From 70e81861fadd9112fa2d425c762e163910a4ee52 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Wed, 16 Feb 2022 09:30:38 +0200 Subject: [PATCH] Split xlog.c into xlog.c and xlogrecovery.c. This moves the functions related to performing WAL recovery into the new xlogrecovery.c source file, leaving xlog.c responsible for maintaining the WAL buffers, coordinating the startup and switch from recovery to normal operations, and other miscellaneous stuff that have always been in xlog.c. Reviewed-by: Andres Freund, Kyotaro Horiguchi, Robert Haas Discussion: https://www.postgresql.org/message-id/a31f27b4-a31d-f976-6217-2b03be646ffa%40iki.fi --- contrib/pg_prewarm/autoprewarm.c | 1 + src/backend/access/transam/Makefile | 1 + src/backend/access/transam/xact.c | 1 + src/backend/access/transam/xlog.c | 4483 +--------------- src/backend/access/transam/xlogfuncs.c | 2 +- src/backend/access/transam/xlogrecovery.c | 4537 +++++++++++++++++ src/backend/access/transam/xlogutils.c | 6 +- src/backend/postmaster/checkpointer.c | 1 + src/backend/postmaster/postmaster.c | 1 + src/backend/postmaster/startup.c | 1 + .../replication/logical/logicalfuncs.c | 1 + src/backend/replication/slotfuncs.c | 1 + src/backend/replication/walreceiver.c | 1 + src/backend/replication/walreceiverfuncs.c | 1 + src/backend/replication/walsender.c | 1 + src/backend/storage/ipc/ipci.c | 3 + src/backend/storage/ipc/standby.c | 1 + src/backend/storage/sync/sync.c | 1 + src/backend/utils/misc/guc.c | 1 + src/include/access/xlog.h | 87 +- src/include/access/xlogrecovery.h | 157 + src/tools/pgindent/typedefs.list | 2 + 22 files changed, 4912 insertions(+), 4379 deletions(-) create mode 100644 src/backend/access/transam/xlogrecovery.c create mode 100644 src/include/access/xlogrecovery.h diff --git a/contrib/pg_prewarm/autoprewarm.c b/contrib/pg_prewarm/autoprewarm.c index 5d40fb5020..1d4d74b171 100644 --- a/contrib/pg_prewarm/autoprewarm.c +++ b/contrib/pg_prewarm/autoprewarm.c @@ -38,6 +38,7 @@ #include "postmaster/interrupt.h" #include "storage/buf_internals.h" #include "storage/dsm.h" +#include "storage/fd.h" #include "storage/ipc.h" #include "storage/latch.h" #include "storage/lwlock.h" diff --git a/src/backend/access/transam/Makefile b/src/backend/access/transam/Makefile index 595e02de72..79314c69ab 100644 --- a/src/backend/access/transam/Makefile +++ b/src/backend/access/transam/Makefile @@ -32,6 +32,7 @@ OBJS = \ xlogfuncs.o \ xloginsert.o \ xlogreader.o \ + xlogrecovery.o \ xlogutils.o include $(top_srcdir)/src/backend/common.mk diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index c9516e03fa..bb1f106946 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -29,6 +29,7 @@ #include "access/xact.h" #include "access/xlog.h" #include "access/xloginsert.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "catalog/index.h" #include "catalog/namespace.h" diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 859eb32c48..eb3c516058 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -3,6 +3,30 @@ * xlog.c * PostgreSQL write-ahead log manager * + * The Write-Ahead Log (WAL) functionality is split into several source + * files, in addition to this one: + * + * xloginsert.c - Functions for constructing WAL records + * xlogrecovery.c - WAL recovery and standby code + * xlogreader.c - Facility for reading WAL files and parsing WAL records + * xlogutils.c - Helper functions for WAL redo routines + * + * This file contains functions for coordinating database startup and + * checkpointing, and managing the write-ahead log buffers when the + * system is running. + * + * StartupXLOG() is the main entry point of the startup process. It + * coordinates database startup, performing WAL recovery, and the + * transition from WAL recovery into normal operations. + * + * XLogInsertRecord() inserts a WAL record into the WAL buffers. Most + * callers should not call this directly, but use the functions in + * xloginsert.c to construct the WAL record. XLogFlush() can be used + * to force the WAL to disk. + * + * In addition to those, there are many other functions for interrogating + * the current system state, and for starting/stopping backups. + * * * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -36,12 +60,11 @@ #include "access/xlogarchive.h" #include "access/xloginsert.h" #include "access/xlogreader.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "catalog/catversion.h" #include "catalog/pg_control.h" #include "catalog/pg_database.h" -#include "commands/progress.h" -#include "commands/tablespace.h" #include "common/controldata_utils.h" #include "executor/instrument.h" #include "miscadmin.h" @@ -72,7 +95,6 @@ #include "storage/smgr.h" #include "storage/spin.h" #include "storage/sync.h" -#include "utils/builtins.h" #include "utils/guc.h" #include "utils/memutils.h" #include "utils/ps_status.h" @@ -84,10 +106,6 @@ extern uint32 bootstrap_data_checksum_version; -/* Unsupported old recovery command file names (relative to $PGDATA) */ -#define RECOVERY_COMMAND_FILE "recovery.conf" -#define RECOVERY_COMMAND_DONE "recovery.done" - /* timeline ID to be used when bootstrapping */ #define BootstrapTimeLineID 1 @@ -177,13 +195,6 @@ const struct config_enum_entry archive_mode_options[] = { {NULL, 0, false} }; -const struct config_enum_entry recovery_target_action_options[] = { - {"pause", RECOVERY_TARGET_ACTION_PAUSE, false}, - {"promote", RECOVERY_TARGET_ACTION_PROMOTE, false}, - {"shutdown", RECOVERY_TARGET_ACTION_SHUTDOWN, false}, - {NULL, 0, false} -}; - /* * Statistics for current checkpoint are collected in this global struct. * Because only the checkpointer or a stand-alone backend can perform @@ -191,19 +202,6 @@ const struct config_enum_entry recovery_target_action_options[] = { */ CheckpointStatsData CheckpointStats; -/* Local copy of WalRcv->flushedUpto */ -static XLogRecPtr flushedUpto = 0; -static TimeLineID receiveTLI = 0; - -/* - * abortedRecPtr is the start pointer of a broken record at end of WAL when - * recovery completes; missingContrecPtr is the location of the first - * contrecord that went missing. See CreateOverwriteContrecordRecord for - * details. - */ -static XLogRecPtr abortedRecPtr; -static XLogRecPtr missingContrecPtr; - /* * During recovery, lastFullPageWrites keeps track of full_page_writes that * the replayed WAL records indicate. It's initialized with full_page_writes @@ -219,18 +217,6 @@ static bool lastFullPageWrites; */ static bool LocalRecoveryInProgress = true; -/* - * Local copy of SharedHotStandbyActive variable. False actually means "not - * known, need to check the shared state". - */ -static bool LocalHotStandbyActive = false; - -/* - * Local copy of SharedPromoteIsTriggered variable. False actually means "not - * known, need to check the shared state". - */ -static bool LocalPromoteIsTriggered = false; - /* * Local state for XLogInsertAllowed(): * 1: unconditionally allowed to insert XLOG @@ -243,87 +229,6 @@ static bool LocalPromoteIsTriggered = false; */ static int LocalXLogInsertAllowed = -1; -/* - * When ArchiveRecoveryRequested is set, archive recovery was requested, - * ie. signal files were present. When InArchiveRecovery is set, we are - * currently recovering using offline XLOG archives. These variables are only - * valid in the startup process. - * - * When ArchiveRecoveryRequested is true, but InArchiveRecovery is false, we're - * currently performing crash recovery using only XLOG files in pg_wal, but - * will switch to using offline XLOG archives as soon as we reach the end of - * WAL in pg_wal. -*/ -bool ArchiveRecoveryRequested = false; -bool InArchiveRecovery = false; - -static bool standby_signal_file_found = false; -static bool recovery_signal_file_found = false; - -/* Buffers dedicated to consistency checks of size BLCKSZ */ -static char *replay_image_masked = NULL; -static char *primary_image_masked = NULL; - -/* options formerly taken from recovery.conf for archive recovery */ -char *recoveryRestoreCommand = NULL; -char *recoveryEndCommand = NULL; -char *archiveCleanupCommand = NULL; -RecoveryTargetType recoveryTarget = RECOVERY_TARGET_UNSET; -bool recoveryTargetInclusive = true; -int recoveryTargetAction = RECOVERY_TARGET_ACTION_PAUSE; -TransactionId recoveryTargetXid; -char *recovery_target_time_string; -static TimestampTz recoveryTargetTime; -const char *recoveryTargetName; -XLogRecPtr recoveryTargetLSN; -int recovery_min_apply_delay = 0; - -/* options formerly taken from recovery.conf for XLOG streaming */ -bool StandbyModeRequested = false; -char *PrimaryConnInfo = NULL; -char *PrimarySlotName = NULL; -char *PromoteTriggerFile = NULL; -bool wal_receiver_create_temp_slot = false; - -/* are we currently in standby mode? */ -bool StandbyMode = false; - -/* - * if recoveryStopsBefore/After returns true, it saves information of the stop - * point here - */ -static TransactionId recoveryStopXid; -static TimestampTz recoveryStopTime; -static XLogRecPtr recoveryStopLSN; -static char recoveryStopName[MAXFNAMELEN]; -static bool recoveryStopAfter; - -/* - * recoveryTargetTimeLineGoal: what the user requested, if any - * - * recoveryTargetTLIRequested: numeric value of requested timeline, if constant - * - * recoveryTargetTLI: the currently understood target timeline; changes - * - * expectedTLEs: a list of TimeLineHistoryEntries for recoveryTargetTLI and the timelines of - * its known parents, newest first (so recoveryTargetTLI is always the - * first list member). Only these TLIs are expected to be seen in the WAL - * segments we read, and indeed only these TLIs will be considered as - * candidate WAL files to open at all. - * - * curFileTLI: the TLI appearing in the name of the current input WAL file. - * (This is not necessarily the same as the timeline from which we are - * replaying WAL, which StartupXLOG calls replayTLI, because we could be - * scanning data that was copied from an ancestor timeline when the current - * file was created.) During a sequential scan we do not allow this value - * to decrease. - */ -RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal = RECOVERY_TARGET_TIMELINE_LATEST; -TimeLineID recoveryTargetTLIRequested = 0; -TimeLineID recoveryTargetTLI = 0; -static List *expectedTLEs; -static TimeLineID curFileTLI; - /* * ProcLastRecPtr points to the start of the last XLOG record inserted by the * current backend. It is updated for all inserts. XactLastRecEnd points to @@ -374,21 +279,6 @@ static XLogRecPtr RedoRecPtr; */ static bool doPageWrites; -/* Has the recovery code requested a walreceiver wakeup? */ -static bool doRequestWalReceiverReply; - -/* - * RedoStartLSN points to the checkpoint's REDO location which is specified - * in a backup label file, backup history file or control file. In standby - * mode, XLOG streaming usually starts from the position where an invalid - * record was found. But if we fail to read even the initial checkpoint - * record, we use the REDO location instead of the checkpoint location as - * the start position of XLOG streaming. Otherwise we would have to jump - * backwards to the REDO location after reading the checkpoint record, - * because the REDO record can precede the checkpoint record. - */ -static XLogRecPtr RedoStartLSN = InvalidXLogRecPtr; - /*---------- * Shared-memory data structures for XLOG control * @@ -650,12 +540,6 @@ typedef struct XLogCtlData */ RecoveryState SharedRecoveryState; - /* - * SharedHotStandbyActive indicates if we allow hot standby queries to be - * run. Protected by info_lck. - */ - bool SharedHotStandbyActive; - /* * InstallXLogFileSegmentActive indicates whether the checkpointer should * arrange for future segments by recycling and/or PreallocXlogFiles(). @@ -666,12 +550,6 @@ typedef struct XLogCtlData */ bool InstallXLogFileSegmentActive; - /* - * SharedPromoteIsTriggered indicates if a standby promotion has been - * triggered. Protected by info_lck. - */ - bool SharedPromoteIsTriggered; - /* * WalWriterSleeping indicates whether the WAL writer is currently in * low-power mode (and hence should be nudged if an async commit occurs). @@ -679,23 +557,6 @@ typedef struct XLogCtlData */ bool WalWriterSleeping; - /* - * recoveryWakeupLatch is used to wake up the startup process to continue - * WAL replay, if it is waiting for WAL to arrive or failover trigger file - * to appear. - * - * Note that the startup process also uses another latch, its procLatch, - * to wait for recovery conflict. If we get rid of recoveryWakeupLatch for - * signaling the startup process in favor of using its procLatch, which - * comports better with possible generic signal handlers using that latch. - * But we should not do that because the startup process doesn't assume - * that it's waken up by walreceiver process or SIGHUP signal handler - * while it's waiting for recovery conflict. The separate latches, - * recoveryWakeupLatch and procLatch, should be used for inter-process - * communication for WAL replay and recovery conflict, respectively. - */ - Latch recoveryWakeupLatch; - /* * During recovery, we keep a copy of the latest checkpoint record here. * lastCheckPointRecPtr points to start of checkpoint record and @@ -708,28 +569,6 @@ typedef struct XLogCtlData XLogRecPtr lastCheckPointEndPtr; CheckPoint lastCheckPoint; - /* - * lastReplayedEndRecPtr points to end+1 of the last record successfully - * replayed. When we're currently replaying a record, ie. in a redo - * function, replayEndRecPtr points to the end+1 of the record being - * replayed, otherwise it's equal to lastReplayedEndRecPtr. - */ - XLogRecPtr lastReplayedEndRecPtr; - TimeLineID lastReplayedTLI; - XLogRecPtr replayEndRecPtr; - TimeLineID replayEndTLI; - /* timestamp of last COMMIT/ABORT record replayed (or being replayed) */ - TimestampTz recoveryLastXTime; - - /* - * timestamp of when we started replaying the current chunk of WAL data, - * only relevant for replication or archive recovery - */ - TimestampTz currentChunkStartTime; - /* Recovery pause state */ - RecoveryPauseState recoveryPauseState; - ConditionVariable recoveryNotPausedCV; - /* * lastFpwDisableRecPtr points to the start of the last replayed * XLOG_FPW_CHANGE record that instructs full_page_writes is disabled. @@ -787,21 +626,6 @@ static int UsableBytesInSegment; */ static XLogwrtResult LogwrtResult = {0, 0}; -/* - * Codes indicating where we got a WAL file from during recovery, or where - * to attempt to get one. - */ -typedef enum -{ - XLOG_FROM_ANY = 0, /* request to read WAL from any source */ - XLOG_FROM_ARCHIVE, /* restored using restore_command */ - XLOG_FROM_PG_WAL, /* existing file in pg_wal */ - XLOG_FROM_STREAM /* streamed from primary */ -} XLogSource; - -/* human-readable names for XLogSources, for debugging output */ -static const char *const xlogSourceNames[] = {"any", "archive", "pg_wal", "stream"}; - /* * openLogFile is -1 or a kernel FD for an open log file segment. * openLogSegNo identifies the segment, and openLogTLI the corresponding TLI. @@ -814,74 +638,17 @@ static int openLogFile = -1; static XLogSegNo openLogSegNo = 0; static TimeLineID openLogTLI = 0; -/* - * These variables are used similarly to the ones above, but for reading - * the XLOG. readOff is the offset of the page just read, readLen - * indicates how much of it has been read into readBuf, and readSource - * indicates where we got the currently open file from. - * Note: we could use Reserve/ReleaseExternalFD to track consumption of - * this FD too; but it doesn't currently seem worthwhile, since the XLOG is - * not read by general-purpose sessions. - */ -static int readFile = -1; -static XLogSegNo readSegNo = 0; -static uint32 readOff = 0; -static uint32 readLen = 0; -static XLogSource readSource = XLOG_FROM_ANY; - -/* - * Keeps track of which source we're currently reading from. This is - * different from readSource in that this is always set, even when we don't - * currently have a WAL file open. If lastSourceFailed is set, our last - * attempt to read from currentSource failed, and we should try another source - * next. - * - * pendingWalRcvRestart is set when a config change occurs that requires a - * walreceiver restart. This is only valid in XLOG_FROM_STREAM state. - */ -static XLogSource currentSource = XLOG_FROM_ANY; -static bool lastSourceFailed = false; -static bool pendingWalRcvRestart = false; - -typedef struct XLogPageReadPrivate -{ - int emode; - bool fetching_ckpt; /* are we fetching a checkpoint record? */ - bool randAccess; - TimeLineID replayTLI; -} XLogPageReadPrivate; - -/* - * These variables track when we last obtained some WAL data to process, - * and where we got it from. (XLogReceiptSource is initially the same as - * readSource, but readSource gets reset to zero when we don't have data - * to process right now. It is also different from currentSource, which - * also changes when we try to read from a source and fail, while - * XLogReceiptSource tracks where we last successfully read some WAL.) - */ -static TimestampTz XLogReceiptTime = 0; -static XLogSource XLogReceiptSource = XLOG_FROM_ANY; - /* * Local copies of equivalent fields in the control file. When running - * crash recovery, minRecoveryPoint is set to InvalidXLogRecPtr as we + * crash recovery, LocalMinRecoveryPoint is set to InvalidXLogRecPtr as we * expect to replay all the WAL available, and updateMinRecoveryPoint is * switched to false to prevent any updates while replaying records. * Those values are kept consistent as long as crash recovery runs. */ -static XLogRecPtr minRecoveryPoint; -static TimeLineID minRecoveryPointTLI; +static XLogRecPtr LocalMinRecoveryPoint; +static TimeLineID LocalMinRecoveryPointTLI; static bool updateMinRecoveryPoint = true; -/* - * Have we reached a consistent database state? In crash recovery, we have - * to replay all the WAL, so reachedConsistency is never set. During archive - * recovery, the database is consistent once minRecoveryPoint is reached. - */ -bool reachedConsistency = false; - -static bool InRedo = false; - /* For WALInsertLockAcquire/Release functions */ static int MyLockNo = 0; static bool holdingAllLocks = false; @@ -890,27 +657,11 @@ static bool holdingAllLocks = false; static MemoryContext walDebugCxt = NULL; #endif -static void readRecoverySignalFile(void); -static void validateRecoveryParameters(void); -static void XLogInitNewTimeline(TimeLineID endTLI, XLogRecPtr endOfLog, - TimeLineID newTLI); static void CleanupAfterArchiveRecovery(TimeLineID EndOfLogTLI, XLogRecPtr EndOfLog, TimeLineID newTLI); -static bool recoveryStopsBefore(XLogReaderState *record); -static bool recoveryStopsAfter(XLogReaderState *record); -static char *getRecoveryStopReason(void); -static void ConfirmRecoveryPaused(void); -static void recoveryPausesHere(bool endOfRecovery); -static bool recoveryApplyDelay(XLogReaderState *record); -static void SetLatestXTime(TimestampTz xtime); -static void SetCurrentChunkStartTime(TimestampTz xtime); static void CheckRequiredParameterValues(void); static void XLogReportParameters(void); -static void checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, - TimeLineID prevTLI, TimeLineID replayTLI); -static void VerifyOverwriteContrecord(xl_overwrite_contrecord *xlrec, - XLogReaderState *state); static int LocalSetXLogInsertAllowed(void); static void CreateEndOfRecoveryRecord(void); static XLogRecPtr CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn, @@ -922,22 +673,10 @@ static XLogRecPtr XLogGetReplicationSlotMinimumLSN(void); static void AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic); -static bool XLogCheckpointNeeded(XLogSegNo new_segno); static void XLogWrite(XLogwrtRqst WriteRqst, TimeLineID tli, bool flexible); static bool InstallXLogFileSegment(XLogSegNo *segno, char *tmppath, bool find_free, XLogSegNo max_segno, TimeLineID tli); -static int XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli, - XLogSource source, bool notfoundOk); -static int XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source); -static int XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, - int reqLen, XLogRecPtr targetRecPtr, char *readBuf); -static bool WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, - bool fetching_ckpt, XLogRecPtr tliRecPtr, - TimeLineID replayTLI, - XLogRecPtr replayLSN); -static void XLogShutdownWalRcv(void); -static int emode_for_corrupt_record(int emode, XLogRecPtr RecPtr); static void XLogFileClose(void); static void PreallocXlogFiles(XLogRecPtr endptr, TimeLineID tli); static void RemoveTempXlogFiles(void); @@ -949,36 +688,16 @@ static void UpdateLastRemovedPtr(char *filename); static void ValidateXLOGDirectoryStructure(void); static void CleanupBackupHistory(void); static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force); -static XLogRecord *ReadRecord(XLogReaderState *xlogreader, - int emode, bool fetching_ckpt, - TimeLineID replayTLI); -static void CheckRecoveryConsistency(void); static bool PerformRecoveryXLogAction(void); -static XLogRecord *ReadCheckpointRecord(XLogReaderState *xlogreader, - XLogRecPtr RecPtr, int whichChkpt, bool report, - TimeLineID replayTLI); -static bool rescanLatestTimeLine(TimeLineID replayTLI, - XLogRecPtr replayLSN); static void InitControlFile(uint64 sysidentifier); static void WriteControlFile(void); static void ReadControlFile(void); +static void UpdateControlFile(void); static char *str_time(pg_time_t tnow); -static void SetPromoteIsTriggered(void); -static bool CheckForStandbyTrigger(void); -#ifdef WAL_DEBUG -static void xlog_outrec(StringInfo buf, XLogReaderState *record); -#endif -static void xlog_block_info(StringInfo buf, XLogReaderState *record); -static void xlog_outdesc(StringInfo buf, XLogReaderState *record); static void pg_start_backup_callback(int code, Datum arg); static void pg_stop_backup_callback(int code, Datum arg); -static bool read_backup_label(XLogRecPtr *checkPointLoc, - TimeLineID *backupLabelTLI, - bool *backupEndRequired, bool *backupFromStandby); -static bool read_tablespace_map(List **tablespaces); -static void rm_redo_error_callback(void *arg); static int get_sync_bit(int method); static void CopyXLogRecordToWAL(int write_len, bool isLogSwitch, @@ -994,7 +713,6 @@ static char *GetXLogBuffer(XLogRecPtr ptr, TimeLineID tli); static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos); static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos); static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr); -static