From a1b8b3b2e38595efc67165cf748947a64910af0e Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Tue, 4 Nov 2025 10:52:42 +0900 Subject: [PATCH] Fix unconditional WAL receiver shutdown during stream-archive transition Commit b4f584f9d2a1 (affecting v15~, later backpatched down to 13 as of 3635a0a35aaf) introduced an unconditional WAL receiver shutdown when switching from streaming to archive WAL sources. This causes problems during a timeline switch, when a WAL receiver enters WALRCV_WAITING state but remains alive, waiting for instructions. The unconditional shutdown can break some monitoring scenarios as the WAL receiver gets repeatedly terminated and re-spawned, causing pg_stat_wal_receiver.status to show a "streaming" instead of "waiting" status, masking the fact that the WAL receiver is waiting for a new TLI and a new LSN to be able to continue streaming. This commit changes the WAL receiver behavior so as the shutdown becomes conditional, with InstallXLogFileSegmentActive being always reset to prevent the regression fixed by b4f584f9d2a1: only terminate the WAL receiver when it is actively streaming (WALRCV_STREAMING, WALRCV_STARTING, or WALRCV_RESTARTING). When in WALRCV_WAITING state, just reset InstallXLogFileSegmentActive flag to allow archive restoration without killing the process. WALRCV_STOPPED and WALRCV_STOPPING are not reachable states in this code path. For the latter, the startup process is the one in charge of setting WALRCV_STOPPING via ShutdownWalRcv(), waiting for the WAL receiver to reach a WALRCV_STOPPED state after switching walRcvState, so WaitForWALToBecomeAvailable() cannot be reached while a WAL receiver is in a WALRCV_STOPPING state. A regression test is added to check that a WAL receiver is not stopped on timeline jump, that fails when the fix of this commit is reverted. Reported-by: Ryan Bird Author: Xuneng Zhou Reviewed-by: Noah Misch Reviewed-by: Michael Paquier Discussion: https://postgr.es/m/19093-c4fff49a608f82a0@postgresql.org Backpatch-through: 13 --- src/backend/access/transam/xlog.c | 27 ++++++++++++++++++---- src/test/recovery/t/004_timeline_switch.pl | 10 +++++++- 2 files changed, 31 insertions(+), 6 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 3f8de31b386..1d81fa1c2af 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -946,6 +946,7 @@ static int XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, int reqLen, XLogRecPtr targetRecPtr, char *readBuf); static bool WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, bool fetching_ckpt, XLogRecPtr tliRecPtr); +static void ResetInstallXLogFileSegmentActive(void); static void XLogShutdownWalRcv(void); static int emode_for_corrupt_record(int emode, XLogRecPtr RecPtr); static void XLogFileClose(void); @@ -12837,8 +12838,18 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, * Before we leave XLOG_FROM_STREAM state, make sure that * walreceiver is not active, so that it won't overwrite * WAL that we restore from archive. + * If walreceiver is actively streaming (or attempting to + * connect), we must shut it down. However, if it's + * already in WAITING state (e.g., due to timeline + * divergence), we only need to reset the install flag to + * allow archive restoration. */ - XLogShutdownWalRcv(); + if (WalRcvStreaming()) + XLogShutdownWalRcv(); + else + { + ResetInstallXLogFileSegmentActive(); + } /* * Before we sleep, re-scan for possible new timelines if @@ -13191,17 +13202,23 @@ StartupRequestWalReceiverRestart(void) } } -/* Thin wrapper around ShutdownWalRcv(). */ +/* Disable WAL file recycling and preallocation. */ static void -XLogShutdownWalRcv(void) +ResetInstallXLogFileSegmentActive(void) { - ShutdownWalRcv(); - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); XLogCtl->InstallXLogFileSegmentActive = false; LWLockRelease(ControlFileLock); } +/* Thin wrapper around ShutdownWalRcv(). */ +static void +XLogShutdownWalRcv(void) +{ + ShutdownWalRcv(); + ResetInstallXLogFileSegmentActive(); +} + /* * Determine what log level should be used to report a corrupt WAL record * in the current WAL page, previously read by XLogPageRead(). diff --git a/src/test/recovery/t/004_timeline_switch.pl b/src/test/recovery/t/004_timeline_switch.pl index c101980e9e2..a777d8e6a3d 100644 --- a/src/test/recovery/t/004_timeline_switch.pl +++ b/src/test/recovery/t/004_timeline_switch.pl @@ -7,7 +7,7 @@ use warnings; use File::Path qw(rmtree); use PostgresNode; use TestLib; -use Test::More tests => 3; +use Test::More tests => 4; $ENV{PGDATABASE} = 'postgres'; @@ -71,6 +71,14 @@ my $result = $node_standby_2->safe_psql('postgres', "SELECT count(*) FROM tab_int"); is($result, qq(2000), 'check content of standby 2'); +# Check the logs, WAL receiver should not have been stopped while +# transitioning to its new timeline. There is no need to rely on an +# offset in this check of the server logs: a new log file is used on +# node restart when primary_conninfo is updated above. +ok( !$node_standby_2->log_contains( + "FATAL: .* terminating walreceiver process due to administrator command" + ), + 'WAL receiver should not be stopped across timeline jumps'); # Ensure that a standby is able to follow a primary on a newer timeline # when WAL archiving is enabled. -- 2.47.3