Raise some timeouts to 180s, in test code.

nmisch · nmisch · commit eff124233916 · 2018-12-10T20:15:57.000-08:00
Slow runs of buildfarm members chipmunk, hornet and mandrill saw the shorter timeouts expire. The 180s timeout in poll_query_until has been trouble-free since 2a0f89c introduced it two years ago, so use 180s more widely. Back-patch to 9.6, where the first of these timeouts was introduced. Reviewed by Michael Paquier. Discussion: https://postgr.es/m/20181209001601.GC2973271@rfd.leadboat.com
diff --git a/src/test/isolation/README b/src/test/isolation/README
@@ -108,8 +108,8 @@ Each step may contain commands that block until further action has been taken
 deadlock).  A test that uses this ability must manually specify valid
 permutations, i.e. those that would not expect a blocked session to execute a
 command.  If a test fails to follow that rule, isolationtester will cancel it
-after 60 seconds.  If the cancel doesn't work, isolationtester will exit
-uncleanly after a total of 75 seconds of wait time.  Testing invalid
+after 180 seconds.  If the cancel doesn't work, isolationtester will exit
+uncleanly after a total of 200 seconds of wait time.  Testing invalid
 permutations should be avoided because they can make the isolation tests take
 a very long time to run, and they serve no useful testing purpose.
 
diff --git a/src/test/isolation/isolationtester.c b/src/test/isolation/isolationtester.c
@@ -765,15 +765,15 @@ try_complete_step(Step *step, int flags)
 			td += (int64) current_time.tv_usec - (int64) start_time.tv_usec;
 
 			/*
-			 * After 60 seconds, try to cancel the query.
+			 * After 180 seconds, try to cancel the query.
 			 *
 			 * If the user tries to test an invalid permutation, we don't want
 			 * to hang forever, especially when this is running in the
-			 * buildfarm.  So try to cancel it after a minute.  This will
-			 * presumably lead to this permutation failing, but remaining
-			 * permutations and tests should still be OK.
+			 * buildfarm.  This will presumably lead to this permutation
+			 * failing, but remaining permutations and tests should still be
+			 * OK.
 			 */
-			if (td > 60 * USECS_PER_SEC && !canceled)
+			if (td > 180 * USECS_PER_SEC && !canceled)
 			{
 				PGcancel   *cancel = PQgetCancel(conn);
 
@@ -790,15 +790,15 @@ try_complete_step(Step *step, int flags)
 			}
 
 			/*
-			 * After 75 seconds, just give up and die.
+			 * After 200 seconds, just give up and die.
 			 *
 			 * Since cleanup steps won't be run in this case, this may cause
 			 * later tests to fail.  That stinks, but it's better than waiting
 			 * forever for the server to respond to the cancel.
 			 */
-			if (td > 75 * USECS_PER_SEC)
+			if (td > 200 * USECS_PER_SEC)
 			{
-				fprintf(stderr, "step %s timed out after 75 seconds\n",
+				fprintf(stderr, "step %s timed out after 200 seconds\n",
 						step->name);
 				exit_nicely();
 			}
diff --git a/src/test/recovery/t/006_logical_decoding.pl b/src/test/recovery/t/006_logical_decoding.pl
@@ -71,7 +71,7 @@
 print "waiting to replay $endpos\n";
 
 my $stdout_recv = $node_master->pg_recvlogical_upto(
-	'postgres', 'test_slot', $endpos, 10,
+	'postgres', 'test_slot', $endpos, 180,
 	'include-xids'     => '0',
 	'skip-empty-xacts' => '1');
 chomp($stdout_recv);
@@ -84,7 +84,7 @@
   or die "slot never became inactive";
 
 $stdout_recv = $node_master->pg_recvlogical_upto(
-	'postgres', 'test_slot', $endpos, 10,
+	'postgres', 'test_slot', $endpos, 180,
 	'include-xids'     => '0',
 	'skip-empty-xacts' => '1');
 chomp($stdout_recv);
diff --git a/src/test/recovery/t/010_logical_decoding_timelines.pl b/src/test/recovery/t/010_logical_decoding_timelines.pl
@@ -182,7 +182,7 @@ BEGIN
 
 $stdout = $node_replica->pg_recvlogical_upto(
 	'postgres', 'before_basebackup',
-	$endpos,    30,
+	$endpos,    180,
 	'include-xids'     => '0',
 	'skip-empty-xacts' => '1');
 
