mirror of
https://git.postgresql.org/git/postgresql.git
synced 2025-03-19 20:00:51 +08:00
Fix issue in recovery test 041_checkpoint_at_promote
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 6782709df81f. Author: Nitin Jadhav Discussion: https://postgr.es/m/CAMm1aWa_6u+o52r7h7G6pX-oWD0Qraf0ee17Ma50qxGS0B_Rzg@mail.gmail.com Backpatch-through: 17
This commit is contained in:
parent
5b94e27534
commit
0fc68c8421
@ -110,7 +110,7 @@ $node_standby->safe_psql('postgres',
|
||||
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;
|
||||
|
Loading…
x
Reference in New Issue
Block a user