conf('postgresql.conf',
+ 'wal_consistency_checking = all');
+}
+
+$node_primary->start;
+is( $node_primary->psql(
+ 'postgres',
+ qq[SELECT pg_create_physical_replication_slot('standby_1');]),
+ 0,
+ 'physical slot 1 created on primary');
+is( $node_primary->psql(
+ 'postgres',
+ qq[SELECT pg_create_physical_replication_slot('standby_2');]),
+ 0,
+ 'physical slot 2 created on primary');
+my $backup_name = 'my_backup';
+
+# Take backup
+$node_primary->backup($backup_name);
+
+# Create streaming standby linking to primary
+my $node_standby_1 = PostgreSQL::Test::Cluster->new('standby_1');
+$node_standby_1->init_from_backup($node_primary, $backup_name,
+ has_streaming => 1);
+$node_standby_1->append_conf('postgresql.conf',
+ "primary_slot_name = standby_1");
+$node_standby_1->append_conf('postgresql.conf',
+ 'max_standby_streaming_delay = 600s');
+$node_standby_1->start;
+
+my $node_standby_2 = PostgreSQL::Test::Cluster->new('standby_2');
+$node_standby_2->init_from_backup($node_primary, $backup_name,
+ has_streaming => 1);
+$node_standby_2->append_conf('postgresql.conf',
+ "primary_slot_name = standby_2");
+$node_standby_2->append_conf('postgresql.conf',
+ 'max_standby_streaming_delay = 600s');
+$node_standby_2->start;
+
+# Both standbys have to be synchronous. A bare list would mean FIRST 1, which
+# makes only the first one synchronous and leaves the second one free to lag
+# behind the dumps taken below.
+$node_primary->safe_psql('postgres',
+ "ALTER SYSTEM SET synchronous_standby_names = 'ANY 2 (standby_1, standby_2)';"
+);
+$node_primary->reload;
+
+my $dlpath = dirname($ENV{REGRESS_SHLIB});
+my $outputdir = $PostgreSQL::Test::Utils::tmp_check;
+
+# Run the regression tests against the primary.
+my $extra_opts = $ENV{EXTRA_REGRESS_OPTS} || "";
+command_ok(
+ [
+ $ENV{PG_REGRESS},
+ split(' ', $extra_opts),
+ "--dlpath=$dlpath",
+ '--bindir=',
+ '--host=' . $node_primary->host,
+ '--port=' . $node_primary->port,
+ '--schedule=../regress/parallel_schedule',
+ '--max-concurrent-tests=20',
+ '--inputdir=../regress',
+ "--outputdir=$outputdir"
+ ],
+ 'regression tests pass');
+
+my $primary_alive = $node_primary->is_alive;
+my $standby1_alive = $node_standby_1->is_alive;
+my $standby2_alive = $node_standby_2->is_alive;
+is($primary_alive, 1, 'primary alive after regression test run');
+is($standby1_alive, 1, 'standby_1 alive after regression test run');
+is($standby2_alive, 1, 'standby_2 alive after regression test run');
+
+# Clobber all sequences with their next value, so that we don't have
+# differences between nodes due to caching.
+$node_primary->psql('regression',
+ "select setval(seqrelid, nextval(seqrelid)) from pg_sequence");
+
+# No need to wait for the standbys to catch up: under remote_apply both
+# have applied everything committed above before COMMIT returned.
+
+# Perform a logical dump of primary and standby, and check that they match
+command_ok(
+ [
+ 'pg_dumpall',
+ '--file' => $outputdir . '/primary.dump',
+ '--no-sync', '--no-statistics',
+ '--restrict-key' => 'test',
+ '--port' => $node_primary->port,
+ '--no-unlogged-table-data', # if unlogged, standby has schema only
+ ],
+ 'dump primary server');
+command_ok(
+ [
+ 'pg_dumpall',
+ '--file' => $outputdir . '/standby1.dump',
+ '--no-sync', '--no-statistics',
+ '--restrict-key' => 'test',
+ '--port' => $node_standby_1->port,
+ ],
+ 'dump standby_1 server');
+command_ok(
+ [
+ 'pg_dumpall',
+ '--file' => $outputdir . '/standby2.dump',
+ '--no-sync', '--no-statistics',
+ '--restrict-key' => 'test',
+ '--port' => $node_standby_2->port,
+ ],
+ 'dump standby_2 server');
+compare_files(
+ $outputdir . '/primary.dump',
+ $outputdir . '/standby1.dump',
+ 'compare primary and standby_1 dumps');
+compare_files(
+ $outputdir . '/primary.dump',
+ $outputdir . '/standby2.dump',
+ 'compare primary and standby_2 dumps');
+
+# Likewise for the catalogs of the regression database, after disabling
+# autovacuum to make fields like relpages stop changing.
