From f66e3160652b73637b157df5326bf67f6bc9e19a Mon Sep 17 00:00:00 2001 From: Imran Zaheer Date: Sun, 16 Aug 2026 00:08:56 +0900 Subject: [PATCH v3] Fix checkpointer restartpoint assertion failure When recovery starts from a backup without a signal file, pg_subtrans is not started at the beginning of recovery and remains unstarted throughout recovery. However, previously, a restartpoint run by the checkpointer during recovery nevertheless tried to truncate pg_subtrans, triggering the assertion failure: TRAP: failed Assert("TransactionIdIsValid(initial)") This commit fixes this by tracking whether pg_subtrans has been started during recovery, and have the checkpointer check this flag before truncating pg_subtrans at restartpoints. Backpatch to all supported versions. --- src/backend/access/transam/xlog.c | 42 ++++++++++++++++++++++++++++--- 1 file changed, 39 insertions(+), 3 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index ec84c77ddfa..bb84525e665 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -689,6 +689,12 @@ typedef struct XLogCtlData */ bool SharedPromoteIsTriggered; + /* + * SharedRecoverySubtransInitialized indicates whether hot standby + * initialization has started pg_subtrans. Protected by info_lck. + */ + bool SharedRecoverySubtransInitialized; + /* * WalWriterSleeping indicates whether the WAL writer is currently in * low-power mode (and hence should be nudged if an async commit occurs). @@ -971,6 +977,8 @@ static void ReadControlFile(void); static char *str_time(pg_time_t tnow); static void SetPromoteIsTriggered(void); static bool CheckForStandbyTrigger(void); +static bool RecoverySubtransInitialized(void); +static void SetRecoverySubtransInitialized(void); #ifdef WAL_DEBUG static void xlog_outrec(StringInfo buf, XLogReaderState *record); @@ -5295,6 +5303,7 @@ XLOGShmemInit(void) XLogCtl->SharedHotStandbyActive = false; XLogCtl->InstallXLogFileSegmentActive = false; XLogCtl->SharedPromoteIsTriggered = false; + XLogCtl->SharedRecoverySubtransInitialized = false; XLogCtl->WalWriterSleeping = false; SpinLockInit(&XLogCtl->Insert.insertpos_lck); @@ -7308,6 +7317,7 @@ StartupXLOG(void) * during recovery and need not be started yet. */ StartupSUBTRANS(oldestActiveXID); + SetRecoverySubtransInitialized(); /* * If we're beginning at a shutdown checkpoint, we know that @@ -10029,10 +10039,10 @@ CreateRestartPoint(int flags) * Truncate pg_subtrans if possible. We can throw away all data before * the oldest XMIN of any running transaction. No future transaction will * attempt to reference any pg_subtrans entry older than that (see Asserts - * in subtrans.c). When hot standby is disabled, though, we mustn't do - * this because StartupSUBTRANS hasn't been called yet. + * in subtrans.c). During recovery, don't truncate pg_subtrans until hot + * standby initialization has started it. */ - if (EnableHotStandby) + if (RecoverySubtransInitialized()) TruncateSUBTRANS(GetOldestTransactionIdConsideredRunning()); /* Real work is done; log and update stats. */ @@ -13408,6 +13418,32 @@ CheckPromoteSignal(void) return false; } +/* + * Has hot standby initialization started pg_subtrans? + */ +static bool +RecoverySubtransInitialized(void) +{ + bool result; + + SpinLockAcquire(&XLogCtl->info_lck); + result = XLogCtl->SharedRecoverySubtransInitialized; + SpinLockRelease(&XLogCtl->info_lck); + + return result; +} + +/* + * Remember that hot standby initialization has started pg_subtrans. + */ +static void +SetRecoverySubtransInitialized(void) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->SharedRecoverySubtransInitialized = true; + SpinLockRelease(&XLogCtl->info_lck); +} + /* * Wake up startup process to replay newly arrived WAL, or to notice that * failover has been requested. -- 2.55.0