From 958130099bc76534031acc4d3f2e94ccbcfa5451 Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Tue, 15 Aug 2023 15:09:28 +0900 Subject: [PATCH] Add test to emulate random garbage data during WAL replay, doing OOMs This requires an extra flush wait at the end of LogLogicalMessage() to make the test stable. --- src/backend/replication/logical/message.c | 7 ++- src/test/recovery/t/038_wal_invalid.pl | 69 +++++++++++++++++++++++ 2 files changed, 75 insertions(+), 1 deletion(-) create mode 100644 src/test/recovery/t/038_wal_invalid.pl diff --git a/src/backend/replication/logical/message.c b/src/backend/replication/logical/message.c index c5de14afc6..cebe6c5d05 100644 --- a/src/backend/replication/logical/message.c +++ b/src/backend/replication/logical/message.c @@ -47,6 +47,7 @@ LogLogicalMessage(const char *prefix, const char *message, size_t size, bool transactional) { xl_logical_message xlrec; + XLogRecPtr lsn; /* * Force xid to be allocated if we're emitting a transactional message. @@ -71,7 +72,11 @@ LogLogicalMessage(const char *prefix, const char *message, size_t size, /* allow origin filtering */ XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN); - return XLogInsert(RM_LOGICALMSG_ID, XLOG_LOGICAL_MESSAGE); + lsn = XLogInsert(RM_LOGICALMSG_ID, XLOG_LOGICAL_MESSAGE); + + /* Make sure that the message hits disk before leaving */ + XLogFlush(lsn); + return lsn; } /* diff --git a/src/test/recovery/t/038_wal_invalid.pl b/src/test/recovery/t/038_wal_invalid.pl new file mode 100644 index 0000000000..87a6e93734 --- /dev/null +++ b/src/test/recovery/t/038_wal_invalid.pl @@ -0,0 +1,69 @@ + +# Copyright (c) 2021-2023, PostgreSQL Global Development Group + +# Test for code paths involving detection of incorrect WAL records. + +use strict; +use warnings; +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +# Initialize and start node with wal_level = minimal and some +# configuration aimed at minimizing the WAL activity of the cluster. +my $node = PostgreSQL::Test::Cluster->new('primary'); +$node->init; +$node->append_conf('postgresql.conf', q[ +wal_level = minimal +autovacuum = off +checkpoint_timeout = '30min' +]); +$node->start; + +# Generate two WAL records that will be used for the follow-up test, +# using pg_logical_emit_message. This function returns the end LSN +# of the record inserted, and the LSN of the first record is what +# we use to invalidate the beginning of the second record. This +# emulates some historical patterns where a record is read on a +# page read from a recycled segment at the end of WAL. The second +# record could be anything, but pg_logical_emit_message() does not +# impact the cluster consistency. +my $result = $node->safe_psql('postgres', + q{SELECT * FROM pg_walfile_name_offset(pg_logical_emit_message(false, 'a', 'a'))}); +my ($wal_segment_name, $lsn_offset) = split /\|/, $result; +$lsn_offset = int($lsn_offset); + +$node->safe_psql('postgres', + q{SELECT pg_logical_emit_message(false, 'a', 'a')}); + +# Shut down the cluster, to replay the previous records. +$node->stop('immediate'); + +# Add 4 bytes of garbage at the beginning of the second record, to +# emulate the case of a recycled page. The previous offset points +# at the beginning of the second record's xl_tot_len. +my $pgdata = $node->data_dir; + +my $fh; +open($fh, '+<', "$pgdata/pg_wal/$wal_segment_name") + or BAIL_OUT("open failed: $!"); +sysseek($fh, $lsn_offset, 0) + or BAIL_OUT("sysseek failed: $!"); +syswrite($fh, pack("L", 0xFFFFFFFF)) or BAIL_OUT("syswrite failed: $!"); +close($fh) + or BAIL_OUT("close failed: $!"); + +# The node should be able to start. +my $log_location = -s $node->logfile; +$node->start; +$result = $node->safe_psql('postgres', q(SELECT 1)); +is($result, "1", "node is up and running"); + +# Confirm thatrecovery has finished with the expected error +my $logfile = slurp_file($node->logfile, $log_location); +ok( $logfile =~ + qr/LOG: .* invalid magic number 0000 in WAL segment $wal_segment_name/, + "recovery completed up to the invalid record" +); + +done_testing(); -- 2.40.1