public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v3] Avoid creating archive status ".ready" files too early. 7+ messages / 3 participants [nested] [flat]
* [PATCH v3] Avoid creating archive status ".ready" files too early. @ 2021-07-30 22:35 Alvaro Herrera <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Alvaro Herrera @ 2021-07-30 22:35 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file will be created. If PostgreSQL crashes before it is able to write the rest of the record, it will end up reusing segments that have already been marked as ready-for-archival. However, the archiver process may have already processed the old version of the segment, so the wrong version of the segment may be backed-up. This backed-up segment will cause operations such as point-in-time restores to fail. To fix this, we keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 286 ++++++++++++++++++++++- src/backend/access/transam/xlogarchive.c | 14 +- src/backend/replication/walreceiver.c | 6 +- src/backend/storage/lmgr/lwlocknames.txt | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 5 + 7 files changed, 296 insertions(+), 22 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f84c0bb01e..99fe1ac0a2 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -512,6 +512,13 @@ typedef enum ExclusiveBackupState */ static SessionBackupState sessionBackupState = SESSION_BACKUP_NONE; +/* entries for RecordBoundaryMap, used to mark segments ready for archival */ +typedef struct RecordBoundaryEntry +{ + XLogSegNo seg; /* must be first */ + XLogRecPtr pos; +} RecordBoundaryEntry; + /* * Shared state data for WAL insertion. */ @@ -723,6 +730,12 @@ typedef struct XLogCtlData */ XLogRecPtr lastFpwDisableRecPtr; + /* + * The last segment we've marked ready for archival. Protected by + * info_lck. + */ + XLogSegNo lastNotifiedSeg; + slock_t info_lck; /* locks shared variables shown above */ } XLogCtlData; @@ -736,6 +749,12 @@ static WALInsertLockPadded *WALInsertLocks = NULL; */ static ControlFileData *ControlFile = NULL; +/* + * Record boundary map, used for marking segments as ready for archival. + * Protected by ArchNotifyLock. + */ +static HTAB *RecordBoundaryMap = NULL; + /* * Calculate the amount of space left on the page after 'endptr'. Beware * multiple evaluation! @@ -962,6 +981,13 @@ static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos); static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos); static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr); static void checkXLogConsistency(XLogReaderState *record); +static void RegisterRecordBoundaryEntry(XLogSegNo seg, XLogRecPtr pos); +static void NotifySegmentsReadyForArchive(void); +static XLogSegNo GetLastNotifiedSegment(void); +static void SetLastNotifiedSegment(XLogSegNo seg); +static void SetLastNotifiedSegmentIfInvalid(XLogSegNo seg); +static XLogSegNo GetLatestRecordBoundarySegment(void); +static void RemoveRecordBoundariesUpTo(XLogSegNo seg); static void WALInsertLockAcquire(void); static void WALInsertLockAcquireExclusive(void); @@ -1009,6 +1035,8 @@ XLogInsertRecord(XLogRecData *rdata, info == XLOG_SWITCH); XLogRecPtr StartPos; XLogRecPtr EndPos; + XLogSegNo StartSeg; + XLogSegNo EndSeg; bool prevDoPageWrites = doPageWrites; /* we assume that all of the record header is in the first chunk */ @@ -1167,10 +1195,33 @@ XLogInsertRecord(XLogRecData *rdata, SpinLockRelease(&XLogCtl->info_lck); } + /* + * Record the record boundary if we crossed the segment boundary. This is + * used to ensure that segments are not marked ready for archival before the + * entire record has been flushed to disk. + * + * Note that we do not use XLByteToPrevSeg() for determining the ending + * segment. This is done so that a record that fits perfectly into the end + * of the segment is marked ready for archival as soon as the flushed + * pointer jumps to the next segment. + */ + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + if (StartSeg != EndSeg && XLogArchivingActive()) + { + RegisterRecordBoundaryEntry(EndSeg, EndPos); + + /* + * There's a chance that the record was already flushed to disk and we + * missed marking segments as ready for archive, so try to do that now. + */ + NotifySegmentsReadyForArchive(); + } + /* * If this was an XLOG_SWITCH record, flush the record and the empty - * padding space that fills the rest of the segment, and perform - * end-of-segment actions (eg, notifying archiver). + * padding space that fills the rest of the segment. */ if (isLogSwitch) { @@ -1264,6 +1315,205 @@ XLogInsertRecord(XLogRecData *rdata, return EndPos; } +/* + * RegisterRecordBoundaryEntry + * + * This enters a new entry into the record boundary map, which is used for + * determing when it is safe to mark a segment as ready for archival. An entry + * with the given key (the segment number) must not already exist in the map. + * Also, the caller is responsible for ensuring that XLByteToSeg() would return + * the same segment number for the given record pointer. + */ +static void +RegisterRecordBoundaryEntry(XLogSegNo seg, XLogRecPtr pos) +{ + RecordBoundaryEntry *entry; + bool found; + + LWLockAcquire(ArchNotifyLock, LW_EXCLUSIVE); + + entry = (RecordBoundaryEntry *) hash_search(RecordBoundaryMap, + (void *) &seg, HASH_ENTER, + &found); + if (found) + elog(ERROR, "record boundary entry for segment already exists"); + + entry->pos = pos; + + LWLockRelease(ArchNotifyLock); +} + +/* + * NotifySegmentsReadyForArchive + * + * This function marks segments as ready for archival, given that it is safe to + * do so. It is safe to call this function repeatedly, even if nothing has + * changed since the last time it was called. + */ +static void +NotifySegmentsReadyForArchive(void) +{ + XLogRecPtr flushed; + XLogSegNo flushed_seg; + XLogSegNo latest_boundary_seg; + XLogSegNo last_notified; + + /* + * We first do a quick sanity check to see if we can bail out without taking + * the ArchNotifyLock at all. It is expected that this function will run + * frequently and that it will need to do nothing the vast majority of the + * time. + * + * Specifically, we bail out if the shared memory value for the last + * notified segment has not yet been initialized or if we've already marked + * the segment prior to the segment that contains "flushed" as ready for + * archival. We intentionally use XLByteToSeg() instead of + * XLByteToPrevSeg() so that we don't skip notifying when a record fits + * perfectly into the end of a segment. ("flushed" should point to the + * first byte of the record _after_ the one that is known to be flushed to + * disk.) + */ + last_notified = GetLastNotifiedSegment(); + + if (XLogSegNoIsInvalid(last_notified)) + return; + + flushed = GetFlushRecPtr(); + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + if (last_notified >= flushed_seg - 1) + return; + + /* + * Notify archiver about segments that are ready for archival (by creating + * the corresponding .ready files), and discard segment boundaries no + * longer needed. + */ + LWLockAcquire(ArchNotifyLock, LW_EXCLUSIVE); + latest_boundary_seg = GetLatestRecordBoundarySegment(); + if (!XLogSegNoIsInvalid(latest_boundary_seg)) + { + XLogSegNo seg; + + /* create the archive status files */ + for (seg = GetLastNotifiedSegment() + 1; seg < latest_boundary_seg; seg++) + XLogArchiveNotifySeg(seg, false); + + /* update shared memory */ + SetLastNotifiedSegment(latest_boundary_seg - 1); + + /* remove old boundaries from the map */ + RemoveRecordBoundariesUpTo(latest_boundary_seg); + + PgArchWakeup(); + } + LWLockRelease(ArchNotifyLock); +} + +/* + * GetLatestRecordBoundarySegment + * + * This function finds the latest record boundary in RecordBoundaryMap that is + * less than or equal to the current "flushed" pointer and returns its + * associated segment number, given that it is greater than the last notified + * segment. Otherwise, InvalidXLogSegNo is returned. + */ +static XLogSegNo +GetLatestRecordBoundarySegment(void) +{ + XLogRecPtr flushed; + XLogSegNo flushed_seg; + XLogSegNo last_notified; + XLogSegNo seg; + + Assert(LWLockHeldByMe(ArchNotifyLock)); + + flushed = GetFlushRecPtr(); + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + last_notified = GetLastNotifiedSegment(); + + for (seg = flushed_seg; seg > last_notified; seg--) + { + RecordBoundaryEntry *entry; + + entry = (RecordBoundaryEntry *) hash_search(RecordBoundaryMap, + (void *) &seg, HASH_FIND, + NULL); + + if (entry != NULL && flushed >= entry->pos) + return entry->seg; + } + + return InvalidXLogSegNo; +} + +/* + * RemoveOldRecordBoundaries + * + * This function removes all entries in the RecordBoundaryMap with segment + * numbers up to an including seg. + */ +static void +RemoveRecordBoundariesUpTo(XLogSegNo seg) +{ + RecordBoundaryEntry *entry; + HASH_SEQ_STATUS status; + + Assert(LWLockHeldByMeInMode(ArchNotifyLock, LW_EXCLUSIVE)); + + hash_seq_init(&status, RecordBoundaryMap); + + while ((entry = (RecordBoundaryEntry *) hash_seq_search(&status)) != NULL) + { + if (entry->seg <= seg) + (void) hash_search(RecordBoundaryMap, (void *) &entry->seg, + HASH_REMOVE, NULL); + } +} + +/* + * GetLastNotifiedSegment + * + * Retrieves last notified segment from shared memory. + */ +XLogSegNo +GetLastNotifiedSegment(void) +{ + XLogSegNo seg; + + SpinLockAcquire(&XLogCtl->info_lck); + seg = XLogCtl->lastNotifiedSeg; + SpinLockRelease(&XLogCtl->info_lck); + + return seg; +} + +/* + * SetLastNotifiedSegment + * + * Sets last notified segment in shared memory. + */ +static void +SetLastNotifiedSegment(XLogSegNo seg) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->lastNotifiedSeg = seg; + SpinLockRelease(&XLogCtl->info_lck); +} + +/* + * SetLastNotifiedSegmentIfInvalid + * + * Sets last notified segment, but only if it's currently unset. + */ +static void +SetLastNotifiedSegmentIfInvalid(XLogSegNo seg) +{ + SpinLockAcquire(&XLogCtl->info_lck); + if (XLogCtl->lastNotifiedSeg == InvalidXLogSegNo) + XLogCtl->lastNotifiedSeg = seg; + SpinLockRelease(&XLogCtl->info_lck); +} + /* * Reserves the right amount of space for a record of given size from the WAL. * *StartPos is set to the beginning of the reserved section, *EndPos to @@ -2586,11 +2836,14 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * If WAL archiving is active and lastNotifiedSeg hasn't been + * initialized yet, do that, too. This will let us notify + * archiver correctly later. + * + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. + * */ if (finishing_seg) { @@ -2602,7 +2855,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + SetLastNotifiedSegmentIfInvalid(openLogSegNo - 1); XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2690,6 +2943,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(); } /* @@ -5117,6 +5373,9 @@ XLOGShmemSize(void) /* and the buffers themselves */ size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers)); + /* stuff for marking segments as ready for archival */ + size = add_size(size, hash_estimate_size(16, sizeof(RecordBoundaryEntry))); + /* * Note: we don't count ControlFileData, it comes out of the "slop factor" * added by CreateSharedMemoryAndSemaphores. This lets us use this @@ -5134,6 +5393,7 @@ XLOGShmemInit(void) char *allocptr; int i; ControlFileData *localControlFile; + HASHCTL info; #ifdef WAL_DEBUG @@ -5227,12 +5487,20 @@ XLOGShmemInit(void) XLogCtl->InstallXLogFileSegmentActive = false; XLogCtl->SharedPromoteIsTriggered = false; XLogCtl->WalWriterSleeping = false; + XLogCtl->lastNotifiedSeg = InvalidXLogSegNo; SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + memset(&info, 0, sizeof(info)); + info.keysize = sizeof(XLogSegNo); + info.entrysize = sizeof(RecordBoundaryEntry); + RecordBoundaryMap = ShmemInitHash("Record Boundary Table", 