Fix race condition in remove_temp_files_after_crash TAP test

tvondra · tvondra · commit e589c4890b05 · 2021-03-19T18:12:39.000+01:00
The TAP test was written so that it was not waiting for the correct SQL command, but for output from the preceding one. This resulted in race conditions, allowing the commands to run in a different order, not block as expected and so on. This fixes it by inverting the order of commands where possible, so that observing the output guarantees the data was inserted properly, and waiting for a lock to appear in pg_locks. Discussion: https://postgr.es/m/CAH503wDKdYzyq7U-QJqGn%3DGm6XmoK%2B6_6xTJ-Yn5WSvoHLY1Ww%40mail.gmail.com
diff --git a/src/test/recovery/t/022_crash_temp_files.pl b/src/test/recovery/t/022_crash_temp_files.pl
@@ -79,8 +79,8 @@
 # Insert one tuple and leave the transaction open
 $killme_stdin2 .= q[
 BEGIN;
-SELECT $$insert-tuple-to-lock-next-insert$$;
 INSERT INTO tab_crash (a) VALUES(1);
+SELECT $$insert-tuple-to-lock-next-insert$$;
 ];
 pump_until($killme2, \$killme_stdout2, qr/insert-tuple-to-lock-next-insert/m);
 $killme_stdout2 = '';
@@ -100,6 +100,26 @@
 $killme_stdout = '';
 $killme_stderr = '';
 
+# Wait until the batch insert gets stuck on the lock.
+$killme_stdin2 .= q[
+DO $c$
+DECLARE
+  c INT;
+BEGIN
+  LOOP
+    SELECT COUNT(*) INTO c FROM pg_locks WHERE pid = ] . $pid . q[ AND NOT granted;
+    IF c > 0 THEN
+      EXIT;
+    END IF;
+  END LOOP;
+END; $c$;
+SELECT $$insert-tuple-lock-waiting$$;
+];
+
+pump_until($killme2, \$killme_stdout2, qr/insert-tuple-lock-waiting/m);
+$killme_stdout2 = '';
+$killme_stderr2 = '';
+
 # Kill with SIGKILL
 my $ret = TestLib::system_log('pg_ctl', 'kill', 'KILL', $pid);
 is($ret, 0, 'killed process with KILL');
@@ -147,8 +167,8 @@
 # Insert one tuple and leave the transaction open
 $killme_stdin2 .= q[
 BEGIN;
-SELECT $$insert-tuple-to-lock-next-insert$$;
 INSERT INTO tab_crash (a) VALUES(1);
+SELECT $$insert-tuple-to-lock-next-insert$$;
 ];
 pump_until($killme2, \$killme_stdout2, qr/insert-tuple-to-lock-next-insert/m);
 $killme_stdout2 = '';
@@ -168,6 +188,26 @@
 $killme_stdout = '';
 $killme_stderr = '';
 
+# Wait until the batch insert gets stuck on the lock.
+$killme_stdin2 .= q[
+DO $c$
+DECLARE
+  c INT;
+BEGIN
+  LOOP
+    SELECT COUNT(*) INTO c FROM pg_locks WHERE pid = ] . $pid . q[ AND NOT granted;
+    IF c > 0 THEN
+      EXIT;
+    END IF;
+  END LOOP;
+END; $c$;
+SELECT $$insert-tuple-lock-waiting$$;
+];
+
+pump_until($killme2, \$killme_stdout2, qr/insert-tuple-lock-waiting/m);
+$killme_stdout2 = '';
+$killme_stderr2 = '';
+
 # Kill with SIGKILL
 $ret = TestLib::system_log('pg_ctl', 'kill', 'KILL', $pid);
 is($ret, 0, 'killed process with KILL');
