From ad3fb04b9cc2d490e64d4a16e516b5f9eeadc7f3 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Fri, 4 Dec 2020 18:20:18 +0200 Subject: [PATCH] Fix race conditions in newly-added test. Buildfarm has been failing sporadically on the new test. I was able to reproduce this by adding a random 0-10 s delay in the walreceiver, just before it connects to the primary. There's a race condition where node_3 is promoted before it has fully caught up with node_1, leading to diverged timelines. When node_1 is later reconfigured as standby following node_3, it fails to catch up: LOG: primary server contains no more WAL on requested timeline 1 LOG: new timeline 2 forked off current database system timeline 1 before current recovery point 0/30000A0 That's the situation where you'd need to use pg_rewind, but in this case it happens already when we are just setting up the actual pg_rewind scenario we want to test, so change the test so that it waits until node_3 is connected and fully caught up before promoting it, so that you get a clean, controlled failover. Also rewrite some of the comments, for clarity. The existing comments detailed what each step in the test did, but didn't give a good overview of the situation the steps were trying to create. For reasons I don't understand, the test setup had to be written slightly differently in 9.6 and 9.5 than in later versions. The 9.5/9.6 version needed node 1 to be reinitialized from backup, whereas in later versions it could be shut down and reconfigured to be a standby. But even 9.5 should support "clean switchover", where primary makes sure that pending WAL is replicated to standby on shutdown. It would be nice to figure out what's going on there, but that's independent of pg_rewind and the scenario that this test tests. Discussion: https://www.postgresql.org/message-id/b0a3b95b-82d2-6089-6892-40570f8c5e60%40iki.fi --- src/bin/pg_rewind/t/008_min_recovery_point.pl | 33 +++++++++++-------- 1 file changed, 20 insertions(+), 13 deletions(-) diff --git a/src/bin/pg_rewind/t/008_min_recovery_point.pl b/src/bin/pg_rewind/t/008_min_recovery_point.pl index 6c010bfc6a..747134d702 100644 --- a/src/bin/pg_rewind/t/008_min_recovery_point.pl +++ b/src/bin/pg_rewind/t/008_min_recovery_point.pl @@ -50,54 +50,61 @@ $node_1->safe_psql('postgres', 'CREATE TABLE public.foo (t TEXT)'); $node_1->safe_psql('postgres', 'CREATE TABLE public.bar (t TEXT)'); $node_1->safe_psql('postgres', "INSERT INTO public.bar VALUES ('in both')"); - -# Take backup +# +# Create node_2 and node_3 as standbys following node_1 +# my $backup_name = 'my_backup'; $node_1->backup($backup_name); -# Create streaming standby from backup my $node_2 = get_new_node('node_2'); $node_2->init_from_backup($node_1, $backup_name, has_streaming => 1); $node_2->start; -# Create streaming standby from backup my $node_3 = get_new_node('node_3'); $node_3->init_from_backup($node_1, $backup_name, has_streaming => 1); $node_3->start; -# Stop node_1 +# Wait until node 3 has connected and caught up +my $lsn = $node_1->lsn('insert'); +$node_1->wait_for_catchup('node_3', 'replay', $lsn); +# +# Swap the roles of node_1 and node_3, so that node_1 follows node_3. +# $node_1->stop('fast'); - -# Promote node_3 $node_3->promote; -# node_1 rejoins node_3 - +# reconfigure node_1 as a standby following node_3 my $node_3_connstr = $node_3->connstr; - $node_1->append_conf('postgresql.conf', qq( primary_conninfo='$node_3_connstr' )); $node_1->set_standby_mode(); $node_1->start(); -# node_2 follows node_3 - +# also reconfigure node_2 to follow node_3 $node_2->append_conf('postgresql.conf', qq( primary_conninfo='$node_3_connstr' )); $node_2->restart(); -# Promote node_1 +# +# Promote node_1, to create a split-brain scenario. +# + +# make sure node_1 is full caught up with node_3 first +$lsn = $node_3->lsn('insert'); +$node_3->wait_for_catchup('node_1', 'replay', $lsn); $node_1->promote; +# # We now have a split-brain with two primaries. Insert a row on both to # demonstratively create a split brain. After the rewind, we should only # see the insert on 1, as the insert on node 3 is rewound away. +# $node_1->safe_psql('postgres', "INSERT INTO public.foo (t) VALUES ('keep this')"); # Insert more rows in node 1, to bump up the XID counter. Otherwise, if