postgres.git / summary / log / commit / refs

commit    ae395f0f7edbbf8e9ebe92e2ed3a471192789f0c
Author:   Amit Kapila <akapila@postgresql.org>
Date:     Wed Jul 03 09:34:59 2024 +0000
First released in: 18.0, 17.0

    Fix the testcase introduced in commit 81d20fbf7a.
    
    The failed test was syncing failover replication slot to standby to test
    that we remove such slots after the standby is converted to subscriber by
    pg_createsubscriber.
    
    In one of the buildfarm members, the sync of the slot failed because the
    LSN on the standby was before the syncslot's LSN. We need to wait for
    standby to catch up before trying to sync the slot with
    pg_sync_replication_slots().
    
    The other buildfarm failed because autovacuum generated a xid which is
    replicated to the standby at some random point making slots at primary
    lag behind standby during slot sync.
    
    Both these failures wouldn't have occurred if we had used built-in
    slotsync worker as it would have waited for the standby to sync with
    primary but for this test, it is sufficient to use
    pg_sync_replication_slots().
    
    Reported-by: Alexander Lakhin as per buildfarm
    Author: Kuroda Hayato
    Reviewed-by: Amit Kapila
    Backpatch-through: 17
    Discussion: https://postgr.es/m/0dffca12-bf17-4a7a-334d-225569de5e6e@gmail.com
    Discussion: https://postgr.es/m/OSBPR01MB25528300C71FDD83EA1DCA12F5DD2@OSBPR01MB2552.jpnprd01.prod.outlook.com


 src/bin/pg_basebackup/t/040_pg_createsubscriber.pl | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl b/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl
index 80002c5a17f..74b90d9a913 100644
--- a/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl
+++ b/src/bin/pg_basebackup/t/040_pg_createsubscriber.pl
@@ -116,6 +116,10 @@ command_fails(
 my $node_p = PostgreSQL::Test::Cluster->new('node_p');
 my $pconnstr = $node_p->connstr;
 $node_p->init(allows_streaming => 'logical');
+# Disable autovacuum to avoid generating xid during stats update as otherwise
+# the new XID could then be replicated to standby at some random point making
+# slots at primary lag behind standby during slot sync.
+$node_p->append_conf('postgresql.conf', 'autovacuum = off');
 $node_p->start;
 
 # Set up node F as about-to-fail node
@@ -293,6 +297,9 @@ $node_p->safe_psql($db1,
 	"SELECT pg_create_logical_replication_slot('$fslotname', 'pgoutput', false, false, true)"
 );
 $node_s->start;
+# Wait for the standby to catch up so that the standby is not lagging behind
+# the failover slot.
+$node_p->wait_for_replay_catchup($node_s);
 $node_s->safe_psql('postgres', "SELECT pg_sync_replication_slots()");
 my $result = $node_s->safe_psql('postgres',
 	"SELECT slot_name FROM pg_replication_slots WHERE slot_name = '$fslotname' AND synced AND NOT temporary"


[parent: 9fd02525793f]