From 279956817ff4f8e69a2892d0677e303cb2a8c30b Mon Sep 17 00:00:00 2001 From: Noah Misch Date: Wed, 26 Jan 2022 18:06:19 -0800 Subject: [PATCH] On sparc64+ext4, suppress test failures from known WAL read failure. Buildfarm members kittiwake, tadarida and snapper began to fail frequently when commits 3cd9c3b921977272e6650a5efbeade4203c4bca2 and f47ed79cc8a0cfa154dc7f01faaf59822552363f added tests of concurrency, but the problem was reachable before those commits. Back-patch to v10 (all supported versions). Discussion: https://postgr.es/m/20220116210241.GC756210@rfd.leadboat.com --- contrib/amcheck/t/003_cic_2pc.pl | 2 ++ src/test/perl/TestLib.pm | 23 +++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/contrib/amcheck/t/003_cic_2pc.pl b/contrib/amcheck/t/003_cic_2pc.pl index c539186965..d81734fca7 100644 --- a/contrib/amcheck/t/003_cic_2pc.pl +++ b/contrib/amcheck/t/003_cic_2pc.pl @@ -11,6 +11,8 @@ use TestLib; use Test::More tests => 5; +local $TODO = 'filesystem bug' if TestLib::has_wal_read_bug; + my ($node, $result); # diff --git a/src/test/perl/TestLib.pm b/src/test/perl/TestLib.pm index 2320ead9d5..5c21cd5608 100644 --- a/src/test/perl/TestLib.pm +++ b/src/test/perl/TestLib.pm @@ -220,6 +220,29 @@ sub perl2host return $dir . $leaf; } +=pod + +=item has_wal_read_bug() + +Returns true if $tmp_check is subject to a sparc64+ext4 bug that causes WAL +readers to see zeros if another process simultaneously wrote the same offsets. +Consult this in tests that fail frequently on affected configurations. The +bug has made streaming standbys fail to advance, reporting corrupt WAL. It +has made COMMIT PREPARED fail with "could not read two-phase state from WAL". +Non-WAL PostgreSQL reads haven't been affected, likely because those readers +and writers have buffering systems in common. See +https://postgr.es/m/20220116210241.GC756210@rfd.leadboat.com for details. + +=cut + +sub has_wal_read_bug +{ + return + $Config{osname} eq 'linux' + && $Config{archname} =~ /^sparc/ + && !run_log([ qw(df -x ext4), $tmp_check ], '>', '/dev/null', '2>&1'); +} + sub system_log { print("# Running: " . join(" ", @_) . "\n");