Stabilize 039_end_of_wal test.

macdice · macdice · commit 777f50b9b582 · 2024-08-31T15:00:46.000+12:00
The first test was sensitive to the insert LSN after setting up the catalogs, which depended on environmental things like the locales on the OS and usernames. Switch to a new WAL file before the first test, as a simple way to put every computer into the same state. Back-patch to all supported releases. Reported-by: Anton Voloshin <a.voloshin@postgrespro.ru> Reported-by: Nathan Bossart <nathandbossart@gmail.com> Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> Reviewed-by: Nathan Bossart <nathandbossart@gmail.com> Discussion: https://postgr.es/m/b26aeac2-cb6d-4633-a7ea-945baae83dcf%40postgrespro.ru
diff --git a/src/test/recovery/t/039_end_of_wal.pl b/src/test/recovery/t/039_end_of_wal.pl
@@ -251,6 +251,12 @@ sub advance_to_record_splitting_zone
 $TLI = $node->safe_psql('postgres',
 	"SELECT timeline_id FROM pg_control_checkpoint();");
 
+# Initial LSN may vary across systems due to different catalog contents set up
+# by initdb.  Switch to a new WAL file so all systems start out in the same
+# place.  The first test depends on trailing zeroes on a page with a valid
+# header.
+$node->safe_psql('postgres', "SELECT pg_switch_wal();");
+
 my $end_lsn;
 my $prev_lsn;
 