16, 16, &info, + HASH_ELEM | HASH_BLOBS); } /* @@ -7997,7 +8265,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..e9cac90b4a 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -464,7 +464,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * then when complete, rename it to 0000000100000001000000C6.done */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool notify) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +489,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, notify archiver that it's got something to do */ + if (notify) PgArchWakeup(); } @@ -498,12 +498,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool notify) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, notify); } /* @@ -608,7 +608,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt index 6c7cf6c295..d39225bf94 100644 --- a/src/backend/storage/lmgr/lwlocknames.txt +++ b/src/backend/storage/lmgr/lwlocknames.txt @@ -53,3 +53,4 @@ XactTruncationLock 44 # 45 was XactTruncationLock until removal of BackendRandomLock WrapLimitsVacuumLock 46 NotifyQueueTailLock 47 +ArchNotifyLock 48 diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..e25c3d8117 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool notify); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool notify); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..b5a0023d81 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -47,6 +47,11 @@ typedef uint64 XLogRecPtr; */ typedef uint64 XLogSegNo; +#define InvalidXLogSegNo ((XLogSegNo) 0xFFFFFFFFFFFFFFFF) +#define XLogSegNoIsInvalid(s) \ + (AssertVariableIsOfTypeMacro(s, XLogSegNo), \ + (s) == InvalidXLogSegNo) + /* * TimeLineID (TLI) - identifies different database histories to prevent * confusion after restoring a prior state of a database installation. -- 2.20.1 --vp4c52all22p7wxm-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v2] Avoid creating archive status ".ready" files too early. @ 2021-07-30 22:35 Alvaro Herrera <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Alvaro Herrera @ 2021-07-30 22:35 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file will be created. If PostgreSQL crashes before it is able to write the rest of the record, it will end up reusing segments that have already been marked as ready-for-archival. However, the archiver process may have already processed the old version of the segment, so the wrong version of the segment may be backed-up. This backed-up segment will cause operations such as point-in-time restores to fail. To fix this, we keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 279 ++++++++++++++++++++++- src/backend/access/transam/xlogarchive.c | 14 +- src/backend/replication/walreceiver.c | 6 +- src/backend/storage/lmgr/lwlocknames.txt | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 3 + 7 files changed, 289 insertions(+), 20 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 26fa2b6c8f..700bbccff8 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -531,6 +531,13 @@ typedef enum ExclusiveBackupState */ static SessionBackupState sessionBackupState = SESSION_BACKUP_NONE; +/* entries for RecordBoundaryMap, used to mark segments ready for archival */ +typedef struct RecordBoundaryEntry +{ + XLogSegNo seg; /* must be first */ + XLogRecPtr pos; +} RecordBoundaryEntry; + /* * Shared state data for WAL insertion. */ @@ -742,6 +749,12 @@ typedef struct XLogCtlData */ XLogRecPtr lastFpwDisableRecPtr; + /* + * The last segment we've marked ready for archival. Protected by + * ArchNotifyLock. + */ + XLogSegNo lastNotifiedSeg; + slock_t info_lck; /* locks shared variables shown above */ } XLogCtlData; @@ -755,6 +768,12 @@ static WALInsertLockPadded *WALInsertLocks = NULL; */ static ControlFileData *ControlFile = NULL; +/* + * Record boundary map, used for marking segments as ready for archival. + * Protected by ArchNotifyLock. + */ +static HTAB *RecordBoundaryMap = NULL; + /* * Calculate the amount of space left on the page after 'endptr'. Beware * multiple evaluation! @@ -983,6 +1002,12 @@ static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos); static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos); static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr); static void checkXLogConsistency(XLogReaderState *record); +static void RegisterRecordBoundaryEntry(XLogSegNo seg, XLogRecPtr pos); +static void NotifySegmentsReadyForArchive(void); +static XLogSegNo GetLastNotifiedSegment(void); +static void SetLastNotifiedSegment(XLogSegNo seg); +static XLogSegNo GetLatestRecordBoundarySegment(void); +static void RemoveRecordBoundariesUpTo(XLogSegNo seg); static void WALInsertLockAcquire(void); static void WALInsertLockAcquireExclusive(void); @@ -1030,6 +1055,8 @@ XLogInsertRecord(XLogRecData *rdata, info == XLOG_SWITCH); XLogRecPtr StartPos; XLogRecPtr EndPos; + XLogSegNo StartSeg; + XLogSegNo EndSeg; bool prevDoPageWrites = doPageWrites; /* we assume that all of the record header is in the first chunk */ @@ -1188,6 +1215,31 @@ XLogInsertRecord(XLogRecData *rdata, SpinLockRelease(&XLogCtl->info_lck); } + /* + * Record the record boundary if we crossed the segment boundary. This is + * used to ensure that segments are not marked ready for archival before the + * entire record has been flushed to disk. + * + * Note that we do not use XLByteToPrevSeg() for determining the ending + * segment. This is done so that a record that fits perfectly into the end + * of the segment is marked ready for archival as soon as the flushed + * pointer jumps to the next segment. + */ + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + if (StartSeg != EndSeg && + XLogArchivingActive()) + { + RegisterRecordBoundaryEntry(EndSeg, EndPos); + + /* + * There's a chance that the record was already flushed to disk and we + * missed marking segments as ready for archive, so try to do that now. + */ + NotifySegmentsReadyForArchive(); + } + /* * If this was an XLOG_SWITCH record, flush the record and the empty * padding space that fills the rest of the segment, and perform @@ -1285,6 +1337,197 @@ XLogInsertRecord(XLogRecData *rdata, return EndPos; } +/* + * RegisterRecordBoundaryEntry + * + * This enters a new entry into the record boundary map, which is used for + * determing when it is safe to mark a segment as ready for archival. An entry + * with the given key (the segment number) must not already exist in the map. + * Also, the caller is responsible for ensuring that XLByteToSeg() would return + * the same segment number for the given record pointer. + */ +static void +RegisterRecordBoundaryEntry(XLogSegNo seg, XLogRecPtr pos) +{ + RecordBoundaryEntry *entry; + bool found; + + LWLockAcquire(ArchNotifyLock, LW_EXCLUSIVE); + + entry = (RecordBoundaryEntry *) hash_search(RecordBoundaryMap, + (void *) &seg, HASH_ENTER, + &found); + if (found) + elog(ERROR, "record boundary entry for segment already exists"); + + entry->pos = pos; + + LWLockRelease(ArchNotifyLock); +} + +/* + * NotifySegmentsReadyForArchive + * + * This function marks segments as ready for archival, given that it is safe to + * do so. It is safe to call this function repeatedly, even if nothing has + * changed since the last time it was called. + */ +static void +NotifySegmentsReadyForArchive(void) +{ + XLogRecPtr flushed; + XLogSegNo flushed_seg; + XLogSegNo latest_boundary_seg; + XLogSegNo last_notified; + + /* + * We first do a quick sanity check to see if we can bail out without taking + * the ArchNotifyLock at all. It is expected that this function will run + * frequently and that it will need to do nothing the vast majority of the + * time. + * + * Specifically, we bail out if the shared memory value for the last + * notified segment has not yet been initialized or if we've already marked + * the segment prior to the segment that contains "flushed" as ready for + * archival. We intentionally use XLByteToSeg() instead of + * XLByteToPrevSeg() so that we don't skip notifying when a record fits + * perfectly into the end of a segment. ("flushed" should point to the + * first byte of the record _after_ the one that is known to be flushed to + * disk.) + */ + LWLockAcquire(ArchNotifyLock, LW_SHARED); + last_notified = GetLastNotifiedSegment(); + LWLockRelease(ArchNotifyLock); + + if (XLogSegNoIsInvalid(last_notified)) + return; + + flushed = GetFlushRecPtr(); + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + if (last_notified >= flushed_seg - 1) + return; + + /* + * At this point, we must acquire ArchNotifyLock before proceeding. In this + * section, we look for the latest record boundary in RecordBoundaryMap that + * is less than or equal to the current "flushed" pointer, and we notify the + * archiver that all segments up to (but not including) that boundary's + * associated segment are ready for archival. + */ + LWLockAcquire(ArchNotifyLock, LW_EXCLUSIVE); + + latest_boundary_seg = GetLatestRecordBoundarySegment(); + if (!XLogSegNoIsInvalid(latest_boundary_seg)) + { + XLogSegNo i; + + /* create the archive status files */ + for (i = GetLastNotifiedSegment() + 1; i < latest_boundary_seg; i++) + XLogArchiveNotifySeg(i, false); + + /* update shared memory */ + SetLastNotifiedSegment(latest_boundary_seg - 1); + + /* remove old boundaries from the map */ + RemoveRecordBoundariesUpTo(latest_boundary_seg); + + PgArchWakeup(); + } + + LWLockRelease(ArchNotifyLock); +} + +/* + * GetLatestRecordBoundarySegment + * + * This function finds the latest record boundary in RecordBoundaryMap that is + * less than or equal to the current "flushed" pointer and returns its + * associated segment number, given that it is greater than the last notified + * segment. Otherwise, InvalidXLogSegNo is returned. + * + * Caller is expected to be holding ArchNotifyLock. + */ +static XLogSegNo +GetLatestRecordBoundarySegment(void) +{ + XLogRecPtr flushed; + XLogSegNo flushed_seg; + XLogSegNo last_notified; + + flushed = GetFlushRecPtr(); + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + last_notified = GetLastNotifiedSegment(); + + for (XLogSegNo i = flushed_seg; i > last_notified; i--) + { + RecordBoundaryEntry *entry; + + entry = (RecordBoundaryEntry *) hash_search(RecordBoundaryMap, + (void *) &i, HASH_FIND, + NULL); + + if (entry != NULL && flushed >= entry->pos) + return entry->seg; + } + + return InvalidXLogSegNo; +} + +/* + * RemoveOldRecordBoundaries + * + * This function removes all entries in the RecordBoundaryMap with segment + * numbers up to an including seg. + * + * Caller is expected to be holding ArchNotifyLock. + */ +static void +RemoveRecordBoundariesUpTo(XLogSegNo seg) +{ + RecordBoundaryEntry *entry; + HASH_SEQ_STATUS status; + + hash_seq_init(&status, RecordBoundaryMap); + + while ((entry = (RecordBoundaryEntry *) hash_seq_search(&status)) != NULL) + { + if (entry->seg <= seg) + (void) hash_search(RecordBoundaryMap, (void *) &entry->seg, + HASH_REMOVE, NULL); + } +} + +/* + * GetLastNotifiedSegment + * + * Retrieves last notified segment from shared memory. + */ +XLogSegNo +GetLastNotifiedSegment(void) +{ + XLogSegNo seg; + + Assert(LWLockHeldByMe(ArchNotifyLock)); + + seg = XLogCtl->lastNotifiedSeg; + + return seg; +} + +/* + * SetLastNotifiedSegment + * + * Sets last notified segment in shared memory. Callers should hold + * ArchNotifyLock exclusively when calling this function. + */ +static void +SetLastNotifiedSegment(XLogSegNo seg) +{ + Assert(LWLockHeldByMeInMode(ArchNotifyLock, LW_EXCLUSIVE)); + + XLogCtl->lastNotifiedSeg = seg; +} + /* * Reserves the right amount of space for a record of given size from the WAL. * *StartPos is set to the beginning of the reserved section, *EndPos to @@ -2607,11 +2850,11 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. If + * lastNotifiedSeg hasn't been