Thanks for the review!
Updatedthe patchbasedonyourcomments. Regards, Andrey Silitskiy
From 948127c0edef957559c5ae6e61b81d75f394831d Mon Sep 17 00:00:00 2001
From: "a.silitskiy" <[email protected]>
Date: Fri, 28 Nov 2025 14:40:10 +0700
Subject: [PATCH v5] Introduce a new GUC 'wal_sender_shutdown_mode'.
Previously, at shutdown, walsender processes were always waiting to send all
pending data and ensure that all data is flushed in remote node. But in some cases
an unexpected wait may be unacceptable. For example, in logical replication,
apply_workers may hang on locks for some time, excluding the possibility of
sender's shutdown.
New guc allows to change shutdown mode of walsenders without changing
default behavior.
The shutdown modes are:
1) 'wait_flush' (the default). In this mode, the walsender will wait for all
WALs to be flushed on the receiver side, before exiting the process.
2) 'immediate'. In this mode, the walsender will exit without confirming the
remote flush. This may break the consistency between sender and receiver.
This mode might be useful for a system that has a high-latency network (to
reduce the amount of time for shutdown), or to allow the shutdown of
publisher even when when the subscriber's apply_worker is waiting for any
locks to be released.
Author: Andrey Silitskiy
Co-authored by: Hayato Kuroda
Discussion: https://postgr.es/m/TYAPR01MB586668E50FC2447AD7F92491F5E89%40TYAPR01MB5866.jpnprd01.prod.outlook.com
---
doc/src/sgml/config.sgml | 30 +++++
doc/src/sgml/high-availability.sgml | 9 +-
src/backend/replication/walsender.c | 52 ++++++++
src/backend/utils/misc/guc_parameters.dat | 7 +
src/backend/utils/misc/guc_tables.c | 6 +
src/backend/utils/misc/postgresql.conf.sample | 2 +
src/include/replication/walsender.h | 7 +
src/test/subscription/meson.build | 1 +
.../t/037_walsnd_immediate_shutdown.pl | 121 ++++++++++++++++++
src/tools/pgindent/typedefs.list | 1 +
10 files changed, 232 insertions(+), 4 deletions(-)
create mode 100644 src/test/subscription/t/037_walsnd_immediate_shutdown.pl
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 5560b95ee60..c8c5e736cd5 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4722,6 +4722,36 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows
</listitem>
</varlistentry>
+ <varlistentry id="guc-wal_sender_shutdown_mode" xreflabel="wal_sender_shutdown_mode">
+ <term><varname>wal_sender_shutdown_mode</varname> (<type>enum</type>)
+ <indexterm>
+ <primary><varname>wal_sender_shutdown_mode</varname> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the mode in which walsender process will terminate
+ after receival of shutdown request. Valid values are <literal>wait_flush</literal>
+ and <literal>immediate</literal>. Default value is <literal>wait_flush</literal>.
+ Can be set for each walsender.
+ </para>
+ <para>
+ In <literal>wait_flush</literal> mode, the walsender will wait for all
+ WAL data to be flushed on the receiver side, before exiting the process.
+ This helps to keep the sender and receiver in sync after shutdown, which is
+ especially important for physical replication switchovers. However,
+ it can delay server shutdown.
+ </para>
+ <para>
+ In <literal>immediate</literal> mode, the walsender will exit without waiting
+ for WAL data replication to the receiver. This can reduce shutdown time when
+ flushing WAL data to the receiver would take a long time, for example on
+ high-latency networks or when the subscriber's apply worker is blocked waiting
+ for locks in logical replication.
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry id="guc-synchronized-standby-slots" xreflabel="synchronized_standby_slots">
<term><varname>synchronized_standby_slots</varname> (<type>string</type>)
<indexterm>
diff --git a/doc/src/sgml/high-availability.sgml b/doc/src/sgml/high-availability.sgml
index c3f269e0364..65e119f4851 100644
--- a/doc/src/sgml/high-availability.sgml
+++ b/doc/src/sgml/high-availability.sgml
@@ -1190,10 +1190,11 @@ primary_slot_name = 'node_a_slot'
</para>
<para>
- Users will stop waiting if a fast shutdown is requested. However, as
- when using asynchronous replication, the server will not fully
- shutdown until all outstanding WAL records are transferred to the currently
- connected standby servers.
