Re: A failure of standby to follow timeline switch - Mailing list pgsql-hackers
From | Kyotaro Horiguchi |
---|---|
Subject | Re: A failure of standby to follow timeline switch |
Date | |
Msg-id | 20210106.104804.1837050045776994380.horikyota.ntt@gmail.com Whole thread Raw |
In response to | Re: A failure of standby to follow timeline switch (Kyotaro Horiguchi <horikyota.ntt@gmail.com>) |
List | pgsql-hackers |
At Tue, 05 Jan 2021 17:26:02 +0900 (JST), Kyotaro Horiguchi <horikyota.ntt@gmail.com> wrote in > Thanks. The attached is the revised patchset. It is not applicable to PG13 due to wording changes. This is an applicable all-in-one version to PG13. regards. -- Kyotaro Horiguchi NTT Open Source Software Center From d4b11d93f93f3af2aa55033b91ddbec176763325 Mon Sep 17 00:00:00 2001 From: Kyotaro Horiguchi <horikyoga.ntt@gmail.com> Date: Tue, 5 Jan 2021 13:34:36 +0900 Subject: [PATCH] Fix timeline-tracking failure while sending a historic timeline Walsender should track timeline switches while sending a historic timeline. Regain that behavior, which was broken in PG13, by a thinko of 709d003fbd. Backpatch to PG13. --- src/backend/replication/walsender.c | 2 +- src/test/perl/PostgresNode.pm | 33 ++++++++++++++++++ src/test/perl/TestLib.pm | 16 ++++++--- src/test/recovery/t/001_stream_rep.pl | 41 ++++++++++++++++++++++- src/test/recovery/t/019_replslot_limit.pl | 37 ++++---------------- 5 files changed, 92 insertions(+), 37 deletions(-) diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 7f87eb7f19..04f6c3ebb4 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -2478,7 +2478,7 @@ WalSndSegmentOpen(XLogReaderState *state, XLogSegNo nextSegNo, XLogSegNo endSegNo; XLByteToSeg(sendTimeLineValidUpto, endSegNo, state->segcxt.ws_segsize); - if (state->seg.ws_segno == endSegNo) + if (nextSegNo == endSegNo) *tli_p = sendTimeLineNextTLI; } diff --git a/src/test/perl/PostgresNode.pm b/src/test/perl/PostgresNode.pm index 980f1f1533..687aa3ac88 100644 --- a/src/test/perl/PostgresNode.pm +++ b/src/test/perl/PostgresNode.pm @@ -2138,6 +2138,39 @@ sub pg_recvlogical_upto =pod +=item $node->current_log_position() + +Return the current position of server log. + +=cut + +sub current_log_position +{ + my $self = shift; + + return (stat $self->logfile)[7]; +} + +=pod + +=item $node->find_in_log($pattern, $startpos) + +Returns whether the $pattern occurs after $startpos in the server log. + +=cut + +sub find_in_log +{ + my ($self, $pattern, $startpos) = @_; + + $startpos = 0 unless defined $startpos; + my $log = TestLib::slurp_file($self->logfile, $startpos); + + return $log =~ m/$pattern/; +} + +=pod + =back =cut diff --git a/src/test/perl/TestLib.pm b/src/test/perl/TestLib.pm index a7490d2ce7..a0ce9521e2 100644 --- a/src/test/perl/TestLib.pm +++ b/src/test/perl/TestLib.pm @@ -402,30 +402,38 @@ sub slurp_dir =pod -=item slurp_file(filename) +=item slurp_file(filename, pos) -Return the full contents of the specified file. +Return the contents after pos of the specified file. +Reutrns the full contents if pos is omitted. =cut sub slurp_file { - my ($filename) = @_; + my ($filename, $from) = @_; local $/; my $contents; + + $from = 0 unless defined $from; + if ($Config{osname} ne 'MSWin32') { open(my $in, '<', $filename) or die "could not read \"$filename\": $!"; + seek($in, $from, 0) + or die "could not seek \"$filename\" to $from: $!"; $contents = <$in>; close $in; } else { my $fHandle = createFile($filename, "r", "rwd") - or die "could not open \"$filename\": $^E"; + or die "could not open \"$filename\": $^E\n"; OsFHandleOpen(my $fh = IO::Handle->new(), $fHandle, 'r') or die "could not read \"$filename\": $^E\n"; + seek($fh, $from, 0) + or die "could not seek \"$filename\" to $from: $^E\n"; $contents = <$fh>; CloseHandle($fHandle) or die "could not close \"$filename\": $^E\n"; diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl index 778f11b28b..8d2b24fe55 100644 --- a/src/test/recovery/t/001_stream_rep.pl +++ b/src/test/recovery/t/001_stream_rep.pl @@ -2,8 +2,9 @@ use strict; use warnings; use PostgresNode; +use Time::HiRes qw(usleep); use TestLib; -use Test::More tests => 36; +use Test::More tests => 37; # Initialize master node my $node_master = get_new_node('master'); @@ -409,3 +410,41 @@ ok( ($phys_restart_lsn_pre cmp $phys_restart_lsn_post) == 0, my $master_data = $node_master->data_dir; ok(!