Fix end LSN determination in recently added test

alvherre · alvherre · commit 6602599ce256 · 2022-12-23T17:27:05.000+01:00
The test added in commit e44dae0 has a thinko: it wants to read info about a few WAL records, but it obtains the LSN of the final record to read by asking for the WAL insert position; however, pg_get_wal_records_info only accepts to read up to the flush position (cf. IsFutureLSN()). In normal conditions there is no difference, since the last record written by the preceding loop is known flushed and it's the one the test wants; but it's possible to have some other process insert another WAL record that isn't flushed, and that causes the whole test to explode. Fix by having pg_get_wal_records_info() read only up to the flushed position. Backpatch to 15, which is where pg_walinspect appeared. Author: Karina Litskevich <litskevichkarina@gmail.com> Discussion: https://postgr.es/m/a5559c95-52c3-5eea-cd63-9b4f1c70ff96@gmail.com
diff --git a/src/test/modules/brin/t/02_wal_consistency.pl b/src/test/modules/brin/t/02_wal_consistency.pl
@@ -60,7 +60,7 @@
 end
 $$;
 });
-my $end_lsn = $whiskey->lsn('insert');
+my $end_lsn = $whiskey->lsn('flush');
 
 my ($ret, $out, $err) = $whiskey->psql(
 	'postgres', qq{