void checkXLogConsistency(XLogReaderState *record); static void WALInsertLockAcquire(void); static void WALInsertLockAcquireExclusive(void); @@ -1442,114 +1160,6 @@ ReserveXLogSwitch(XLogRecPtr *StartPos, XLogRecPtr *EndPos, XLogRecPtr *PrevPtr) return true; } -/* - * Checks whether the current buffer page and backup page stored in the - * WAL record are consistent or not. Before comparing the two pages, a - * masking can be applied to the pages to ignore certain areas like hint bits, - * unused space between pd_lower and pd_upper among other things. This - * function should be called once WAL replay has been completed for a - * given record. - */ -static void -checkXLogConsistency(XLogReaderState *record) -{ - RmgrId rmid = XLogRecGetRmid(record); - RelFileNode rnode; - ForkNumber forknum; - BlockNumber blkno; - int block_id; - - /* Records with no backup blocks have no need for consistency checks. */ - if (!XLogRecHasAnyBlockRefs(record)) - return; - - Assert((XLogRecGetInfo(record) & XLR_CHECK_CONSISTENCY) != 0); - - for (block_id = 0; block_id <= record->max_block_id; block_id++) - { - Buffer buf; - Page page; - - if (!XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blkno)) - { - /* - * WAL record doesn't contain a block reference with the given id. - * Do nothing. - */ - continue; - } - - Assert(XLogRecHasBlockImage(record, block_id)); - - if (XLogRecBlockImageApply(record, block_id)) - { - /* - * WAL record has already applied the page, so bypass the - * consistency check as that would result in comparing the full - * page stored in the record with itself. - */ - continue; - } - - /* - * Read the contents from the current buffer and store it in a - * temporary page. - */ - buf = XLogReadBufferExtended(rnode, forknum, blkno, - RBM_NORMAL_NO_LOG); - if (!BufferIsValid(buf)) - continue; - - LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE); - page = BufferGetPage(buf); - - /* - * Take a copy of the local page where WAL has been applied to have a - * comparison base before masking it... - */ - memcpy(replay_image_masked, page, BLCKSZ); - - /* No need for this page anymore now that a copy is in. */ - UnlockReleaseBuffer(buf); - - /* - * If the block LSN is already ahead of this WAL record, we can't - * expect contents to match. This can happen if recovery is - * restarted. - */ - if (PageGetLSN(replay_image_masked) > record->EndRecPtr) - continue; - - /* - * Read the contents from the backup copy, stored in WAL record and - * store it in a temporary page. There is no need to allocate a new - * page here, a local buffer is fine to hold its contents and a mask - * can be directly applied on it. - */ - if (!RestoreBlockImage(record, block_id, primary_image_masked)) - elog(ERROR, "failed to restore block image"); - - /* - * If masking function is defined, mask both the primary and replay - * images - */ - if (RmgrTable[rmid].rm_mask != NULL) - { - RmgrTable[rmid].rm_mask(replay_image_masked, blkno); - RmgrTable[rmid].rm_mask(primary_image_masked, blkno); - } - - /* Time to compare the primary and replay images. */ - if (memcmp(replay_image_masked, primary_image_masked, BLCKSZ) != 0) - { - elog(FATAL, - "inconsistent page found, rel %u/%u/%u, forknum %u, blkno %u", - rnode.spcNode, rnode.dbNode, rnode.relNode, - forknum, blkno); - } - } -} - /* * Subroutine of XLogInsertRecord. Copies a WAL record to an already-reserved * area in the WAL. @@ -2435,7 +2045,7 @@ XLOGfileslop(XLogRecPtr lastredoptr) * * Note: it is caller's responsibility that RedoRecPtr is up-to-date. */ -static bool +bool XLogCheckpointNeeded(XLogSegNo new_segno) { XLogSegNo old_segno; @@ -2829,7 +2439,7 @@ static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) { /* Quick check using our local copy of the variable */ - if (!updateMinRecoveryPoint || (!force && lsn <= minRecoveryPoint)) + if (!updateMinRecoveryPoint || (!force && lsn <= LocalMinRecoveryPoint)) return; /* @@ -2843,7 +2453,7 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) * available is replayed in this case. This also saves from extra locks * taken on the control file from the startup process. */ - if (XLogRecPtrIsInvalid(minRecoveryPoint) && InRecovery) + if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint) && InRecovery) { updateMinRecoveryPoint = false; return; @@ -2852,12 +2462,12 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); /* update local copy */ - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; - if (XLogRecPtrIsInvalid(minRecoveryPoint)) + if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint)) updateMinRecoveryPoint = false; - else if (force || minRecoveryPoint < lsn) + else if (force || LocalMinRecoveryPoint < lsn) { XLogRecPtr newMinRecoveryPoint; TimeLineID newMinRecoveryPointTLI; @@ -2875,11 +2485,7 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) * all. Instead, we just log a warning and continue with recovery. * (See also the comments about corrupt LSNs in XLogFlush.) */ - SpinLockAcquire(&XLogCtl->info_lck); - newMinRecoveryPoint = XLogCtl->replayEndRecPtr; - newMinRecoveryPointTLI = XLogCtl->replayEndTLI; - SpinLockRelease(&XLogCtl->info_lck); - + newMinRecoveryPoint = GetCurrentReplayRecPtr(&newMinRecoveryPointTLI); if (!force && newMinRecoveryPoint < lsn) elog(WARNING, "xlog min recovery request %X/%X is past current point %X/%X", @@ -2891,12 +2497,12 @@ UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force) ControlFile->minRecoveryPoint = newMinRecoveryPoint; ControlFile->minRecoveryPointTLI = newMinRecoveryPointTLI; UpdateControlFile(); - minRecoveryPoint = newMinRecoveryPoint; - minRecoveryPointTLI = newMinRecoveryPointTLI; + LocalMinRecoveryPoint = newMinRecoveryPoint; + LocalMinRecoveryPointTLI = newMinRecoveryPointTLI; ereport(DEBUG2, (errmsg_internal("updated min recovery point to %X/%X on timeline %u", - LSN_FORMAT_ARGS(minRecoveryPoint), + LSN_FORMAT_ARGS(newMinRecoveryPoint), newMinRecoveryPointTLI))); } } @@ -3256,11 +2862,11 @@ XLogNeedsFlush(XLogRecPtr record) * which cannot update its local copy of minRecoveryPoint as long as * it has not replayed all WAL available when doing crash recovery. */ - if (XLogRecPtrIsInvalid(minRecoveryPoint) && InRecovery) + if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint) && InRecovery) updateMinRecoveryPoint = false; /* Quick exit if already known to be updated or cannot be updated */ - if (record <= minRecoveryPoint || !updateMinRecoveryPoint) + if (record <= LocalMinRecoveryPoint || !updateMinRecoveryPoint) return false; /* @@ -3269,8 +2875,8 @@ XLogNeedsFlush(XLogRecPtr record) */ if (!LWLockConditionalAcquire(ControlFileLock, LW_SHARED)) return true; - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; LWLockRelease(ControlFileLock); /* @@ -3278,11 +2884,11 @@ XLogNeedsFlush(XLogRecPtr record) * process doing crash recovery, which should not update the control * file value if crash recovery is still running. */ - if (XLogRecPtrIsInvalid(minRecoveryPoint)) + if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint)) updateMinRecoveryPoint = false; /* check again */ - if (record <= minRecoveryPoint || !updateMinRecoveryPoint) + if (record <= LocalMinRecoveryPoint || !updateMinRecoveryPoint) return false; else return true; @@ -3763,192 +3369,6 @@ XLogFileOpen(XLogSegNo segno, TimeLineID tli) return fd; } -/* - * Open a logfile segment for reading (during recovery). - * - * If source == XLOG_FROM_ARCHIVE, the segment is retrieved from archive. - * Otherwise, it's assumed to be already available in pg_wal. - */ -static int -XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli, - XLogSource source, bool notfoundOk) -{ - char xlogfname[MAXFNAMELEN]; - char activitymsg[MAXFNAMELEN + 16]; - char path[MAXPGPATH]; - int fd; - - XLogFileName(xlogfname, tli, segno, wal_segment_size); - - switch (source) - { - case XLOG_FROM_ARCHIVE: - /* Report recovery progress in PS display */ - snprintf(activitymsg, sizeof(activitymsg), "waiting for %s", - xlogfname); - set_ps_display(activitymsg); - - if (!RestoreArchivedFile(path, xlogfname, - "RECOVERYXLOG", - wal_segment_size, - InRedo)) - return -1; - break; - - case XLOG_FROM_PG_WAL: - case XLOG_FROM_STREAM: - XLogFilePath(path, tli, segno, wal_segment_size); - break; - - default: - elog(ERROR, "invalid XLogFileRead source %d", source); - } - - /* - * If the segment was fetched from archival storage, replace the existing - * xlog segment (if any) with the archival version. - */ - if (source == XLOG_FROM_ARCHIVE) - { - Assert(!XLogCtl->InstallXLogFileSegmentActive); - KeepFileRestoredFromArchive(path, xlogfname); - - /* - * Set path to point at the new file in pg_wal. - */ - snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlogfname); - } - - fd = BasicOpenFile(path, O_RDONLY | PG_BINARY); - if (fd >= 0) - { - /* Success! */ - curFileTLI = tli; - - /* Report recovery progress in PS display */ - snprintf(activitymsg, sizeof(activitymsg), "recovering %s", - xlogfname); - set_ps_display(activitymsg); - - /* Track source of data in assorted state variables */ - readSource = source; - XLogReceiptSource = source; - /* In FROM_STREAM case, caller tracks receipt time, not me */ - if (source != XLOG_FROM_STREAM) - XLogReceiptTime = GetCurrentTimestamp(); - - return fd; - } - if (errno != ENOENT || !notfoundOk) /* unexpected failure? */ - ereport(PANIC, - (errcode_for_file_access(), - errmsg("could not open file \"%s\": %m", path))); - return -1; -} - -/* - * Open a logfile segment for reading (during recovery). - * - * This version searches for the segment with any TLI listed in expectedTLEs. - */ -static int -XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source) -{ - char path[MAXPGPATH]; - ListCell *cell; - int fd; - List *tles; - - /* - * Loop looking for a suitable timeline ID: we might need to read any of - * the timelines listed in expectedTLEs. - * - * We expect curFileTLI on entry to be the TLI of the preceding file in - * sequence, or 0 if there was no predecessor. We do not allow curFileTLI - * to go backwards; this prevents us from picking up the wrong file when a - * parent timeline extends to higher segment numbers than the child we - * want to read. - * - * If we haven't read the timeline history file yet, read it now, so that - * we know which TLIs to scan. We don't save the list in expectedTLEs, - * however, unless we actually find a valid segment. That way if there is - * neither a timeline history file nor a WAL segment in the archive, and - * streaming replication is set up, we'll read the timeline history file - * streamed from the primary when we start streaming, instead of - * recovering with a dummy history generated here. - */ - if (expectedTLEs) - tles = expectedTLEs; - else - tles = readTimeLineHistory(recoveryTargetTLI); - - foreach(cell, tles) - { - TimeLineHistoryEntry *hent = (TimeLineHistoryEntry *) lfirst(cell); - TimeLineID tli = hent->tli; - - if (tli < curFileTLI) - break; /* don't bother looking at too-old TLIs */ - - /* - * Skip scanning the timeline ID that the logfile segment to read - * doesn't belong to - */ - if (hent->begin != InvalidXLogRecPtr) - { - XLogSegNo beginseg = 0; - - XLByteToSeg(hent->begin, beginseg, wal_segment_size); - - /* - * The logfile segment that doesn't belong to the timeline is - * older or newer than the segment that the timeline started or - * ended at, respectively. It's sufficient to check only the - * starting segment of the timeline here. Since the timelines are - * scanned in descending order in this loop, any segments newer - * than the ending segment should belong to newer timeline and - * have already been read before. So it's not necessary to check - * the ending segment of the timeline here. - */ - if (segno < beginseg) - continue; - } - - if (source == XLOG_FROM_ANY || source == XLOG_FROM_ARCHIVE) - { - fd = XLogFileRead(segno, emode, tli, - XLOG_FROM_ARCHIVE, true); - if (fd != -1) - { - elog(DEBUG1, "got WAL segment from archive"); - if (!expectedTLEs) - expectedTLEs = tles; - return fd; - } - } - - if (source == XLOG_FROM_ANY || source == XLOG_FROM_PG_WAL) - { - fd = XLogFileRead(segno, emode, tli, - XLOG_FROM_PG_WAL, true); - if (fd != -1) - { - if (!expectedTLEs) - expectedTLEs = tles; - return fd; - } - } - } - - /* Couldn't find it. For simplicity, complain about front timeline */ - XLogFilePath(path, recoveryTargetTLI, segno, wal_segment_size); - errno = ENOENT; - ereport(emode, - (errcode_for_file_access(), - errmsg("could not open file \"%s\": %m", path))); - return -1; -} - /* * Close the current logfile segment for writing. */ @@ -4216,7 +3636,7 @@ RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr lastredoptr, XLogRecPtr endptr, * 'switchpoint' is the current point in WAL where we switch to new timeline, * and 'newTLI' is the new timeline we switch to. */ -static void +void RemoveNonParentXlogFiles(XLogRecPtr switchpoint, TimeLineID newTLI) { DIR *xldir; @@ -4441,261 +3861,6 @@ CleanupBackupHistory(void) FreeDir(xldir); } -/* - * Attempt to read the next XLOG record. - * - * Before first call, the reader needs to be positioned to the first record - * by calling XLogBeginRead(). - * - * If no valid record is available, returns NULL, or fails if emode is PANIC. - * (emode must be either PANIC, LOG). In standby mode, retries until a valid - * record is available. - */ -static XLogRecord * -ReadRecord(XLogReaderState *xlogreader, int emode, - bool fetching_ckpt, TimeLineID replayTLI) -{ - XLogRecord *record; - XLogPageReadPrivate *private = (XLogPageReadPrivate *) xlogreader->private_data; - - /* Pass through parameters to XLogPageRead */ - private->fetching_ckpt = fetching_ckpt; - private->emode = emode; - private->randAccess = (xlogreader->ReadRecPtr == InvalidXLogRecPtr); - private->replayTLI = replayTLI; - - /* This is the first attempt to read this page. */ - lastSourceFailed = false; - - for (;;) - { - char *errormsg; - - record = XLogReadRecord(xlogreader, &errormsg); - if (record == NULL) - { - /* - * When not in standby mode we find that WAL ends in an incomplete - * record, keep track of that record. After recovery is done, - * we'll write a record to indicate downstream WAL readers that - * that portion is to be ignored. - */ - if (!StandbyMode && - !XLogRecPtrIsInvalid(xlogreader->abortedRecPtr)) - { - abortedRecPtr = xlogreader->abortedRecPtr; - missingContrecPtr = xlogreader->missingContrecPtr; - } - - if (readFile >= 0) - { - close(readFile); - readFile = -1; - } - - /* - * We only end up here without a message when XLogPageRead() - * failed - in that case we already logged something. In - * StandbyMode that only happens if we have been triggered, so we - * shouldn't loop anymore in that case. - */ - if (errormsg) - ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), - (errmsg_internal("%s", errormsg) /* already translated */ )); - } - - /* - * Check page TLI is one of the expected values. - */ - else if (!tliInHistory(xlogreader->latestPageTLI, expectedTLEs)) - { - char fname[MAXFNAMELEN]; - XLogSegNo segno; - int32 offset; - - XLByteToSeg(xlogreader->latestPagePtr, segno, wal_segment_size); - offset = XLogSegmentOffset(xlogreader->latestPagePtr, - wal_segment_size); - XLogFileName(fname, xlogreader->seg.ws_tli, segno, - wal_segment_size); - ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), - (errmsg("unexpected timeline ID %u in log segment %s, offset %u", - xlogreader->latestPageTLI, - fname, - offset))); - record = NULL; - } - - if (record) - { - /* Great, got a record */ - return record; - } - else - { - /* No valid record available from this source */ - lastSourceFailed = true; - - /* - * If archive recovery was requested, but we were still doing - * crash recovery, switch to archive recovery and retry using the - * offline archive. We have now replayed all the valid WAL in - * pg_wal, so we are presumably now consistent. - * - * We require that there's at least some valid WAL present in - * pg_wal, however (!fetching_ckpt). We could recover using the - * WAL from the archive, even if pg_wal is completely empty, but - * we'd have no idea how far we'd have to replay to reach - * consistency. So err on the safe side and give up. - */ - if (!InArchiveRecovery && ArchiveRecoveryRequested && - !fetching_ckpt) - { - ereport(DEBUG1, - (errmsg_internal("reached end of WAL in pg_wal, entering archive recovery"))); - InArchiveRecovery = true; - if (StandbyModeRequested) - StandbyMode = true; - - /* initialize minRecoveryPoint to this record */ - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); - ControlFile->state = DB_IN_ARCHIVE_RECOVERY; - if (ControlFile->minRecoveryPoint < xlogreader->EndRecPtr) - { - ControlFile->minRecoveryPoint = xlogreader->EndRecPtr; - ControlFile->minRecoveryPointTLI = replayTLI; - } - /* update local copy */ - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; - - /* - * The startup process can update its local copy of - * minRecoveryPoint from this point. - */ - updateMinRecoveryPoint = true; - - UpdateControlFile(); - - /* - * We update SharedRecoveryState while holding the lock on - * ControlFileLock so both states are consistent in shared - * memory. - */ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE; - SpinLockRelease(&XLogCtl->info_lck); - - LWLockRelease(ControlFileLock); - - CheckRecoveryConsistency(); - - /* - * Before we retry, reset lastSourceFailed and currentSource - * so that we will check the archive next. - */ - lastSourceFailed = false; - currentSource = XLOG_FROM_ANY; - - continue; - } - - /* In standby mode, loop back to retry. Otherwise, give up. */ - if (StandbyMode && !CheckForStandbyTrigger()) - continue; - else - return NULL; - } - } -} - -/* - * Scan for new timelines that might have appeared in the archive since we - * started recovery. - * - * If there are any, the function changes recovery target TLI to the latest - * one and returns 'true'. - */ -static bool -rescanLatestTimeLine(TimeLineID replayTLI, XLogRecPtr replayLSN) -{ - List *newExpectedTLEs; - bool found; - ListCell *cell; - TimeLineID newtarget; - TimeLineID oldtarget = recoveryTargetTLI; - TimeLineHistoryEntry *currentTle = NULL; - - newtarget = findNewestTimeLine(recoveryTargetTLI); - if (newtarget == recoveryTargetTLI) - { - /* No new timelines found */ - return false; - } - - /* - * Determine the list of expected TLIs for the new TLI - */ - - newExpectedTLEs = readTimeLineHistory(newtarget); - - /* - * If the current timeline is not part of the history of the new timeline, - * we cannot proceed to it. - */ - found = false; - foreach(cell, newExpectedTLEs) - { - currentTle = (TimeLineHistoryEntry *) lfirst(cell); - - if (currentTle->tli == recoveryTargetTLI) - { - found = true; - break; - } - } - if (!found) - { - ereport(LOG, - (errmsg("new timeline %u is not a child of database system timeline %u", - newtarget, - replayTLI))); - return false; - } - - /* - * The current timeline was found in the history file, but check that the - * next timeline was forked off from it *after* the current recovery - * location. - */ - if (currentTle->end < replayLSN) - { - ereport(LOG, - (errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%X", - newtarget, - replayTLI, - LSN_FORMAT_ARGS(replayLSN)))); - return false; - } - - /* The new timeline history seems valid. Switch target */ - recoveryTargetTLI = newtarget; - list_free_deep(expectedTLEs); - expectedTLEs = newExpectedTLEs; - - /* - * As in StartupXLOG(), try to ensure we have all the history files - * between the old target and new target in pg_wal. - */ - restoreTimeLineHistoryFiles(oldtarget + 1, newtarget); - - ereport(LOG, - (errmsg("new target timeline is %u", - recoveryTargetTLI))); - - return true; -} - /* * I/O routines for pg_control * @@ -5038,7 +4203,7 @@ ReadControlFile(void) * Utility wrapper to update the control file. Note that the control * file gets flushed. */ -void +static void UpdateControlFile(void) { update_controlfile(DataDir, ControlFile, true); @@ -5316,16 +4481,12 @@ XLOGShmemInit(void) */ XLogCtl->XLogCacheBlck = XLOGbuffers - 1; XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH; - XLogCtl->SharedHotStandbyActive = false; XLogCtl->InstallXLogFileSegmentActive = false; - XLogCtl->SharedPromoteIsTriggered = false; XLogCtl->WalWriterSleeping = false; SpinLockInit(&XLogCtl->Insert.insertpos_lck); SpinLockInit(&XLogCtl->info_lck); SpinLockInit(&XLogCtl->ulsn_lck); - InitSharedLatch(&XLogCtl->recoveryWakeupLatch); - ConditionVariableInit(&XLogCtl->recoveryNotPausedCV); } /* @@ -5511,175 +4672,6 @@ str_time(pg_time_t tnow) return buf; } -/* - * See if there are any recovery signal files and if so, set state for - * recovery. - * - * See if there is a recovery command file (recovery.conf), and if so - * throw an ERROR since as of PG12 we no longer recognize that. - */ -static void -readRecoverySignalFile(void) -{ - struct stat stat_buf; - - if (IsBootstrapProcessingMode()) - return; - - /* - * Check for old recovery API file: recovery.conf - */ - if (stat(RECOVERY_COMMAND_FILE, &stat_buf) == 0) - ereport(FATAL, - (errcode_for_file_access(), - errmsg("using recovery command file \"%s\" is not supported", - RECOVERY_COMMAND_FILE))); - - /* - * Remove unused .done file, if present. Ignore if absent. - */ - unlink(RECOVERY_COMMAND_DONE); - - /* - * Check for recovery signal files and if found, fsync them since they - * represent server state information. We don't sweat too much about the - * possibility of fsync failure, however. - * - * If present, standby signal file takes precedence. If neither is present - * then we won't enter archive recovery. - */ - if (stat(STANDBY_SIGNAL_FILE, &stat_buf) == 0) - { - int fd; - - fd = BasicOpenFilePerm(STANDBY_SIGNAL_FILE, O_RDWR | PG_BINARY, - S_IRUSR | S_IWUSR); - if (fd >= 0) - { - (void) pg_fsync(fd); - close(fd); - } - standby_signal_file_found = true; - } - else if (stat(RECOVERY_SIGNAL_FILE, &stat_buf) == 0) - { - int fd; - - fd = BasicOpenFilePerm(RECOVERY_SIGNAL_FILE, O_RDWR | PG_BINARY, - S_IRUSR | S_IWUSR); - if (fd >= 0) - { - (void) pg_fsync(fd); - close(fd); - } - recovery_signal_file_found = true; - } - - StandbyModeRequested = false; - ArchiveRecoveryRequested = false; - if (standby_signal_file_found) - { - StandbyModeRequested = true; - ArchiveRecoveryRequested = true; - } - else