From 57823c5690469cf404de9fbdf37f55d09abaedd5 Mon Sep 17 00:00:00 2001 From: Kyotaro Horiguchi Date: Fri, 4 Mar 2022 13:18:30 +0900 Subject: [PATCH v4] Correctly update contfol file at the end of archive recovery CreateRestartPoint runs WAL file cleanup basing on the checkpoint just have finished in the function. If the database has exited DB_IN_ARCHIVE_RECOVERY state when the function is going to update control file, the function refrains from updating the file at all then proceeds to WAL cleanup having the latest REDO LSN, which is now inconsistent with the control file. As the result, the succeeding cleanup procedure overly removes WAL files against the control file and leaves unrecoverable database until the next checkpoint finishes. Along with that fix, we remove a dead code path for the case some other process ran a simultaneous checkpoint. It seems like just a preventive measure but it's no longer useful because we are sure that checkpoint is performed only by checkpointer except single process mode. --- src/backend/access/transam/xlog.c | 69 ++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 25 deletions(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index ed16f279b1..dd9c564988 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -6900,6 +6900,9 @@ CreateRestartPoint(int flags) XLogSegNo _logSegNo; TimestampTz xtime; + /* we don't assume concurrent checkpoint/restartpoint to run */ + Assert (!IsUnderPostmaster || MyBackendType == B_CHECKPOINTER); + /* Get a local copy of the last safe checkpoint record. */ SpinLockAcquire(&XLogCtl->info_lck); lastCheckPointRecPtr = XLogCtl->lastCheckPointRecPtr; @@ -6965,7 +6968,7 @@ CreateRestartPoint(int flags) /* Also update the info_lck-protected copy */ SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->RedoRecPtr = lastCheckPoint.redo; + XLogCtl->RedoRecPtr = RedoRecPtr; SpinLockRelease(&XLogCtl->info_lck); /* @@ -6984,7 +6987,10 @@ CreateRestartPoint(int flags) /* Update the process title */ update_checkpoint_display(flags, true, false); - CheckPointGuts(lastCheckPoint.redo, flags); + CheckPointGuts(RedoRecPtr, flags); + + /* Update pg_control */ + LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); /* * Remember the prior checkpoint's redo ptr for @@ -6992,30 +6998,26 @@ CreateRestartPoint(int flags) */ PriorRedoPtr = ControlFile->checkPointCopy.redo; + Assert (PriorRedoPtr < RedoRecPtr); + + ControlFile->checkPoint = lastCheckPointRecPtr; + ControlFile->checkPointCopy = lastCheckPoint; + /* - * Update pg_control, using current time. Check that it still shows - * DB_IN_ARCHIVE_RECOVERY state and an older checkpoint, else do nothing; - * this is a quick hack to make sure nothing really bad happens if somehow - * we get here after the end-of-recovery checkpoint. + * Ensure minRecoveryPoint is past the checkpoint record while archive + * recovery is still ongoing. Normally, this will have happened already + * while writing out dirty buffers, but not necessarily - e.g. because no + * buffers were dirtied. We do this because a non-exclusive base backup + * uses minRecoveryPoint to determine which WAL files must be included in + * the backup, and the file (or files) containing the checkpoint record + * must be included, at a minimum. Note that for an ordinary restart of + * recovery there's no value in having the minimum recovery point any + * earlier than this anyway, because redo will begin just after the + * checkpoint record. This is a quick hack to make sure nothing really bad + * happens if somehow we get here after the end-of-recovery checkpoint. */ - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); - if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY && - ControlFile->checkPointCopy.redo < lastCheckPoint.redo) + if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY) { - ControlFile->checkPoint = lastCheckPointRecPtr; - ControlFile->checkPointCopy = lastCheckPoint; - - /* - * Ensure minRecoveryPoint is past the checkpoint record. Normally, - * this will have happened already while writing out dirty buffers, - * but not necessarily - e.g. because no buffers were dirtied. We do - * this because a non-exclusive base backup uses minRecoveryPoint to - * determine which WAL files must be included in the backup, and the - * file (or files) containing the checkpoint record must be included, - * at a minimum. Note that for an ordinary restart of recovery there's - * no value in having the minimum recovery point any earlier than this - * anyway, because redo will begin just after the checkpoint record. - */ if (ControlFile->minRecoveryPoint < lastCheckPointEndPtr) { ControlFile->minRecoveryPoint = lastCheckPointEndPtr; @@ -7027,8 +7029,25 @@ CreateRestartPoint(int flags) } if (flags & CHECKPOINT_IS_SHUTDOWN) ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY; - UpdateControlFile(); } + else + { + /* recovery mode is not supposed to end during shutdown restartpoint */ + Assert((flags & CHECKPOINT_IS_SHUTDOWN) == 0); + + /* + * Aarchive recovery has ended. Crash recovery ever after should + * always recover to the end of WAL + */ + ControlFile->minRecoveryPoint = InvalidXLogRecPtr; + ControlFile->minRecoveryPointTLI = 0; + + /* also update local copy */ + LocalMinRecoveryPoint = InvalidXLogRecPtr; + LocalMinRecoveryPointTLI = 0; + } + + UpdateControlFile(); LWLockRelease(ControlFileLock); /* @@ -7105,7 +7124,7 @@ CreateRestartPoint(int flags) xtime = GetLatestXTime(); ereport((log_checkpoints ? LOG : DEBUG2), (errmsg("recovery restart point at %X/%X", - LSN_FORMAT_ARGS(lastCheckPoint.redo)), + LSN_FORMAT_ARGS(RedoRecPtr)), xtime ? errdetail("Last completed transaction was at log time %s.", timestamptz_to_str(xtime)) : 0)); -- 2.27.0