initialized yet, we need to do that, + * too. */ if (finishing_seg) { @@ -2623,7 +2866,14 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + { + LWLockAcquire(ArchNotifyLock, LW_EXCLUSIVE); + + if (XLogSegNoIsInvalid(GetLastNotifiedSegment())) + SetLastNotifiedSegment(openLogSegNo - 1); + + LWLockRelease(ArchNotifyLock); + } XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2711,6 +2961,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(); } /* @@ -5140,6 +5393,9 @@ XLOGShmemSize(void) /* and the buffers themselves */ size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers)); + /* stuff for marking segments as ready for archival */ + size = add_size(size, hash_estimate_size(16, sizeof(RecordBoundaryEntry))); + /* * Note: we don't count ControlFileData, it comes out of the "slop factor" * added by CreateSharedMemoryAndSemaphores. This lets us use this @@ -5157,6 +5413,7 @@ XLOGShmemInit(void) char *allocptr; int i; ControlFileData *localControlFile; + HASHCTL info; #ifdef WAL_DEBUG @@ -5250,12 +5507,20 @@ XLOGShmemInit(void) XLogCtl->InstallXLogFileSegmentActive = false; XLogCtl->SharedPromoteIsTriggered = false; XLogCtl->WalWriterSleeping = false; + XLogCtl->lastNotifiedSeg = InvalidXLogSegNo; SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + memset(&info, 0, sizeof(info)); + info.keysize = sizeof(XLogSegNo); + info.entrysize = sizeof(RecordBoundaryEntry); + RecordBoundaryMap = ShmemInitHash("Record Boundary Table", 16, 16, &info, + HASH_ELEM | HASH_BLOBS); } /* @@ -8016,7 +8281,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..e9cac90b4a 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -464,7 +464,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * then when complete, rename it to 0000000100000001000000C6.done */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool notify) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +489,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, notify archiver that it's got something to do */ + if (notify) PgArchWakeup(); } @@ -498,12 +498,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool notify) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, notify); } /* @@ -608,7 +608,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt index 6c7cf6c295..d39225bf94 100644 --- a/src/backend/storage/lmgr/lwlocknames.txt +++ b/src/backend/storage/lmgr/lwlocknames.txt @@ -53,3 +53,4 @@ XactTruncationLock 44 # 45 was XactTruncationLock until removal of BackendRandomLock WrapLimitsVacuumLock 46 NotifyQueueTailLock 47 +ArchNotifyLock 48 diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..e25c3d8117 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool notify); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool notify); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..8d172f887a 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -47,6 +47,9 @@ typedef uint64 XLogRecPtr; */ typedef uint64 XLogSegNo; +#define InvalidXLogSegNo 0xFFFFFFFFFFFFFFFF +#define XLogSegNoIsInvalid(s) ((s) == InvalidXLogSegNo) + /* * TimeLineID (TLI) - identifies different database histories to prevent * confusion after restoring a prior state of a database installation. -- 2.20.1 --mdy6umzbb7bbupyj-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v12] Avoid creating archive status ".ready" files too early @ 2021-08-17 03:52 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Nathan Bossart @ 2021-08-17 03:52 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file is created, and the archiver may process it. If PostgreSQL crashes before it is able to write and flush the rest of the record (in the next WAL segment), the wrong version of the first segment file lingers in the archive, which causes operations such as point-in-time restores to fail. To fix this, keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. XXX Note that this may add a new LWLock acquisition in the transaction commit path. (It doesn't happen in all cases.) Author: Nathan Bossart <[email protected]> Reviewed-by: Kyotaro Horiguchi <[email protected]> Reviewed-by: Ryo Matsumura <[email protected]> Reviewed-by: Andrey Borodin <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 307 ++++++++++++++++++++++- src/backend/access/transam/xlogarchive.c | 17 +- src/backend/postmaster/walwriter.c | 7 + src/backend/replication/walreceiver.c | 6 +- src/backend/storage/lmgr/lwlocknames.txt | 1 + src/include/access/xlog.h | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 1 + src/tools/pgindent/typedefs.list | 1 + 10 files changed, 323 insertions(+), 24 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index e51a7a749d..01da4ab7b8 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -512,6 +512,16 @@ typedef enum ExclusiveBackupState */ static SessionBackupState sessionBackupState = SESSION_BACKUP_NONE; +/* + * Entries for SegmentBoundaryMap. Each such entry represents a WAL + * record that ends in endpos and crosses the WAL segment boundary. + */ +typedef struct SegmentBoundaryEntry +{ + XLogSegNo seg; /* must be first */ + XLogRecPtr endpos; +} SegmentBoundaryEntry; + /* * Shared state data for WAL insertion. */ @@ -723,6 +733,12 @@ typedef struct XLogCtlData */ XLogRecPtr lastFpwDisableRecPtr; + /* + * The last segment we've marked ready for archival. Protected by + * info_lck. + */ + XLogSegNo lastNotifiedSeg; + slock_t info_lck; /* locks shared variables shown above */ } XLogCtlData; @@ -736,6 +752,23 @@ static WALInsertLockPadded *WALInsertLocks = NULL; */ static ControlFileData *ControlFile = NULL; +/* + * Segment boundary map. + * + * This hash table tracks WAL records that cross WAL segment boundaries. + * For WAL archiving it is critical not to mark a segment as archivable + * until both halves of the record are flushed: otherwise if we crash + * after archiving the segment containing the first half and before + * flushing the second half of the record, then after recovery the + * primary would overwrite the first half with new data, making the + * segment archived prior to the crash a bogus copy. + * + * XXX note that an equivalent problem exists with streaming replication. + * + * Protected by SegmentBoundaryLock. + */ +static HTAB *SegmentBoundaryMap = NULL; + /* * Calculate the amount of space left on the page after 'endptr'. Beware * multiple evaluation! @@ -920,6 +953,13 @@ static void RemoveXlogFile(const char *segname, XLogSegNo recycleSegNo, XLogSegNo *endlogSegNo); static void UpdateLastRemovedPtr(char *filename); static void ValidateXLOGDirectoryStructure(void); +static void RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos); +static XLogSegNo GetLastNotifiedSegment(void); +static void SetLastNotifiedSegment(XLogSegNo seg); +static bool GetLatestSegmentBoundary(XLogSegNo last_notified, + XLogRecPtr flushed, + XLogSegNo *latest_boundary_seg); +static void RemoveSegmentBoundariesUpTo(XLogSegNo seg); static void CleanupBackupHistory(void); static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force); static XLogRecord *ReadRecord(XLogReaderState *xlogreader, @@ -1154,23 +1194,56 @@ XLogInsertRecord(XLogRecData *rdata, END_CRIT_SECTION(); /* - * Update shared LogwrtRqst.Write, if we crossed page boundary. + * If we crossed page boundary, update LogwrtRqst.Write; if we crossed + * segment boundary, register that and wake up walwriter. */ if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ) { + XLogSegNo StartSeg; + XLogSegNo EndSeg; + + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + /* + * Register our crossing the segment boundary if that occurred. + * + * Note that we did not use XLByteToPrevSeg() for determining the + * ending segment. This is so that a record that fits perfectly into + * the end of the segment is marked ready for archival as soon as the + * flushed pointer jumps to the next segment. + */ + if (StartSeg != EndSeg && XLogArchivingActive()) + RegisterSegmentBoundary(EndSeg, EndPos); + + /* + * Advance LogwrtRqst.Write so that it includes new block(s). + * + * We do this after registering the segment boundary so that the + * comparison with the flushed pointer below can use the latest value + * known globally. + */ SpinLockAcquire(&XLogCtl->info_lck); - /* advance global request to include new block(s) */ if (XLogCtl->LogwrtRqst.Write < EndPos) XLogCtl->LogwrtRqst.Write = EndPos; /* update local result copy while I have the chance */ LogwrtResult = XLogCtl->LogwrtResult; SpinLockRelease(&XLogCtl->info_lck); + + /* + * There's a chance that the record was already flushed to disk and we + * missed marking segments as ready for archive. If this happens, we + * nudge the WALWriter, which will take care of notifying segments as + * needed. + */ + if (StartSeg != EndSeg && XLogArchivingActive() && + LogwrtResult.Flush >= EndPos && ProcGlobal->walwriterLatch) + SetLatch(ProcGlobal->walwriterLatch); } /* * If this was an XLOG_SWITCH record, flush the record and the empty - * padding space that fills the rest of the segment, and perform - * end-of-segment actions (eg, notifying archiver). + * padding space that fills the rest of the segment. */ if (isLogSwitch) { @@ -2421,6 +2494,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) /* We should always be inside a critical section here */ Assert(CritSectionCount > 0); + Assert(LWLockHeldByMe(WALWriteLock)); /* * Update local LogwrtResult (caller probably did this already, but...) @@ -2586,11 +2660,13 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * If WAL archiving is active, we attempt to notify the archiver + * of any segments that are now ready for archival. + * + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. + * */ if (finishing_seg) { @@ -2602,7 +2678,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + NotifySegmentsReadyForArchive(LogwrtResult.Flush); XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2690,6 +2766,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(LogwrtResult.Flush); } /* @@ -4328,6 +4407,189 @@ ValidateXLOGDirectoryStructure(void) } } +/* + * RegisterSegmentBoundary + * Enter a new entry into the segment boundary map. + * + * An entry with the given key (the segment number) must not already exist in + * the map. + */ +static void +RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos) +{ + SegmentBoundaryEntry *entry; + XLogSegNo segno PG_USED_FOR_ASSERTS_ONLY; + bool found; + + /* verify caller computed segment number correctly */ + AssertArg((XLByteToSeg(pos, segno, wal_segment_size), segno == seg)); + + LWLockAcquire(SegmentBoundaryLock, LW_EXCLUSIVE); + + entry = (SegmentBoundaryEntry *) hash_search(SegmentBoundaryMap, + (void *) &seg, HASH_ENTER, + &found); + if (found) + elog(ERROR, "entry for segment already exists"); + + entry->endpos = pos; + + LWLockRelease(SegmentBoundaryLock); +} + +/* + * GetLatestSegmentBoundary + * + * Find the latest segment boundary in SegmentBoundaryMap that is less + * than or equal to the given "flushed" pointer and beyond the last + * notified segment. If such a segment is found, latest_boundary_seg + * is populated and true is returned. Otherwise, false is returned. + */ +static bool +GetLatestSegmentBoundary(XLogSegNo last_notified, XLogRecPtr flushed, + XLogSegNo *latest_boundary_seg) +{ + XLogSegNo flushed_seg; + XLogSegNo seg; + + Assert(LWLockHeldByMe(SegmentBoundaryLock)); + Assert(latest_boundary_seg != NULL); + + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + + for (seg = flushed_seg; seg > last_notified; seg--) + { + SegmentBoundaryEntry *entry; + + entry = (SegmentBoundaryEntry *) hash_search(SegmentBoundaryMap, + (void *) &seg, HASH_FIND, + NULL); + + if (entry != NULL && flushed >= entry->endpos) + { + *latest_boundary_seg = entry->seg; + return true; + } + } + + return false; +} + +/* + * RemoveSegmentBoundariesUpTo + * + * Remove all entries in the SegmentBoundaryMap with segment numbers + * up to and including seg. + */ +static void +RemoveSegmentBoundariesUpTo(XLogSegNo seg) +{ + SegmentBoundaryEntry *entry; + HASH_SEQ_STATUS status; + + Assert(LWLockHeldByMeInMode(SegmentBoundaryLock, LW_EXCLUSIVE)); + + hash_seq_init(&status, SegmentBoundaryMap); + + while ((entry = (SegmentBoundaryEntry *) hash_seq_search(&status)) != NULL) + { + if (entry->seg <= seg) + (void) hash_search(SegmentBoundaryMap, (void *) &entry->seg, + HASH_REMOVE, NULL); + } +} + +/* + * NotifySegmentsReadyForArchive + * + * Mark segments as ready for archival, given that it is safe to do so. + * This function is idempotent. + */ +void +NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr) +{ + XLogSegNo flushed_seg; + XLogSegNo latest_boundary_seg; + XLogSegNo last_notified; + + /* + * We first do a quick sanity check to see if we can bail out without + * taking the SegmentBoundaryLock at all. It is expected that this + * function will run frequently and that it will need to do nothing the + * vast majority of the time. + * + * Specifically, we bail out if we've already marked the segment prior to + * the segment that contains flushRecPtr as ready for archival. We + * intentionally use XLByteToSeg() instead of XLByteToPrevSeg() so that we + * don't skip notifying when a record fits perfectly into the end of a + * segment. (flushRecPtr should point to the first byte of the record + * _after_ the one that is known to be flushed to disk.) + */ + last_notified = GetLastNotifiedSegment(); + XLByteToSeg(flushRecPtr, flushed_seg, wal_segment_size); + if (last_notified >= flushed_seg - 1) + return; + + LWLockAcquire(SegmentBoundaryLock, LW_EXCLUSIVE); + + /* Reobtain lastNotifiedSeg in case someone else changed it. */ + last_notified = GetLastNotifiedSegment(); + + /* Retrieve the latest segment boundary to use for notifying segments. */ + if (GetLatestSegmentBoundary(last_notified, flushRecPtr, &latest_boundary_seg)) + { + /* + * Update shared memory and discard segment boundaries that are no + * longer needed. + * + * It is safe to update shared memory before we attempt to create the + * .ready files. If our calls to XLogArchiveNotifySeg() fail, + * RemoveOldXlogFiles() will retry it as needed. + */ + SetLastNotifiedSegment(latest_boundary_seg - 1); + RemoveSegmentBoundariesUpTo(latest_boundary_seg); + + LWLockRelease(SegmentBoundaryLock); + + /* + * Notify archiver about segments that are ready for archival (by + * creating the corresponding .ready files). + */ + for (XLogSegNo seg = last_notified + 1; seg < latest_boundary_seg; seg++) + XLogArchiveNotifySeg(seg, false); + + PgArchWakeup(); + } + else + LWLockRelease(SegmentBoundaryLock); +} + +/* + * GetLastNotifiedSegment + */ +XLogSegNo +GetLastNotifiedSegment(void) +{ + XLogSegNo seg; + + SpinLockAcquire(&XLogCtl->info_lck); + seg = XLogCtl->lastNotifiedSeg; + SpinLockRelease(&XLogCtl->info_lck); + + return seg; +} + +/* + * SetLastNotifiedSegment + */ +static void +SetLastNotifiedSegment(XLogSegNo seg) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->lastNotifiedSeg = seg; + SpinLockRelease(&XLogCtl->info_lck); +} + /* * Remove previous backup history files. This also retries creation of * .ready files for any backup history files for which XLogArchiveNotify @@ -5117,6 +5379,9 @@ XLOGShmemSize(void) /* and the buffers themselves */ size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers)); + /* hash table of segment-crossing WAL records */ + size = add_size(size, hash_estimate_size(16, sizeof(SegmentBoundaryEntry))); + /* * Note: we don't count ControlFileData, it comes out of the "slop factor" * added by CreateSharedMemoryAndSemaphores. This lets us use this @@ -5134,6 +5399,7 @@ XLOGShmemInit(void) char *allocptr; int i; ControlFileData *localControlFile; + HASHCTL info; #ifdef WAL_DEBUG @@ -5227,12 +5493,20 @@ XLOGShmemInit(void) XLogCtl->InstallXLogFileSegmentActive = false; XLogCtl->SharedPromoteIsTriggered = false; XLogCtl->WalWriterSleeping = false; + XLogCtl->lastNotifiedSeg = MaxXLogSegNo; SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + memset(&info, 0, sizeof(info)); + info.keysize = sizeof(XLogSegNo); + info.entrysize = sizeof(SegmentBoundaryEntry); + SegmentBoundaryMap = ShmemInitHash("Segment Boundary Table", 16, 16, &info, + HASH_ELEM | HASH_BLOBS); } /* @@ -7873,6 +8147,17 @@ StartupXLOG(void) XLogCtl->LogwrtRqst.Write = EndOfLog; XLogCtl->LogwrtRqst.Flush = EndOfLog; + /* + * Initialize XLogCtl->lastNotifiedSeg to the previous WAL file. + */ + if (XLogArchivingActive()) + { + XLogSegNo EndOfLogSeg; + + XLByteToSeg(EndOfLog, EndOfLogSeg, wal_segment_size); + SetLastNotifiedSegment(EndOfLogSeg - 1); + } + /* * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE * record before resource manager writes cleanup WAL records or checkpoint @@ -8000,7 +8285,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..b9c19b2085 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -462,9 +462,12 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * by the archiver, e.g. we write 0000000100000001000000C6.ready * and the archiver then knows to archive XLOGDIR/0000000100000001000000C6, * then when complete, rename it to 0000000100000001000000C6.done + * + * Optionally, nudge the archiver process so that it'll notice the file we + * create. */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool nudge) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +492,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, let archiver know it's got work to do */ + if (nudge) PgArchWakeup(); } @@ -498,12 +501,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool nudge) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, nudge); } /* @@ -608,7 +611,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c index 626fae8454..6a1e16edc2 100644 --- a/src/backend/postmaster/walwriter.c +++ b/src/backend/postmaster/walwriter.c @@ -248,6 +248,13 @@ WalWriterMain(void) /* Process any signals received recently */ HandleWalWriterInterrupts(); + /* + * Notify the archiver of any WAL segments that are ready. We do this + * here to handle a race condition where WAL is flushed to disk prior + * to registering the segment boundary. + */ + NotifySegmentsReadyForArchive(GetFlushRecPtr()); + /* * Do what we're here for; then, if XLogBackgroundFlush() found useful * work to do, reset hibernation counter. diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt index 6c7cf6c295..14a742d655 100644 --- a/src/backend/storage/lmgr/lwlocknames.txt +++ b/src/backend/storage/lmgr/lwlocknames.txt @@ -53,3 +53,4 @@ XactTruncationLock 44 # 45 was XactTruncationLock until removal of BackendRandomLock WrapLimitsVacuumLock 46 NotifyQueueTailLock 47 +SegmentBoundaryLock 48 diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 0a8ede700d..6b6ae81c2d 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -315,6 +315,7 @@ extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); extern void RemovePromoteSignalFiles(void); +extern void NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr); extern bool PromoteIsTriggered(void); extern bool CheckPromoteSignal(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..935b4cb02d 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool nudge); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool nudge); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..9b455e88e3 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -46,6 +46,7 @@ typedef uint64 XLogRecPtr; * XLogSegNo - physical log file sequence number. */ typedef uint64 XLogSegNo; +#define MaxXLogSegNo ((XLogSegNo) 0xFFFFFFFFFFFFFFFF) /* * TimeLineID (TLI) - identifies different database histories to prevent diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 37cf4b2f76..79694b049e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2334,6 +2334,7 @@ SecBufferDesc SecLabelItem SecLabelStmt SeenRelsEntry +SegmentBoundaryEntry SelectLimit SelectStmt Selectivity -- 2.20.1 --ngwxbmustuw56o2o-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v10] Avoid creating archive status ".ready" files too early. @ 2021-08-17 03:52 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Nathan Bossart @ 2021-08-17 03:52 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file will be created. If PostgreSQL crashes before it is able to write the rest of the record, it will end up reusing segments that have already been marked as ready-for-archival. However, the archiver process may have already processed the old version of the segment, so the wrong version of the segment may be backed-up. This backed-up segment will cause operations such as point-in-time restores to fail. To fix this, we keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 291 ++++++++++++++++++++++- src/backend/access/transam/xlogarchive.c | 17 +- src/backend/postmaster/walwriter.c | 7 + src/backend/replication/walreceiver.c | 6 +- src/backend/storage/lmgr/lwlocknames.txt | 1 + src/include/access/xlog.h | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 1 + src/tools/pgindent/typedefs.list | 1 + 10 files changed, 309 insertions(+), 22 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index e51a7a749d..d2ccf2a7bb 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -512,6 +512,16 @@ typedef enum ExclusiveBackupState */ static SessionBackupState sessionBackupState = SESSION_BACKUP_NONE; +/* + * Entries for SegmentBoundaryMap. Each such entry represents a WAL + * record that ends in endpos and crosses a WAL segment boundary. + */ +typedef struct SegmentBoundaryEntry +{ + XLogSegNo seg; /* must be first */ + XLogRecPtr endpos; +} SegmentBoundaryEntry; + /* * Shared state data for WAL insertion. */ @@ -723,6 +733,12 @@ typedef struct XLogCtlData */ XLogRecPtr lastFpwDisableRecPtr; + /* + * The last segment we've marked ready for archival. Protected by + * info_lck. + */ + XLogSegNo lastNotifiedSeg; + slock_t info_lck; /* locks shared variables shown above */ } XLogCtlData; @@ -736,6 +752,12 @@ static WALInsertLockPadded *WALInsertLocks = NULL; */ static ControlFileData *ControlFile = NULL; +/* + * Segment boundary map, used for marking segments as ready for archival. + * Protected by SegmentBoundaryLock. + */ +static HTAB *SegmentBoundaryMap = NULL; + /* * Calculate the amount of space left on the page after 'endptr'. Beware * multiple evaluation! @@ -962,6 +984,13 @@ static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos); static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos); static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr); static void checkXLogConsistency(XLogReaderState *record); +static void RegisterSegmentBoundaryEntry(XLogSegNo seg, XLogRecPtr pos); +static XLogSegNo GetLastNotifiedSegment(void); +static void SetLastNotifiedSegment(XLogSegNo seg); +static bool GetLatestSegmentBoundary(XLogSegNo last_notified, + XLogRecPtr flushed, + XLogSegNo *latest_boundary_seg); +static void RemoveSegmentBoundariesUpTo(XLogSegNo seg); static void WALInsertLockAcquire(void); static void WALInsertLockAcquireExclusive(void); @@ -1158,6 +1187,9 @@ XLogInsertRecord(XLogRecData *rdata, */ if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ) { + XLogSegNo StartSeg; + XLogSegNo EndSeg; + SpinLockAcquire(&XLogCtl->info_lck); /* advance global request to include new block(s) */ if (XLogCtl->LogwrtRqst.Write < EndPos) @@ -1165,12 +1197,38 @@ XLogInsertRecord(XLogRecData *rdata, /* update local result copy while I have the chance */ LogwrtResult = XLogCtl->LogwrtResult; SpinLockRelease(&XLogCtl->info_lck); + + /* + * If we crossed the segment boundary, record it. This is used to + * ensure that segments are not marked ready