if (recovery_signal_file_found) - { - StandbyModeRequested = false; - ArchiveRecoveryRequested = true; - } - else - return; - - /* - * We don't support standby mode in standalone backends; that requires - * other processes such as the WAL receiver to be alive. - */ - if (StandbyModeRequested && !IsUnderPostmaster) - ereport(FATAL, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("standby mode is not supported by single-user servers"))); -} - -static void -validateRecoveryParameters(void) -{ - if (!ArchiveRecoveryRequested) - return; - - /* - * Check for compulsory parameters - */ - if (StandbyModeRequested) - { - if ((PrimaryConnInfo == NULL || strcmp(PrimaryConnInfo, "") == 0) && - (recoveryRestoreCommand == NULL || strcmp(recoveryRestoreCommand, "") == 0)) - ereport(WARNING, - (errmsg("specified neither primary_conninfo nor restore_command"), - errhint("The database server will regularly poll the pg_wal subdirectory to check for files placed there."))); - } - else - { - if (recoveryRestoreCommand == NULL || - strcmp(recoveryRestoreCommand, "") == 0) - ereport(FATAL, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("must specify restore_command when standby mode is not enabled"))); - } - - /* - * Override any inconsistent requests. Note that this is a change of - * behaviour in 9.5; prior to this we simply ignored a request to pause if - * hot_standby = off, which was surprising behaviour. - */ - if (recoveryTargetAction == RECOVERY_TARGET_ACTION_PAUSE && - !EnableHotStandby) - recoveryTargetAction = RECOVERY_TARGET_ACTION_SHUTDOWN; - - /* - * Final parsing of recovery_target_time string; see also - * check_recovery_target_time(). - */ - if (recoveryTarget == RECOVERY_TARGET_TIME) - { - recoveryTargetTime = DatumGetTimestampTz(DirectFunctionCall3(timestamptz_in, - CStringGetDatum(recovery_target_time_string), - ObjectIdGetDatum(InvalidOid), - Int32GetDatum(-1))); - } - - /* - * If user specified recovery_target_timeline, validate it or compute the - * "latest" value. We can't do this until after we've gotten the restore - * command and set InArchiveRecovery, because we need to fetch timeline - * history files from the archive. - */ - if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_NUMERIC) - { - TimeLineID rtli = recoveryTargetTLIRequested; - - /* Timeline 1 does not have a history file, all else should */ - if (rtli != 1 && !existsTimeLineHistory(rtli)) - ereport(FATAL, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("recovery target timeline %u does not exist", - rtli))); - recoveryTargetTLI = rtli; - } - else if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_LATEST) - { - /* We start the "latest" search from pg_control's timeline */ - recoveryTargetTLI = findNewestTimeLine(recoveryTargetTLI); - } - else - { - /* - * else we just use the recoveryTargetTLI as already read from - * ControlFile - */ - Assert(recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_CONTROLFILE); - } -} - /* * Initialize the first WAL segment on new timeline. */ @@ -5840,752 +4832,6 @@ CleanupAfterArchiveRecovery(TimeLineID EndOfLogTLI, XLogRecPtr EndOfLog, } } -/* - * Extract timestamp from WAL record. - * - * If the record contains a timestamp, returns true, and saves the timestamp - * in *recordXtime. If the record type has no timestamp, returns false. - * Currently, only transaction commit/abort records and restore points contain - * timestamps. - */ -static bool -getRecordTimestamp(XLogReaderState *record, TimestampTz *recordXtime) -{ - uint8 info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; - uint8 xact_info = info & XLOG_XACT_OPMASK; - uint8 rmid = XLogRecGetRmid(record); - - if (rmid == RM_XLOG_ID && info == XLOG_RESTORE_POINT) - { - *recordXtime = ((xl_restore_point *) XLogRecGetData(record))->rp_time; - return true; - } - if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_COMMIT || - xact_info == XLOG_XACT_COMMIT_PREPARED)) - { - *recordXtime = ((xl_xact_commit *) XLogRecGetData(record))->xact_time; - return true; - } - if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_ABORT || - xact_info == XLOG_XACT_ABORT_PREPARED)) - { - *recordXtime = ((xl_xact_abort *) XLogRecGetData(record))->xact_time; - return true; - } - return false; -} - -/* - * For point-in-time recovery, this function decides whether we want to - * stop applying the XLOG before the current record. - * - * Returns true if we are stopping, false otherwise. If stopping, some - * information is saved in recoveryStopXid et al for use in annotating the - * new timeline's history file. - */ -static bool -recoveryStopsBefore(XLogReaderState *record) -{ - bool stopsHere = false; - uint8 xact_info; - bool isCommit; - TimestampTz recordXtime = 0; - TransactionId recordXid; - - /* - * Ignore recovery target settings when not in archive recovery (meaning - * we are in crash recovery). - */ - if (!ArchiveRecoveryRequested) - return false; - - /* Check if we should stop as soon as reaching consistency */ - if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE && reachedConsistency) - { - ereport(LOG, - (errmsg("recovery stopping after reaching consistency"))); - - recoveryStopAfter = false; - recoveryStopXid = InvalidTransactionId; - recoveryStopLSN = InvalidXLogRecPtr; - recoveryStopTime = 0; - recoveryStopName[0] = '\0'; - return true; - } - - /* Check if target LSN has been reached */ - if (recoveryTarget == RECOVERY_TARGET_LSN && - !recoveryTargetInclusive && - record->ReadRecPtr >= recoveryTargetLSN) - { - recoveryStopAfter = false; - recoveryStopXid = InvalidTransactionId; - recoveryStopLSN = record->ReadRecPtr; - recoveryStopTime = 0; - recoveryStopName[0] = '\0'; - ereport(LOG, - (errmsg("recovery stopping before WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); - return true; - } - - /* Otherwise we only consider stopping before COMMIT or ABORT records. */ - if (XLogRecGetRmid(record) != RM_XACT_ID) - return false; - - xact_info = XLogRecGetInfo(record) & XLOG_XACT_OPMASK; - - if (xact_info == XLOG_XACT_COMMIT) - { - isCommit = true; - recordXid = XLogRecGetXid(record); - } - else if (xact_info == XLOG_XACT_COMMIT_PREPARED) - { - xl_xact_commit *xlrec = (xl_xact_commit *) XLogRecGetData(record); - xl_xact_parsed_commit parsed; - - isCommit = true; - ParseCommitRecord(XLogRecGetInfo(record), - xlrec, - &parsed); - recordXid = parsed.twophase_xid; - } - else if (xact_info == XLOG_XACT_ABORT) - { - isCommit = false; - recordXid = XLogRecGetXid(record); - } - else if (xact_info == XLOG_XACT_ABORT_PREPARED) - { - xl_xact_abort *xlrec = (xl_xact_abort *) XLogRecGetData(record); - xl_xact_parsed_abort parsed; - - isCommit = false; - ParseAbortRecord(XLogRecGetInfo(record), - xlrec, - &parsed); - recordXid = parsed.twophase_xid; - } - else - return false; - - if (recoveryTarget == RECOVERY_TARGET_XID && !recoveryTargetInclusive) - { - /* - * There can be only one transaction end record with this exact - * transactionid - * - * when testing for an xid, we MUST test for equality only, since - * transactions are numbered in the order they start, not the order - * they complete. A higher numbered xid will complete before you about - * 50% of the time... - */ - stopsHere = (recordXid == recoveryTargetXid); - } - - if (recoveryTarget == RECOVERY_TARGET_TIME && - getRecordTimestamp(record, &recordXtime)) - { - /* - * There can be many transactions that share the same commit time, so - * we stop after the last one, if we are inclusive, or stop at the - * first one if we are exclusive - */ - if (recoveryTargetInclusive) - stopsHere = (recordXtime > recoveryTargetTime); - else - stopsHere = (recordXtime >= recoveryTargetTime); - } - - if (stopsHere) - { - recoveryStopAfter = false; - recoveryStopXid = recordXid; - recoveryStopTime = recordXtime; - recoveryStopLSN = InvalidXLogRecPtr; - recoveryStopName[0] = '\0'; - - if (isCommit) - { - ereport(LOG, - (errmsg("recovery stopping before commit of transaction %u, time %s", - recoveryStopXid, - timestamptz_to_str(recoveryStopTime)))); - } - else - { - ereport(LOG, - (errmsg("recovery stopping before abort of transaction %u, time %s", - recoveryStopXid, - timestamptz_to_str(recoveryStopTime)))); - } - } - - return stopsHere; -} - -/* - * Same as recoveryStopsBefore, but called after applying the record. - * - * We also track the timestamp of the latest applied COMMIT/ABORT - * record in XLogCtl->recoveryLastXTime. - */ -static bool -recoveryStopsAfter(XLogReaderState *record) -{ - uint8 info; - uint8 xact_info; - uint8 rmid; - TimestampTz recordXtime; - - /* - * Ignore recovery target settings when not in archive recovery (meaning - * we are in crash recovery). - */ - if (!ArchiveRecoveryRequested) - return false; - - info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; - rmid = XLogRecGetRmid(record); - - /* - * There can be many restore points that share the same name; we stop at - * the first one. - */ - if (recoveryTarget == RECOVERY_TARGET_NAME && - rmid == RM_XLOG_ID && info == XLOG_RESTORE_POINT) - { - xl_restore_point *recordRestorePointData; - - recordRestorePointData = (xl_restore_point *) XLogRecGetData(record); - - if (strcmp(recordRestorePointData->rp_name, recoveryTargetName) == 0) - { - recoveryStopAfter = true; - recoveryStopXid = InvalidTransactionId; - recoveryStopLSN = InvalidXLogRecPtr; - (void) getRecordTimestamp(record, &recoveryStopTime); - strlcpy(recoveryStopName, recordRestorePointData->rp_name, MAXFNAMELEN); - - ereport(LOG, - (errmsg("recovery stopping at restore point \"%s\", time %s", - recoveryStopName, - timestamptz_to_str(recoveryStopTime)))); - return true; - } - } - - /* Check if the target LSN has been reached */ - if (recoveryTarget == RECOVERY_TARGET_LSN && - recoveryTargetInclusive && - record->ReadRecPtr >= recoveryTargetLSN) - { - recoveryStopAfter = true; - recoveryStopXid = InvalidTransactionId; - recoveryStopLSN = record->ReadRecPtr; - recoveryStopTime = 0; - recoveryStopName[0] = '\0'; - ereport(LOG, - (errmsg("recovery stopping after WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryStopLSN)))); - return true; - } - - if (rmid != RM_XACT_ID) - return false; - - xact_info = info & XLOG_XACT_OPMASK; - - if (xact_info == XLOG_XACT_COMMIT || - xact_info == XLOG_XACT_COMMIT_PREPARED || - xact_info == XLOG_XACT_ABORT || - xact_info == XLOG_XACT_ABORT_PREPARED) - { - TransactionId recordXid; - - /* Update the last applied transaction timestamp */ - if (getRecordTimestamp(record, &recordXtime)) - SetLatestXTime(recordXtime); - - /* Extract the XID of the committed/aborted transaction */ - if (xact_info == XLOG_XACT_COMMIT_PREPARED) - { - xl_xact_commit *xlrec = (xl_xact_commit *) XLogRecGetData(record); - xl_xact_parsed_commit parsed; - - ParseCommitRecord(XLogRecGetInfo(record), - xlrec, - &parsed); - recordXid = parsed.twophase_xid; - } - else if (xact_info == XLOG_XACT_ABORT_PREPARED) - { - xl_xact_abort *xlrec = (xl_xact_abort *) XLogRecGetData(record); - xl_xact_parsed_abort parsed; - - ParseAbortRecord(XLogRecGetInfo(record), - xlrec, - &parsed); - recordXid = parsed.twophase_xid; - } - else - recordXid = XLogRecGetXid(record); - - /* - * There can be only one transaction end record with this exact - * transactionid - * - * when testing for an xid, we MUST test for equality only, since - * transactions are numbered in the order they start, not the order - * they complete. A higher numbered xid will complete before you about - * 50% of the time... - */ - if (recoveryTarget == RECOVERY_TARGET_XID && recoveryTargetInclusive && - recordXid == recoveryTargetXid) - { - recoveryStopAfter = true; - recoveryStopXid = recordXid; - recoveryStopTime = recordXtime; - recoveryStopLSN = InvalidXLogRecPtr; - recoveryStopName[0] = '\0'; - - if (xact_info == XLOG_XACT_COMMIT || - xact_info == XLOG_XACT_COMMIT_PREPARED) - { - ereport(LOG, - (errmsg("recovery stopping after commit of transaction %u, time %s", - recoveryStopXid, - timestamptz_to_str(recoveryStopTime)))); - } - else if (xact_info == XLOG_XACT_ABORT || - xact_info == XLOG_XACT_ABORT_PREPARED) - { - ereport(LOG, - (errmsg("recovery stopping after abort of transaction %u, time %s", - recoveryStopXid, - timestamptz_to_str(recoveryStopTime)))); - } - return true; - } - } - - /* Check if we should stop as soon as reaching consistency */ - if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE && reachedConsistency) - { - ereport(LOG, - (errmsg("recovery stopping after reaching consistency"))); - - recoveryStopAfter = true; - recoveryStopXid = InvalidTransactionId; - recoveryStopTime = 0; - recoveryStopLSN = InvalidXLogRecPtr; - recoveryStopName[0] = '\0'; - return true; - } - - return false; -} - -/* - * Create a comment for the history file to explain why and where - * timeline changed. - */ -static char * -getRecoveryStopReason(void) -{ - char reason[200]; - - if (recoveryTarget == RECOVERY_TARGET_XID) - snprintf(reason, sizeof(reason), - "%s transaction %u", - recoveryStopAfter ? "after" : "before", - recoveryStopXid); - else if (recoveryTarget == RECOVERY_TARGET_TIME) - snprintf(reason, sizeof(reason), - "%s %s\n", - recoveryStopAfter ? "after" : "before", - timestamptz_to_str(recoveryStopTime)); - else if (recoveryTarget == RECOVERY_TARGET_LSN) - snprintf(reason, sizeof(reason), - "%s LSN %X/%X\n", - recoveryStopAfter ? "after" : "before", - LSN_FORMAT_ARGS(recoveryStopLSN)); - else if (recoveryTarget == RECOVERY_TARGET_NAME) - snprintf(reason, sizeof(reason), - "at restore point \"%s\"", - recoveryStopName); - else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) - snprintf(reason, sizeof(reason), "reached consistency"); - else - snprintf(reason, sizeof(reason), "no recovery target specified"); - - return pstrdup(reason); -} - -/* - * Wait until shared recoveryPauseState is set to RECOVERY_NOT_PAUSED. - * - * endOfRecovery is true if the recovery target is reached and - * the paused state starts at the end of recovery because of - * recovery_target_action=pause, and false otherwise. - */ -static void -recoveryPausesHere(bool endOfRecovery) -{ - /* Don't pause unless users can connect! */ - if (!LocalHotStandbyActive) - return; - - /* Don't pause after standby promotion has been triggered */ - if (LocalPromoteIsTriggered) - return; - - if (endOfRecovery) - ereport(LOG, - (errmsg("pausing at the end of recovery"), - errhint("Execute pg_wal_replay_resume() to promote."))); - else - ereport(LOG, - (errmsg("recovery has paused"), - errhint("Execute pg_wal_replay_resume() to continue."))); - - /* loop until recoveryPauseState is set to RECOVERY_NOT_PAUSED */ - while (GetRecoveryPauseState() != RECOVERY_NOT_PAUSED) - { - HandleStartupProcInterrupts(); - if (CheckForStandbyTrigger()) - return; - - /* - * If recovery pause is requested then set it paused. While we are in - * the loop, user might resume and pause again so set this every time. - */ - ConfirmRecoveryPaused(); - - /* - * We wait on a condition variable that will wake us as soon as the - * pause ends, but we use a timeout so we can check the above exit - * condition periodically too. - */ - ConditionVariableTimedSleep(&XLogCtl->recoveryNotPausedCV, 1000, - WAIT_EVENT_RECOVERY_PAUSE); - } - ConditionVariableCancelSleep(); -} - -/* - * Get the current state of the recovery pause request. - */ -RecoveryPauseState -GetRecoveryPauseState(void) -{ - RecoveryPauseState state; - - SpinLockAcquire(&XLogCtl->info_lck); - state = XLogCtl->recoveryPauseState; - SpinLockRelease(&XLogCtl->info_lck); - - return state; -} - -/* - * Set the recovery pause state. - * - * If recovery pause is requested then sets the recovery pause state to - * 'pause requested' if it is not already 'paused'. Otherwise, sets it - * to 'not paused' to resume the recovery. The recovery pause will be - * confirmed by the ConfirmRecoveryPaused. - */ -void -SetRecoveryPause(bool recoveryPause) -{ - SpinLockAcquire(&XLogCtl->info_lck); - - if (!recoveryPause) - XLogCtl->recoveryPauseState = RECOVERY_NOT_PAUSED; - else if (XLogCtl->recoveryPauseState == RECOVERY_NOT_PAUSED) - XLogCtl->recoveryPauseState = RECOVERY_PAUSE_REQUESTED; - - SpinLockRelease(&XLogCtl->info_lck); - - if (!recoveryPause) - ConditionVariableBroadcast(&XLogCtl->recoveryNotPausedCV); -} - -/* - * Confirm the recovery pause by setting the recovery pause state to - * RECOVERY_PAUSED. - */ -static void -ConfirmRecoveryPaused(void) -{ - /* If recovery pause is requested then set it paused */ - SpinLockAcquire(&XLogCtl->info_lck); - if (XLogCtl->recoveryPauseState == RECOVERY_PAUSE_REQUESTED) - XLogCtl->recoveryPauseState = RECOVERY_PAUSED; - SpinLockRelease(&XLogCtl->info_lck); -} - -/* - * When recovery_min_apply_delay is set, we wait long enough to make sure - * certain record types are applied at least that interval behind the primary. - * - * Returns true if we waited. - * - * Note that the delay is calculated between the WAL record log time and - * the current time on standby. We would prefer to keep track of when this - * standby received each WAL record, which would allow a more consistent - * approach and one not affected by time synchronisation issues, but that - * is significantly more effort and complexity for little actual gain in - * usability. - */ -static bool -recoveryApplyDelay(XLogReaderState *record) -{ - uint8 xact_info; - TimestampTz xtime; - TimestampTz delayUntil; - long msecs; - - /* nothing to do if no delay configured */ - if (recovery_min_apply_delay <= 0) - return false; - - /* no delay is applied on a database not yet consistent */ - if (!reachedConsistency) - return false; - - /* nothing to do if crash recovery is requested */ - if (!ArchiveRecoveryRequested) - return false; - - /* - * Is it a COMMIT record? - * - * We deliberately choose not to delay aborts since they have no effect on - * MVCC. We already allow replay of records that don't have a timestamp, - * so there is already opportunity for issues caused by early conflicts on - * standbys. - */ - if (XLogRecGetRmid(record) != RM_XACT_ID) - return false; - - xact_info = XLogRecGetInfo(record) & XLOG_XACT_OPMASK; - - if (xact_info != XLOG_XACT_COMMIT && - xact_info != XLOG_XACT_COMMIT_PREPARED) - return false; - - if (!getRecordTimestamp(record, &xtime)) - return false; - - delayUntil = TimestampTzPlusMilliseconds(xtime, recovery_min_apply_delay); - - /* - * Exit without arming the latch if it's already past time to apply this - * record - */ - msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(), delayUntil); - if (msecs <= 0) - return false; - - while (true) - { - ResetLatch(&XLogCtl->recoveryWakeupLatch); - - /* - * This might change recovery_min_apply_delay or the trigger file's - * location. - */ - HandleStartupProcInterrupts(); - - if (CheckForStandbyTrigger()) - break; - - /* - * Recalculate delayUntil as recovery_min_apply_delay could have - * changed while waiting in this loop. - */ - delayUntil = TimestampTzPlusMilliseconds(xtime, recovery_min_apply_delay); - - /* - * Wait for difference between GetCurrentTimestamp() and delayUntil. - */ - msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(), - delayUntil); - - if (msecs <= 0) - break; - - elog(DEBUG2, "recovery apply delay %ld milliseconds", msecs); - - (void) WaitLatch(&XLogCtl->recoveryWakeupLatch, - WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH, - msecs, - WAIT_EVENT_RECOVERY_APPLY_DELAY); - } - return true; -} - -/* - * Save timestamp of latest processed commit/abort record. - * - * We keep this in XLogCtl, not a simple static variable, so that it can be - * seen by processes other than the startup process. Note in particular - * that CreateRestartPoint is executed in the checkpointer. - */ -static void -SetLatestXTime(TimestampTz xtime) -{ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->recoveryLastXTime = xtime; - SpinLockRelease(&XLogCtl->info_lck); -} - -/* - * Fetch timestamp of latest processed commit/abort record. - */ -TimestampTz -GetLatestXTime(void) -{ - TimestampTz xtime; - - SpinLockAcquire(&XLogCtl->info_lck); - xtime = XLogCtl->recoveryLastXTime; - SpinLockRelease(&XLogCtl->info_lck); - - return xtime; -} - -/* - * Save timestamp of the next chunk of WAL records to apply. - * - * We keep this in XLogCtl, not a simple static variable, so that it can be - * seen by all backends. - */ -static void -SetCurrentChunkStartTime(TimestampTz xtime) -{ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->currentChunkStartTime = xtime; - SpinLockRelease(&XLogCtl->info_lck); -} - -/* - * Fetch timestamp of latest processed commit/abort record. - * Startup process maintains an accurate local copy in XLogReceiptTime - */ -TimestampTz -GetCurrentChunkReplayStartTime(void) -{ - TimestampTz xtime; - - SpinLockAcquire(&XLogCtl->info_lck); - xtime = XLogCtl->currentChunkStartTime; - SpinLockRelease(&XLogCtl->info_lck); - - return xtime; -} - -/* - * Returns time of receipt of current chunk of XLOG data, as well as - * whether it was received from streaming replication or from archives. - */ -void -GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream) -{ - /* - * This must be executed in the startup process, since we don't export the - * relevant state to shared memory. - */ - Assert(InRecovery); - - *rtime = XLogReceiptTime; - *fromStream = (XLogReceiptSource == XLOG_FROM_STREAM); -} - -/* - * Note that text field supplied is a parameter name and does not require - * translation - */ -static void -RecoveryRequiresIntParameter(const char *param_name, int currValue, int minValue) -{ - if (currValue < minValue) - { - if (LocalHotStandbyActive) - { - bool warned_for_promote = false; - - ereport(WARNING, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("hot standby is not possible because of insufficient parameter settings"), - errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", - param_name, - currValue, - minValue))); - - SetRecoveryPause(true); - - ereport(LOG, - (errmsg("recovery has paused"), - errdetail("If recovery is unpaused, the server will shut down."), - errhint("You can then restart the server after making the necessary configuration changes."))); - - while (GetRecoveryPauseState() != RECOVERY_NOT_PAUSED) - { - HandleStartupProcInterrupts(); - - if (CheckForStandbyTrigger()) - { - if (!warned_for_promote) - ereport(WARNING, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("promotion is not