From: Michael Paquier <michael@paquier.xyz>
Date: Mon, 6 Apr 2026 04:23:28 +0000 (+0900)
Subject: Improve more stability of worker_spi termination test
X-Git-Tag: REL_19_BETA1~460
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=283c5fb22b44562428700284aad23eb5245b19d8;p=thirdparty%2Fpostgresql.git

Improve more stability of worker_spi termination test

Alexander Lakhin has noticed that it can be possible on machines with
slow storage to have the spawned workers be stuck in
initialize_worker_spi(), before they reach their main loop.  Waiting for
a flush to happen would block the interrupt attempts done by the
database commands, causing the test to fail on timeout once the number
of interrupt attempts is reached in CountOtherDBBackends().

This commit switches the test to wait for the spawned bgworkers to reach
their main loops before attempting the database commands that would
trigger the interrupts, napping for a time larger than the default, with
worker_spi.naptime set at 10 minutes.  Another thing that could be
attempted is to enforce a larger number of tries in
CountOtherDBBackends(), if what is done here is not enough.  Let's see
first if what this commit does is enough for the buildfarm members
widowbird and jay.

Analyzed-by: Alexander Lakhin <exclusion@gmail.com>
Discussion: https://postgr.es/m/f913fba1-da59-404c-9eb3-07c7304be637@gmail.com
---

diff --git a/src/test/modules/worker_spi/t/002_worker_terminate.pl b/src/test/modules/worker_spi/t/002_worker_terminate.pl
index b0e6a5376d4..69972a838dc 100644
--- a/src/test/modules/worker_spi/t/002_worker_terminate.pl
+++ b/src/test/modules/worker_spi/t/002_worker_terminate.pl
@@ -20,7 +20,6 @@ if ($ENV{enable_injection_points} ne 'yes')
 sub launch_bgworker
 {
 	my ($node, $database, $testcase, $interruptible) = @_;
-	my $offset = -s $node->logfile;
 
 	# Launch a background worker on the given database.
 	my $pid = $node->safe_psql(
@@ -28,13 +27,12 @@ sub launch_bgworker
         SELECT worker_spi_launch($testcase, '$database'::regdatabase, 0, '{}', $interruptible);
     ));
 
-	# Check that the bgworker is initialized.
-	$node->wait_for_log(
-		qr/LOG: .*worker_spi dynamic worker $testcase initialized with .*\..*/,
-		$offset);
-	my $result = $node->safe_psql('postgres',
-		"SELECT count(*) > 0 FROM pg_stat_activity WHERE pid = $pid;");
-	is($result, 't', "dynamic bgworker $testcase launched");
+	# Check that the bgworker is initialized and napping.
+	my $result =
+	  $node->poll_query_until('postgres',
+		qq[SELECT wait_event FROM pg_stat_activity WHERE pid = $pid;],
+		qq[WorkerSpiMain]);
+	is($result, 1, "dynamic bgworker $testcase launched");
 
 	return $pid;
 }
@@ -64,11 +62,15 @@ sub run_bgworker_interruptible_test
 
 my $node = PostgreSQL::Test::Cluster->new('mynode');
 $node->init;
+# The naptime is large enough to give some room on slow machines, so as
+# the spawned workers have the time to process the interrupt requests sent
+# by the database commands.
 $node->append_conf(
 	"postgresql.conf", qq(
 autovacuum = off
 debug_parallel_query = off
 log_min_messages = debug1
+worker_spi.naptime = 600
 ));
 $node->start;