From 61608d38361f911a741d4a7df63afe3c7221437e Mon Sep 17 00:00:00 2001
From: Alvaro Herrera <alvherre@alvh.no-ip.org>
Date: Thu, 31 Mar 2016 15:41:18 -0300
Subject: [PATCH] Fix recovery_min_apply_delay test
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Previously this test was relying too much on WAL replay to occur in the
exact configured interval, which was unreliable on slow or overly busy
servers.  Use a custom loop instead of poll_query_until, which is
hopefully more reliable.

Per continued failures on buildfarm member hamster (which is probably
the only one running this test suite)

Author: Michaël Paquier
---
 src/test/recovery/t/005_replay_delay.pl | 56 ++++++++++++++++---------
 1 file changed, 37 insertions(+), 19 deletions(-)

diff --git a/src/test/recovery/t/005_replay_delay.pl b/src/test/recovery/t/005_replay_delay.pl
index 986851b678..e38ab9dfd2 100644
--- a/src/test/recovery/t/005_replay_delay.pl
+++ b/src/test/recovery/t/005_replay_delay.pl
@@ -1,9 +1,10 @@
 # Checks for recovery_min_apply_delay
 use strict;
 use warnings;
+
 use PostgresNode;
 use TestLib;
-use Test::More tests => 2;
+use Test::More tests => 1;
 
 # Initialize master node
 my $node_master = get_new_node('master');
@@ -12,7 +13,7 @@ $node_master->start;
 
 # And some content
 $node_master->safe_psql('postgres',
-	"CREATE TABLE tab_int AS SELECT generate_series(1,10) AS a");
+	"CREATE TABLE tab_int AS SELECT generate_series(1, 10) AS a");
 
 # Take backup
 my $backup_name = 'my_backup';
@@ -20,30 +21,47 @@ $node_master->backup($backup_name);
 
 # Create streaming standby from backup
 my $node_standby = get_new_node('standby');
+my $delay = 3;
 $node_standby->init_from_backup($node_master, $backup_name,
 	has_streaming => 1);
 $node_standby->append_conf(
 	'recovery.conf', qq(
-recovery_min_apply_delay = '2s'
+recovery_min_apply_delay = '${delay}s'
 ));
 $node_standby->start;
 
-# Make new content on master and check its presence in standby
-# depending on the delay of 2s applied above.
+# Make new content on master and check its presence in standby depending
+# on the delay applied above. Before doing the insertion, get the
+# current timestamp that will be used as a comparison base. Even on slow
+# machines, this allows to have a predictable behavior when comparing the
+# delay between data insertion moment on master and replay time on standby.
+my $master_insert_time = time();
 $node_master->safe_psql('postgres',
-	"INSERT INTO tab_int VALUES (generate_series(11,20))");
-sleep 1;
-
-# Here we should have only 10 rows
-my $result = $node_standby->safe_psql('postgres', "SELECT count(*) FROM tab_int");
-is($result, qq(10), 'check content with delay of 1s');
+	"INSERT INTO tab_int VALUES (generate_series(11, 20))");
 
-# Now wait for replay to complete on standby
+# Now wait for replay to complete on standby. We're done waiting when the
+# slave has replayed up to the previously saved master LSN.
 my $until_lsn =
-  $node_master->safe_psql('postgres', "SELECT pg_current_xlog_location();");
-my $caughtup_query =
-  "SELECT '$until_lsn'::pg_lsn <= pg_last_xlog_replay_location()";
-$node_standby->poll_query_until('postgres', $caughtup_query)
-  or die "Timed out while waiting for standby to catch up";
-$result = $node_standby->safe_psql('postgres', "SELECT count(*) FROM tab_int");
-is($result, qq(20), 'check content with delay of 2s');
+  $node_master->safe_psql('postgres', "SELECT pg_current_xlog_location()");
+
+my $remaining = 90;
+while ($remaining-- > 0)
+{
+	# Done waiting?
+	my $replay_status =
+	  $node_standby->safe_psql('postgres',
+		"SELECT (pg_last_xlog_replay_location() - '$until_lsn'::pg_lsn) >= 0");
+	last if $replay_status eq 't';
+
+	# No, sleep some more.
+	my $sleep = $master_insert_time + $delay - time();
+	$sleep = 1 if $sleep < 1;
+	sleep $sleep;
+}
+
+die "Maximum number of attempts reached ($remaining remain)" if $remaining < 0;
+
+# This test is successful if and only if the LSN has been applied with at least
+# the configured apply delay.
+ok(time() - $master_insert_time >= $delay,
+   "Check that standby applies WAL only after replication delay");
-- 
2.40.0