possible because of insufficient parameter settings"), - - /* - * Repeat the detail from above so it's easy to find - * in the log. - */ - errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", - param_name, - currValue, - minValue), - errhint("Restart the server after making the necessary configuration changes."))); - warned_for_promote = true; - } - - /* - * If recovery pause is requested then set it paused. While - * we are in the loop, user might resume and pause again so - * set this every time. - */ - ConfirmRecoveryPaused(); - - /* - * We wait on a condition variable that will wake us as soon - * as the pause ends, but we use a timeout so we can check the - * above conditions periodically too. - */ - ConditionVariableTimedSleep(&XLogCtl->recoveryNotPausedCV, 1000, - WAIT_EVENT_RECOVERY_PAUSE); - } - ConditionVariableCancelSleep(); - } - - ereport(FATAL, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("recovery aborted because of insufficient parameter settings"), - /* Repeat the detail from above so it's easy to find in the log. */ - errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", - param_name, - currValue, - minValue), - errhint("You can restart the server after making the necessary configuration changes."))); - } -} - /* * Check to see if required parameters are set high enough on this server * for various aspects of recovery operation. @@ -6643,26 +4889,17 @@ StartupXLOG(void) XLogCtlInsert *Insert; CheckPoint checkPoint; bool wasShutdown; - bool reachedRecoveryTarget = false; - bool haveBackupLabel = false; - bool haveTblspcMap = false; - XLogRecPtr RecPtr, - LastRec, - checkPointLoc, - EndOfLog; + bool haveTblspcMap; + bool haveBackupLabel; + XLogRecPtr EndOfLog; TimeLineID EndOfLogTLI; - TimeLineID replayTLI, - newTLI; + TimeLineID newTLI; bool performedWalRecovery; - char *recoveryStopReason; - XLogRecord *record; + EndOfWalRecoveryInfo *endOfRecoveryInfo; + XLogRecPtr abortedRecPtr; + XLogRecPtr missingContrecPtr; TransactionId oldestActiveXID; - bool backupEndRequired = false; - bool backupFromStandby = false; - XLogReaderState *xlogreader; - XLogPageReadPrivate private; bool promoted = false; - struct stat st; /* * We should have an aux process resource owner to use, and we should not @@ -6771,432 +5008,17 @@ StartupXLOG(void) SyncDataDirectory(); } - /*---- BEGIN InitWalRecovery ----*/ - /* - * Initialize on the assumption we want to recover to the latest timeline - * that's active according to pg_control. - */ - if (ControlFile->minRecoveryPointTLI > - ControlFile->checkPointCopy.ThisTimeLineID) - recoveryTargetTLI = ControlFile->minRecoveryPointTLI; - else - recoveryTargetTLI = ControlFile->checkPointCopy.ThisTimeLineID; - - /* - * Check for signal files, and if so set up state for offline recovery - */ - readRecoverySignalFile(); - validateRecoveryParameters(); - - if (ArchiveRecoveryRequested) - { - if (StandbyModeRequested) - ereport(LOG, - (errmsg("entering standby mode"))); - else if (recoveryTarget == RECOVERY_TARGET_XID) - ereport(LOG, - (errmsg("starting point-in-time recovery to XID %u", - recoveryTargetXid))); - else if (recoveryTarget == RECOVERY_TARGET_TIME) - ereport(LOG, - (errmsg("starting point-in-time recovery to %s", - timestamptz_to_str(recoveryTargetTime)))); - else if (recoveryTarget == RECOVERY_TARGET_NAME) - ereport(LOG, - (errmsg("starting point-in-time recovery to \"%s\"", - recoveryTargetName))); - else if (recoveryTarget == RECOVERY_TARGET_LSN) - ereport(LOG, - (errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%X\"", - LSN_FORMAT_ARGS(recoveryTargetLSN)))); - else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) - ereport(LOG, - (errmsg("starting point-in-time recovery to earliest consistent point"))); - else - ereport(LOG, - (errmsg("starting archive recovery"))); - } - - /* - * Take ownership of the wakeup latch if we're going to sleep during - * recovery. - */ - if (ArchiveRecoveryRequested) - OwnLatch(&XLogCtl->recoveryWakeupLatch); - - /* Set up XLOG reader facility */ - MemSet(&private, 0, sizeof(XLogPageReadPrivate)); - xlogreader = - XLogReaderAllocate(wal_segment_size, NULL, - XL_ROUTINE(.page_read = &XLogPageRead, - .segment_open = NULL, - .segment_close = wal_segment_close), - &private); - if (!xlogreader) - ereport(ERROR, - (errcode(ERRCODE_OUT_OF_MEMORY), - errmsg("out of memory"), - errdetail("Failed while allocating a WAL reading processor."))); - xlogreader->system_identifier = ControlFile->system_identifier; - - /* - * Allocate two page buffers dedicated to WAL consistency checks. We do - * it this way, rather than just making static arrays, for two reasons: - * (1) no need to waste the storage in most instantiations of the backend; - * (2) a static char array isn't guaranteed to have any particular - * alignment, whereas palloc() will provide MAXALIGN'd storage. - */ - replay_image_masked = (char *) palloc(BLCKSZ); - primary_image_masked = (char *) palloc(BLCKSZ); - - if (read_backup_label(&checkPointLoc, &replayTLI, &backupEndRequired, - &backupFromStandby)) - { - List *tablespaces = NIL; - - /* - * Archive recovery was requested, and thanks to the backup label - * file, we know how far we need to replay to reach consistency. Enter - * archive recovery directly. - */ - InArchiveRecovery = true; - if (StandbyModeRequested) - StandbyMode = true; - - /* - * When a backup_label file is present, we want to roll forward from - * the checkpoint it identifies, rather than using pg_control. - */ - record = ReadCheckpointRecord(xlogreader, checkPointLoc, 0, true, - replayTLI); - if (record != NULL) - { - memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); - wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); - ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(checkPointLoc)))); - InRecovery = true; /* force recovery even if SHUTDOWNED */ - - /* - * Make sure that REDO location exists. This may not be the case - * if there was a crash during an online backup, which left a - * backup_label around that references a WAL segment that's - * already been archived. - */ - if (checkPoint.redo < checkPointLoc) - { - XLogBeginRead(xlogreader, checkPoint.redo); - if (!ReadRecord(xlogreader, LOG, false, - checkPoint.ThisTimeLineID)) - ereport(FATAL, - (errmsg("could not find redo location referenced by checkpoint record"), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir))); - } - } - else - { - ereport(FATAL, - (errmsg("could not locate required checkpoint record"), - errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" and add required recovery options.\n" - "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" - "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", - DataDir, DataDir, DataDir))); - wasShutdown = false; /* keep compiler quiet */ - } - - /* read the tablespace_map file if present and create symlinks. */ - if (read_tablespace_map(&tablespaces)) - { - ListCell *lc; - - foreach(lc, tablespaces) - { - tablespaceinfo *ti = lfirst(lc); - char *linkloc; - - linkloc = psprintf("pg_tblspc/%s", ti->oid); - - /* - * Remove the existing symlink if any and Create the symlink - * under PGDATA. - */ - remove_tablespace_symlink(linkloc); - - if (symlink(ti->path, linkloc) < 0) - ereport(ERROR, - (errcode_for_file_access(), - errmsg("could not create symbolic link \"%s\": %m", - linkloc))); - - pfree(ti->oid); - pfree(ti->path); - pfree(ti); - } - - /* set flag to delete it later */ - haveTblspcMap = true; - } - - /* set flag to delete it later */ - haveBackupLabel = true; - } - else - { - /* - * If tablespace_map file is present without backup_label file, there - * is no use of such file. There is no harm in retaining it, but it - * is better to get rid of the map file so that we don't have any - * redundant file in data directory and it will avoid any sort of - * confusion. It seems prudent though to just rename the file out of - * the way rather than delete it completely, also we ignore any error - * that occurs in rename operation as even if map file is present - * without backup_label file, it is harmless. - */ - if (stat(TABLESPACE_MAP, &st) == 0) - { - unlink(TABLESPACE_MAP_OLD); - if (durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, DEBUG1) == 0) - ereport(LOG, - (errmsg("ignoring file \"%s\" because no file \"%s\" exists", - TABLESPACE_MAP, BACKUP_LABEL_FILE), - errdetail("File \"%s\" was renamed to \"%s\".", - TABLESPACE_MAP, TABLESPACE_MAP_OLD))); - else - ereport(LOG, - (errmsg("ignoring file \"%s\" because no file \"%s\" exists", - TABLESPACE_MAP, BACKUP_LABEL_FILE), - errdetail("Could not rename file \"%s\" to \"%s\": %m.", - TABLESPACE_MAP, TABLESPACE_MAP_OLD))); - } - - /* - * It's possible that archive recovery was requested, but we don't - * know how far we need to replay the WAL before we reach consistency. - * This can happen for example if a base backup is taken from a - * running server using an atomic filesystem snapshot, without calling - * pg_start/stop_backup. Or if you just kill a running primary server - * and put it into archive recovery by creating a recovery signal - * file. - * - * Our strategy in that case is to perform crash recovery first, - * replaying all the WAL present in pg_wal, and only enter archive - * recovery after that. - * - * But usually we already know how far we need to replay the WAL (up - * to minRecoveryPoint, up to backupEndPoint, or until we see an - * end-of-backup record), and we can enter archive recovery directly. - */ - if (ArchiveRecoveryRequested && - (ControlFile->minRecoveryPoint != InvalidXLogRecPtr || - ControlFile->backupEndRequired || - ControlFile->backupEndPoint != InvalidXLogRecPtr || - ControlFile->state == DB_SHUTDOWNED)) - { - InArchiveRecovery = true; - if (StandbyModeRequested) - StandbyMode = true; - } - - /* Get the last valid checkpoint record. */ - checkPointLoc = ControlFile->checkPoint; - RedoStartLSN = ControlFile->checkPointCopy.redo; - replayTLI = ControlFile->checkPointCopy.ThisTimeLineID; - record = ReadCheckpointRecord(xlogreader, checkPointLoc, 1, true, - replayTLI); - if (record != NULL) - { - ereport(DEBUG1, - (errmsg_internal("checkpoint record is at %X/%X", - LSN_FORMAT_ARGS(checkPointLoc)))); - } - else - { - /* - * We used to attempt to go back to a secondary checkpoint record - * here, but only when not in standby mode. We now just fail if we - * can't read the last checkpoint because this allows us to - * simplify processing around checkpoints. - */ - ereport(PANIC, - (errmsg("could not locate a valid checkpoint record"))); - } - memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); - wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); - } - - /* - * If the location of the checkpoint record is not on the expected - * timeline in the history of the requested timeline, we cannot proceed: - * the backup is not part of the history of the requested timeline. - */ - Assert(expectedTLEs); /* was initialized by reading checkpoint - * record */ - if (tliOfPointInHistory(checkPointLoc, expectedTLEs) != - checkPoint.ThisTimeLineID) - { - XLogRecPtr switchpoint; - - /* - * tliSwitchPoint will throw an error if the checkpoint's timeline is - * not in expectedTLEs at all. - */ - switchpoint = tliSwitchPoint(ControlFile->checkPointCopy.ThisTimeLineID, expectedTLEs, NULL); - ereport(FATAL, - (errmsg("requested timeline %u is not a child of this server's history", - recoveryTargetTLI), - errdetail("Latest checkpoint is at %X/%X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%X.", - LSN_FORMAT_ARGS(ControlFile->checkPoint), - ControlFile->checkPointCopy.ThisTimeLineID, - LSN_FORMAT_ARGS(switchpoint)))); - } - - /* - * The min recovery point should be part of the requested timeline's - * history, too. - */ - if (!XLogRecPtrIsInvalid(ControlFile->minRecoveryPoint) && - tliOfPointInHistory(ControlFile->minRecoveryPoint - 1, expectedTLEs) != - ControlFile->minRecoveryPointTLI) - ereport(FATAL, - (errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u", - recoveryTargetTLI, - LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), - ControlFile->minRecoveryPointTLI))); - - LastRec = RecPtr = checkPointLoc; - - ereport(DEBUG1, - (errmsg_internal("redo record is at %X/%X; shutdown %s", - LSN_FORMAT_ARGS(checkPoint.redo), - wasShutdown ? "true" : "false"))); - ereport(DEBUG1, - (errmsg_internal("next transaction ID: " UINT64_FORMAT "; next OID: %u", - U64FromFullTransactionId(checkPoint.nextXid), - checkPoint.nextOid))); - ereport(DEBUG1, - (errmsg_internal("next MultiXactId: %u; next MultiXactOffset: %u", - checkPoint.nextMulti, checkPoint.nextMultiOffset))); - ereport(DEBUG1, - (errmsg_internal("oldest unfrozen transaction ID: %u, in database %u", - checkPoint.oldestXid, checkPoint.oldestXidDB))); - ereport(DEBUG1, - (errmsg_internal("oldest MultiXactId: %u, in database %u", - checkPoint.oldestMulti, checkPoint.oldestMultiDB))); - ereport(DEBUG1, - (errmsg_internal("commit timestamp Xid oldest/newest: %u/%u", - checkPoint.oldestCommitTsXid, - checkPoint.newestCommitTsXid))); - - /* sanity checks on the checkpoint record */ - if (!TransactionIdIsNormal(XidFromFullTransactionId(checkPoint.nextXid))) - ereport(PANIC, - (errmsg("invalid next transaction ID"))); - if (checkPoint.redo > checkPointLoc) - ereport(PANIC, - (errmsg("invalid redo in checkpoint record"))); - - /* - * Check whether we need to force recovery from WAL. If it appears to - * have been a clean shutdown and we did not have a recovery signal file, - * then assume no recovery needed. - */ - if (checkPoint.redo < checkPointLoc) - { - if (wasShutdown) - ereport(PANIC, - (errmsg("invalid redo record in shutdown checkpoint"))); - InRecovery = true; - } - else if (ControlFile->state != DB_SHUTDOWNED) - InRecovery = true; - else if (ArchiveRecoveryRequested) - { - /* force recovery due to presence of recovery signal file */ - InRecovery = true; - } - - /* - * If recovery is needed, update our in-memory copy of pg_control to show - * that we are recovering and to show the selected checkpoint as the place - * we are starting from. We also mark pg_control with any minimum recovery - * stop point obtained from a backup history file. + * Prepare for WAL recovery if needed. * - * We don't write the changes to disk yet, though. Only do that after - * initializing various subsystems. + * InitWalRecovery analyzes the control file and the backup label file, if + * any. It updates the in-memory ControlFile buffer according to the + * starting checkpoint, and sets InRecovery and ArchiveRecoveryRequested. + * It also applies the tablespace map file, if any. */ - if (InRecovery) - { - DBState dbstate_at_startup; - - dbstate_at_startup = ControlFile->state; - if (InArchiveRecovery) - { - ControlFile->state = DB_IN_ARCHIVE_RECOVERY; - } - else - { - ereport(LOG, - (errmsg("database system was not properly shut down; " - "automatic recovery in progress"))); - if (recoveryTargetTLI > ControlFile->checkPointCopy.ThisTimeLineID) - ereport(LOG, - (errmsg("crash recovery starts in timeline %u " - "and has target timeline %u", - ControlFile->checkPointCopy.ThisTimeLineID, - recoveryTargetTLI))); - ControlFile->state = DB_IN_CRASH_RECOVERY; - } - ControlFile->checkPoint = checkPointLoc; - ControlFile->checkPointCopy = checkPoint; - if (InArchiveRecovery) - { - /* initialize minRecoveryPoint if not set yet */ - if (ControlFile->minRecoveryPoint < checkPoint.redo) - { - ControlFile->minRecoveryPoint = checkPoint.redo; - ControlFile->minRecoveryPointTLI = checkPoint.ThisTimeLineID; - } - } - - /* - * Set backupStartPoint if we're starting recovery from a base backup. - * - * Also set backupEndPoint and use minRecoveryPoint as the backup end - * location if we're starting recovery from a base backup which was - * taken from a standby. In this case, the database system status in - * pg_control must indicate that the database was already in recovery. - * Usually that will be DB_IN_ARCHIVE_RECOVERY but also can be - * DB_SHUTDOWNED_IN_RECOVERY if recovery previously was interrupted - * before reaching this point; e.g. because restore_command or - * primary_conninfo were faulty. - * - * Any other state indicates that the backup somehow became corrupted - * and we can't sensibly continue with recovery. - */ - if (haveBackupLabel) - { - ControlFile->backupStartPoint = checkPoint.redo; - ControlFile->backupEndRequired = backupEndRequired; - - if (backupFromStandby) - { - if (dbstate_at_startup != DB_IN_ARCHIVE_RECOVERY && - dbstate_at_startup != DB_SHUTDOWNED_IN_RECOVERY) - ereport(FATAL, - (errmsg("backup_label contains data inconsistent with control file"), - errhint("This means that the backup is corrupted and you will " - "have to use another backup for recovery."))); - ControlFile->backupEndPoint = ControlFile->minRecoveryPoint; - } - } - } - - /*---- END InitWalRecovery ----*/ + InitWalRecovery(ControlFile, &wasShutdown, + &haveBackupLabel, &haveTblspcMap); + checkPoint = ControlFile->checkPointCopy; /* initialize shared memory variables from the checkpoint record */ ShmemVariableCache->nextXid = checkPoint.nextXid; @@ -7272,13 +5094,6 @@ StartupXLOG(void) else XLogCtl->unloggedLSN = FirstNormalUnloggedLSN; - /* - * We must replay WAL entries using the same TimeLineID they were created - * under, so temporarily adopt the TLI indicated by the checkpoint (see - * also xlog_redo()). - */ - replayTLI = checkPoint.ThisTimeLineID; - /* * Copy any missing timeline history files between 'now' and the recovery * target timeline from archive to pg_wal. While we don't need those files @@ -7291,7 +5106,7 @@ StartupXLOG(void) * are small, so it's better to copy them unnecessarily than not copy them * and regret later. */ - restoreTimeLineHistoryFiles(replayTLI, recoveryTargetTLI); + restoreTimeLineHistoryFiles(checkPoint.ThisTimeLineID, recoveryTargetTLI); /* * Before running in recovery, scan pg_twophase and fill in its status to @@ -7308,17 +5123,9 @@ StartupXLOG(void) RedoRecPtr = XLogCtl->RedoRecPtr = XLogCtl->Insert.RedoRecPtr = checkPoint.redo; doPageWrites = lastFullPageWrites; - /* - * Start recovery assuming that the final record isn't lost. - */ - abortedRecPtr = InvalidXLogRecPtr; - missingContrecPtr = InvalidXLogRecPtr; - /* REDO */ if (InRecovery) { - int rmid; - /* Initialize state for RecoveryInProgress() */ SpinLockAcquire(&XLogCtl->info_lck); if (InArchiveRecovery) @@ -7376,13 +5183,13 @@ StartupXLOG(void) */ if (InArchiveRecovery) { - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; } else { - minRecoveryPoint = InvalidXLogRecPtr; - minRecoveryPointTLI = 0; + LocalMinRecoveryPoint = InvalidXLogRecPtr; + LocalMinRecoveryPointTLI = 0; } /* @@ -7473,460 +5280,31 @@ StartupXLOG(void) } } - /*---- BEGIN PerformWalRecovery ----*/ - /* - * Initialize shared variables for tracking progress of WAL replay, as - * if we had just replayed the record before the REDO location (or the - * checkpoint record itself, if it's a shutdown checkpoint). + * We're all set for replaying the WAL now. Do it. */ - SpinLockAcquire(&XLogCtl->info_lck); - if (checkPoint.redo < checkPointLoc) - XLogCtl->replayEndRecPtr = checkPoint.redo; - else - XLogCtl->replayEndRecPtr = xlogreader->EndRecPtr; - XLogCtl->replayEndTLI = replayTLI; - XLogCtl->lastReplayedEndRecPtr = XLogCtl->replayEndRecPtr; - XLogCtl->lastReplayedTLI = XLogCtl->replayEndTLI; - XLogCtl->recoveryLastXTime = 0; - XLogCtl->currentChunkStartTime = 0; - XLogCtl->recoveryPauseState = RECOVERY_NOT_PAUSED; - SpinLockRelease(&XLogCtl->info_lck); - - /* Also ensure XLogReceiptTime has a sane value */ - XLogReceiptTime = GetCurrentTimestamp(); - - /* - * Let postmaster know we've started redo now, so that it can launch - * the archiver if necessary. - */ - if (IsUnderPostmaster) - SendPostmasterSignal(PMSIGNAL_RECOVERY_STARTED); - - /* - * Allow read-only connections immediately if we're consistent - * already. - */ - CheckRecoveryConsistency(); - - /* - * Find the first record that logically follows the checkpoint --- it - * might physically precede it, though. - */ - if (checkPoint.redo < checkPointLoc) - { - /* back up to find the record */ - XLogBeginRead(xlogreader, checkPoint.redo); - record = ReadRecord(xlogreader, PANIC, false, replayTLI); - } - else - { - /* just have to read next record after CheckPoint */ - Assert(RecPtr == checkPointLoc); - record = ReadRecord(xlogreader, LOG, false, replayTLI); - } - - if (record != NULL) - { - ErrorContextCallback errcallback; - TimestampTz xtime; - PGRUsage ru0; - - pg_rusage_init(&ru0); - - InRedo = true; - - /* Initialize resource managers */ - for (rmid = 0; rmid <= RM_MAX_ID; rmid++) - { - if (RmgrTable[rmid].rm_startup != NULL) - RmgrTable[rmid].rm_startup(); - } - - ereport(LOG, - (errmsg("redo starts at %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); - - /* Prepare to report progress of the redo phase. */ - if (!StandbyMode) - begin_startup_progress_phase(); - - /* - * main redo apply loop - */ - do - { - bool switchedTLI = false; - - if (!StandbyMode) - ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%X", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)); - -#ifdef WAL_DEBUG - if (XLOG_DEBUG || - (rmid == RM_XACT_ID && trace_recovery_messages <= DEBUG2) || - (rmid != RM_XACT_ID && trace_recovery_messages <= DEBUG3)) - { - StringInfoData buf; - - initStringInfo(&buf); - appendStringInfo(&buf, "REDO @ %X/%X; LSN %X/%X: ", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), - LSN_FORMAT_ARGS(xlogreader->EndRecPtr)); - xlog_outrec(&buf, xlogreader); - appendStringInfoString(&buf, " - "); - xlog_outdesc(&buf, xlogreader); - elog(LOG, "%s", buf.data); - pfree(buf.data); - } -#endif - - /* Handle interrupt signals of startup process */ - HandleStartupProcInterrupts(); - - /* - * Pause WAL replay, if requested by a hot-standby session via - * SetRecoveryPause(). - * - * Note that we intentionally don't take the info_lck spinlock - * here. We might therefore read a slightly stale value of - * the recoveryPause flag, but it can't be very stale (no - * worse than the last spinlock we did acquire). Since a - * pause request is a pretty asynchronous thing anyway, - * possibly responding to it one WAL record later than we - * otherwise would is a minor issue, so it doesn't seem worth - * adding another spinlock cycle to prevent that. - */ - if (((volatile XLogCtlData *) XLogCtl)->recoveryPauseState != - RECOVERY_NOT_PAUSED) - recoveryPausesHere(false); - - /* - * Have we reached our recovery target? - */ - if (recoveryStopsBefore(xlogreader)) - { - reachedRecoveryTarget = true; - break; - } - - /* - * If we've been asked to lag the primary, wait on latch until - * enough time has passed. - */ - if (recoveryApplyDelay(xlogreader)) - { - /* - * We test for paused recovery again here. If user sets - * delayed apply, it may be because they expect to pause - * recovery in case of problems, so we must test again - * here otherwise pausing during the delay-wait wouldn't - * work. - */ - if (((volatile XLogCtlData *) XLogCtl)->recoveryPauseState != - RECOVERY_NOT_PAUSED) - recoveryPausesHere(false); - } - - /* Setup error traceback support for ereport() */ - errcallback.callback = rm_redo_error_callback; - errcallback.arg = (void *) xlogreader; - errcallback.previous = error_context_stack; - error_context_stack = &errcallback; - - /* - * ShmemVariableCache->nextXid must be beyond record's xid. - */ - AdvanceNextFullTransactionIdPastXid(record->xl_xid); - - /* - * Before replaying this record, check if this record causes - * the current timeline to change. The record is already - * considered to be part of the new timeline, so we update - * replayTLI before replaying it. That's important so that - * replayEndTLI, which is recorded as the minimum recovery - * point's TLI if recovery stops after this record, is set - * correctly. - */ - if (record->xl_rmid == RM_XLOG_ID) - { - TimeLineID newReplayTLI = replayTLI; - TimeLineID prevReplayTLI = replayTLI; - uint8 info = record->xl_info & ~XLR_INFO_MASK; - - if (info == XLOG_CHECKPOINT_SHUTDOWN) - { - CheckPoint checkPoint; - - memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); - newReplayTLI = checkPoint.ThisTimeLineID; - prevReplayTLI = checkPoint.PrevTimeLineID; - } - else if (info == XLOG_END_OF_RECOVERY) - { - xl_end_of_recovery xlrec; - - memcpy(&xlrec, XLogRecGetData(xlogreader), sizeof(xl_end_of_recovery)); - newReplayTLI = xlrec.ThisTimeLineID; - prevReplayTLI = xlrec.PrevTimeLineID; - } - - if (newReplayTLI != replayTLI) - { - /* Check that it's OK to switch to this TLI */ - checkTimeLineSwitch(xlogreader->EndRecPtr, - newReplayTLI, - prevReplayTLI, replayTLI); - - /* Following WAL records should be run with new TLI */ - replayTLI = newReplayTLI; - switchedTLI = true; - } - } - - /* - * Update shared replayEndRecPtr before replaying this record, - * so that XLogFlush will update minRecoveryPoint correctly. - */ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->replayEndRecPtr = xlogreader->EndRecPtr; - XLogCtl->replayEndTLI = replayTLI; - SpinLockRelease(&XLogCtl->info_lck); - - /* - * If we are attempting to enter Hot Standby mode, process - * XIDs we see - */ - if (standbyState >= STANDBY_INITIALIZED && - TransactionIdIsValid(record->xl_xid)) - RecordKnownAssignedTransactionIds(record->xl_xid); - - /* Now apply the WAL record itself */ - RmgrTable[record->xl_rmid].rm_redo(xlogreader); - - /* - * After redo, check whether the backup pages associated with - * the WAL record are consistent with the existing pages. This - * check is done only if consistency check is enabled for this - * record. - */ - if ((record->xl_info & XLR_CHECK_CONSISTENCY) != 0) - checkXLogConsistency(xlogreader); - - /* Pop the error context stack */ - error_context_stack = errcallback.previous; - - /* - * Update lastReplayedEndRecPtr after this record has been - * successfully replayed. - */ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->lastReplayedEndRecPtr = xlogreader->EndRecPtr; - XLogCtl->lastReplayedTLI = replayTLI; - SpinLockRelease(&XLogCtl->info_lck); - - /* - * If rm_redo called XLogRequestWalReceiverReply, then we wake - * up the receiver so that it notices the updated - * lastReplayedEndRecPtr and sends a reply to the primary. - */ - if (doRequestWalReceiverReply) - { - doRequestWalReceiverReply = false; - WalRcvForceReply(); - } - - /* Remember this record as the last-applied one */ - LastRec = xlogreader->ReadRecPtr; - - /* Allow read-only connections if we're consistent now */ - CheckRecoveryConsistency(); - - /* Is this a timeline switch? */ - if (switchedTLI) - { - /* - * Before we continue on the new timeline, clean up any - * (possibly bogus) future WAL segments on the old - * timeline. - */ - RemoveNonParentXlogFiles(xlogreader->EndRecPtr, replayTLI); - - /* - * Wake up any walsenders to notice that we are on a new - * timeline. - */ - if (AllowCascadeReplication()) - WalSndWakeup(); - } - - /* Exit loop if we reached inclusive recovery target */ - if (recoveryStopsAfter(xlogreader)) - { - reachedRecoveryTarget = true; - break; - } - - /* Else, try to fetch the next WAL record */ - record = ReadRecord(xlogreader, LOG, false, replayTLI); - } while (record != NULL); - - /* - * end of main redo apply loop - */ - - if (reachedRecoveryTarget) - { - if (!reachedConsistency) - ereport(FATAL, - (errmsg("requested recovery stop point is before consistent recovery point"))); - - /* - * This is the last point where we can restart recovery with a - * new recovery target, if we shutdown and begin again. After - * this, Resource Managers may choose to do permanent - * corrective actions at end of recovery. - */ - switch (recoveryTargetAction) - { - case RECOVERY_TARGET_ACTION_SHUTDOWN: - - /* - * exit with special return code to request shutdown - * of postmaster. Log messages issued from - * postmaster. - */ - proc_exit(3); - - case RECOVERY_TARGET_ACTION_PAUSE: - SetRecoveryPause(true); - recoveryPausesHere(true); - - /* drop into promote */ - - case RECOVERY_TARGET_ACTION_PROMOTE: - break; - } - } - - /* Allow resource managers to do any required cleanup. */ - for (rmid = 0; rmid <= RM_MAX_ID; rmid++) - { - if (RmgrTable[rmid].rm_cleanup != NULL) - RmgrTable[rmid].rm_cleanup(); - } - - ereport(LOG, - (errmsg("redo done at %X/%X system usage: %s", - LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), - pg_rusage_show(&ru0)))); - xtime = GetLatestXTime(); - if (xtime) - ereport(LOG, - (errmsg("last completed transaction was at log time %s", - timestamptz_to_str(xtime)))); - - InRedo = false; - } - else - { - /* there are no WAL records following the checkpoint */ - ereport(LOG, - (errmsg("redo is not required"))); - - } - - /* - * This check is intentionally after the above log messages that - * indicate how far recovery went. - */ - if (ArchiveRecoveryRequested && - recoveryTarget != RECOVERY_TARGET_UNSET && - !reachedRecoveryTarget) - ereport(FATAL, - (errmsg("recovery ended before configured recovery target was reached"))); - - /*---- END PerformWalRecovery ----*/ + PerformWalRecovery(); performedWalRecovery = true; } - /*---- BEGIN FinishWalRecovery ----*/ - /* - * Kill WAL receiver, if it's still running, before we continue to write - * the startup checkpoint and aborted-contrecord records. It will trump - * over these records and subsequent ones if it's still alive when we - * start writing WAL. + * Finish WAL recovery. */ - XLogShutdownWalRcv(); - - /* - * We are now done reading the xlog from stream. Turn off streaming - * recovery to force fetching the files (which would be required at end of - * recovery, e.g., timeline history file) from archive or pg_wal. - * - * Note that standby mode must be turned off after killing WAL receiver, - * i.e., calling XLogShutdownWalRcv(). - */ - Assert(!WalRcvStreaming()); - StandbyMode = false; - - /* - * Determine where to start writing WAL next. - * - * When recovery ended in an incomplete record, write a WAL record about - * that and continue after it. In all other cases, re-fetch the last - * valid or last applied record, so we can identify the exact endpoint of - * what we consider the valid portion of WAL. - */ - XLogBeginRead(xlogreader, LastRec); - record = ReadRecord(xlogreader, PANIC, false, replayTLI); - EndOfLog = xlogreader->EndRecPtr; - - /* - * EndOfLogTLI is the TLI in the filename of the XLOG segment containing - * the end-of-log. It could be different from the timeline that EndOfLog - * nominally belongs to, if there was a timeline switch in that segment, - * and we were reading the old WAL from a segment belonging to a higher - * timeline. - */ - EndOfLogTLI = xlogreader->seg.ws_tli; - - if (ArchiveRecoveryRequested) - { - /* - * We are no longer in archive recovery state. - * - * We are now done reading the old WAL. Turn off archive fetching if - * it was active. - */ - Assert(InArchiveRecovery); - InArchiveRecovery = false; - - /* - * If the ending log segment is still open, close it (to avoid - * problems on Windows with trying to rename or delete an open file). - */ - if (readFile >= 0) - { - close(readFile); - readFile = -1; - } - } - - recoveryStopReason = getRecoveryStopReason(); - - /*---- END FinishWalRecovery ----*/ + endOfRecoveryInfo = FinishWalRecovery(); + EndOfLog = endOfRecoveryInfo->endOfLog; + EndOfLogTLI = endOfRecoveryInfo->endOfLogTLI; + abortedRecPtr = endOfRecoveryInfo->abortedRecPtr; + missingContrecPtr = endOfRecoveryInfo->missingContrecPtr; /* * Complain if we did not roll forward far enough to render the backup * dump consistent. Note: it is indeed okay to look at the local variable - * minRecoveryPoint here, even though ControlFile->minRecoveryPoint might - * be further ahead --- ControlFile->minRecoveryPoint cannot have been - * advanced beyond the WAL we processed. + * LocalMinRecoveryPoint here, even though ControlFile->minRecoveryPoint + * might be further ahead --- ControlFile->minRecoveryPoint cannot have + * been advanced beyond the WAL we processed. */ if (InRecovery && - (EndOfLog < minRecoveryPoint || + (EndOfLog < LocalMinRecoveryPoint || !XLogRecPtrIsInvalid(ControlFile->backupStartPoint))) { /* @@ -7993,7 +5371,7 @@ StartupXLOG(void) * * In a normal crash recovery, we can just extend the timeline we were in. */ - newTLI = replayTLI; + newTLI = endOfRecoveryInfo->lastRecTLI; if (ArchiveRecoveryRequested) { newTLI = findNewestTimeLine(recoveryTargetTLI) + 1; @@ -8002,8 +5380,8 @@ StartupXLOG(void) /* * Make a writable copy of the last WAL segment. (Note that we also - * have a copy of the last block of the old WAL in readBuf; we will - * use that below.) + * have a copy of the last block of the old WAL in + * endOfRecovery->lastPage; we will use that below.) */ XLogInitNewTimeline(EndOfLogTLI, EndOfLog, newTLI); @@ -8011,10 +5389,10 @@ StartupXLOG(void) * Remove the signal files out of the way, so that we don't * accidentally re-enter archive recovery mode in a subsequent crash. */ - if (standby_signal_file_found) + if (endOfRecoveryInfo->standby_signal_file_found) durable_unlink(STANDBY_SIGNAL_FILE, FATAL); - if (recovery_signal_file_found) + if (endOfRecoveryInfo->recovery_signal_file_found) durable_unlink(RECOVERY_SIGNAL_FILE, FATAL); /* @@ -8028,7 +5406,7 @@ StartupXLOG(void) * between here and writing the end-of-recovery record. */ writeTimeLineHistory(newTLI, recoveryTargetTLI, - EndOfLog, recoveryStopReason); + EndOfLog, endOfRecoveryInfo->recoveryStopReason); ereport(LOG, (errmsg("archive recovery complete"))); @@ -8036,7 +5414,7 @@ StartupXLOG(void) /* Save the selected TimeLineID in shared memory, too */ XLogCtl->InsertTimeLineID = newTLI; - XLogCtl->PrevTimeLineID = replayTLI; + XLogCtl->PrevTimeLineID = endOfRecoveryInfo->lastRecTLI; /* * Actually, if WAL ended in an incomplete record, skip the parts that @@ -8056,11 +5434,11 @@ StartupXLOG(void) * previous incarnation. */ Insert = &XLogCtl->Insert; - Insert->PrevBytePos = XLogRecPtrToBytePos(LastRec); + Insert->PrevBytePos = XLogRecPtrToBytePos(endOfRecoveryInfo->lastRec); Insert->CurrBytePos = XLogRecPtrToBytePos(EndOfLog); /* - * Tricky point here: readBuf contains the *last* block that the LastRec + * Tricky point here: lastPage contains the *last* block that the LastRec * record spans, not the one it starts in. The last block is indeed the * one we want to use. */ @@ -8069,21 +5447,18 @@ StartupXLOG(void) char *page; int len; int firstIdx; - XLogRecPtr pageBeginPtr; - - pageBeginPtr = EndOfLog - (EndOfLog % XLOG_BLCKSZ); - Assert(readOff == XLogSegmentOffset(pageBeginPtr, wal_segment_size)); firstIdx = XLogRecPtrToBufIdx(EndOfLog); + len = EndOfLog - endOfRecoveryInfo->lastPageBeginPtr; + Assert(len < XLOG_BLCKSZ); /* Copy the valid part of the last block, and zero the rest */ page = &XLogCtl->pages[firstIdx * XLOG_BLCKSZ]; - len = EndOfLog % XLOG_BLCKSZ; - memcpy(page, xlogreader->readBuf, len); + memcpy(page, endOfRecoveryInfo->lastPage, XLOG_BLCKSZ); memset(page + len, 0, XLOG_BLCKSZ - len); - XLogCtl->xlblocks[firstIdx] = pageBeginPtr + XLOG_BLCKSZ; - XLogCtl->InitializedUpTo = pageBeginPtr + XLOG_BLCKSZ; + XLogCtl->xlblocks[firstIdx] = endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ; + XLogCtl->InitializedUpTo = endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ; } else { @@ -8138,40 +5513,8 @@ StartupXLOG(void) /* Reload shared-memory state for prepared transactions */ RecoverPreparedTransactions(); - /*---- BEGIN ShutdownWalRecovery ----*/ - /* Shut down xlogreader */ - if (readFile >= 0) - { - close(readFile); - readFile = -1; - } - XLogReaderFree(xlogreader); - - if (ArchiveRecoveryRequested) - { - char recoveryPath[MAXPGPATH]; - - /* - * Since there might be a partial WAL segment named RECOVERYXLOG, get - * rid of it. - */ - snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYXLOG"); - unlink(recoveryPath); /* ignore any error */ - - /* Get rid of any remaining recovered timeline-history file, too */ - snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYHISTORY"); - unlink(recoveryPath); /* ignore any error */ - } - - /* - * We don't need the latch anymore. It's not strictly necessary to disown - * it, but let's do it for the sake of tidiness. - */ - if (ArchiveRecoveryRequested) - DisownLatch(&XLogCtl->recoveryWakeupLatch); - - /*---- END ShutdownWalRecovery ----*/ + ShutdownWalRecovery(); /* Enable WAL writes for this backend only. */ LocalSetXLogInsertAllowed(); @@ -8181,8 +5524,6 @@ StartupXLOG(void) { Assert(!XLogRecPtrIsInvalid(missingContrecPtr)); CreateOverwriteContrecordRecord(abortedRecPtr, missingContrecPtr, newTLI); - abortedRecPtr = InvalidXLogRecPtr; - missingContrecPtr = InvalidXLogRecPtr; } /* @@ -8269,99 +5610,72 @@ StartupXLOG(void) } /* - * Checks if recovery has reached a consistent state. When consistency is - * reached and we have a valid starting standby snapshot, tell postmaster - * that it can start accepting read-only connections. + * Callback from PerformWalRecovery(), called when we switch from crash + * recovery to archive recovery mode. Updates the control file accordingly. */ -static void -CheckRecoveryConsistency(void) +void +SwitchIntoArchiveRecovery(XLogRecPtr EndRecPtr, TimeLineID replayTLI) { - XLogRecPtr lastReplayedEndRecPtr; - - /* - * During crash recovery, we don't reach a consistent state until we've - * replayed all the WAL. - */ - if (XLogRecPtrIsInvalid(minRecoveryPoint)) - return; - - Assert(InArchiveRecovery); - - /* - * assume that we are called in the startup process, and hence don't need - * a lock to read lastReplayedEndRecPtr - */ - lastReplayedEndRecPtr = XLogCtl->lastReplayedEndRecPtr; - - /* - * Have we reached the point where our base backup was completed? - */ - if (!XLogRecPtrIsInvalid(ControlFile->backupEndPoint) && - ControlFile->backupEndPoint <= lastReplayedEndRecPtr) + /* initialize minRecoveryPoint to this record */ + LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); + ControlFile->state = DB_IN_ARCHIVE_RECOVERY; + if (ControlFile->minRecoveryPoint < EndRecPtr) { - /* - * We have reached the end of base backup, as indicated by pg_control. - * The data on disk is now consistent. Reset backupStartPoint and - * backupEndPoint, and update minRecoveryPoint to make sure we don't - * allow starting up at an earlier point even if recovery is stopped - * and restarted soon after this. - */ - elog(DEBUG1, "end of backup reached"); + ControlFile->minRecoveryPoint = EndRecPtr; + ControlFile->minRecoveryPointTLI = replayTLI; + } + /* update local copy */ + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); + /* + * The startup process can update its local copy of minRecoveryPoint from + * this point. + */ + updateMinRecoveryPoint = true; - if (ControlFile->minRecoveryPoint < lastReplayedEndRecPtr) - ControlFile->minRecoveryPoint = lastReplayedEndRecPtr; + UpdateControlFile(); - ControlFile->backupStartPoint = InvalidXLogRecPtr; - ControlFile->backupEndPoint = InvalidXLogRecPtr; - ControlFile->backupEndRequired = false; - UpdateControlFile(); + /* + * We update SharedRecoveryState while holding the lock on ControlFileLock + * so both states are consistent in shared memory. + */ + SpinLockAcquire(&XLogCtl->info_lck); + XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE; + SpinLockRelease(&XLogCtl->info_lck); - LWLockRelease(ControlFileLock); + LWLockRelease(ControlFileLock); +} + +/* + * Callback from PerformWalRecovery(), called when we reach the end of backup. + * Updates the control file accordingly. + */ +void +ReachedEndOfBackup(XLogRecPtr EndRecPtr, TimeLineID tli) +{ + /* + * We have reached the end of base backup, as indicated by pg_control. The + * data on disk is now consistent (unless minRecovery point is further + * ahead, which can happen if we crashed during previous recovery). Reset + * backupStartPoint and backupEndPoint, and update minRecoveryPoint to + * make sure we don't allow starting up at an earlier point even if + * recovery is stopped and restarted soon after this. + */ + LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); + + if (ControlFile->minRecoveryPoint < EndRecPtr) + { + ControlFile->minRecoveryPoint = EndRecPtr; + ControlFile->minRecoveryPointTLI = tli; } - /* - * Have we passed our safe starting point? Note that minRecoveryPoint is - * known to be incorrectly set if ControlFile->backupEndRequired, until - * the XLOG_BACKUP_END arrives to advise us of the correct - * minRecoveryPoint. All we know prior to that is that we're not - * consistent yet. - */ - if (!reachedConsistency && !ControlFile->backupEndRequired && - minRecoveryPoint <= lastReplayedEndRecPtr && - XLogRecPtrIsInvalid(ControlFile->backupStartPoint)) - { - /* - * Check to see if the XLOG sequence contained any unresolved - * references to uninitialized pages. - */ - XLogCheckInvalidPages(); + ControlFile->backupStartPoint = InvalidXLogRecPtr; + ControlFile->backupEndPoint = InvalidXLogRecPtr; + ControlFile->backupEndRequired = false; + UpdateControlFile(); - reachedConsistency = true; - ereport(LOG, - (errmsg("consistent recovery state reached at %X/%X", - LSN_FORMAT_ARGS(lastReplayedEndRecPtr)))); - } - - /* - * Have we got a valid starting snapshot that will allow queries to be - * run? If so, we can tell postmaster that the database is consistent now, - * enabling connections. - */ - if (standbyState == STANDBY_SNAPSHOT_READY && - !LocalHotStandbyActive && - reachedConsistency && - IsUnderPostmaster) - { - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->SharedHotStandbyActive = true; - SpinLockRelease(&XLogCtl->info_lck); - - LocalHotStandbyActive = true; - - SendPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY); - } + LWLockRelease(ControlFileLock); } /* @@ -8393,7 +5707,7 @@ PerformRecoveryXLogAction(void) * fully out of recovery mode and already accepting queries. */ if (ArchiveRecoveryRequested && IsUnderPostmaster && - LocalPromoteIsTriggered) + PromoteIsTriggered()) { promoted = true; @@ -8472,47 +5786,6 @@ GetRecoveryState(void) return retval; } -/* - * Is HotStandby active yet? This is only important in special backends - * since normal backends won't ever be able to connect until this returns - * true. Postmaster knows this by way of signal, not via shared memory. - * - * Unlike testing standbyState, this works in any process that's connected to - * shared memory. (And note that standbyState alone doesn't tell the truth - * anyway.) - */ -bool -HotStandbyActive(void) -{ - /* - * We check shared state each time only until Hot Standby is active. We - * can't de-activate Hot Standby, so there's no need to keep checking - * after the shared variable has once been seen true. - */ - if (LocalHotStandbyActive) - return true; - else - { - /* spinlock is essential on machines with weak memory ordering! */ - SpinLockAcquire(&XLogCtl->info_lck); - LocalHotStandbyActive = XLogCtl->SharedHotStandbyActive; - SpinLockRelease(&XLogCtl->info_lck); - - return LocalHotStandbyActive; - } -} - -/* - * Like HotStandbyActive(), but to be used only in WAL replay code, - * where we don't need to ask any other process what the state is. - */ -bool -HotStandbyActiveInReplay(void) -{ - Assert(AmStartupProcess() || !IsPostmasterEnvironment); - return LocalHotStandbyActive; -} - /* * Is this process allowed to insert new WAL records? * @@ -8563,109 +5836,6 @@ LocalSetXLogInsertAllowed(void) return oldXLogAllowed; } -/* - * Subroutine to try to fetch and validate a prior checkpoint record. - * - * whichChkpt identifies the checkpoint (merely for reporting purposes). - * 1 for "primary", 0 for "other" (backup_label) - */ -static XLogRecord * -ReadCheckpointRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, - int whichChkpt, bool report, TimeLineID replayTLI) -{ - XLogRecord *record; - uint8 info; - - if (!XRecOffIsValid(RecPtr)) - { - if (!report) - return NULL; - - switch (whichChkpt) - { - case 1: - ereport(LOG, - (errmsg("invalid primary checkpoint link in control file"))); - break; - default: - ereport(LOG, - (errmsg("invalid checkpoint link in backup_label file"))); - break; - } - return NULL; - } - - XLogBeginRead(xlogreader, RecPtr); - record = ReadRecord(xlogreader, LOG, true, replayTLI); - - if (record == NULL) - { - if (!report) - return NULL; - - switch (whichChkpt) - { - case 1: - ereport(LOG, - (errmsg("invalid primary checkpoint record"))); - break; - default: - ereport(LOG, - (errmsg("invalid checkpoint record"))); - break; - } - return NULL; - } - if (record->xl_rmid != RM_XLOG_ID) - { - switch (whichChkpt) - { - case 1: - ereport(LOG, - (errmsg("invalid resource manager ID in primary checkpoint record"))); - break; - default: - ereport(LOG, - (errmsg("invalid resource manager ID in checkpoint record"))); - break; - } - return NULL; - } - info = record->xl_info & ~XLR_INFO_MASK; - if (info != XLOG_CHECKPOINT_SHUTDOWN && - info != XLOG_CHECKPOINT_ONLINE) - { - switch (whichChkpt) - { - case 1: - ereport(LOG, - (errmsg("invalid xl_info in primary checkpoint record"))); - break; - default: - ereport(LOG, - (errmsg("invalid xl_info in checkpoint record"))); - break; - } - return NULL; - } - if (record->xl_tot_len != SizeOfXLogRecord + SizeOfXLogRecordDataHeaderShort + sizeof(CheckPoint)) - { - switch (whichChkpt) - { - case 1: - ereport(LOG, - (errmsg("invalid length of primary checkpoint record"))); - break; - default: - ereport(LOG, - (errmsg("invalid length of checkpoint record"))); - break; - } - return NULL; - } - return record; -} - /* * Return the current Redo pointer from shared memory. * @@ -9849,8 +7019,8 @@ CreateRestartPoint(int flags) ControlFile->minRecoveryPointTLI = lastCheckPoint.ThisTimeLineID; /* update local copy */ - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; } if (flags & CHECKPOINT_IS_SHUTDOWN) ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY; @@ -10313,67 +7483,20 @@ UpdateFullPageWrites(void) END_CRIT_SECTION(); } -/* - * Check that it's OK to switch to new timeline during recovery. - * - * 'lsn' is the address of the shutdown checkpoint record we're about to - * replay. (Currently, timeline can only change at a shutdown checkpoint). - */ -static void -checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI, - TimeLineID replayTLI) -{ - /* Check that the record agrees on what the current (old) timeline is */ - if (prevTLI != replayTLI) - ereport(PANIC, - (errmsg("unexpected previous timeline ID %u (current timeline ID %u) in checkpoint record", - prevTLI, replayTLI))); - - /* - * The new timeline better be in the list of timelines we expect to see, - * according to the timeline history. It should also not decrease. - */ - if (newTLI < replayTLI || !tliInHistory(newTLI, expectedTLEs)) - ereport(PANIC, - (errmsg("unexpected timeline ID %u (after %u) in checkpoint record", - newTLI, replayTLI))); - - /* - * If we have not yet reached min recovery point, and we're about to - * switch to a timeline greater than the timeline of the min recovery - * point: trouble. After switching to the new timeline, we could not - * possibly visit the min recovery point on the correct timeline anymore. - * This can happen if there is a newer timeline in the archive that - * branched before the timeline the min recovery point is on, and you - * attempt to do PITR to the new timeline. - */ - if (!XLogRecPtrIsInvalid(minRecoveryPoint) && - lsn < minRecoveryPoint && - newTLI > minRecoveryPointTLI) - ereport(PANIC, - (errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u", - newTLI, - LSN_FORMAT_ARGS(minRecoveryPoint), - minRecoveryPointTLI))); - - /* Looks good */ -} - /* * XLOG resource manager's routines * * Definitions of info values are in include/catalog/pg_control.h, though * not all record types are related to control file updates. + * + * NOTE: Some XLOG record types that are directly related to WAL recovery + * are handled in xlogrecovery_redo(). */ void xlog_redo(XLogReaderState *record) { uint8 info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; XLogRecPtr lsn = record->EndRecPtr; - TimeLineID replayTLI; - - /* No other process can change this, so we can read it without a lock. */ - replayTLI = XLogCtl->replayEndTLI; /* * In XLOG rmgr, backup blocks are only used by XLOG_FPI and @@ -10402,6 +7525,7 @@ xlog_redo(XLogReaderState *record) else if (info == XLOG_CHECKPOINT_SHUTDOWN) { CheckPoint checkPoint; + TimeLineID replayTLI; memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint)); /* In a SHUTDOWN checkpoint, believe the counters exactly */ @@ -10487,6 +7611,7 @@ xlog_redo(XLogReaderState *record) * We should've already switched to the new TLI before replaying this * record. */ + (void) GetCurrentReplayRecPtr(&replayTLI); if (checkPoint.ThisTimeLineID != replayTLI) ereport(PANIC, (errmsg("unexpected timeline ID %u (should be %u) in shutdown checkpoint record", @@ -10497,6 +7622,7 @@ xlog_redo(XLogReaderState *record) else if (info == XLOG_CHECKPOINT_ONLINE) { CheckPoint checkPoint; + TimeLineID replayTLI; memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint)); /* In an ONLINE checkpoint, treat the XID counter as a minimum */ @@ -10543,6 +7669,7 @@ xlog_redo(XLogReaderState *record) SpinLockRelease(&XLogCtl->info_lck); /* TLI should not change in an on-line checkpoint */ + (void) GetCurrentReplayRecPtr(&replayTLI); if (checkPoint.ThisTimeLineID != replayTLI) ereport(PANIC, (errmsg("unexpected timeline ID %u (should be %u) in online checkpoint record", @@ -10552,14 +7679,12 @@ xlog_redo(XLogReaderState *record) } else if (info == XLOG_OVERWRITE_CONTRECORD) { - xl_overwrite_contrecord xlrec; - - memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_overwrite_contrecord)); - VerifyOverwriteContrecord(&xlrec, record); + /* nothing to do here, handled in xlogrecovery_redo() */ } else if (info == XLOG_END_OF_RECOVERY) { xl_end_of_recovery xlrec; + TimeLineID replayTLI; memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_end_of_recovery)); @@ -10573,6 +7698,7 @@ xlog_redo(XLogReaderState *record) * We should've already switched to the new TLI before replaying this * record. */ + (void) GetCurrentReplayRecPtr(&replayTLI); if (xlrec.ThisTimeLineID != replayTLI) ereport(PANIC, (errmsg("unexpected timeline ID %u (should be %u) in end-of-recovery record", @@ -10588,7 +7714,7 @@ xlog_redo(XLogReaderState *record) } else if (info == XLOG_RESTORE_POINT) { - /* nothing to do here */ + /* nothing to do here, handled in xlogrecovery.c */ } else if (info == XLOG_FPI || info == XLOG_FPI_FOR_HINT) { @@ -10626,34 +7752,7 @@ xlog_redo(XLogReaderState *record) } else if (info == XLOG_BACKUP_END) { - XLogRecPtr startpoint; - - memcpy(&startpoint, XLogRecGetData(record), sizeof(startpoint)); - - if (ControlFile->backupStartPoint == startpoint) - { - /* - * We have reached the end of base backup, the point where - * pg_stop_backup() was done. The data on disk is now consistent. - * Reset backupStartPoint, and update minRecoveryPoint to make - * sure we don't allow starting up at an earlier point even if - * recovery is stopped and restarted soon after this. - */ - elog(DEBUG1, "end of backup reached"); - - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); - - if (ControlFile->minRecoveryPoint < lsn) - { - ControlFile->minRecoveryPoint = lsn; - ControlFile->minRecoveryPointTLI = replayTLI; - } - ControlFile->backupStartPoint = InvalidXLogRecPtr; - ControlFile->backupEndRequired = false; - UpdateControlFile(); - - LWLockRelease(ControlFileLock); - } + /* nothing to do here, handled in xlogrecovery_redo() */ } else if (info == XLOG_PARAMETER_CHANGE) { @@ -10681,11 +7780,14 @@ xlog_redo(XLogReaderState *record) */ if (InArchiveRecovery) { - minRecoveryPoint = ControlFile->minRecoveryPoint; - minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + LocalMinRecoveryPoint = ControlFile->minRecoveryPoint; + LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI; } - if (minRecoveryPoint != InvalidXLogRecPtr && minRecoveryPoint < lsn) + if (LocalMinRecoveryPoint != InvalidXLogRecPtr && LocalMinRecoveryPoint < lsn) { + TimeLineID replayTLI; + + (void) GetCurrentReplayRecPtr(&replayTLI); ControlFile->minRecoveryPoint = lsn; ControlFile->minRecoveryPointTLI = replayTLI; } @@ -10724,102 +7826,6 @@ xlog_redo(XLogReaderState *record) } } -/* - * Verify the payload of a XLOG_OVERWRITE_CONTRECORD record. - */ -static void -VerifyOverwriteContrecord(xl_overwrite_contrecord *xlrec, XLogReaderState *state) -{ - if (xlrec->overwritten_lsn != state->overwrittenRecPtr) - elog(FATAL, "mismatching overwritten LSN %X/%X -> %X/%X", - LSN_FORMAT_ARGS(xlrec->overwritten_lsn), - LSN_FORMAT_ARGS(state->overwrittenRecPtr)); - - ereport(LOG, - (errmsg("successfully skipped missing contrecord at %X/%X, overwritten at %s", - LSN_FORMAT_ARGS(xlrec->overwritten_lsn), - timestamptz_to_str(xlrec->overwrite_time)))); - - /* Verifying the record should only happen once */ - state->overwrittenRecPtr = InvalidXLogRecPtr; -} - -#ifdef WAL_DEBUG - -static void -xlog_outrec(StringInfo buf, XLogReaderState *record) -{ - appendStringInfo(buf, "prev %X/%X; xid %u", - LSN_FORMAT_ARGS(XLogRecGetPrev(record)), - XLogRecGetXid(record)); - - appendStringInfo(buf, "; len %u", - XLogRecGetDataLen(record)); - - xlog_block_info(buf, record); -} -#endif /* WAL_DEBUG */ - -/* - * Returns a string giving information about all the blocks in an - * XLogRecord. - */ -static void -xlog_block_info(StringInfo buf, XLogReaderState *record) -{ - int block_id; - - /* decode block references */ - for (block_id = 0; block_id <= record->max_block_id; block_id++) - { - RelFileNode rnode; - ForkNumber forknum; - BlockNumber blk; - - if (!XLogRecHasBlockRef(record, block_id)) - continue; - - XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blk); - if (forknum != MAIN_FORKNUM) - appendStringInfo(buf, "; blkref #%d: rel %u/%u/%u, fork %u, blk %u", - block_id, - rnode.spcNode, rnode.dbNode, rnode.relNode, - forknum, - blk); - else - appendStringInfo(buf, "; blkref #%d: rel %u/%u/%u, blk %u", - block_id, - rnode.spcNode, rnode.dbNode, rnode.relNode, - blk); - if (XLogRecHasBlockImage(record, block_id)) - appendStringInfoString(buf, " FPW"); - } -} - -/* - * Returns a string describing an XLogRecord, consisting of its identity - * optionally followed by a colon, a space, and a further description. - */ -static void -xlog_outdesc(StringInfo buf, XLogReaderState *record) -{ - RmgrId rmid = XLogRecGetRmid(record); - uint8 info = XLogRecGetInfo(record); - const char *id; - - appendStringInfoString(buf, RmgrTable[rmid].rm_name); - appendStringInfoChar(buf, '/'); - - id = RmgrTable[rmid].rm_identify(info); - if (id == NULL) - appendStringInfo(buf, "UNKNOWN (%X): ", info & ~XLR_INFO_MASK); - else - appendStringInfo(buf, "%s: ", id); - - RmgrTable[rmid].rm_desc(buf, record); -} - - /* * Return the (possible) sync flag used for opening a file, depending on the * value of the GUC wal_sync_method. @@ -12024,27 +9030,6 @@ register_persistent_abort_backup_handler(void) already_done = true; } -/* - * Get latest redo apply position. - * - * Exported to allow WALReceiver to read the pointer directly. - */ -XLogRecPtr -GetXLogReplayRecPtr(TimeLineID *replayTLI) -{ - XLogRecPtr recptr; - TimeLineID tli; - - SpinLockAcquire(&XLogCtl->info_lck); - recptr = XLogCtl->lastReplayedEndRecPtr; - tli = XLogCtl->lastReplayedTLI; - SpinLockRelease(&XLogCtl->info_lck); - - if (replayTLI) - *replayTLI = tli; - return recptr; -} - /* * Get latest WAL insert pointer */ @@ -12087,262 +9072,6 @@ GetOldestRestartPoint(XLogRecPtr *oldrecptr, TimeLineID *oldtli) LWLockRelease(ControlFileLock); } -/* - * read_backup_label: check to see if a backup_label file is present - * - * If we see a backup_label during recovery, we assume that we are recovering - * from a backup dump file, and we therefore roll forward from the checkpoint - * identified by the label file, NOT what pg_control says. This avoids the - * problem that pg_control might have been archived one or more checkpoints - * later than the start of the dump, and so if we rely on it as the start - * point, we will fail to restore a consistent database state. - * - * Returns true if a backup_label was found (and fills the checkpoint - * location and TLI into *checkPointLoc and *backupLabelTLI, respectively); - * returns false if not. If this backup_label came from a streamed backup, - * *backupEndRequired is set to true. If this backup_label was created during - * recovery, *backupFromStandby is set to true. - * - * Also sets the global variable RedoStartLSN with the LSN read from the - * backup file. - */ -static bool -read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, - bool *backupEndRequired, bool *backupFromStandby) -{ - char startxlogfilename[MAXFNAMELEN]; - TimeLineID tli_from_walseg, - tli_from_file; - FILE *lfp; - char ch; - char backuptype[20]; - char backupfrom[20]; - char backuplabel[MAXPGPATH]; - char backuptime[128]; - uint32 hi, - lo; - - /* suppress possible uninitialized-variable warnings */ - *checkPointLoc = InvalidXLogRecPtr; - *backupLabelTLI = 0; - *backupEndRequired = false; - *backupFromStandby = false; - - /* - * See if label file is present - */ - lfp = AllocateFile(BACKUP_LABEL_FILE, "r"); - if (!lfp) - { - if (errno != ENOENT) - ereport(FATAL, - (errcode_for_file_access(), - errmsg("could not read file \"%s\": %m", - BACKUP_LABEL_FILE))); - return false; /* it's not there, all is fine */ - } - - /* - * Read and parse the START WAL LOCATION and CHECKPOINT lines (this code - * is pretty crude, but we are not expecting any variability in the file - * format). - */ - if (fscanf(lfp, "START WAL LOCATION: %X/%X (file %08X%16s)%c", - &hi, &lo, &tli_from_walseg, startxlogfilename, &ch) != 5 || ch != '\n') - ereport(FATAL, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); - RedoStartLSN = ((uint64) hi) << 32 | lo; - if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%X%c", - &hi, &lo, &ch) != 3 || ch != '\n') - ereport(FATAL, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); - *checkPointLoc = ((uint64) hi) << 32 | lo; - - /* - * BACKUP METHOD and BACKUP FROM lines are new in 9.2. We can't restore - * from an older backup anyway, but since the information on it is not - * strictly required, don't error out if it's missing for some reason. - */ - if (fscanf(lfp, "BACKUP METHOD: %19s\n", backuptype) == 1) - { - if (strcmp(backuptype, "streamed") == 0) - *backupEndRequired = true; - } - - if (fscanf(lfp, "BACKUP FROM: %19s\n", backupfrom) == 1) - { - if (strcmp(backupfrom, "standby") == 0) - *backupFromStandby = true; - } - - /* - * Parse START TIME and LABEL. Those are not mandatory fields for recovery - * but checking for their presence is useful for debugging and the next - * sanity checks. Cope also with the fact that the result buffers have a - * pre-allocated size, hence if the backup_label file has been generated - * with strings longer than the maximum assumed here an incorrect parsing - * happens. That's fine as only minor consistency checks are done - * afterwards. - */ - if (fscanf(lfp, "START TIME: %127[^\n]\n", backuptime) == 1) - ereport(DEBUG1, - (errmsg_internal("backup time %s in file \"%s\"", - backuptime, BACKUP_LABEL_FILE))); - - if (fscanf(lfp, "LABEL: %1023[^\n]\n", backuplabel) == 1) - ereport(DEBUG1, - (errmsg_internal("backup label %s in file \"%s\"", - backuplabel, BACKUP_LABEL_FILE))); - - /* - * START TIMELINE is new as of 11. Its parsing is not mandatory, still use - * it as a sanity check if present. - */ - if (fscanf(lfp, "START TIMELINE: %u\n", &tli_from_file) == 1) - { - if (tli_from_walseg != tli_from_file) - ereport(FATAL, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE), - errdetail("Timeline ID parsed is %u, but expected %u.", - tli_from_file, tli_from_walseg))); - - ereport(DEBUG1, - (errmsg_internal("backup timeline %u in file \"%s\"", - tli_from_file, BACKUP_LABEL_FILE))); - } - - if (ferror(lfp) || FreeFile(lfp)) - ereport(FATAL, - (errcode_for_file_access(), - errmsg("could not read file \"%s\": %m", - BACKUP_LABEL_FILE))); - - *backupLabelTLI = tli_from_walseg; - - return true; -} - -/* - * read_tablespace_map: check to see if a tablespace_map file is present - * - * If we see a tablespace_map file during recovery, we assume that we are - * recovering from a backup dump file, and we therefore need to create symlinks - * as per the information present in tablespace_map file. - * - * Returns true if a tablespace_map file was found (and fills *tablespaces - * with a tablespaceinfo struct for each tablespace listed in the file); - * returns false if not. - */ -static bool -read_tablespace_map(List **tablespaces) -{ - tablespaceinfo *ti; - FILE *lfp; - char str[MAXPGPATH]; - int ch, - i, - n; - bool was_backslash; - - /* - * See if tablespace_map file is present - */ - lfp = AllocateFile(TABLESPACE_MAP, "r"); - if (!lfp) - { - if (errno != ENOENT) - ereport(FATAL, - (errcode_for_file_access(), - errmsg("could not read file \"%s\": %m", - TABLESPACE_MAP))); - return false; /* it's not there, all is fine */ - } - - /* - * Read and parse the link name and path lines from tablespace_map file - * (this code is pretty crude, but we are not expecting any variability in - * the file format). De-escape any backslashes that were inserted. - */ - i = 0; - was_backslash = false; - while ((ch = fgetc(lfp)) != EOF) - { - if (!was_backslash && (ch == '\n' || ch == '\r')) - { - if (i == 0) - continue; /* \r immediately followed by \n */ - - /* - * The de-escaped line should contain an OID followed by exactly - * one space followed by a path. The path might start with - * spaces, so don't be too liberal about parsing. - */ - str[i] = '\0'; - n = 0; - while (str[n] && str[n] != ' ') - n++; - if (n < 1 || n >= i - 1) - ereport(FATAL, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("invalid data in file \"%s\"", TABLESPACE_MAP))); - str[n++] = '\0'; - - ti = palloc0(sizeof(tablespaceinfo)); - ti->oid = pstrdup(str); - ti->path = pstrdup(str + n); - *tablespaces = lappend(*tablespaces, ti); - - i = 0; - continue; - } - else if (!was_backslash && ch == '\\') - was_backslash = true; - else - { - if (i < sizeof(str) - 1) - str[i++] = ch; - was_backslash = false; - } - } - - if (i != 0 || was_backslash) /* last line not terminated? */ - ereport(FATAL, - (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), - errmsg("invalid data in file \"%s\"", TABLESPACE_MAP))); - - if (ferror(lfp) || FreeFile(lfp)) - ereport(FATAL, - (errcode_for_file_access(), - errmsg("could not read file \"%s\": %m", - TABLESPACE_MAP))); - - return true; -} - -/* - * Error context callback for errors occurring during rm_redo(). - */ -static void -rm_redo_error_callback(void *arg) -{ - XLogReaderState *record = (XLogReaderState *) arg; - StringInfoData buf; - - initStringInfo(&buf); - xlog_outdesc(&buf, record); - xlog_block_info(&buf, record); - - /* translator: %s is a WAL record description */ - errcontext("WAL redo at %X/%X for %s", - LSN_FORMAT_ARGS(record->ReadRecPtr), - buf.data); - - pfree(buf.data); -} - /* * BackupInProgress: check if online backup mode is active * @@ -12424,715 +9153,8 @@ CancelBackup(void) } } -/* - * Read the XLOG page containing RecPtr into readBuf (if not read already). - * Returns number of bytes read, if the page is read successfully, or -1 - * in case of errors. When errors occur, they are ereport'ed, but only - * if they have not been previously reported. - * - * This is responsible for restoring files from archive as needed, as well - * as for waiting for the requested WAL record to arrive in standby mode. - * - * 'emode' specifies the log level used for reporting "file not found" or - * "end of WAL" situations in archive recovery, or in standby mode when a - * trigger file is found. If set to WARNING or below, XLogPageRead() returns - * false in those situations, on higher log levels the ereport() won't - * return. - * - * In standby mode, if after a successful return of XLogPageRead() the - * caller finds the record it's interested in to be broken, it should - * ereport the error with the level determined by - * emode_for_corrupt_record(), and then set lastSourceFailed - * and call XLogPageRead() again with the same arguments. This lets - * XLogPageRead() to try fetching the record from another source, or to - * sleep and retry. - */ -static int -XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, int reqLen, - XLogRecPtr targetRecPtr, char *readBuf) -{ - XLogPageReadPrivate *private = - (XLogPageReadPrivate *) xlogreader->private_data; - int emode = private->emode; - uint32 targetPageOff; - XLogSegNo targetSegNo PG_USED_FOR_ASSERTS_ONLY; - int r; - - XLByteToSeg(targetPagePtr, targetSegNo, wal_segment_size); - targetPageOff = XLogSegmentOffset(targetPagePtr, wal_segment_size); - - /* - * See if we need to switch to a new segment because the requested record - * is not in the currently open one. - */ - if (readFile >= 0 && - !XLByteInSeg(targetPagePtr, readSegNo, wal_segment_size)) - { - /* - * Request a restartpoint if we've replayed too much xlog since the - * last one. - */ - if (ArchiveRecoveryRequested && IsUnderPostmaster) - { - if (XLogCheckpointNeeded(readSegNo)) - { - (void) GetRedoRecPtr(); - if (XLogCheckpointNeeded(readSegNo)) - RequestCheckpoint(CHECKPOINT_CAUSE_XLOG); - } - } - - close(readFile); - readFile = -1; - readSource = XLOG_FROM_ANY; - } - - XLByteToSeg(targetPagePtr, readSegNo, wal_segment_size); - -retry: - /* See if we need to retrieve more data */ - if (readFile < 0 || - (readSource == XLOG_FROM_STREAM && - flushedUpto < targetPagePtr + reqLen)) - { - if (!WaitForWALToBecomeAvailable(targetPagePtr + reqLen, - private->randAccess, - private->fetching_ckpt, - targetRecPtr, - private->replayTLI, - xlogreader->EndRecPtr)) - { - if (readFile >= 0) - close(readFile); - readFile = -1; - readLen = 0; - readSource = XLOG_FROM_ANY; - - return -1; - } - } - - /* - * At this point, we have the right segment open and if we're streaming we - * know the requested record is in it. - */ - Assert(readFile != -1); - - /* - * If the current segment is being streamed from the primary, calculate - * how much of the current page we have received already. We know the - * requested record has been received, but this is for the benefit of - * future calls, to allow quick exit at the top of this function. - */ - if (readSource == XLOG_FROM_STREAM) - { - if (((targetPagePtr) / XLOG_BLCKSZ) != (flushedUpto / XLOG_BLCKSZ)) - readLen = XLOG_BLCKSZ; - else - readLen = XLogSegmentOffset(flushedUpto, wal_segment_size) - - targetPageOff; - } - else - readLen = XLOG_BLCKSZ; - - /* Read the requested page */ - readOff = targetPageOff; - - pgstat_report_wait_start(WAIT_EVENT_WAL_READ); - r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff); - if (r != XLOG_BLCKSZ) - { - char fname[MAXFNAMELEN]; - int save_errno = errno; - - pgstat_report_wait_end(); - XLogFileName(fname, curFileTLI, readSegNo, wal_segment_size); - if (r < 0) - { - errno = save_errno; - ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), - (errcode_for_file_access(), - errmsg("could not read from log segment %s, offset %u: %m", - fname, readOff))); - } - else - ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), - (errcode(ERRCODE_DATA_CORRUPTED), - errmsg("could not read from log segment %s, offset %u: read %d of %zu", - fname, readOff, r, (Size) XLOG_BLCKSZ))); - goto next_record_is_invalid; - } - pgstat_report_wait_end(); - - Assert(targetSegNo == readSegNo); - Assert(targetPageOff == readOff); - Assert(reqLen <= readLen); - - xlogreader->seg.ws_tli = curFileTLI; - - /* - * Check the page header immediately, so that we can retry immediately if - * it's not valid. This may seem unnecessary, because ReadPageInternal() - * validates the page header anyway, and would propagate the failure up to - * ReadRecord(), which would retry. However, there's a corner case with - * continuation records, if a record is split across two pages such that - * we would need to read the two pages from different sources. For - * example, imagine a scenario where a streaming replica is started up, - * and replay reaches a record that's split across two WAL segments. The - * first page is only available locally, in pg_wal, because it's already - * been recycled on the primary. The second page, however, is not present - * in pg_wal, and we should stream it from the primary. There is a - * recycled WAL segment present in pg_wal, with garbage contents, however. - * We would read the first page from the local WAL segment, but when - * reading the second page, we would read the bogus, recycled, WAL - * segment. If we didn't catch that case here, we would never recover, - * because ReadRecord() would retry reading the whole record from the - * beginning. - * - * Of course, this only catches errors in the page header, which is what - * happens in the case of a recycled WAL segment. Other kinds of errors or - * corruption still has the same problem. But this at least fixes the - * common case, which can happen as part of normal operation. - * - * Validating the page header is cheap enough that doing it twice - * shouldn't be a big deal from a performance point of view. - * - * When not in standby mode, an invalid page header should cause recovery - * to end, not retry reading the page, so we don't need to validate the - * page header here for the retry. Instead, ReadPageInternal() is - * responsible for the validation. - */ - if (StandbyMode && - !XLogReaderValidatePageHeader(xlogreader, targetPagePtr, readBuf)) - { - /* - * Emit this error right now then retry this page immediately. Use - * errmsg_internal() because the message was already translated. - */ - if (xlogreader->errormsg_buf[0]) - ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), - (errmsg_internal("%s", xlogreader->errormsg_buf))); - - /* reset any error XLogReaderValidatePageHeader() might have set */ - xlogreader->errormsg_buf[0] = '\0'; - goto next_record_is_invalid; - } - - return readLen; - -next_record_is_invalid: - lastSourceFailed = true; - - if (readFile >= 0) - close(readFile); - readFile = -1; - readLen = 0; - readSource = XLOG_FROM_ANY; - - /* In standby-mode, keep trying */ - if (StandbyMode) - goto retry; - else - return -1; -} - -/* - * Open the WAL segment containing WAL location 'RecPtr'. - * - * The segment can be fetched via restore_command, or via walreceiver having - * streamed the record, or it can already be present in pg_wal. Checking - * pg_wal is mainly for crash recovery, but it will be polled in standby mode - * too, in case someone copies a new segment directly to pg_wal. That is not - * documented or recommended, though. - * - * If 'fetching_ckpt' is true, we're fetching a checkpoint record, and should - * prepare to read WAL starting from RedoStartLSN after this. - * - * 'RecPtr' might not point to the beginning of the record we're interested - * in, it might also point to the page or segment header. In that case, - * 'tliRecPtr' is the position of the WAL record we're interested in. It is - * used to decide which timeline to stream the requested WAL from. - * - * 'replayLSN' is the current replay LSN, so that if we scan for new - * timelines, we can reject a switch to a timeline that branched off before - * this point. - * - * If the record is not immediately available, the function returns false - * if we're not in standby mode. In standby mode, waits for it to become - * available. - * - * When the requested record becomes available, the function opens the file - * containing it (if not open already), and returns true. When end of standby - * mode is triggered by the user, and there is no more WAL available, returns - * false. - */ -static bool -WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, - bool fetching_ckpt, XLogRecPtr tliRecPtr, - TimeLineID replayTLI, XLogRecPtr replayLSN) -{ - static TimestampTz last_fail_time = 0; - TimestampTz now; - bool streaming_reply_sent = false; - - /*------- - * Standby mode is implemented by a state machine: - * - * 1. Read from either archive or pg_wal (XLOG_FROM_ARCHIVE), or just - * pg_wal (XLOG_FROM_PG_WAL) - * 2. Check trigger file - * 3. Read from primary server via walreceiver (XLOG_FROM_STREAM) - * 4. Rescan timelines - * 5. Sleep wal_retrieve_retry_interval milliseconds, and loop back to 1. - * - * Failure to read from the current source advances the state machine to - * the next state. - * - * 'currentSource' indicates the current state. There are no currentSource - * values for "check trigger", "rescan timelines", and "sleep" states, - * those actions are taken when reading from the previous source fails, as - * part of advancing to the next state. - * - * If standby mode is turned off while reading WAL from stream, we move - * to XLOG_FROM_ARCHIVE and reset lastSourceFailed, to force fetching - * the files (which would be required at end of recovery, e.g., timeline - * history file) from archive or pg_wal. We don't need to kill WAL receiver - * here because it's already stopped when standby mode is turned off at - * the end of recovery. - *------- - */ - if (!InArchiveRecovery) - currentSource = XLOG_FROM_PG_WAL; - else if (currentSource == XLOG_FROM_ANY || - (!StandbyMode && currentSource == XLOG_FROM_STREAM)) - { - lastSourceFailed = false; - currentSource = XLOG_FROM_ARCHIVE; - } - - for (;;) - { - XLogSource oldSource = currentSource; - bool startWalReceiver = false; - - /* - * First check if we failed to read from the current source, and - * advance the state machine if so. The failure to read might've - * happened outside this function, e.g when a CRC check fails on a - * record, or within this loop. - */ - if (lastSourceFailed) - { - switch (currentSource) - { - case XLOG_FROM_ARCHIVE: - case XLOG_FROM_PG_WAL: - - /* - * Check to see if the trigger file exists. Note that we - * do this only after failure, so when you create the - * trigger file, we still finish replaying as much as we - * can from archive and pg_wal before failover. - */ - if (StandbyMode && CheckForStandbyTrigger()) - { - XLogShutdownWalRcv(); - return false; - } - - /* - * Not in standby mode, and we've now tried the archive - * and pg_wal. - */ - if (!StandbyMode) - return false; - - /* - * Move to XLOG_FROM_STREAM state, and set to start a - * walreceiver if necessary. - */ - currentSource = XLOG_FROM_STREAM; - startWalReceiver = true; - break; - - case XLOG_FROM_STREAM: - - /* - * Failure while streaming. Most likely, we got here - * because streaming replication was terminated, or - * promotion was triggered. But we also get here if we - * find an invalid record in the WAL streamed from the - * primary, in which case something is seriously wrong. - * There's little chance that the problem will just go - * away, but PANIC is not good for availability either, - * especially in hot standby mode. So, we treat that the - * same as disconnection, and retry from archive/pg_wal - * again. The WAL in the archive should be identical to - * what was streamed, so it's unlikely that it helps, but - * one can hope... - */ - - /* - * We should be able to move to XLOG_FROM_STREAM only in - * standby mode. - */ - Assert(StandbyMode); - - /* - * Before we leave XLOG_FROM_STREAM state, make sure that - * walreceiver is not active, so that it won't overwrite - * WAL that we restore from archive. - */ - if (WalRcvStreaming()) - XLogShutdownWalRcv(); - - /* - * Before we sleep, re-scan for possible new timelines if - * we were requested to recover to the latest timeline. - */ - if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_LATEST) - { - if (rescanLatestTimeLine(replayTLI, replayLSN)) - { - currentSource = XLOG_FROM_ARCHIVE; - break; - } - } - - /* - * XLOG_FROM_STREAM is the last state in our state - * machine, so we've exhausted all the options for - * obtaining the requested WAL. We're going to loop back - * and retry from the archive, but if it hasn't been long - * since last attempt, sleep wal_retrieve_retry_interval - * milliseconds to avoid busy-waiting. - */ - now = GetCurrentTimestamp(); - if (!TimestampDifferenceExceeds(last_fail_time, now, - wal_retrieve_retry_interval)) - { - long wait_time; - - wait_time = wal_retrieve_retry_interval - - TimestampDifferenceMilliseconds(last_fail_time, now); - - (void) WaitLatch(&XLogCtl->recoveryWakeupLatch, - WL_LATCH_SET | WL_TIMEOUT | - WL_EXIT_ON_PM_DEATH, - wait_time, - WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL); - ResetLatch(&XLogCtl->recoveryWakeupLatch); - now = GetCurrentTimestamp(); - - /* Handle interrupt signals of startup process */ - HandleStartupProcInterrupts(); - } - last_fail_time = now; - currentSource = XLOG_FROM_ARCHIVE; - break; - - default: - elog(ERROR, "unexpected WAL source %d", currentSource); - } - } - else if (currentSource == XLOG_FROM_PG_WAL) - { - /* - * We just successfully read a file in pg_wal. We prefer files in - * the archive over ones in pg_wal, so try the next file again - * from the archive first. - */ - if (InArchiveRecovery) - currentSource = XLOG_FROM_ARCHIVE; - } - - if (currentSource != oldSource) - elog(DEBUG2, "switched WAL source from %s to %s after %s", - xlogSourceNames[oldSource], xlogSourceNames[currentSource], - lastSourceFailed ? "failure" : "success"); - - /* - * We've now handled possible failure. Try to read from the chosen - * source. - */ - lastSourceFailed = false; - - switch (currentSource) - { - case XLOG_FROM_ARCHIVE: - case XLOG_FROM_PG_WAL: - - /* - * WAL receiver must not be running when reading WAL from - * archive or pg_wal. - */ - Assert(!WalRcvStreaming()); - - /* Close any old file we might have open. */ - if (readFile >= 0) - { - close(readFile); - readFile = -1; - } - /* Reset curFileTLI if random fetch. */ - if (randAccess) - curFileTLI = 0; - - /* - * Try to restore the file from archive, or read an existing - * file from pg_wal. - */ - readFile = XLogFileReadAnyTLI(readSegNo, DEBUG2, - currentSource == XLOG_FROM_ARCHIVE ? XLOG_FROM_ANY : - currentSource); - if (readFile >= 0) - return true; /* success! */ - - /* - * Nope, not found in archive or pg_wal. - */ - lastSourceFailed = true; - break; - - case XLOG_FROM_STREAM: - { - bool havedata; - - /* - * We should be able to move to XLOG_FROM_STREAM only in - * standby mode. - */ - Assert(StandbyMode); - - /* - * First, shutdown walreceiver if its restart has been - * requested -- but no point if we're already slated for - * starting it. - */ - if (pendingWalRcvRestart && !startWalReceiver) - { - XLogShutdownWalRcv(); - - /* - * Re-scan for possible new timelines if we were - * requested to recover to the latest timeline. - */ - if (recoveryTargetTimeLineGoal == - RECOVERY_TARGET_TIMELINE_LATEST) - rescanLatestTimeLine(replayTLI, replayLSN); - - startWalReceiver = true; - } - pendingWalRcvRestart = false; - - /* - * Launch walreceiver if needed. - * - * If fetching_ckpt is true, RecPtr points to the initial - * checkpoint location. In that case, we use RedoStartLSN - * as the streaming start position instead of RecPtr, so - * that when we later jump backwards to start redo at - * RedoStartLSN, we will have the logs streamed already. - */ - if (startWalReceiver && - PrimaryConnInfo && strcmp(PrimaryConnInfo, "") != 0) - { - XLogRecPtr ptr; - TimeLineID tli; - - if (fetching_ckpt) - { - ptr = RedoStartLSN; - tli = ControlFile->checkPointCopy.ThisTimeLineID; - } - else - { - ptr = RecPtr; - - /* - * Use the record begin position to determine the - * TLI, rather than the position we're reading. - */ - tli = tliOfPointInHistory(tliRecPtr, expectedTLEs); - - if (curFileTLI > 0 && tli < curFileTLI) - elog(ERROR, "according to history file, WAL location %X/%X belongs to timeline %u, but previous recovered WAL file came from timeline %u", - LSN_FORMAT_ARGS(tliRecPtr), - tli, curFileTLI); - } - curFileTLI = tli; - LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); - XLogCtl->InstallXLogFileSegmentActive = true; - LWLockRelease(ControlFileLock); - RequestXLogStreaming(tli, ptr, PrimaryConnInfo, - PrimarySlotName, - wal_receiver_create_temp_slot); - flushedUpto = 0; - } - - /* - * Check if WAL receiver is active or wait to start up. - */ - if (!WalRcvStreaming()) - { - lastSourceFailed = true; - break; - } - - /* - * Walreceiver is active, so see if new data has arrived. - * - * We only advance XLogReceiptTime when we obtain fresh - * WAL from walreceiver and observe that we had already - * processed everything before the most recent "chunk" - * that it flushed to disk. In steady state where we are - * keeping up with the incoming data, XLogReceiptTime will - * be updated on each cycle. When we are behind, - * XLogReceiptTime will not advance, so the grace time - * allotted to conflicting queries will decrease. - */ - if (RecPtr < flushedUpto) - havedata = true; - else - { - XLogRecPtr latestChunkStart; - - flushedUpto = GetWalRcvFlushRecPtr(&latestChunkStart, &receiveTLI); - if (RecPtr < flushedUpto && receiveTLI == curFileTLI) - { - havedata = true; - if (latestChunkStart <= RecPtr) - { - XLogReceiptTime = GetCurrentTimestamp(); - SetCurrentChunkStartTime(XLogReceiptTime); - } - } - else - havedata = false; - } - if (havedata) - { - /* - * Great, streamed far enough. Open the file if it's - * not open already. Also read the timeline history - * file if we haven't initialized timeline history - * yet; it should be streamed over and present in - * pg_wal by now. Use XLOG_FROM_STREAM so that source - * info is set correctly and XLogReceiptTime isn't - * changed. - * - * NB: We must set readTimeLineHistory based on - * recoveryTargetTLI, not receiveTLI. Normally they'll - * be the same, but if recovery_target_timeline is - * 'latest' and archiving is configured, then it's - * possible that we managed to retrieve one or more - * new timeline history files from the archive, - * updating recoveryTargetTLI. - */ - if (readFile < 0) - { - if (!expectedTLEs) - expectedTLEs = readTimeLineHistory(recoveryTargetTLI); - readFile = XLogFileRead(readSegNo, PANIC, - receiveTLI, - XLOG_FROM_STREAM, false); - Assert(readFile >= 0); - } - else - { - /* just make sure source info is correct... */ - readSource = XLOG_FROM_STREAM; - XLogReceiptSource = XLOG_FROM_STREAM; - return true; - } - break; - } - - /* - * Data not here yet. Check for trigger, then wait for - * walreceiver to wake us up when new WAL arrives. - */ - if (CheckForStandbyTrigger()) - { - /* - * Note that we don't "return false" immediately here. - * After being triggered, we still want to replay all - * the WAL that was already streamed. It's in pg_wal - * now, so we just treat this as a failure, and the - * state machine will move on to replay the streamed - * WAL from pg_wal, and then recheck the trigger and - * exit replay. - */ - lastSourceFailed = true; - break; - } - - /* - * Since we have replayed everything we have received so - * far and are about to start waiting for more WAL, let's - * tell the upstream server our replay location now so - * that pg_stat_replication doesn't show stale - * information. - */ - if (!streaming_reply_sent) - { - WalRcvForceReply(); - streaming_reply_sent = true; - } - - /* - * Wait for more WAL to arrive. Time out after 5 seconds - * to react to a trigger file promptly and to check if the - * WAL receiver is still active. - */ - (void) WaitLatch(&XLogCtl->recoveryWakeupLatch, - WL_LATCH_SET | WL_TIMEOUT | - WL_EXIT_ON_PM_DEATH, - 5000L, WAIT_EVENT_RECOVERY_WAL_STREAM); - ResetLatch(&XLogCtl->recoveryWakeupLatch); - break; - } - - default: - elog(ERROR, "unexpected WAL source %d", currentSource); - } - - /* - * Check for recovery pause here so that we can confirm more quickly - * that a requested pause has actually taken effect. - */ - if (((volatile XLogCtlData *) XLogCtl)->recoveryPauseState != - RECOVERY_NOT_PAUSED) - recoveryPausesHere(false); - - /* - * This possibly-long loop needs to handle interrupts of startup - * process. - */ - HandleStartupProcInterrupts(); - } - - return false; /* not reached */ -} - -/* - * Set flag to signal the walreceiver to restart. (The startup process calls - * this on noticing a relevant configuration change.) - */ -void -StartupRequestWalReceiverRestart(void) -{ - if (currentSource == XLOG_FROM_STREAM && WalRcvRunning()) - { - ereport(LOG, - (errmsg("WAL receiver process shutdown requested"))); - - pendingWalRcvRestart = true; - } -} - /* Thin wrapper around ShutdownWalRcv(). */ -static void +void XLogShutdownWalRcv(void) { ShutdownWalRcv(); @@ -13142,153 +9164,25 @@ XLogShutdownWalRcv(void) LWLockRelease(ControlFileLock); } -/* - * Determine what log level should be used to report a corrupt WAL record - * in the current WAL page, previously read by XLogPageRead(). - * - * 'emode' is the error mode that would be used to report a file-not-found - * or legitimate end-of-WAL situation. Generally, we use it as-is, but if - * we're retrying the exact same record that we've tried previously, only - * complain the first time to keep the noise down. However, we only do when - * reading from pg_wal, because we don't expect any invalid records in archive - * or in records streamed from the primary. Files in the archive should be complete, - * and we should never hit the end of WAL because we stop and wait for more WAL - * to arrive before replaying it. - * - * NOTE: This function remembers the RecPtr value it was last called with, - * to suppress repeated messages about the same record. Only call this when - * you are about to ereport(), or you might cause a later message to be - * erroneously suppressed. - */ -static int -emode_for_corrupt_record(int emode, XLogRecPtr RecPtr) -{ - static XLogRecPtr lastComplaint = 0; - - if (readSource == XLOG_FROM_PG_WAL && emode == LOG) - { - if (RecPtr == lastComplaint) - emode = DEBUG1; - else - lastComplaint = RecPtr; - } - return emode; -} - -/* - * Has a standby promotion already been triggered? - * - * Unlike CheckForStandbyTrigger(), this works in any process - * that's connected to shared memory. - */ -bool -PromoteIsTriggered(void) -{ - /* - * We check shared state each time only until a standby promotion is - * triggered. We can't trigger a promotion again, so there's no need to - * keep checking after the shared variable has once been seen true. - */ - if (LocalPromoteIsTriggered) - return true; - - SpinLockAcquire(&XLogCtl->info_lck); - LocalPromoteIsTriggered = XLogCtl->SharedPromoteIsTriggered; - SpinLockRelease(&XLogCtl->info_lck); - - return LocalPromoteIsTriggered; -} - -static void -SetPromoteIsTriggered(void) -{ - SpinLockAcquire(&XLogCtl->info_lck); - XLogCtl->SharedPromoteIsTriggered = true; - SpinLockRelease(&XLogCtl->info_lck); - - /* - * Mark the recovery pause state as 'not paused' because the paused state - * ends and promotion continues if a promotion is triggered while recovery - * is paused. Otherwise pg_get_wal_replay_pause_state() can mistakenly - * return 'paused' while a promotion is ongoing. - */ - SetRecoveryPause(false); - - LocalPromoteIsTriggered = true; -} - -/* - * Check to see whether the user-specified trigger file exists and whether a - * promote request has arrived. If either condition holds, return true. - */ -static bool -CheckForStandbyTrigger(void) -{ - struct stat stat_buf; - - if (LocalPromoteIsTriggered) - return true; - - if (IsPromoteSignaled() && CheckPromoteSignal()) - { - ereport(LOG, (errmsg("received promote request"))); - RemovePromoteSignalFiles(); - ResetPromoteSignaled(); - SetPromoteIsTriggered(); - return true; - } - - if (PromoteTriggerFile == NULL || strcmp(PromoteTriggerFile, "") == 0) - return false; - - if (stat(PromoteTriggerFile, &stat_buf) == 0) - { - ereport(LOG, - (errmsg("promote trigger file found: %s", PromoteTriggerFile))); - unlink(PromoteTriggerFile); - SetPromoteIsTriggered(); - return true; - } - else if (errno != ENOENT) - ereport(ERROR, - (errcode_for_file_access(), - errmsg("could not stat promote trigger file \"%s\": %m", - PromoteTriggerFile))); - - return false; -} - -/* - * Remove the files signaling a standby promotion request. - */ +/* Enable WAL file recycling and preallocation. */ void -RemovePromoteSignalFiles(void) +SetInstallXLogFileSegmentActive(void) { - unlink(PROMOTE_SIGNAL_FILE); + LWLockAcquire(ControlFileLock, LW_EXCLUSIVE); + XLogCtl->InstallXLogFileSegmentActive = true; + LWLockRelease(ControlFileLock); } -/* - * Check to see if a promote request has arrived. - */ bool -CheckPromoteSignal(void) +IsInstallXLogFileSegmentActive(void) { - struct stat stat_buf; + bool result; - if (stat(PROMOTE_SIGNAL_FILE, &stat_buf) == 0) - return true; + LWLockAcquire(ControlFileLock, LW_SHARED); + result = XLogCtl->InstallXLogFileSegmentActive; + LWLockRelease(ControlFileLock); - return false; -} - -/* - * Wake up startup process to replay newly arrived WAL, or to notice that - * failover has been requested. - */ -void -WakeupRecovery(void) -{ - SetLatch(&XLogCtl->recoveryWakeupLatch); + return result; } /* @@ -13301,12 +9195,3 @@ SetWalWriterSleeping(bool sleeping) XLogCtl->WalWriterSleeping = sleeping; SpinLockRelease(&XLogCtl->info_lck); } - -/* - * Schedule a walreceiver wakeup in the main recovery loop. - */ -void -XLogRequestWalReceiverReply(void) -{ - doRequestWalReceiverReply = true; -} diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c index d8af5aad58..2f900533cd 100644 --- a/src/backend/access/transam/xlogfuncs.c +++ b/src/backend/access/transam/xlogfuncs.c @@ -19,8 +19,8 @@ #include #include "access/htup_details.h" -#include "access/xlog.h" #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "catalog/pg_type.h" #include "funcapi.h" diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c new file mode 100644 index 0000000000..d5269ede80 --- /dev/null +++ b/src/backend/access/transam/xlogrecovery.c @@ -0,0 +1,4537 @@ +/*------------------------------------------------------------------------- + * + * xlogrecovery.c + * Functions for WAL recovery, standby mode + * + * This source file contains functions controlling WAL recovery. + * InitWalRecovery() initializes the system for crash or archive recovery, + * or standby mode, depending on configuration options and the state of + * the control file and possible backup label file. PerformWalRecovery() + * performs the actual WAL replay, calling the rmgr-specific redo routines. + * EndWalRecovery() performs end-of-recovery checks and cleanup actions, + * and prepares information needed to initialize the WAL for writes. In + * addition to these three main functions, there are a bunch of functions + * for interrogating recovery state and controlling the recovery process. + * + * + * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/backend/access/transam/xlogrecovery.