Stabilize 039_end_of_wal test.

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

Author: macdice

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;