for archival before the + * entire record has been flushed to disk. + * + * Note that we do not use XLByteToPrevSeg() for determining the + * ending segment. This is done so that a record that fits perfectly + * into the end of the segment is marked ready for archival as soon as + * the flushed pointer jumps to the next segment. + */ + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + if (StartSeg != EndSeg && XLogArchivingActive()) + { + RegisterSegmentBoundaryEntry(EndSeg, EndPos); + + /* + * There's a chance that the record was already flushed to disk + * and we missed marking segments as ready for archive. If this + * happens, we nudge the WALWriter, which will take care of + * notifying segments as needed. + */ + if (LogwrtResult.Flush > EndPos && ProcGlobal->walwriterLatch) + SetLatch(ProcGlobal->walwriterLatch); + } } /* * If this was an XLOG_SWITCH record, flush the record and the empty - * padding space that fills the rest of the segment, and perform - * end-of-segment actions (eg, notifying archiver). + * padding space that fills the rest of the segment. */ if (isLogSwitch) { @@ -1264,6 +1322,192 @@ XLogInsertRecord(XLogRecData *rdata, return EndPos; } +/* + * RegisterSegmentBoundaryEntry + * + * This enters a new entry into the segment boundary map, which is used for + * determing when it is safe to mark a segment as ready for archival. An entry + * with the given key (the segment number) must not already exist in the map. + * Also, the caller is responsible for ensuring that XLByteToSeg() would return + * the same segment number for the given record pointer. + */ +static void +RegisterSegmentBoundaryEntry(XLogSegNo seg, XLogRecPtr pos) +{ + SegmentBoundaryEntry *entry; + bool found; + + LWLockAcquire(SegmentBoundaryLock, LW_EXCLUSIVE); + + entry = (SegmentBoundaryEntry *) hash_search(SegmentBoundaryMap, + (void *) &seg, HASH_ENTER, + &found); + if (found) + elog(ERROR, "entry for segment already exists"); + + entry->endpos = pos; + + LWLockRelease(SegmentBoundaryLock); +} + +/* + * NotifySegmentsReadyForArchive + * + * This function marks segments as ready for archival, given that it is safe to + * do so. It is safe to call this function repeatedly, even if nothing has + * changed since the last time it was called. + */ +void +NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr) +{ + XLogSegNo flushed_seg; + XLogSegNo latest_boundary_seg; + XLogSegNo last_notified; + + /* + * We first do a quick sanity check to see if we can bail out without + * taking the SegmentBoundaryLock at all. It is expected that this + * function will run frequently and that it will need to do nothing the + * vast majority of the time. + * + * Specifically, we bail out if we've already marked the segment prior to + * the segment that contains flushRecPtr as ready for archival. We + * intentionally use XLByteToSeg() instead of XLByteToPrevSeg() so that we + * don't skip notifying when a record fits perfectly into the end of a + * segment. (flushRecPtr should point to the first byte of the record + * _after_ the one that is known to be flushed to disk.) + */ + last_notified = GetLastNotifiedSegment(); + XLByteToSeg(flushRecPtr, flushed_seg, wal_segment_size); + if (last_notified >= flushed_seg - 1) + return; + + LWLockAcquire(SegmentBoundaryLock, LW_EXCLUSIVE); + + /* Reobtain lastNotifiedSeg in case someone else changed it. */ + last_notified = GetLastNotifiedSegment(); + + /* Retrieve the latest segment boundary to use for notifying segments. */ + if (GetLatestSegmentBoundary(last_notified, flushRecPtr, &latest_boundary_seg)) + { + /* + * Update shared memory and discard segment boundaries that are no + * longer needed. + * + * It is safe to update shared memory before we attempt to create the + * .ready files. If our calls to XLogArchiveNotifySeg() fail, + * RemoveOldXlogFiles() will retry it as needed. + */ + SetLastNotifiedSegment(latest_boundary_seg - 1); + RemoveSegmentBoundariesUpTo(latest_boundary_seg); + + LWLockRelease(SegmentBoundaryLock); + + /* + * Notify archiver about segments that are ready for archival (by + * creating the corresponding .ready files). + */ + for (XLogSegNo seg = last_notified + 1; seg < latest_boundary_seg; seg++) + XLogArchiveNotifySeg(seg, false); + + PgArchWakeup(); + } + else + LWLockRelease(SegmentBoundaryLock); +} + +/* + * GetLatestSegmentBoundary + * + * This function finds the latest segment boundary in SegmentBoundaryMap that is + * less than or equal to the given "flushed" pointer and beyond the last + * notified segment. If such a segment is found, latest_boundary_seg is + * populated and true is returned. Otherwise, false is returned. + */ +static bool +GetLatestSegmentBoundary(XLogSegNo last_notified, XLogRecPtr flushed, + XLogSegNo *latest_boundary_seg) +{ + XLogSegNo flushed_seg; + XLogSegNo seg; + + Assert(LWLockHeldByMe(SegmentBoundaryLock)); + Assert(latest_boundary_seg != NULL); + + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + + for (seg = flushed_seg; seg > last_notified; seg--) + { + SegmentBoundaryEntry *entry; + + entry = (SegmentBoundaryEntry *) hash_search(SegmentBoundaryMap, + (void *) &seg, HASH_FIND, + NULL); + + if (entry != NULL && flushed >= entry->endpos) + { + *latest_boundary_seg = entry->seg; + return true; + } + } + + return false; +} + +/* + * RemoveSegmentBoundariesUpTo + * + * This function removes all entries in the SegmentBoundaryMap with segment + * numbers up to and including seg. + */ +static void +RemoveSegmentBoundariesUpTo(XLogSegNo seg) +{ + SegmentBoundaryEntry *entry; + HASH_SEQ_STATUS status; + + Assert(LWLockHeldByMeInMode(SegmentBoundaryLock, LW_EXCLUSIVE)); + + hash_seq_init(&status, SegmentBoundaryMap); + + while ((entry = (SegmentBoundaryEntry *) hash_seq_search(&status)) != NULL) + { + if (entry->seg <= seg) + (void) hash_search(SegmentBoundaryMap, (void *) &entry->seg, + HASH_REMOVE, NULL); + } +} + +/* + * GetLastNotifiedSegment + * + * Retrieves last notified segment from shared memory. + */ +XLogSegNo +GetLastNotifiedSegment(void) +{ + XLogSegNo seg; + + SpinLockAcquire(&XLogCtl->info_lck); + seg = XLogCtl->lastNotifiedSeg; + SpinLockRelease(&XLogCtl->info_lck); + + return seg; +} + +/* + * SetLastNotifiedSegment + * + * Sets last notified segment in shared memory. + */ +static void +SetLastNotifiedSegment(XLogSegNo seg) +{ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->lastNotifiedSeg = seg; + SpinLockRelease(&XLogCtl->info_lck); +} + /* * Reserves the right amount of space for a record of given size from the WAL. * *StartPos is set to the beginning of the reserved section, *EndPos to @@ -2421,6 +2665,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) /* We should always be inside a critical section here */ Assert(CritSectionCount > 0); + Assert(LWLockHeldByMe(WALWriteLock)); /* * Update local LogwrtResult (caller probably did this already, but...) @@ -2586,11 +2831,13 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * If WAL archiving is active, we attempt to notify the archiver + * of any segments that are now ready for archival. + * + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. + * */ if (finishing_seg) { @@ -2602,7 +2849,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + NotifySegmentsReadyForArchive(LogwrtResult.Flush); XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2690,6 +2937,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(LogwrtResult.Flush); } /* @@ -5117,6 +5367,9 @@ XLOGShmemSize(void) /* and the buffers themselves */ size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers)); + /* stuff for marking segments as ready for archival */ + size = add_size(size, hash_estimate_size(16, sizeof(SegmentBoundaryEntry))); + /* * Note: we don't count ControlFileData, it comes out of the "slop factor" * added by CreateSharedMemoryAndSemaphores. This lets us use this @@ -5134,6 +5387,7 @@ XLOGShmemInit(void) char *allocptr; int i; ControlFileData *localControlFile; + HASHCTL info; #ifdef WAL_DEBUG @@ -5227,12 +5481,20 @@ XLOGShmemInit(void) XLogCtl->InstallXLogFileSegmentActive = false; XLogCtl->SharedPromoteIsTriggered = false; XLogCtl->WalWriterSleeping = false; + XLogCtl->lastNotifiedSeg = MaxXLogSegNo; SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + memset(&info, 0, sizeof(info)); + info.keysize = sizeof(XLogSegNo); + info.entrysize = sizeof(SegmentBoundaryEntry); + SegmentBoundaryMap = ShmemInitHash("Segment Boundary Table", 16, 16, &info, + HASH_ELEM | HASH_BLOBS); } /* @@ -7873,6 +8135,17 @@ StartupXLOG(void) XLogCtl->LogwrtRqst.Write = EndOfLog; XLogCtl->LogwrtRqst.Flush = EndOfLog; + /* + * Initialize XLogCtl->lastNotifiedSeg to the previous WAL file. + */ + if (XLogArchivingActive()) + { + XLogSegNo EndOfLogSeg; + + XLByteToSeg(EndOfLog, EndOfLogSeg, wal_segment_size); + SetLastNotifiedSegment(EndOfLogSeg - 1); + } + /* * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE * record before resource manager writes cleanup WAL records or checkpoint @@ -8000,7 +8273,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..b9c19b2085 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -462,9 +462,12 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * by the archiver, e.g. we write 0000000100000001000000C6.ready * and the archiver then knows to archive XLOGDIR/0000000100000001000000C6, * then when complete, rename it to 0000000100000001000000C6.done + * + * Optionally, nudge the archiver process so that it'll notice the file we + * create. */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool nudge) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +492,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, let archiver know it's got work to do */ + if (nudge) PgArchWakeup(); } @@ -498,12 +501,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool nudge) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, nudge); } /* @@ -608,7 +611,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c index 626fae8454..6a1e16edc2 100644 --- a/src/backend/postmaster/walwriter.c +++ b/src/backend/postmaster/walwriter.c @@ -248,6 +248,13 @@ WalWriterMain(void) /* Process any signals received recently */ HandleWalWriterInterrupts(); + /* + * Notify the archiver of any WAL segments that are ready. We do this + * here to handle a race condition where WAL is flushed to disk prior + * to registering the segment boundary. + */ + NotifySegmentsReadyForArchive(GetFlushRecPtr()); + /* * Do what we're here for; then, if XLogBackgroundFlush() found useful * work to do, reset hibernation counter. diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt index 6c7cf6c295..14a742d655 100644 --- a/src/backend/storage/lmgr/lwlocknames.txt +++ b/src/backend/storage/lmgr/lwlocknames.txt @@ -53,3 +53,4 @@ XactTruncationLock 44 # 45 was XactTruncationLock until removal of BackendRandomLock WrapLimitsVacuumLock 46 NotifyQueueTailLock 47 +SegmentBoundaryLock 48 diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 0a8ede700d..6b6ae81c2d 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -315,6 +315,7 @@ extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); extern void RemovePromoteSignalFiles(void); +extern void NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr); extern bool PromoteIsTriggered(void); extern bool CheckPromoteSignal(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..935b4cb02d 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool nudge); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool nudge); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..9b455e88e3 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -46,6 +46,7 @@ typedef uint64 XLogRecPtr; * XLogSegNo - physical log file sequence number. */ typedef uint64 XLogSegNo; +#define MaxXLogSegNo ((XLogSegNo) 0xFFFFFFFFFFFFFFFF) /* * TimeLineID (TLI) - identifies different database histories to prevent diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 37cf4b2f76..79694b049e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2334,6 +2334,7 @@ SecBufferDesc SecLabelItem SecLabelStmt SeenRelsEntry +SegmentBoundaryEntry SelectLimit SelectStmt Selectivity -- 2.30.2 --aabamu5eazcf6rc5-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v14] Avoid creating archive status ".ready" files too early @ 2021-08-20 19:25 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Nathan Bossart @ 2021-08-20 19:25 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file is created, and the archiver may process it. If PostgreSQL crashes before it is able to write and flush the rest of the record (in the next WAL segment), the wrong version of the first segment file lingers in the archive, which causes operations such as point-in-time restores to fail. To fix this, keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. Author: Nathan Bossart <[email protected]> Reviewed-by: Kyotaro Horiguchi <[email protected]> Reviewed-by: Ryo Matsumura <[email protected]> Reviewed-by: Andrey Borodin <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 242 +++++++++++++++++++++-- src/backend/access/transam/xlogarchive.c | 17 +- src/backend/postmaster/walwriter.c | 7 + src/backend/replication/walreceiver.c | 6 +- src/include/access/xlog.h | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 1 + 8 files changed, 256 insertions(+), 24 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index e51a7a749d..95f03adef8 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -724,6 +724,18 @@ typedef struct XLogCtlData XLogRecPtr lastFpwDisableRecPtr; slock_t info_lck; /* locks shared variables shown above */ + + /* + * Variables used to track cross-segment records. Protected by + * segtrack_lck. + */ + XLogSegNo lastNotifiedSeg; + XLogSegNo earliestSegBoundary; + XLogRecPtr earliestSegBoundaryRecPtr; + XLogSegNo latestSegBoundary; + XLogRecPtr latestSegBoundaryRecPtr; + + slock_t segtrack_lck; /* locks shared variables shown above */ } XLogCtlData; static XLogCtlData *XLogCtl = NULL; @@ -920,6 +932,9 @@ static void RemoveXlogFile(const char *segname, XLogSegNo recycleSegNo, XLogSegNo *endlogSegNo); static void UpdateLastRemovedPtr(char *filename); static void ValidateXLOGDirectoryStructure(void); +static void RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos); +static bool GetLatestSegmentBoundary(XLogRecPtr flushed, XLogSegNo *latest_boundary_seg); +static void RemoveSegmentBoundariesUpTo(XLogSegNo seg); static void CleanupBackupHistory(void); static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force); static XLogRecord *ReadRecord(XLogReaderState *xlogreader, @@ -1154,23 +1169,56 @@ XLogInsertRecord(XLogRecData *rdata, END_CRIT_SECTION(); /* - * Update shared LogwrtRqst.Write, if we crossed page boundary. + * If we crossed page boundary, update LogwrtRqst.Write; if we crossed + * segment boundary, register that and wake up walwriter. */ if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ) { + XLogSegNo StartSeg; + XLogSegNo EndSeg; + + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + /* + * Register our crossing the segment boundary if that occurred. + * + * Note that we did not use XLByteToPrevSeg() for determining the + * ending segment. This is so that a record that fits perfectly into + * the end of the segment is marked ready for archival as soon as the + * flushed pointer jumps to the next segment. + */ + if (StartSeg != EndSeg && XLogArchivingActive()) + RegisterSegmentBoundary(EndSeg, EndPos); + + /* + * Advance LogwrtRqst.Write so that it includes new block(s). + * + * We do this after registering the segment boundary so that the + * comparison with the flushed pointer below can use the latest value + * known globally. + */ SpinLockAcquire(&XLogCtl->info_lck); - /* advance global request to include new block(s) */ if (XLogCtl->LogwrtRqst.Write < EndPos) XLogCtl->LogwrtRqst.Write = EndPos; /* update local result copy while I have the chance */ LogwrtResult = XLogCtl->LogwrtResult; SpinLockRelease(&XLogCtl->info_lck); + + /* + * There's a chance that the record was already flushed to disk and we + * missed marking segments as ready for archive. If this happens, we + * nudge the WALWriter, which will take care of notifying segments as + * needed. + */ + if (StartSeg != EndSeg && XLogArchivingActive() && + LogwrtResult.Flush >= EndPos && ProcGlobal->walwriterLatch) + SetLatch(ProcGlobal->walwriterLatch); } /* * If this was an XLOG_SWITCH record, flush the record and the empty - * padding space that fills the rest of the segment, and perform - * end-of-segment actions (eg, notifying archiver). + * padding space that fills the rest of the segment. */ if (isLogSwitch) { @@ -2421,6 +2469,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) /* We should always be inside a critical section here */ Assert(CritSectionCount > 0); + Assert(LWLockHeldByMe(WALWriteLock)); /* * Update local LogwrtResult (caller probably did this already, but...) @@ -2586,11 +2635,12 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * If WAL archiving is active, we attempt to notify the archiver + * of any segments that are now ready for archival. + * + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. */ if (finishing_seg) { @@ -2602,7 +2652,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + NotifySegmentsReadyForArchive(LogwrtResult.Flush); XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2690,6 +2740,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(LogwrtResult.Flush); } /* @@ -4328,6 +4381,151 @@ ValidateXLOGDirectoryStructure(void) } } +/* + * RegisterSegmentBoundary + * Record a new segment boundary if needed. + */ +static void +RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos) +{ + XLogSegNo segno PG_USED_FOR_ASSERTS_ONLY; + + /* verify caller computed segment number correctly */ + AssertArg((XLByteToSeg(pos, segno, wal_segment_size), segno == seg)); + + SpinLockAcquire(&XLogCtl->segtrack_lck); + + /* + * If no segment boundaries are registered, store the new segment boundary + * in earliestSegBoundary. Otherwise, store the greater segment boundaries in + * latestSegBoundary. + */ + if (XLogCtl->earliestSegBoundary == MaxXLogSegNo) + { + XLogCtl->earliestSegBoundary = seg; + XLogCtl->earliestSegBoundaryRecPtr = pos; + } + else if (seg > XLogCtl->earliestSegBoundary && + (XLogCtl->latestSegBoundary == MaxXLogSegNo || + seg > XLogCtl->latestSegBoundary)) + { + XLogCtl->latestSegBoundary = seg; + XLogCtl->latestSegBoundaryRecPtr = pos; + } + + SpinLockRelease(&XLogCtl->segtrack_lck); +} + +/* + * GetLatestSegmentBoundary + * + * Look up the latest segment boundary that is less than or equal to the + * given "flushed" pointer. If such a segment is found, + * latest_boundary_seg is populated and true is returned. Otherwise, false + * is returned. + * + * Callers should hold XLogCtl->segtrack_lck when calling this function. + */ +static bool +GetLatestSegmentBoundary(XLogRecPtr flushed, XLogSegNo *latest_boundary_seg) +{ + XLogSegNo flushed_seg; + + Assert(latest_boundary_seg != NULL); + + XLByteToSeg(flushed, flushed_seg, wal_segment_size); + + if (XLogCtl->latestSegBoundary <= flushed_seg && + XLogCtl->latestSegBoundaryRecPtr <= flushed) + { + *latest_boundary_seg = XLogCtl->latestSegBoundary; + return true; + } + + if (XLogCtl->earliestSegBoundary <= flushed_seg && + XLogCtl->earliestSegBoundaryRecPtr <= flushed) + { + *latest_boundary_seg = XLogCtl->earliestSegBoundary; + return true; + } + + return false; +} + +/* + * RemoveSegmentBoundariesUpTo + * + * Remove all segment boundaries with segment numbers up to and including + * seg. + * + * Callers should hold XLogCtl->segtrack_lck when calling this function. + */ +static void +RemoveSegmentBoundariesUpTo(XLogSegNo seg) +{ + if (XLogCtl->latestSegBoundary <= seg) + { + XLogCtl->earliestSegBoundary = MaxXLogSegNo; + XLogCtl->earliestSegBoundaryRecPtr = InvalidXLogRecPtr; + + XLogCtl->latestSegBoundary = MaxXLogSegNo; + XLogCtl->latestSegBoundaryRecPtr = InvalidXLogRecPtr; + } + else if (XLogCtl->earliestSegBoundary <= seg) + { + XLogCtl->earliestSegBoundary = XLogCtl->latestSegBoundary; + XLogCtl->earliestSegBoundaryRecPtr = XLogCtl->latestSegBoundaryRecPtr; + + XLogCtl->latestSegBoundary = MaxXLogSegNo; + XLogCtl->latestSegBoundaryRecPtr = InvalidXLogRecPtr; + } +} + +/* + * NotifySegmentsReadyForArchive + * + * Mark segments as ready for archival, given that it is safe to do so. + * This function is idempotent. + */ +void +NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr) +{ + XLogSegNo latest_boundary_seg = 0; + + SpinLockAcquire(&XLogCtl->segtrack_lck); + + /* Retrieve the latest segment boundary to use for notifying segments. */ + if (GetLatestSegmentBoundary(flushRecPtr, &latest_boundary_seg)) + { + XLogSegNo last_notified = XLogCtl->lastNotifiedSeg; + + /* + * Update shared memory and discard segment boundaries that are no + * longer needed. + * + * It is safe to update shared memory before we attempt to create the + * .ready files. If our calls to XLogArchiveNotifySeg() fail, + * RemoveOldXlogFiles() will retry it as needed. + */ + if (last_notified < latest_boundary_seg - 1) + XLogCtl->lastNotifiedSeg = latest_boundary_seg - 1; + RemoveSegmentBoundariesUpTo(latest_boundary_seg); + + SpinLockRelease(&XLogCtl->segtrack_lck); + + /* + * Notify archiver about segments that are ready for archival (by + * creating the corresponding .ready files). + */ + for (XLogSegNo seg = last_notified + 1; seg < latest_boundary_seg; seg++) + XLogArchiveNotifySeg(seg, false); + + PgArchWakeup(); + } + else + SpinLockRelease(&XLogCtl->segtrack_lck); +} + /* * Remove previous backup history files. This also retries creation of * .ready files for any backup history files for which XLogArchiveNotify @@ -5230,9 +5428,17 @@ XLOGShmemInit(void) SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); + SpinLockInit(&XLogCtl->segtrack_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + XLogCtl->lastNotifiedSeg = MaxXLogSegNo; + XLogCtl->earliestSegBoundary = MaxXLogSegNo; + XLogCtl->earliestSegBoundaryRecPtr = InvalidXLogRecPtr; + XLogCtl->latestSegBoundary = MaxXLogSegNo; + XLogCtl->latestSegBoundaryRecPtr = InvalidXLogRecPtr; } /* @@ -7873,6 +8079,20 @@ StartupXLOG(void) XLogCtl->LogwrtRqst.Write = EndOfLog; XLogCtl->LogwrtRqst.Flush = EndOfLog; + /* + * Initialize XLogCtl->lastNotifiedSeg to the previous WAL file. + */ + if (XLogArchivingActive()) + { + XLogSegNo EndOfLogSeg; + + XLByteToSeg(EndOfLog, EndOfLogSeg, wal_segment_size); + + SpinLockAcquire(&XLogCtl->segtrack_lck); + XLogCtl->lastNotifiedSeg = EndOfLogSeg - 1; + SpinLockRelease(&XLogCtl->segtrack_lck); + } + /* * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE * record before resource manager writes cleanup WAL records or checkpoint @@ -8000,7 +8220,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..b9c19b2085 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -462,9 +462,12 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * by the archiver, e.g. we write 0000000100000001000000C6.ready * and the archiver then knows to archive XLOGDIR/0000000100000001000000C6, * then when complete, rename it to 0000000100000001000000C6.done + * + * Optionally, nudge the archiver process so that it'll notice the file we + * create. */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool nudge) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +492,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, let archiver know it's got work to do */ + if (nudge) PgArchWakeup(); } @@ -498,12 +501,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool nudge) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, nudge); } /* @@ -608,7 +611,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c index 626fae8454..6a1e16edc2 100644 --- a/src/backend/postmaster/walwriter.c +++ b/src/backend/postmaster/walwriter.c @@ -248,6 +248,13 @@ WalWriterMain(void) /* Process any signals received recently */ HandleWalWriterInterrupts(); + /* + * Notify the archiver of any WAL segments that are ready. We do this + * here to handle a race condition where WAL is flushed to disk prior + * to registering the segment boundary. + */ + NotifySegmentsReadyForArchive(GetFlushRecPtr()); + /* * Do what we're here for; then, if XLogBackgroundFlush() found useful * work to do, reset hibernation counter. diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 0a8ede700d..6b6ae81c2d 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -315,6 +315,7 @@ extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); extern void RemovePromoteSignalFiles(void); +extern void NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr); extern bool PromoteIsTriggered(void); extern bool CheckPromoteSignal(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..935b4cb02d 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool nudge); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool nudge); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..9b455e88e3 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -46,6 +46,7 @@ typedef uint64 XLogRecPtr; * XLogSegNo - physical log file sequence number. */ typedef uint64 XLogSegNo; +#define MaxXLogSegNo ((XLogSegNo) 0xFFFFFFFFFFFFFFFF) /* * TimeLineID (TLI) - identifies different database histories to prevent -- 2.30.2 --3l72er6sf3zeysw4-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* [PATCH v15] Avoid creating archive status ".ready" files too early @ 2021-08-23 13:06 Alvaro Herrera <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Alvaro Herrera @ 2021-08-23 13:06 UTC (permalink / raw) WAL records may span multiple segments, but XLogWrite() does not wait for the entire record to be written out to disk before creating archive status files. Instead, as soon as the last WAL page of the segment is written, the archive status file is created, and the archiver may process it. If PostgreSQL crashes before it is able to write and flush the rest of the record (in the next WAL segment), the wrong version of the first segment file lingers in the archive, which causes operations such as point-in-time restores to fail. To fix this, keep track of records that span across segments and ensure that segments are only marked ready-for-archival once such records have been completely written to disk. This has always been wrong, so backpatch all the way back. Author: Nathan Bossart <[email protected]> Reviewed-by: Kyotaro Horiguchi <[email protected]> Reviewed-by: Ryo Matsumura <[email protected]> Reviewed-by: Andrey Borodin <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/transam/timeline.c | 2 +- src/backend/access/transam/xlog.c | 220 +++++++++++++++++++++-- src/backend/access/transam/xlogarchive.c | 17 +- src/backend/postmaster/walwriter.c | 7 + src/backend/replication/walreceiver.c | 6 +- src/include/access/xlog.h | 1 + src/include/access/xlogarchive.h | 4 +- src/include/access/xlogdefs.h | 1 + 8 files changed, 234 insertions(+), 24 deletions(-) diff --git a/src/backend/access/transam/timeline.c b/src/backend/access/transam/timeline.c index 8d0903c175..acd5c2431d 100644 --- a/src/backend/access/transam/timeline.c +++ b/src/backend/access/transam/timeline.c @@ -452,7 +452,7 @@ writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI, if (XLogArchivingActive()) { TLHistoryFileName(histfname, newTLI); - XLogArchiveNotify(histfname); + XLogArchiveNotify(histfname, true); } } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index e51a7a749d..8e7c3a364a 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -724,6 +724,18 @@ typedef struct XLogCtlData XLogRecPtr lastFpwDisableRecPtr; slock_t info_lck; /* locks shared variables shown above */ + + /* + * Variables used to track cross-segment records. Protected by + * segtrack_lck. + */ + XLogSegNo lastNotifiedSeg; + XLogSegNo earliestSegBoundary; + XLogRecPtr earliestSegBoundaryRecPtr; + XLogSegNo latestSegBoundary; + XLogRecPtr latestSegBoundaryRecPtr; + + slock_t segtrack_lck; /* locks shared variables shown above */ } XLogCtlData; static XLogCtlData *XLogCtl = NULL; @@ -920,6 +932,7 @@ static void RemoveXlogFile(const char *segname, XLogSegNo recycleSegNo, XLogSegNo *endlogSegNo); static void UpdateLastRemovedPtr(char *filename); static void ValidateXLOGDirectoryStructure(void); +static void RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos); static void CleanupBackupHistory(void); static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force); static XLogRecord *ReadRecord(XLogReaderState *xlogreader, @@ -1154,23 +1167,56 @@ XLogInsertRecord(XLogRecData *rdata, END_CRIT_SECTION(); /* - * Update shared LogwrtRqst.Write, if we crossed page boundary. + * If we crossed page boundary, update LogwrtRqst.Write; if we crossed + * segment boundary, register that and wake up walwriter. */ if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ) { + XLogSegNo StartSeg; + XLogSegNo EndSeg; + + XLByteToSeg(StartPos, StartSeg, wal_segment_size); + XLByteToSeg(EndPos, EndSeg, wal_segment_size); + + /* + * Register our crossing the segment boundary if that occurred. + * + * Note that we did not use XLByteToPrevSeg() for determining the + * ending segment. This is so that a record that fits perfectly into + * the end of the segment is marked ready for archival as soon as the + * flushed pointer jumps to the next segment. + */ + if (StartSeg != EndSeg && XLogArchivingActive()) + RegisterSegmentBoundary(EndSeg, EndPos); + + /* + * Advance LogwrtRqst.Write so that it includes new block(s). + * + * We do this after registering the segment boundary so that the + * comparison with the flushed pointer below can use the latest value + * known globally. + */ SpinLockAcquire(&XLogCtl->info_lck); - /* advance global request to include new block(s) */ if (XLogCtl->LogwrtRqst.Write < EndPos) XLogCtl->LogwrtRqst.Write = EndPos; /* update local result copy while I have the chance */ LogwrtResult = XLogCtl->LogwrtResult; SpinLockRelease(&XLogCtl->info_lck); + + /* + * There's a chance that the record was already flushed to disk and we + * missed marking segments as ready for archive. If this happens, we + * nudge the WALWriter, which will take care of notifying segments as + * needed. + */ + if (StartSeg != EndSeg && XLogArchivingActive() && + LogwrtResult.Flush >= EndPos && ProcGlobal->walwriterLatch) + SetLatch(ProcGlobal->walwriterLatch); } /* * If this was an XLOG_SWITCH record, flush the record and the empty - * padding space that fills the rest of the segment, and perform - * end-of-segment actions (eg, notifying archiver). + * padding space that fills the rest of the segment. */ if (isLogSwitch) { @@ -2421,6 +2467,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) /* We should always be inside a critical section here */ Assert(CritSectionCount > 0); + Assert(LWLockHeldByMe(WALWriteLock)); /* * Update local LogwrtResult (caller probably did this already, but...) @@ -2586,11 +2633,12 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) * later. Doing it here ensures that one and only one backend will * perform this fsync. * - * This is also the right place to notify the Archiver that the - * segment is ready to copy to archival storage, and to update the - * timer for archive_timeout, and to signal for a checkpoint if - * too many logfile segments have been used since the last - * checkpoint. + * If WAL archiving is active, we attempt to notify the archiver + * of any segments that are now ready for archival. + * + * This is also the right place to update the timer for + * archive_timeout and to signal for a checkpoint if too many + * logfile segments have been used since the last checkpoint. */ if (finishing_seg) { @@ -2602,7 +2650,7 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) LogwrtResult.Flush = LogwrtResult.Write; /* end of page */ if (XLogArchivingActive()) - XLogArchiveNotifySeg(openLogSegNo); + NotifySegmentsReadyForArchive(LogwrtResult.Flush); XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL); XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush; @@ -2690,6 +2738,9 @@ XLogWrite(XLogwrtRqst WriteRqst, bool flexible) XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush; SpinLockRelease(&XLogCtl->info_lck); } + + if (XLogArchivingActive()) + NotifySegmentsReadyForArchive(LogwrtResult.Flush); } /* @@ -4328,6 +4379,131 @@ ValidateXLOGDirectoryStructure(void) } } +/* + * RegisterSegmentBoundary + * + * WAL records that are split across a segment boundary require special + * treatment for archiving: the initial segment must not be archived until + * the end segment has been flushed, in case we crash before we have + * the chance to flush the end segment (because after recovery we would + * overwrite that WAL record with a different one, and so the file we + * archived no longer represents truth.) This also applies to streaming + * physical replication. + * + * To handle this, we keep track of the LSN of WAL records that cross + * segment boundaries. Two such are sufficient: the earliest and the + * latest we know about, since the flush position advances monotonically. + * WAL record writers register boundary-crossing records here, which is + * used by .ready file creation to delay until the end segment is known + * flushed. + */ +static void +RegisterSegmentBoundary(XLogSegNo seg, XLogRecPtr pos) +{ + XLogSegNo segno PG_USED_FOR_ASSERTS_ONLY; + + /* verify caller computed segment number correctly */ + AssertArg((XLByteToSeg(pos, segno, wal_segment_size), segno == seg)); + + SpinLockAcquire(&XLogCtl->segtrack_lck); + + /* + * If no segment boundaries are registered, store the new segment boundary + * in earliestSegBoundary. Otherwise, store the greater segment boundaries in + * latestSegBoundary. + */ + if (XLogCtl->earliestSegBoundary == MaxXLogSegNo) + { + XLogCtl->earliestSegBoundary = seg; + XLogCtl->earliestSegBoundaryRecPtr = pos; + } + else if (seg > XLogCtl->earliestSegBoundary && + (XLogCtl->latestSegBoundary == MaxXLogSegNo || + seg > XLogCtl->latestSegBoundary)) + { + XLogCtl->latestSegBoundary = seg; + XLogCtl->latestSegBoundaryRecPtr = pos; + } + + SpinLockRelease(&XLogCtl->segtrack_lck); +} + +/* + * NotifySegmentsReadyForArchive + * + * Mark segments as ready for archival, given that it is safe to do so. + * This function is idempotent. + */ +void +NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr) +{ + XLogSegNo latest_boundary_seg; + XLogSegNo last_notified; + XLogSegNo flushed_seg; + XLogSegNo seg; + bool keep_latest; + + XLByteToSeg(flushRecPtr, flushed_seg, wal_segment_size); + + SpinLockAcquire(&XLogCtl->segtrack_lck); + + if (XLogCtl->latestSegBoundary <= flushed_seg && + XLogCtl->latestSegBoundaryRecPtr <= flushRecPtr) + { + latest_boundary_seg = XLogCtl->latestSegBoundary; + keep_latest = false; + } + else if (XLogCtl->earliestSegBoundary <= flushed_seg && + XLogCtl->earliestSegBoundaryRecPtr <= flushRecPtr) + { + latest_boundary_seg = XLogCtl->earliestSegBoundary; + keep_latest = true; + } + else + { + SpinLockRelease(&XLogCtl->segtrack_lck); + return; + } + + last_notified = XLogCtl->lastNotifiedSeg; + + /* + * Update shared memory and discard segment boundaries that are no + * longer needed. + * + * It is safe to update shared memory before we attempt to create the + * .ready files. If our calls to XLogArchiveNotifySeg() fail, + * RemoveOldXlogFiles() will