From: Alexander Korotkov <akorotkov@postgresql.org>
Date: Mon, 5 Jan 2026 17:41:31 +0000 (+0200)
Subject: Use WAIT FOR LSN in PostgreSQL::Test::Cluster::wait_for_catchup()
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=f30848cb05d4d63e1a5a2d6a9d72604f3b63370d;p=thirdparty%2Fpostgresql.git

Use WAIT FOR LSN in PostgreSQL::Test::Cluster::wait_for_catchup()

When the standby is passed as a PostgreSQL::Test::Cluster instance,
use the WAIT FOR LSN command on the standby server to implement
wait_for_catchup() for replay, write, and flush modes.  This is more
efficient than polling pg_stat_replication on the upstream, as the
WAIT FOR LSN command uses a latch-based wakeup mechanism.

The optimization applies when:
- The standby is passed as a Cluster object (not just a name string)
- The mode is 'replay', 'write', or 'flush' (not 'sent')
- The standby is in recovery

For 'sent' mode, when the standby is passed as a string (e.g., a
subscription name for logical replication), or when the standby has
been promoted, the function falls back to the original polling-based
approach using pg_stat_replication on the upstream.

Discussion: https://postgr.es/m/CABPTF7UiArgW-sXj9CNwRzUhYOQrevLzkYcgBydmX5oDes1sjg%40mail.gmail.com
Author: Xuneng Zhou <xunengzhou@gmail.com>
Reviewed-by: Alexander Korotkov <aekorotkov@gmail.com>
Reviewed-by: Chao Li <li.evan.chao@gmail.com>
Reviewed-by: Alvaro Herrera <alvherre@kurilemu.de>
---

diff --git a/src/test/perl/PostgreSQL/Test/Cluster.pm b/src/test/perl/PostgreSQL/Test/Cluster.pm
index 955dfc0e7f8..a28ea89aa10 100644
--- a/src/test/perl/PostgreSQL/Test/Cluster.pm
+++ b/src/test/perl/PostgreSQL/Test/Cluster.pm
@@ -3320,6 +3320,13 @@ If you pass an explicit value of target_lsn, it should almost always be
 the primary's write LSN; so this parameter is seldom needed except when
 querying some intermediate replication node rather than the primary.
 
+When the standby is passed as a PostgreSQL::Test::Cluster instance and is
+in recovery, this function uses the WAIT FOR LSN command on the standby
+for modes replay, write, and flush.  This is more efficient than polling
+pg_stat_replication on the upstream, as WAIT FOR LSN uses a latch-based
+wakeup mechanism.  For 'sent' mode, or when the standby is passed as a
+string (e.g., a subscription name), it falls back to polling.
+
 If there is no active replication connection from this peer, waits until
 poll_query_until timeout.
 
@@ -3339,10 +3346,13 @@ sub wait_for_catchup
 	  . join(', ', keys(%valid_modes))
 	  unless exists($valid_modes{$mode});
 
-	# Allow passing of a PostgreSQL::Test::Cluster instance as shorthand
+	# Keep a reference to the standby node if passed as an object, so we can
+	# use WAIT FOR LSN on it later.
+	my $standby_node;
 	if (blessed($standby_name)
 		&& $standby_name->isa("PostgreSQL::Test::Cluster"))
 	{
+		$standby_node = $standby_name;
 		$standby_name = $standby_name->name;
 	}
 	if (!defined($target_lsn))
@@ -3367,6 +3377,53 @@ sub wait_for_catchup
 	  . $self->name . "\n";
 	# Before release 12 walreceiver just set the application name to
 	# "walreceiver"
+
+	# Use WAIT FOR LSN on the standby when:
+	# - The standby was passed as a Cluster object (so we can connect to it)
+	# - The mode is replay, write, or flush (not 'sent')
+	# - The standby is in recovery
+	# This is more efficient than polling pg_stat_replication on the upstream,
+	# as WAIT FOR LSN uses a latch-based wakeup mechanism.
+	if (defined($standby_node) && ($mode ne 'sent'))
+	{
+		my $standby_in_recovery =
+		  $standby_node->safe_psql('postgres', "SELECT pg_is_in_recovery()");
+		chomp($standby_in_recovery);
+
+		if ($standby_in_recovery eq 't')
+		{
+			# Map mode names to WAIT FOR LSN mode names
+			my %mode_map = (
+				'replay' => 'standby_replay',
+				'write' => 'standby_write',
+				'flush' => 'standby_flush',);
+			my $wait_mode = $mode_map{$mode};
+			my $timeout = $PostgreSQL::Test::Utils::timeout_default;
+			my $wait_query =
+			  qq[WAIT FOR LSN '${target_lsn}' WITH (MODE '${wait_mode}', timeout '${timeout}s', no_throw);];
+			my $output = $standby_node->safe_psql('postgres', $wait_query);
+			chomp($output);
+
+			if ($output ne 'success')
+			{
+				# Fetch additional detail for debugging purposes
+				my $details = $self->safe_psql('postgres',
+					"SELECT * FROM pg_catalog.pg_stat_replication");
+				diag qq(WAIT FOR LSN failed with status:
+	${output});
+				diag qq(Last pg_stat_replication contents:
+	${details});
+				croak "failed waiting for catchup";
+			}
+			print "done\n";
+			return;
+		}
+	}
+
+	# Fall back to polling pg_stat_replication on the upstream for:
+	# - 'sent' mode (no corresponding WAIT FOR LSN mode)
+	# - When standby_name is a string (e.g., subscription name)
+	# - When the standby is no longer in recovery (was promoted)
 	my $query = qq[SELECT '$target_lsn' <= ${mode}_lsn AND state = 'streaming'
          FROM pg_catalog.pg_stat_replication
          WHERE application_name IN ('$standby_name', 'walreceiver')];