-f "$master_data/pg_wal/$segment_removed", "WAL segment $segment_removed recycled after physical slot advancing"); + +# +# Check if timeline-increment works while reading a historic timeline. +my $node_primary_2 = get_new_node('primary_2'); +# archiving is needed to create .paritial segment +$node_primary_2->init(allows_streaming => 1, has_archiving => 1); +$node_primary_2->start; +$node_primary_2->backup($backup_name); +my $node_standby_3 = get_new_node('standby_3'); +$node_standby_3->init_from_backup($node_primary_2, $backup_name, + has_streaming => 1); +$node_primary_2->stop; +$node_primary_2->set_standby_mode; # increment primary timeline +$node_primary_2->start; +$node_primary_2->promote; +my $logstart = $node_standby_3->current_log_position(); +$node_standby_3->start; + +my $success = 0; +for (my $i = 0 ; $i < 1000; $i++) +{ + if ($node_standby_3->find_in_log( + "requested WAL segment [0-9A-F]+ has already been removed", + $logstart)) + { + last; + } + elsif ($node_standby_3->find_in_log( + "End of WAL reached on timeline", + $logstart)) + { + $success = 1; + last; + } + usleep(100_000); +} + +ok($success, 'Timeline increment while reading a historic timeline'); diff --git a/src/test/recovery/t/019_replslot_limit.pl b/src/test/recovery/t/019_replslot_limit.pl index a7231dcd47..8b3c5de057 100644 --- a/src/test/recovery/t/019_replslot_limit.pl +++ b/src/test/recovery/t/019_replslot_limit.pl @@ -165,19 +165,17 @@ $node_master->wait_for_catchup($node_standby, 'replay', $start_lsn); $node_standby->stop; -ok( !find_in_log( - $node_standby, - "requested WAL segment [0-9A-F]+ has already been removed"), +ok( !$node_standby->find_in_log( + "requested WAL segment [0-9A-F]+ has already been removed"), 'check that required WAL segments are still available'); # Advance WAL again, the slot loses the oldest segment. -my $logstart = get_log_size($node_master); +my $logstart = $node_master->current_log_position(); advance_wal($node_master, 7); $node_master->safe_psql('postgres', "CHECKPOINT;"); # WARNING should be issued -ok( find_in_log( - $node_master, +ok( $node_master->find_in_log( "invalidating slot \"rep1\" because its restart_lsn [0-9A-F/]+ exceeds max_slot_wal_keep_size", $logstart), 'check that the warning is logged'); @@ -190,14 +188,13 @@ is($result, "rep1|f|t|lost|", 'check that the slot became inactive and the state "lost" persists'); # The standby no longer can connect to the master -$logstart = get_log_size($node_standby); +$logstart = $node_standby->current_log_position(); $node_standby->start; my $failed = 0; for (my $i = 0; $i < 10000; $i++) { - if (find_in_log( - $node_standby, + if ($node_standby->find_in_log( "requested WAL segment [0-9A-F]+ has already been removed", $logstart)) { @@ -264,25 +261,3 @@ sub advance_wal } return; } - -# return the size of logfile of $node in bytes -sub get_log_size -{ - my ($node) = @_; - - return (stat $node->logfile)[7]; -} - -# find $pat in logfile of $node after $off-th byte -sub find_in_log -{ - my ($node, $pat, $off) = @_; - - $off = 0 unless defined $off; - my $log = TestLib::slurp_file($node->logfile); - return 0 if (length($log) <= $off); - - $log = substr($log, $off); - - return $log =~ m/$pat/; -} -- 2.27.0
pgsql-hackers by date: