Fix instability in contrib/bloom TAP tests.

tglsfdc · tglsfdc · commit cf26a8d8a75f · 2021-09-28T17:34:31.000-04:00
It turns out that the instability complained of in commit d3c09b9 has an embarrassingly simple explanation. The test script waits for the standby to flush incoming WAL to disk, but it should wait for the WAL to be replayed, since we are testing for the effects of that to be visible. While at it, use wait_for_catchup instead of reinventing that logic, and adjust $Test::Builder::Level to improve future error reports. Back-patch to v12 where the necessary infrastructure came in (cf. aforesaid commit). Also back-patch 7d1aa6b so that the test will actually get run. Discussion: https://postgr.es/m/2854602.1632852664@sss.pgh.pa.us
diff --git a/contrib/bloom/Makefile b/contrib/bloom/Makefile
@@ -16,9 +16,7 @@ PGFILEDESC = "bloom access method - signature file based index"
 
 REGRESS = bloom
 
-# Disable TAP tests for this module for now, as these are unstable on several
-# buildfarm environments.
-# TAP_TESTS = 1
+TAP_TESTS = 1
 
 ifdef USE_PGXS
 PG_CONFIG = pg_config
diff --git a/contrib/bloom/t/001_wal.pl b/contrib/bloom/t/001_wal.pl
@@ -13,12 +13,10 @@ sub test_index_replay
 {
 	my ($test_name) = @_;
 
+	local $Test::Builder::Level = $Test::Builder::Level + 1;
+
 	# Wait for standby to catch up
-	my $applname = $node_standby->name;
-	my $caughtup_query =
-	  "SELECT pg_current_wal_lsn() <= write_lsn FROM pg_stat_replication WHERE application_name = '$applname';";
-	$node_master->poll_query_until('postgres', $caughtup_query)
-	  or die "Timed out while waiting for standby 1 to catch up";
+	$node_master->wait_for_catchup($node_standby);
 
 	my $queries = qq(SET enable_seqscan=off;
 SET enable_bitmapscan=on;
