From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Mon, 26 Jun 2017 18:39:55 +0000 (-0400)
Subject: Improve wait logic in TAP tests for streaming replication.
X-Git-Tag: REL_10_BETA2~67
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=5c77690f6;p=postgresql

Improve wait logic in TAP tests for streaming replication.

Remove hard-wired sleep(2) delays in 001_stream_rep.pl in favor of using
poll_query_until to check for the desired state to appear.  In addition,
add such a wait before the last test in the script, as it's possible
to demonstrate failures there after upcoming improvements in pg_ctl.

(We might end up adding polling before each of the get_slot_xmins calls in
this script, but I feel no great need to do that until shown necessary.)

In passing, clarify the description strings for some of the test cases.

Michael Paquier and Craig Ringer, pursuant to a complaint from me

Discussion: https://postgr.es/m/8962.1498425057@sss.pgh.pa.us
---

diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index 266d27c8a2..750e40c3da 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -146,6 +146,20 @@ $node_standby_2->append_conf('postgresql.conf',
 	"wal_receiver_status_interval = 1");
 $node_standby_2->restart;
 
+# Wait for given condition on slot's pg_replication_slots row --- useful for
+# ensuring we've reached a quiescent condition for reading slot xmins
+sub wait_slot_xmins
+{
+	my ($node, $slot_name, $check_expr) = @_;
+
+	$node->poll_query_until('postgres', qq[
+		SELECT $check_expr
+		FROM pg_catalog.pg_replication_slots
+		WHERE slot_name = '$slot_name';
+	]);
+}
+
+# Fetch xmin columns from slot's pg_replication_slots row
 sub get_slot_xmins
 {
 	my ($node, $slotname) = @_;
@@ -156,12 +170,12 @@ sub get_slot_xmins
 # There's no hot standby feedback and there are no logical slots on either peer
 # so xmin and catalog_xmin should be null on both slots.
 my ($xmin, $catalog_xmin) = get_slot_xmins($node_master, $slotname_1);
-is($xmin,         '', 'non-cascaded slot xmin null with no hs_feedback');
-is($catalog_xmin, '', 'non-cascaded slot xmin null with no hs_feedback');
+is($xmin,         '', 'xmin of non-cascaded slot null with no hs_feedback');
+is($catalog_xmin, '', 'catalog xmin of non-cascaded slot null with no hs_feedback');
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_standby_1, $slotname_2);
-is($xmin,         '', 'cascaded slot xmin null with no hs_feedback');
-is($catalog_xmin, '', 'cascaded slot xmin null with no hs_feedback');
+is($xmin,         '', 'xmin of cascaded slot null with no hs_feedback');
+is($catalog_xmin, '', 'catalog xmin of cascaded slot null with no hs_feedback');
 
 # Replication still works?
 $node_master->safe_psql('postgres', 'CREATE TABLE replayed(val integer);');
@@ -196,15 +210,18 @@ $node_standby_2->safe_psql('postgres',
 	'ALTER SYSTEM SET hot_standby_feedback = on;');
 $node_standby_2->reload;
 replay_check();
-sleep(2);
+
+wait_slot_xmins($node_master, $slotname_1,
+				"xmin IS NOT NULL AND catalog_xmin IS NULL");
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_master, $slotname_1);
-isnt($xmin, '', 'non-cascaded slot xmin non-null with hs feedback');
-is($catalog_xmin, '', 'non-cascaded slot xmin still null with hs_feedback');
+isnt($xmin, '', 'xmin of non-cascaded slot non-null with hs feedback');
+is($catalog_xmin, '',
+	'catalog xmin of non-cascaded slot still null with hs_feedback');
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_standby_1, $slotname_2);
-isnt($xmin, '', 'cascaded slot xmin non-null with hs feedback');
-is($catalog_xmin, '', 'cascaded slot xmin still null with hs_feedback');
+isnt($xmin, '', 'xmin of cascaded slot non-null with hs feedback');
+is($catalog_xmin, '', 'catalog xmin of cascaded slot still null with hs_feedback');
 
 note "doing some work to advance xmin";
 for my $i (10000 .. 11000)
@@ -216,15 +233,15 @@ $node_master->safe_psql('postgres', 'CHECKPOINT;');
 
 my ($xmin2, $catalog_xmin2) = get_slot_xmins($node_master, $slotname_1);
 note "new xmin $xmin2, old xmin $xmin";
-isnt($xmin2, $xmin, 'non-cascaded slot xmin with hs feedback has changed');
+isnt($xmin2, $xmin, 'xmin of non-cascaded slot with hs feedback has changed');
 is($catalog_xmin2, '',
-	'non-cascaded slot xmin still null with hs_feedback unchanged');
+	'catalog xmin of non-cascaded slot still null with hs_feedback unchanged');
 
 ($xmin2, $catalog_xmin2) = get_slot_xmins($node_standby_1, $slotname_2);
 note "new xmin $xmin2, old xmin $xmin";
-isnt($xmin2, $xmin, 'cascaded slot xmin with hs feedback has changed');
+isnt($xmin2, $xmin, 'xmin of cascaded slot with hs feedback has changed');
 is($catalog_xmin2, '',
-	'cascaded slot xmin still null with hs_feedback unchanged');
+	'catalog xmin of cascaded slot still null with hs_feedback unchanged');
 
 note "disabling hot_standby_feedback";
 
@@ -236,16 +253,22 @@ $node_standby_2->safe_psql('postgres',
 	'ALTER SYSTEM SET hot_standby_feedback = off;');
 $node_standby_2->reload;
 replay_check();
-sleep(2);
+
+wait_slot_xmins($node_master, $slotname_1,
+					   "xmin IS NULL AND catalog_xmin IS NULL");
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_master, $slotname_1);
-is($xmin, '', 'non-cascaded slot xmin null with hs feedback reset');
+is($xmin, '', 'xmin of non-cascaded slot null with hs feedback reset');
 is($catalog_xmin, '',
-	'non-cascaded slot xmin still null with hs_feedback reset');
+   'catalog xmin of non-cascaded slot still null with hs_feedback reset');
+
+wait_slot_xmins($node_standby_1, $slotname_2,
+					   "xmin IS NULL AND catalog_xmin IS NULL");
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_standby_1, $slotname_2);
-is($xmin,         '', 'cascaded slot xmin null with hs feedback reset');
-is($catalog_xmin, '', 'cascaded slot xmin still null with hs_feedback reset');
+is($xmin,         '', 'xmin of cascaded slot null with hs feedback reset');
+is($catalog_xmin, '',
+	'catalog xmin of cascaded slot still null with hs_feedback reset');
 
 note "re-enabling hot_standby_feedback and disabling while stopped";
 $node_standby_2->safe_psql('postgres',
@@ -260,11 +283,13 @@ $node_standby_2->safe_psql('postgres',
 $node_standby_2->stop;
 
 ($xmin, $catalog_xmin) = get_slot_xmins($node_standby_1, $slotname_2);
-isnt($xmin, '', 'cascaded slot xmin non-null with postgres shut down');
+isnt($xmin, '', 'xmin of cascaded slot non-null with postgres shut down');
 
 # Xmin from a previous run should be cleared on startup.
 $node_standby_2->start;
 
+wait_slot_xmins($node_standby_1, $slotname_2, "xmin IS NULL");
+
 ($xmin, $catalog_xmin) = get_slot_xmins($node_standby_1, $slotname_2);
 is($xmin, '',
-	'cascaded slot xmin reset after startup with hs feedback reset');
+	'xmin of cascaded slot reset after startup with hs feedback reset');