+ Users will stop waiting if a fast shutdown is requested. However, if
+ <varname>wal_sender_shutdown_mode<varname> is set to <literal>wait_flush<literal>, the
+ server will not fully shutdown until all outstanding WAL records are
+ transferred to the currently connected standby servers. This waiting
+ applies to both asynchronous and synchronous replication.
</para>
</sect3>
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a0e6a3d200c..80cd6086908 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -35,6 +35,8 @@
* checkpoint finishes, the postmaster sends us SIGUSR2. This instructs
* walsender to send any outstanding WAL, including the shutdown checkpoint
* record, wait for it to be replicated to the standby, and then exit.
+ * If wal_sender_shutdown_mode = immediate is set, walsender process will
+ * skip these steps and terminate after receival of shutdown request.
*
*
* Portions Copyright (c) 2010-2026, PostgreSQL Global Development Group
@@ -130,6 +132,9 @@ int max_wal_senders = 10; /* the maximum number of concurrent
* walsenders */
int wal_sender_timeout = 60 * 1000; /* maximum time to send one WAL
* data message */
+
+int wal_sender_shutdown_mode = WALSND_SHUTDOWN_MODE_WAIT_FLUSH;
+
bool log_replication_commands = false;
/*
@@ -262,6 +267,7 @@ static void WalSndKill(int code, Datum arg);
pg_noreturn static void WalSndShutdown(void);
static void XLogSendPhysical(void);
static void XLogSendLogical(void);
+pg_noreturn static void WalSndDoneImmediate(void);
static void WalSndDone(WalSndSendDataCallback send_data);
static void IdentifySystem(void);
static void UploadManifest(void);
@@ -1656,6 +1662,11 @@ ProcessPendingWrites(void)
/* Try to flush pending output to the client */
if (pq_flush_if_writable() != 0)
WalSndShutdown();
+
+ /* If we got shut down request in immediate shutdown mode, exit the process */
+ if ((got_STOPPING || got_SIGUSR2) &&
+ wal_sender_shutdown_mode == WALSND_SHUTDOWN_MODE_IMMEDIATE)
+ WalSndDoneImmediate();
}
/* reactivate latch so WalSndLoop knows to continue */
@@ -2933,6 +2944,14 @@ WalSndLoop(WalSndSendDataCallback send_data)
if (pq_flush_if_writable() != 0)
WalSndShutdown();
+ /*
+ * When immediate shutdown of walsender is requested, we do not
+ * wait for successfull sending of all data.
+ */
+ if ((got_STOPPING || got_SIGUSR2) &&
+ wal_sender_shutdown_mode == WALSND_SHUTDOWN_MODE_IMMEDIATE)
+ WalSndDoneImmediate();
+
/* If nothing remains to be sent right now ... */
if (WalSndCaughtUp && !pq_is_send_pending())
{
@@ -3581,6 +3600,39 @@ XLogSendLogical(void)
}
}
+/*
+ * Shutdown walsender in immediate mode.
+ */
+static void
+WalSndDoneImmediate()
+{
+ QueryCompletion qc;
+
+ /* Try to inform receiver that XLOG streaming is done */
+ SetQueryCompletion(&qc, CMDTAG_COPY, 0);
+ EndCommand(&qc, DestRemote, false);
+
+ /*
+ * Note that the output buffer may be full during immediate shutdown of
+ * walsender. If pq_flush() is called at that time, the walsender process
+ * will be stuck. Therefore, call pq_flush_if_writable() instead. Successfull
+ * receival of done message in immediate shutdown mode is not guaranteed.
+ */
+ pq_flush_if_writable();
+
+ /*
+ * Prevent ereport from attempting to send any more messages to the standby.
+ * Otherwise it can cause process stuck if output buffers are full.
+ */
+ if (whereToSendOutput == DestRemote)
+ whereToSendOutput = DestNone;
+
+ ereport(WARNING,
+ (errmsg("walsender shutting down in immediate mode: replication may be incomplete")));
+
+ proc_exit(0);
+}
+
/*
* Shutdown if the sender is caught up.
