From 9a7229948c70945ca6ef0b36adfe61b74f4fdaf5 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Tue, 5 Apr 2022 20:44:01 -0400 Subject: [PATCH] Remove race condition in 022_crash_temp_files.pl test. It's possible for the query that "waits for restart" to complete a successful iteration before the postmaster has noticed its SIGKILL'd child and begun the restart cycle. (This is a bit hard to believe perhaps, but it's been seen at least twice in the buildfarm, mainly on ancient platforms that likely have quirky schedulers.) To provide a more secure interlock, wait for the other session we're using to report that it's been forcibly shut down. Patch by me, based on a suggestion from Andres Freund. Back-patch to v14 where this test case came in. Discussion: https://postgr.es/m/1801850.1649047827@sss.pgh.pa.us --- src/test/recovery/t/022_crash_temp_files.pl | 34 ++++++++++++++++++--- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/src/test/recovery/t/022_crash_temp_files.pl b/src/test/recovery/t/022_crash_temp_files.pl index 74965348791..5ddc00fb05f 100644 --- a/src/test/recovery/t/022_crash_temp_files.pl +++ b/src/test/recovery/t/022_crash_temp_files.pl @@ -16,7 +16,7 @@ if ($Config{osname} eq 'MSWin32') } else { - plan tests => 9; + plan tests => 11; } @@ -130,11 +130,23 @@ $killme_stderr2 = ''; my $ret = TestLib::system_log('pg_ctl', 'kill', 'KILL', $pid); is($ret, 0, 'killed process with KILL'); -# Close psql session +# Close that psql session $killme->finish; + +# Wait till the other session reports failure, ensuring that the postmaster +# has noticed its dead child and begun a restart cycle. +$killme_stdin2 .= qq[ +SELECT pg_sleep($TestLib::timeout_default); +]; +ok( pump_until( + $killme2, + \$killme_stderr2, + qr/WARNING: terminating connection because of crash of another server process|server closed the connection unexpectedly|connection to server was lost|could not send data to server/m + ), + "second psql session died successfully after SIGKILL"); $killme2->finish; -# Wait till server restarts +# Wait till server finishes restarting $node->poll_query_until('postgres', undef, ''); # Check for temporary files @@ -219,11 +231,23 @@ $killme_stderr2 = ''; $ret = TestLib::system_log('pg_ctl', 'kill', 'KILL', $pid); is($ret, 0, 'killed process with KILL'); -# Close psql session +# Close that psql session $killme->finish; + +# Wait till the other session reports failure, ensuring that the postmaster +# has noticed its dead child and begun a restart cycle. +$killme_stdin2 .= qq[ +SELECT pg_sleep($TestLib::timeout_default); +]; +ok( pump_until( + $killme2, + \$killme_stderr2, + qr/WARNING: terminating connection because of crash of another server process|server closed the connection unexpectedly|connection to server was lost|could not send data to server/m + ), + "second psql session died successfully after SIGKILL"); $killme2->finish; -# Wait till server restarts +# Wait till server finishes restarting $node->poll_query_until('postgres', undef, ''); # Check for temporary files -- should be there