aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRobert Haas <rhaas@postgresql.org>2024-01-31 11:35:41 -0500
committerRobert Haas <rhaas@postgresql.org>2024-01-31 11:37:41 -0500
commitb6ee30ec0866619eafc10cf43c4714ed1b89fec6 (patch)
tree77e3a03de19d9c9fdb70dc00416eeea6d48f9a87
parentf0106b6d2dc28660d9ecba3de77cee14de921c94 (diff)
downloadpostgresql-b6ee30ec0866619eafc10cf43c4714ed1b89fec6.tar.gz
postgresql-b6ee30ec0866619eafc10cf43c4714ed1b89fec6.zip
In 002_blocks.pl, try to prevent a HOT update.
Make the new tuple larger than the old one so that it, hopefully, won't manage to squeeze into leftover freespace on the same page. The test is trying to verify that the UPDATE touches 2 pages, but if a HOT update happens, then it doesn't. Per buildfarm.
-rw-r--r--src/bin/pg_walsummary/t/002_blocks.pl3
1 files changed, 2 insertions, 1 deletions
diff --git a/src/bin/pg_walsummary/t/002_blocks.pl b/src/bin/pg_walsummary/t/002_blocks.pl
index 723285943f5..c1303b188cf 100644
--- a/src/bin/pg_walsummary/t/002_blocks.pl
+++ b/src/bin/pg_walsummary/t/002_blocks.pl
@@ -56,7 +56,8 @@ note_wal_summary_dir("after insert", $node1);
# Update a row in the first block of the table and trigger a checkpoint.
$node1->safe_psql('postgres', <<EOM);
-UPDATE mytable SET b = 'abcdefghijklmnopqrstuvwxyz' WHERE a = 2;
+UPDATE mytable SET b = 'abcdefghijklmnopqrstuvwxyz' || b || '01234567890'
+ WHERE a = 2;
CHECKPOINT;
EOM