*
diff --git a/src/backend/utils/misc/guc_parameters.dat b/src/backend/utils/misc/guc_parameters.dat
index f0260e6e412..1b2267a1a15 100644
--- a/src/backend/utils/misc/guc_parameters.dat
+++ b/src/backend/utils/misc/guc_parameters.dat
@@ -3429,6 +3429,13 @@
check_hook => 'check_wal_segment_size',
},
+{ name => 'wal_sender_shutdown_mode', type => 'enum', context => 'PGC_USERSET', group => 'REPLICATION_SENDING',
+ short_desc => 'Sets the mode in which walsender will be terminated after shutdown request.',
+ variable => 'wal_sender_shutdown_mode',
+ boot_val => 'WALSND_SHUTDOWN_MODE_WAIT_FLUSH',
+ options => 'wal_sender_shutdown_mode_options',
+},
+
{ name => 'wal_sender_timeout', type => 'int', context => 'PGC_USERSET', group => 'REPLICATION_SENDING',
short_desc => 'Sets the maximum time to wait for WAL replication.',
flags => 'GUC_UNIT_MS',
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index 13c569d8790..017c3f98b4f 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -335,6 +335,12 @@ static const struct config_enum_entry constraint_exclusion_options[] = {
{NULL, 0, false}
};
+static const struct config_enum_entry wal_sender_shutdown_mode_options[] = {
+ {"wait_flush", WALSND_SHUTDOWN_MODE_WAIT_FLUSH, false},
+ {"immediate", WALSND_SHUTDOWN_MODE_IMMEDIATE, false},
+ {NULL, 0, false}
+};
+
/*
* Although only "on", "off", "remote_apply", "remote_write", and "local" are
* documented, we accept all the likely variants of "on" and "off".
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index c4f92fcdac8..29172585b93 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -344,6 +344,8 @@
#max_slot_wal_keep_size = -1 # in megabytes; -1 disables
#idle_replication_slot_timeout = 0 # in seconds; 0 disables
#wal_sender_timeout = 60s # in milliseconds; 0 disables
+#wal_sender_shutdown_mode = wait_flush # walsender termination mode after
+ # receival of shutdown request
#track_commit_timestamp = off # collect timestamp of transaction commit
# (change requires restart)
diff --git a/src/include/replication/walsender.h b/src/include/replication/walsender.h
index a4df3b8e0ae..3f962ea2792 100644
--- a/src/include/replication/walsender.h
+++ b/src/include/replication/walsender.h
@@ -24,6 +24,12 @@ typedef enum
CRS_USE_SNAPSHOT,
} CRSSnapshotAction;
+typedef enum
+{
+ WALSND_SHUTDOWN_MODE_WAIT_FLUSH = 0,
+ WALSND_SHUTDOWN_MODE_IMMEDIATE
+} WalSndShutdownMode;
+
/* global state */
extern PGDLLIMPORT bool am_walsender;
extern PGDLLIMPORT bool am_cascading_walsender;
@@ -33,6 +39,7 @@ extern PGDLLIMPORT bool wake_wal_senders;
/* user-settable parameters */
extern PGDLLIMPORT int max_wal_senders;
extern PGDLLIMPORT int wal_sender_timeout;
+extern PGDLLIMPORT int wal_sender_shutdown_mode;
extern PGDLLIMPORT bool log_replication_commands;
extern void InitWalSender(void);
diff --git a/src/test/subscription/meson.build b/src/test/subscription/meson.build
index a4c7dbaff59..3b9d27fba0b 100644
--- a/src/test/subscription/meson.build
+++ b/src/test/subscription/meson.build
@@ -46,6 +46,7 @@ tests += {
't/034_temporal.pl',
't/035_conflicts.pl',
't/036_sequences.pl',
+ 't/037_walsnd_immediate_shutdown.pl',
't/100_bugs.pl',
],
},
diff --git a/src/test/subscription/t/037_walsnd_immediate_shutdown.pl b/src/test/subscription/t/037_walsnd_immediate_shutdown.pl
new file mode 100644
index 00000000000..c991b274cd0
--- /dev/null
+++ b/src/test/subscription/t/037_walsnd_immediate_shutdown.pl
@@ -0,0 +1,121 @@
+# Copyright (c) 2026, PostgreSQL Global Development Group
+
+# Checks that publisher is able to shut down without
+# waiting for sending of all pending data to subscriber
+# with wal_sender_shutdown_mode = immediate
+
+use strict;
+use warnings FATAL => 'all';
+
+use PostgreSQL::Test::Cluster;
+use Test::More;
+
+# create publisher