retry it as needed. + */ + if (last_notified < latest_boundary_seg - 1) + XLogCtl->lastNotifiedSeg = latest_boundary_seg - 1; + + if (keep_latest) + { + XLogCtl->earliestSegBoundary = XLogCtl->latestSegBoundary; + XLogCtl->earliestSegBoundaryRecPtr = XLogCtl->latestSegBoundaryRecPtr; + } + else + { + XLogCtl->earliestSegBoundary = MaxXLogSegNo; + XLogCtl->earliestSegBoundaryRecPtr = InvalidXLogRecPtr; + } + + XLogCtl->latestSegBoundary = MaxXLogSegNo; + XLogCtl->latestSegBoundaryRecPtr = InvalidXLogRecPtr; + + SpinLockRelease(&XLogCtl->segtrack_lck); + + /* + * Notify archiver about segments that are ready for archival (by + * creating the corresponding .ready files). + */ + for (seg = last_notified + 1; seg < latest_boundary_seg; seg++) + XLogArchiveNotifySeg(seg, false); + + PgArchWakeup(); +} + /* * Remove previous backup history files. This also retries creation of * .ready files for any backup history files for which XLogArchiveNotify @@ -5230,9 +5406,17 @@ XLOGShmemInit(void) SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); + SpinLockInit(&XLogCtl->segtrack_lck); SpinLockInit(&XLogCtl->ulsn_lck); InitSharedLatch(&XLogCtl->recoveryWakeupLatch); ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); + + /* Initialize stuff for marking segments as ready for archival. */ + XLogCtl->lastNotifiedSeg = MaxXLogSegNo; + XLogCtl->earliestSegBoundary = MaxXLogSegNo; + XLogCtl->earliestSegBoundaryRecPtr = InvalidXLogRecPtr; + XLogCtl->latestSegBoundary = MaxXLogSegNo; + XLogCtl->latestSegBoundaryRecPtr = InvalidXLogRecPtr; } /* @@ -7873,6 +8057,20 @@ StartupXLOG(void) XLogCtl->LogwrtRqst.Write = EndOfLog; XLogCtl->LogwrtRqst.Flush = EndOfLog; + /* + * Initialize XLogCtl->lastNotifiedSeg to the previous WAL file. + */ + if (XLogArchivingActive()) + { + XLogSegNo EndOfLogSeg; + + XLByteToSeg(EndOfLog, EndOfLogSeg, wal_segment_size); + + SpinLockAcquire(&XLogCtl->segtrack_lck); + XLogCtl->lastNotifiedSeg = EndOfLogSeg - 1; + SpinLockRelease(&XLogCtl->segtrack_lck); + } + /* * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE * record before resource manager writes cleanup WAL records or checkpoint @@ -8000,7 +8198,7 @@ StartupXLOG(void) XLogArchiveCleanup(partialfname); durable_rename(origpath, partialpath, ERROR); - XLogArchiveNotify(partialfname); + XLogArchiveNotify(partialfname, true); } } } diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c index 26b023e754..b9c19b2085 100644 --- a/src/backend/access/transam/xlogarchive.c +++ b/src/backend/access/transam/xlogarchive.c @@ -433,7 +433,7 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); /* * If the existing file was replaced, since walsenders might have it open, @@ -462,9 +462,12 @@ KeepFileRestoredFromArchive(const char *path, const char *xlogfname) * by the archiver, e.g. we write 0000000100000001000000C6.ready * and the archiver then knows to archive XLOGDIR/0000000100000001000000C6, * then when complete, rename it to 0000000100000001000000C6.done + * + * Optionally, nudge the archiver process so that it'll notice the file we + * create. */ void -XLogArchiveNotify(const char *xlog) +XLogArchiveNotify(const char *xlog, bool nudge) { char archiveStatusPath[MAXPGPATH]; FILE *fd; @@ -489,8 +492,8 @@ XLogArchiveNotify(const char *xlog) return; } - /* Notify archiver that it's got something to do */ - if (IsUnderPostmaster) + /* If caller requested, let archiver know it's got work to do */ + if (nudge) PgArchWakeup(); } @@ -498,12 +501,12 @@ XLogArchiveNotify(const char *xlog) * Convenience routine to notify using segment number representation of filename */ void -XLogArchiveNotifySeg(XLogSegNo segno) +XLogArchiveNotifySeg(XLogSegNo segno, bool nudge) { char xlog[MAXFNAMELEN]; XLogFileName(xlog, ThisTimeLineID, segno, wal_segment_size); - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, nudge); } /* @@ -608,7 +611,7 @@ XLogArchiveCheckDone(const char *xlog) return true; /* Retry creation of the .ready file */ - XLogArchiveNotify(xlog); + XLogArchiveNotify(xlog, true); return false; } diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c index 626fae8454..6a1e16edc2 100644 --- a/src/backend/postmaster/walwriter.c +++ b/src/backend/postmaster/walwriter.c @@ -248,6 +248,13 @@ WalWriterMain(void) /* Process any signals received recently */ HandleWalWriterInterrupts(); + /* + * Notify the archiver of any WAL segments that are ready. We do this + * here to handle a race condition where WAL is flushed to disk prior + * to registering the segment boundary. + */ + NotifySegmentsReadyForArchive(GetFlushRecPtr()); + /* * Do what we're here for; then, if XLogBackgroundFlush() found useful * work to do, reset hibernation counter. diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index 9a2bc37fd7..60de3be92c 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -622,7 +622,7 @@ WalReceiverMain(void) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; @@ -760,7 +760,7 @@ WalRcvFetchTimeLineHistoryFiles(TimeLineID first, TimeLineID last) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(fname); else - XLogArchiveNotify(fname); + XLogArchiveNotify(fname, true); pfree(fname); pfree(content); @@ -915,7 +915,7 @@ XLogWalRcvWrite(char *buf, Size nbytes, XLogRecPtr recptr) if (XLogArchiveMode != ARCHIVE_MODE_ALWAYS) XLogArchiveForceDone(xlogfname); else - XLogArchiveNotify(xlogfname); + XLogArchiveNotify(xlogfname, true); } recvFile = -1; diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 0a8ede700d..6b6ae81c2d 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -315,6 +315,7 @@ extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(void); extern XLogRecPtr GetLastImportantRecPtr(void); extern void RemovePromoteSignalFiles(void); +extern void NotifySegmentsReadyForArchive(XLogRecPtr flushRecPtr); extern bool PromoteIsTriggered(void); extern bool CheckPromoteSignal(void); diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h index 3edd1a976c..935b4cb02d 100644 --- a/src/include/access/xlogarchive.h +++ b/src/include/access/xlogarchive.h @@ -23,8 +23,8 @@ extern bool RestoreArchivedFile(char *path, const char *xlogfname, extern void ExecuteRecoveryCommand(const char *command, const char *commandName, bool failOnSignal); extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname); -extern void XLogArchiveNotify(const char *xlog); -extern void XLogArchiveNotifySeg(XLogSegNo segno); +extern void XLogArchiveNotify(const char *xlog, bool nudge); +extern void XLogArchiveNotifySeg(XLogSegNo segno, bool nudge); extern void XLogArchiveForceDone(const char *xlog); extern bool XLogArchiveCheckDone(const char *xlog); extern bool XLogArchiveIsBusy(const char *xlog); diff --git a/src/include/access/xlogdefs.h b/src/include/access/xlogdefs.h index 60348d1850..9b455e88e3 100644 --- a/src/include/access/xlogdefs.h +++ b/src/include/access/xlogdefs.h @@ -46,6 +46,7 @@ typedef uint64 XLogRecPtr; * XLogSegNo - physical log file sequence number. */ typedef uint64 XLogSegNo; +#define MaxXLogSegNo ((XLogSegNo) 0xFFFFFFFFFFFFFFFF) /* * TimeLineID (TLI) - identifies different database histories to prevent -- 2.30.2 --erxcxkqg4k65gkj3-- ^ permalink raw reply [nested|flat] 7+ messages in thread
* Re: CHECK Constraint Deferrable @ 2023-10-02 15:01 Himanshu Upadhyaya <[email protected]> 0 siblings, 0 replies; 7+ messages in thread From: Himanshu Upadhyaya @ 2023-10-02 15:01 UTC (permalink / raw) To: vignesh C <[email protected]>; +Cc: David G. Johnston <[email protected]>; Dilip Kumar <[email protected]>; PostgreSQL Hackers <[email protected]> On Thu, Sep 14, 2023 at 9:57 AM vignesh C <[email protected]> wrote: > 2) I was not sure, if the error message change was intentional: > 2a) > In Head: > CREATE FOREIGN TABLE t9(a int CHECK(a<>0) DEFERRABLE) SERVER s1; > ERROR: misplaced DEFERRABLE clause > LINE 1: CREATE FOREIGN TABLE t9(a int CHECK(a<>0) DEFERRABLE) SERVER... > ^ > postgres=# CREATE FOREIGN TABLE t9(a int CHECK(a<>0) DEFERRABLE) SERVER s1; > ERROR: "t9" is a foreign table > DETAIL: Foreign tables cannot have constraint triggers. > > 2b) > In Head: > postgres=# CREATE FOREIGN TABLE t2(a int CHECK(a<>0)) SERVER s1; > CREATE FOREIGN TABLE > postgres=# ALTER FOREIGN TABLE t2 ADD CONSTRAINT t2_chk_1 CHECK(a<>1) > DEFERRABLE; > ERROR: CHECK constraints cannot be marked DEFERRABLE > > With patch: > postgres=# ALTER FOREIGN TABLE t8 ADD CONSTRAINT t8_chk_1 CHECK(a<>1) > DEFERRABLE; > ERROR: "t8" is a foreign table > DETAIL: Foreign tables cannot have constraint triggers. > > We are creating a constraint trigger for DEFERRED check constraint and as per implementation of FOREIGN table we are restricting to have a constraint trigger. I need to do more analysis before reaching to any conclusion, I think we can restrict this gram.y itself. > 3) Insert check is not deferred to commit: > This insert check here is deferred to commit: > postgres=# CREATE TABLE tbl (i int ) partition by range (i); > CREATE TABLE tbl_1 PARTITION OF tbl FOR VALUES FROM (0) TO (10); > CREATE TABLE tbl_2 PARTITION OF tbl FOR VALUES FROM (20) TO (30); > CREATE TABLE > CREATE TABLE > CREATE TABLE > postgres=# ALTER TABLE tbl ADD CONSTRAINT tbl_chk_1 CHECK(i<>1) DEFERRABLE; > ALTER TABLE > postgres=# begin; > BEGIN > postgres=*# SET CONSTRAINTS tbl_chk_1 DEFERRED; > SET CONSTRAINTS > postgres=*# INSERT INTO tbl values (1); > INSERT 0 1 > postgres=*# commit; > ERROR: new row for relation "tbl_1" violates check constraint "tbl_chk_1" > DETAIL: Failing row contains (1). > > But the check here is not deferred to commit: > postgres=# CREATE TABLE tbl (i int check(i<>0) DEFERRABLE) partition > by range (i); > CREATE TABLE tbl_1 PARTITION OF tbl FOR VALUES FROM (0) TO (10); > CREATE TABLE tbl_2 PARTITION OF tbl FOR VALUES FROM (20) TO (30); > CREATE TABLE > CREATE TABLE > CREATE TABLE > postgres=# ALTER TABLE tbl ADD CONSTRAINT tbl_chk_1 CHECK(i<>1) DEFERRABLE; > ALTER TABLE > postgres=# begin; > BEGIN > postgres=*# SET CONSTRAINTS tbl_chk_1 DEFERRED; > SET CONSTRAINTS > postgres=*# INSERT INTO tbl values (1); > ERROR: new row for relation "tbl_1" violates check constraint "tbl_chk_1" > DETAIL: Failing row contains (1). > > Fixed in V3 patch. > 4) There is a new warning popping up now: > CREATE TABLE tbl_new_3 (i int check(i<>0)) partition by range (i); > CREATE FOREIGN TABLE ftbl_new_3 PARTITION OF tbl_new_3 FOR VALUES FROM > (40) TO (50) server s1; > postgres=# ALTER TABLE tbl_new_3 ADD CONSTRAINT tbl_new_3_chk > CHECK(i<>1) DEFERRABLE; > WARNING: unexpected pg_constraint record found for relation "tbl_new_3" > ERROR: "ftbl_new_3" is a foreign table > DETAIL: Foreign tables cannot have constraint triggers. > > Fixed in V3 patch. -- Regards, Himanshu Upadhyaya EnterpriseDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 7+ messages in thread
end of thread, other threads:[~2023-10-02 15:01 UTC | newest] Thread overview: 7+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2021-07-30 22:35 [PATCH v3] Avoid creating archive status ".ready" files too early. Alvaro Herrera <[email protected]> 2021-07-30 22:35 [PATCH v2] Avoid creating archive status ".ready" files too early. Alvaro Herrera <[email protected]> 2021-08-17 03:52 [PATCH v12] Avoid creating archive status ".ready" files too early Nathan Bossart <[email protected]> 2021-08-17 03:52 [PATCH v10] Avoid creating archive status ".ready" files too early. Nathan Bossart <[email protected]> 2021-08-20 19:25 [PATCH v14] Avoid creating archive status ".ready" files too early Nathan Bossart <[email protected]> 2021-08-23 13:06 [PATCH v15] Avoid creating archive status ".ready" files too early Alvaro Herrera <[email protected]> 2023-10-02 15:01 Re: CHECK Constraint Deferrable Himanshu Upadhyaya <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox