Fix issue in recovery test 041_checkpoint_at_promote

michaelpq · michaelpq · commit 3dea7af519fd · 2025-02-12T17:58:29.000+09:00
The phase of the test waiting for a restartpoint to complete was not working as intended, due to a log_contains() call incorrectly written. The problem reported by the author could be simply reproduced by removing the injection_points_wakeup() call: the test succeeds rather than waiting for the restartpoint completion. In most cases, the restartpoint completion is fast enough that the test offered the wanted coverage. On slow machines, it could have become unreliable. Oversight in 6782709. Author: Nitin Jadhav Discussion: https://postgr.es/m/CAMm1aWa_6u+o52r7h7G6pX-oWD0Qraf0ee17Ma50qxGS0B_Rzg@mail.gmail.com Backpatch-through: 17
diff --git a/src/test/recovery/t/041_checkpoint_at_promote.pl b/src/test/recovery/t/041_checkpoint_at_promote.pl
@@ -113,7 +113,7 @@
 my $checkpoint_complete = 0;
 foreach my $i (0 .. 10 * $PostgreSQL::Test::Utils::timeout_default)
 {
-	if ($node_standby->log_contains("restartpoint complete"), $logstart)
+	if ($node_standby->log_contains("restartpoint complete", $logstart))
 	{
 		$checkpoint_complete = 1;
 		last;

Original file line number	Diff line number	Diff line change
`@@ -113,7 +113,7 @@`
`113`	`113`	`my $checkpoint_complete = 0;`
`114`	`114`	`foreach my $i (0 .. 10 * $PostgreSQL::Test::Utils::timeout_default)`
`115`	`115`	`{`
`116`		`- if ($node_standby->log_contains("restartpoint complete"), $logstart)`
	`116`	`+ if ($node_standby->log_contains("restartpoint complete", $logstart))`
`117`	`117`	`{`
`118`	`118`	`$checkpoint_complete = 1;`
`119`	`119`	`last;`