+my $publisher = PostgreSQL::Test::Cluster->new('publisher');
+$publisher->init(allows_streaming => 'logical');
+# set wal_sender_shutdown_mode GUC parameter to immediate
+$publisher->append_conf('postgresql.conf',
+ "wal_sender_timeout = 0
+ wal_sender_shutdown_mode = 'immediate'");
+$publisher->start();
+
+# create subscriber
+my $subscriber = PostgreSQL::Test::Cluster->new('subscriber');
+$subscriber->init();
+$subscriber->append_conf('postgresql.conf',
+ "wal_receiver_status_interval = 1");
+$subscriber->start();
+
+# create publication for test table
+$publisher->safe_psql('postgres', q{
+ CREATE TABLE pub_test (id int PRIMARY KEY);
+ CREATE PUBLICATION pub_all FOR TABLE pub_test;
+});
+
+# create matching table on subscriber
+$subscriber->safe_psql('postgres', q{
+ CREATE TABLE pub_test (id int PRIMARY KEY);
+});
+
+# form connection string to publisher
+my $pub_connstr = $publisher->connstr;
+
+# create the subscription on subscriber
+$subscriber->safe_psql('postgres', qq{
+ CREATE SUBSCRIPTION sub_all
+ CONNECTION '$pub_connstr'
+ PUBLICATION pub_all;
+});
+
+# wait for initial sync to finish
+$subscriber->wait_for_subscription_sync($publisher, 'sub_all');
+
+# create background psql session
+my $bpgsql = $subscriber->background_psql('postgres', on_error_stop => 0);
+
+# =============================================================================
+# Testcase start: Shutdown of publisher with empty output buffers
+
+# start transaction on subscriber to hold locks
+$bpgsql->query_safe(
+ "BEGIN; INSERT INTO pub_test VALUES (0);"
+);
+
+# run concurrent transaction on publisher and commit
+$publisher->safe_psql('postgres', 'BEGIN; INSERT INTO pub_test VALUES (0); COMMIT;');
+
+# test publisher shutdown
+$publisher->stop('fast');
+pass('successfull fast shutdown of server with empty output buffers');
+
+# Testcase end: Shutdown of publisher with empty output buffers
+# =============================================================================
+
+$bpgsql->query_safe(
+ "ABORT;"
+);
+
+# restart publisher for the next testcase
+$publisher->start();
+
+$publisher->wait_for_catchup('sub_all');
+
+# =============================================================================
+# Testcase start: Shutdown of publisher with full output buffers
+
+# lock table to make apply_worker hang
+$bpgsql->query_safe(
+ "BEGIN; LOCK TABLE pub_test IN EXCLUSIVE MODE;"
+);
+
+my $last_sent_lsn = $publisher->safe_psql('postgres', "select sent_lsn from pg_stat_replication where application_name = 'sub_all';");
+my $cur_sent_lsn;
+
+# generate big amount of wal records for locked table
+$publisher->safe_psql('postgres', 'BEGIN; INSERT INTO pub_test SELECT i from generate_series(1, 25000) s(i); COMMIT;');
+
+# waiting for walsender to fill output buffers
+my $max_attempts = $PostgreSQL::Test::Utils::timeout_default;
+while ($max_attempts-- >= 0)
+{
+ sleep 1;
+
+ $cur_sent_lsn = $publisher->safe_psql('postgres', "select sent_lsn from pg_stat_replication where application_name = 'sub_all';");
+
+ my $diff = $publisher->safe_psql('postgres', qq(
+ SELECT pg_wal_lsn_diff('$cur_sent_lsn', '$last_sent_lsn');
+ ));
+
+ last if $diff == 0;
+
+ $last_sent_lsn = $cur_sent_lsn;
+}
+
+# test publisher shutdown
+$publisher->stop('fast');
+pass('successfull fast shutdown of server with full output buffers');
+
+# Testcase end: Shutdown of publisher with full output buffers
+# =============================================================================
+
+done_testing();
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ddbe4c64971..6ec7fef2f29 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3330,6 +3330,7 @@ WalReceiverFunctionsType
WalSnd
WalSndCtlData
WalSndSendDataCallback
+WalSndShutdownMode
WalSndState
WalSummarizerData
WalSummaryFile
--
2.34.1