+$node_primary->append_conf('postgresql.conf', 'autovacuum = off');
+$node_primary->restart;
+command_ok(
+ [
+ 'pg_dump',
+ '--schema' => 'pg_catalog',
+ '--file' => $outputdir . '/catalogs_primary.dump',
+ '--no-sync',
+ '--restrict-key' => 'test',
+ '--port', $node_primary->port,
+ '--no-unlogged-table-data',
+ 'regression',
+ ],
+ 'dump catalogs of primary server');
+command_ok(
+ [
+ 'pg_dump',
+ '--schema' => 'pg_catalog',
+ '--file' => $outputdir . '/catalogs_standby1.dump',
+ '--no-sync',
+ '--restrict-key' => 'test',
+ '--port' => $node_standby_1->port,
+ 'regression',
+ ],
+ 'dump catalogs of standby_1 server');
+command_ok(
+ [
+ 'pg_dump',
+ '--schema' => 'pg_catalog',
+ '--file' => $outputdir . '/catalogs_standby2.dump',
+ '--no-sync',
+ '--restrict-key' => 'test',
+ '--port' => $node_standby_2->port,
+ 'regression',
+ ],
+ 'dump catalogs of standby_2 server');
+compare_files(
+ $outputdir . '/catalogs_primary.dump',
+ $outputdir . '/catalogs_standby1.dump',
+ 'compare primary and standby_1 catalog dumps');
+compare_files(
+ $outputdir . '/catalogs_primary.dump',
+ $outputdir . '/catalogs_standby2.dump',
+ 'compare primary and standby_2 catalog dumps');
+
+# Check some data from pg_stat_statements.
+$node_primary->safe_psql('postgres', 'CREATE EXTENSION pg_stat_statements');
+# This gathers data based on the first characters for some common query types,
+# checking that reports are generated for SELECT, DMLs, and DDL queries with
+# CREATE.
+my $result = $node_primary->safe_psql(
+ 'postgres',
+ qq{WITH select_stats AS
+ (SELECT upper(substr(query, 1, 6)) AS select_query
+ FROM pg_stat_statements
+ WHERE upper(substr(query, 1, 6)) IN ('SELECT', 'UPDATE',
+ 'INSERT', 'DELETE',
+ 'CREATE'))
+ SELECT select_query, count(select_query) > 1 AS some_rows
+ FROM select_stats
+ GROUP BY select_query ORDER BY select_query;});
+is( $result, qq(CREATE|t
+DELETE|t
+INSERT|t
+SELECT|t
+UPDATE|t), 'check contents of pg_stat_statements on regression database');
+
+$node_standby_1->stop;
+$node_standby_2->stop;
+$node_primary->stop;
+
+done_testing();
diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out
index 8b15471248b..4b2f2a50882 100644
--- a/src/test/regress/expected/stats.out
+++ b/src/test/regress/expected/stats.out
@@ -1669,7 +1669,7 @@ SELECT current_setting('fsync') = 'off'
SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
FROM pg_stat_io
WHERE context = 'normal' AND object = 'wal' \gset io_sum_wal_normal_after_
-SELECT current_setting('synchronous_commit') = 'on';
+SELECT current_setting('synchronous_commit') IN ('on', 'remote_apply');
?column?
----------
t
diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql
index 674637e172b..c69b5db4af1 100644
--- a/src/test/regress/sql/stats.sql
+++ b/src/test/regress/sql/stats.sql
@@ -769,7 +769,7 @@ SELECT current_setting('fsync') = 'off'
SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs
FROM pg_stat_io
WHERE context = 'normal' AND object = 'wal' \gset io_sum_wal_normal_after_
-SELECT current_setting('synchronous_commit') = 'on';
+SELECT current_setting('synchronous_commit') IN ('on', 'remote_apply');
SELECT :io_sum_wal_normal_after_writes > :io_sum_wal_normal_before_writes;
SELECT current_setting('fsync') = 'off'
OR current_setting('wal_sync_method') IN ('open_sync', 'open_datasync')
--
2.34.1
