Improve the stability of the recovery test 047_checkpoint_physical_slot

akorotkov · akorotkov · commit fd39c3cf2839 · 2025-07-19T13:51:34.000+03:00
Currently, the comments in 047_checkpoint_physical_slot. It shows an incomplete intention to wait for checkpoint completion before performing an immediate database stop. However, an immediate node stop can occur both before and after checkpoint completion. Both cases should work correctly. But we would like the test to be more stable and deterministic. This is why this commit makes this test explicitly wait for the checkpoint completion log message. Discussion: https://postgr.es/m/CAPpHfdurV-j_e0pb%3DUFENAy3tyzxfF%2ByHveNDNQk2gM82WBU5A%40mail.gmail.com Discussion: https://postgr.es/m/aHXLep3OaX_vRTNQ%40paquier.xyz Author: Alexander Korotkov <akorotkov@postgresql.org> Reviewed-by: Michael Paquier <michael@paquier.xyz> Backpatch-through: 17
diff --git a/src/test/recovery/t/047_checkpoint_physical_slot.pl b/src/test/recovery/t/047_checkpoint_physical_slot.pl
@@ -97,18 +97,19 @@
 	q{select pg_replication_slot_advance('slot_physical', pg_current_wal_lsn())}
 );
 
-# Continue the checkpoint.
+# Continue the checkpoint and wait for its completion.
+my $log_offset = -s $node->logfile;
 $node->safe_psql('postgres',
 	q{select injection_points_wakeup('checkpoint-before-old-wal-removal')});
+$node->wait_for_log(qr/checkpoint complete/, $log_offset);
 
 my $restart_lsn_old = $node->safe_psql('postgres',
 	q{select restart_lsn from pg_replication_slots where slot_name = 'slot_physical'}
 );
 chomp($restart_lsn_old);
 note("restart lsn before stop: $restart_lsn_old");
 
-# Abruptly stop the server (1 second should be enough for the checkpoint
-# to finish; it would be better).
+# Abruptly stop the server.
 $node->stop('immediate');
 
 $node->start;
