Fix end LSN determination in recently added test

The test added in commit e44dae07f931 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
index f7dbb0d0141c21934776ab09cc21c566649b54a6..cbc269b1dfeb669c050b914cae6c4c6ff730e0f4 100644 (file)
--- a/src/test/modules/brin/t/02_wal_consistency.pl
+++ b/src/test/modules/brin/t/02_wal_consistency.pl
@@ -60,7 +60,7 @@ begin
 end
 $$;
 });
-my $end_lsn = $whiskey->lsn('insert');
+my $end_lsn = $whiskey->lsn('flush');
 
 my ($ret, $out, $err) = $whiskey->psql(
    'postgres', qq{