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include +#include +#include +#include +#include +#include + +#include "access/timeline.h" +#include "access/transam.h" +#include "access/xact.h" +#include "access/xlog_internal.h" +#include "access/xlogarchive.h" +#include "access/xlogreader.h" +#include "access/xlogrecovery.h" +#include "access/xlogutils.h" +#include "catalog/pg_control.h" +#include "commands/tablespace.h" +#include "miscadmin.h" +#include "pgstat.h" +#include "postmaster/bgwriter.h" +#include "postmaster/startup.h" +#include "replication/basebackup.h" +#include "replication/walreceiver.h" +#include "storage/fd.h" +#include "storage/ipc.h" +#include "storage/latch.h" +#include "storage/pmsignal.h" +#include "storage/proc.h" +#include "storage/procarray.h" +#include "storage/spin.h" +#include "utils/builtins.h" +#include "utils/guc.h" +#include "utils/ps_status.h" +#include "utils/pg_rusage.h" + +/* Unsupported old recovery command file names (relative to $PGDATA) */ +#define RECOVERY_COMMAND_FILE "recovery.conf" +#define RECOVERY_COMMAND_DONE "recovery.done" + +/* + * GUC support + */ +const struct config_enum_entry recovery_target_action_options[] = { + {"pause", RECOVERY_TARGET_ACTION_PAUSE, false}, + {"promote", RECOVERY_TARGET_ACTION_PROMOTE, false}, + {"shutdown", RECOVERY_TARGET_ACTION_SHUTDOWN, false}, + {NULL, 0, false} +}; + +/* options formerly taken from recovery.conf for archive recovery */ +char *recoveryRestoreCommand = NULL; +char *recoveryEndCommand = NULL; +char *archiveCleanupCommand = NULL; +RecoveryTargetType recoveryTarget = RECOVERY_TARGET_UNSET; +bool recoveryTargetInclusive = true; +int recoveryTargetAction = RECOVERY_TARGET_ACTION_PAUSE; +TransactionId recoveryTargetXid; +char *recovery_target_time_string; +TimestampTz recoveryTargetTime; +const char *recoveryTargetName; +XLogRecPtr recoveryTargetLSN; +int recovery_min_apply_delay = 0; + +/* options formerly taken from recovery.conf for XLOG streaming */ +char *PrimaryConnInfo = NULL; +char *PrimarySlotName = NULL; +char *PromoteTriggerFile = NULL; +bool wal_receiver_create_temp_slot = false; + +/* + * recoveryTargetTimeLineGoal: what the user requested, if any + * + * recoveryTargetTLIRequested: numeric value of requested timeline, if constant + * + * recoveryTargetTLI: the currently understood target timeline; changes + * + * expectedTLEs: a list of TimeLineHistoryEntries for recoveryTargetTLI and + * the timelines of its known parents, newest first (so recoveryTargetTLI is + * always the first list member). Only these TLIs are expected to be seen in + * the WAL segments we read, and indeed only these TLIs will be considered as + * candidate WAL files to open at all. + * + * curFileTLI: the TLI appearing in the name of the current input WAL file. + * (This is not necessarily the same as the timeline from which we are + * replaying WAL, which StartupXLOG calls replayTLI, because we could be + * scanning data that was copied from an ancestor timeline when the current + * file was created.) During a sequential scan we do not allow this value + * to decrease. + */ +RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal = RECOVERY_TARGET_TIMELINE_LATEST; +TimeLineID recoveryTargetTLIRequested = 0; +TimeLineID recoveryTargetTLI = 0; +static List *expectedTLEs; +static TimeLineID curFileTLI; + +/* + * When ArchiveRecoveryRequested is set, archive recovery was requested, + * ie. signal files were present. When InArchiveRecovery is set, we are + * currently recovering using offline XLOG archives. These variables are only + * valid in the startup process. + * + * When ArchiveRecoveryRequested is true, but InArchiveRecovery is false, we're + * currently performing crash recovery using only XLOG files in pg_wal, but + * will switch to using offline XLOG archives as soon as we reach the end of + * WAL in pg_wal. +*/ +bool ArchiveRecoveryRequested = false; +bool InArchiveRecovery = false; + +/* + * When StandbyModeRequested is set, standby mode was requested, i.e. + * standby.signal file was present. When StandbyMode is set, we are currently + * in standby mode. These variables are only valid in the startup process. + * They work similarly to ArchiveRecoveryRequested and InArchiveRecovery. + */ +static bool StandbyModeRequested = false; +bool StandbyMode = false; + +/* was a signal file present at startup? */ +static bool standby_signal_file_found = false; +static bool recovery_signal_file_found = false; + +/* + * CheckPointLoc is the position of the checkpoint record that determines + * where to start the replay. It comes from the backup label file or the + * control file. + * + * RedoStartLSN is the checkpoint's REDO location, also from the backup label + * file or the control file. In standby mode, XLOG streaming usually starts + * from the position where an invalid record was found. But if we fail to + * read even the initial checkpoint record, we use the REDO location instead + * of the checkpoint location as the start position of XLOG streaming. + * Otherwise we would have to jump backwards to the REDO location after + * reading the checkpoint record, because the REDO record can precede the + * checkpoint record. + */ +static XLogRecPtr CheckPointLoc = InvalidXLogRecPtr; +static TimeLineID CheckPointTLI = 0; +static XLogRecPtr RedoStartLSN = InvalidXLogRecPtr; +static TimeLineID RedoStartTLI = 0; + +/* + * Local copy of SharedHotStandbyActive variable. False actually means "not + * known, need to check the shared state". + */ +static bool LocalHotStandbyActive = false; + +/* + * Local copy of SharedPromoteIsTriggered variable. False actually means "not + * known, need to check the shared state". + */ +static bool LocalPromoteIsTriggered = false; + +/* Has the recovery code requested a walreceiver wakeup? */ +static bool doRequestWalReceiverReply; + +/* XLogReader object used to parse the WAL records */ +static XLogReaderState *xlogreader = NULL; + +/* Parameters passed down from ReadRecord to the XLogPageRead callback. */ +typedef struct XLogPageReadPrivate +{ + int emode; + bool fetching_ckpt; /* are we fetching a checkpoint record? */ + bool randAccess; + TimeLineID replayTLI; +} XLogPageReadPrivate; + +/* flag to tell XLogPageRead that we have started replaying */ +static bool InRedo = false; + +/* + * Codes indicating where we got a WAL file from during recovery, or where + * to attempt to get one. + */ +typedef enum +{ + XLOG_FROM_ANY = 0, /* request to read WAL from any source */ + XLOG_FROM_ARCHIVE, /* restored using restore_command */ + XLOG_FROM_PG_WAL, /* existing file in pg_wal */ + XLOG_FROM_STREAM /* streamed from primary */ +} XLogSource; + +/* human-readable names for XLogSources, for debugging output */ +static const char *const xlogSourceNames[] = {"any", "archive", "pg_wal", "stream"}; + +/* + * readFile is -1 or a kernel FD for the log file segment that's currently + * open for reading. readSegNo identifies the segment. readOff is the offset + * of the page just read, readLen indicates how much of it has been read into + * readBuf, and readSource indicates where we got the currently open file from. + * + * Note: we could use Reserve/ReleaseExternalFD to track consumption of this + * FD too (like for openLogFile in xlog.c); but it doesn't currently seem + * worthwhile, since the XLOG is not read by general-purpose sessions. + */ +static int readFile = -1; +static XLogSegNo readSegNo = 0; +static uint32 readOff = 0; +static uint32 readLen = 0; +static XLogSource readSource = XLOG_FROM_ANY; + +/* + * Keeps track of which source we're currently reading from. This is + * different from readSource in that this is always set, even when we don't + * currently have a WAL file open. If lastSourceFailed is set, our last + * attempt to read from currentSource failed, and we should try another source + * next. + * + * pendingWalRcvRestart is set when a config change occurs that requires a + * walreceiver restart. This is only valid in XLOG_FROM_STREAM state. + */ +static XLogSource currentSource = XLOG_FROM_ANY; +static bool lastSourceFailed = false; +static bool pendingWalRcvRestart = false; + +/* + * These variables track when we last obtained some WAL data to process, + * and where we got it from. (XLogReceiptSource is initially the same as + * readSource, but readSource gets reset to zero when we don't have data + * to process right now. It is also different from currentSource, which + * also changes when we try to read from a source and fail, while + * XLogReceiptSource tracks where we last successfully read some WAL.) + */ +static TimestampTz XLogReceiptTime = 0; +static XLogSource XLogReceiptSource = XLOG_FROM_ANY; + +/* Local copy of WalRcv->flushedUpto */ +static XLogRecPtr flushedUpto = 0; +static TimeLineID receiveTLI = 0; + +/* + * Copy of minRecoveryPoint and backupEndPoint from the control file. + * + * In order to reach consistency, we must replay the WAL up to + * minRecoveryPoint. If backupEndRequired is true, we must also reach + * backupEndPoint, or if it's invalid, an end-of-backup record corresponding + * to backupStartPoint. + * + * Note: In archive recovery, after consistency has been reached, the + * functions in xlog.c will start updating minRecoveryPoint in the control + * file. But this copy of minRecoveryPoint variable reflects the value at the + * beginning of recovery, and is *not* updated after consistency is reached. + */ +static XLogRecPtr minRecoveryPoint; +static TimeLineID minRecoveryPointTLI; + +static XLogRecPtr backupStartPoint; +static XLogRecPtr backupEndPoint; +static bool backupEndRequired = false; + +/* + * Have we reached a consistent database state? In crash recovery, we have + * to replay all the WAL, so reachedConsistency is never set. During archive + * recovery, the database is consistent once minRecoveryPoint is reached. + * + * Consistent state means that the system is internally consistent, all + * the WAL has been replayed up to a certain point, and importantly, there + * is no trace of later actions on disk. + */ +bool reachedConsistency = false; + +/* Buffers dedicated to consistency checks of size BLCKSZ */ +static char *replay_image_masked = NULL; +static char *primary_image_masked = NULL; + + +/* + * Shared-memory state for WAL recovery. + */ +typedef struct XLogRecoveryCtlData +{ + /* + * SharedHotStandbyActive indicates if we allow hot standby queries to be + * run. Protected by info_lck. + */ + bool SharedHotStandbyActive; + + /* + * SharedPromoteIsTriggered indicates if a standby promotion has been + * triggered. Protected by info_lck. + */ + bool SharedPromoteIsTriggered; + + /* + * recoveryWakeupLatch is used to wake up the startup process to continue + * WAL replay, if it is waiting for WAL to arrive or failover trigger file + * to appear. + * + * Note that the startup process also uses another latch, its procLatch, + * to wait for recovery conflict. If we get rid of recoveryWakeupLatch for + * signaling the startup process in favor of using its procLatch, which + * comports better with possible generic signal handlers using that latch. + * But we should not do that because the startup process doesn't assume + * that it's waken up by walreceiver process or SIGHUP signal handler + * while it's waiting for recovery conflict. The separate latches, + * recoveryWakeupLatch and procLatch, should be used for inter-process + * communication for WAL replay and recovery conflict, respectively. + */ + Latch recoveryWakeupLatch; + + /* + * Last record successfully replayed. + */ + XLogRecPtr lastReplayedReadRecPtr; /* start position */ + XLogRecPtr lastReplayedEndRecPtr; /* end+1 position */ + TimeLineID lastReplayedTLI; /* timeline */ + + /* + * When we're currently replaying a record, ie. in a redo function, + * replayEndRecPtr points to the end+1 of the record being replayed, + * otherwise it's equal to lastReplayedEndRecPtr. + */ + XLogRecPtr replayEndRecPtr; + TimeLineID replayEndTLI; + /* timestamp of last COMMIT/ABORT record replayed (or being replayed) */ + TimestampTz recoveryLastXTime; + + /* + * timestamp of when we started replaying the current chunk of WAL data, + * only relevant for replication or archive recovery + */ + TimestampTz currentChunkStartTime; + /* Recovery pause state */ + RecoveryPauseState recoveryPauseState; + ConditionVariable recoveryNotPausedCV; + + slock_t info_lck; /* locks shared variables shown above */ +} XLogRecoveryCtlData; + +static XLogRecoveryCtlData *XLogRecoveryCtl = NULL; + +/* + * abortedRecPtr is the start pointer of a broken record at end of WAL when + * recovery completes; missingContrecPtr is the location of the first + * contrecord that went missing. See CreateOverwriteContrecordRecord for + * details. + */ +static XLogRecPtr abortedRecPtr; +static XLogRecPtr missingContrecPtr; + +/* + * if recoveryStopsBefore/After returns true, it saves information of the stop + * point here + */ +static TransactionId recoveryStopXid; +static TimestampTz recoveryStopTime; +static XLogRecPtr recoveryStopLSN; +static char recoveryStopName[MAXFNAMELEN]; +static bool recoveryStopAfter; + +/* prototypes for local functions */ +static void ApplyWalRecord(XLogReaderState *xlogreader, XLogRecord *record, TimeLineID *replayTLI); + +static void readRecoverySignalFile(void); +static void validateRecoveryParameters(void); +static bool read_backup_label(XLogRecPtr *checkPointLoc, + TimeLineID *backupLabelTLI, + bool *backupEndRequired, bool *backupFromStandby); +static bool read_tablespace_map(List **tablespaces); + +static void xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI); +static void CheckRecoveryConsistency(void); +static void rm_redo_error_callback(void *arg); +#ifdef WAL_DEBUG +static void xlog_outrec(StringInfo buf, XLogReaderState *record); +#endif +static void xlog_block_info(StringInfo buf, XLogReaderState *record); +static void checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, + TimeLineID prevTLI, TimeLineID replayTLI); +static bool getRecordTimestamp(XLogReaderState *record, TimestampTz *recordXtime); +static void verifyBackupPageConsistency(XLogReaderState *record); + +static bool recoveryStopsBefore(XLogReaderState *record); +static bool recoveryStopsAfter(XLogReaderState *record); +static char *getRecoveryStopReason(void); +static void recoveryPausesHere(bool endOfRecovery); +static bool recoveryApplyDelay(XLogReaderState *record); +static void ConfirmRecoveryPaused(void); + +static XLogRecord *ReadRecord(XLogReaderState *xlogreader, + int emode, bool fetching_ckpt, TimeLineID replayTLI); + +static int XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, + int reqLen, XLogRecPtr targetRecPtr, char *readBuf); +static bool WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, + bool fetching_ckpt, + XLogRecPtr tliRecPtr, + TimeLineID replayTLI, + XLogRecPtr replayLSN); +static int emode_for_corrupt_record(int emode, XLogRecPtr RecPtr); +static XLogRecord *ReadCheckpointRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, + int whichChkpt, bool report, TimeLineID replayTLI); +static bool rescanLatestTimeLine(TimeLineID replayTLI, XLogRecPtr replayLSN); +static int XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli, + XLogSource source, bool notfoundOk); +static int XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source); + +static bool CheckForStandbyTrigger(void); +static void SetPromoteIsTriggered(void); +static bool HotStandbyActiveInReplay(void); + +static void SetCurrentChunkStartTime(TimestampTz xtime); +static void SetLatestXTime(TimestampTz xtime); + +/* + * Initialization of shared memory for WAL recovery + */ +Size +XLogRecoveryShmemSize(void) +{ + Size size; + + /* XLogRecoveryCtl */ + size = sizeof(XLogRecoveryCtlData); + + return size; +} + +void +XLogRecoveryShmemInit(void) +{ + bool found; + + XLogRecoveryCtl = (XLogRecoveryCtlData *) + ShmemInitStruct("XLOG Recovery Ctl", XLogRecoveryShmemSize(), &found); + if (found) + return; + memset(XLogRecoveryCtl, 0, sizeof(XLogRecoveryCtlData)); + + SpinLockInit(&XLogRecoveryCtl->info_lck); + InitSharedLatch(&XLogRecoveryCtl->recoveryWakeupLatch); + ConditionVariableInit(&XLogRecoveryCtl->recoveryNotPausedCV); +} + +/* + * Prepare the system for WAL recovery, if needed. + * + * This is called by StartupXLOG() which coordinates the server startup + * sequence. This function analyzes the control file and the backup label + * file, if any, and figures out whether we need to perform crash recovery or + * archive recovery, and how far we need to replay the WAL to reach a + * consistent state. + * + * This doesn't yet change the on-disk state, except for creating the symlinks + * from table space map file if any, and for fetching WAL files needed to find + * the checkpoint record. On entry, the caller has already read the control + * file into memory, and passes it as argument. This function updates it to + * reflect the recovery state, and the caller is expected to write it back to + * disk does after initializing other subsystems, but before calling + * PerformWalRecovery(). + * + * This initializes some global variables like ArchiveModeRequested, and + * StandbyModeRequested and InRecovery. + */ +void +InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdown_ptr, + bool *haveBackupLabel_ptr, bool *haveTblspcMap_ptr) +{ + XLogPageReadPrivate *private; + struct stat st; + bool wasShutdown; + XLogRecord *record; + DBState dbstate_at_startup; + bool haveTblspcMap = false; + bool haveBackupLabel = false; + CheckPoint checkPoint; + bool backupFromStandby = false; + + dbstate_at_startup = ControlFile->state; + + /* + * Initialize on the assumption we want to recover to the latest timeline + * that's active according to pg_control. + */ + if (ControlFile->minRecoveryPointTLI > + ControlFile->checkPointCopy.ThisTimeLineID) + recoveryTargetTLI = ControlFile->minRecoveryPointTLI; + else + recoveryTargetTLI = ControlFile->checkPointCopy.ThisTimeLineID; + + /* + * Check for signal files, and if so set up state for offline recovery + */ + readRecoverySignalFile(); + validateRecoveryParameters(); + + if (ArchiveRecoveryRequested) + { + if (StandbyModeRequested) + ereport(LOG, + (errmsg("entering standby mode"))); + else if (recoveryTarget == RECOVERY_TARGET_XID) + ereport(LOG, + (errmsg("starting point-in-time recovery to XID %u", + recoveryTargetXid))); + else if (recoveryTarget == RECOVERY_TARGET_TIME) + ereport(LOG, + (errmsg("starting point-in-time recovery to %s", + timestamptz_to_str(recoveryTargetTime)))); + else if (recoveryTarget == RECOVERY_TARGET_NAME) + ereport(LOG, + (errmsg("starting point-in-time recovery to \"%s\"", + recoveryTargetName))); + else if (recoveryTarget == RECOVERY_TARGET_LSN) + ereport(LOG, + (errmsg("starting point-in-time recovery to WAL location (LSN) \"%X/%X\"", + LSN_FORMAT_ARGS(recoveryTargetLSN)))); + else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) + ereport(LOG, + (errmsg("starting point-in-time recovery to earliest consistent point"))); + else + ereport(LOG, + (errmsg("starting archive recovery"))); + } + + /* + * Take ownership of the wakeup latch if we're going to sleep during + * recovery. + */ + if (ArchiveRecoveryRequested) + OwnLatch(&XLogRecoveryCtl->recoveryWakeupLatch); + + private = palloc0(sizeof(XLogPageReadPrivate)); + xlogreader = + XLogReaderAllocate(wal_segment_size, NULL, + XL_ROUTINE(.page_read = &XLogPageRead, + .segment_open = NULL, + .segment_close = wal_segment_close), + private); + if (!xlogreader) + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory"), + errdetail("Failed while allocating a WAL reading processor."))); + xlogreader->system_identifier = ControlFile->system_identifier; + + /* + * Allocate two page buffers dedicated to WAL consistency checks. We do + * it this way, rather than just making static arrays, for two reasons: + * (1) no need to waste the storage in most instantiations of the backend; + * (2) a static char array isn't guaranteed to have any particular + * alignment, whereas palloc() will provide MAXALIGN'd storage. + */ + replay_image_masked = (char *) palloc(BLCKSZ); + primary_image_masked = (char *) palloc(BLCKSZ); + + if (read_backup_label(&CheckPointLoc, &CheckPointTLI, &backupEndRequired, + &backupFromStandby)) + { + List *tablespaces = NIL; + + /* + * Archive recovery was requested, and thanks to the backup label + * file, we know how far we need to replay to reach consistency. Enter + * archive recovery directly. + */ + InArchiveRecovery = true; + if (StandbyModeRequested) + StandbyMode = true; + + /* + * When a backup_label file is present, we want to roll forward from + * the checkpoint it identifies, rather than using pg_control. + */ + record = ReadCheckpointRecord(xlogreader, CheckPointLoc, 0, true, CheckPointTLI); + if (record != NULL) + { + memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); + wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); + ereport(DEBUG1, + (errmsg_internal("checkpoint record is at %X/%X", + LSN_FORMAT_ARGS(CheckPointLoc)))); + InRecovery = true; /* force recovery even if SHUTDOWNED */ + + /* + * Make sure that REDO location exists. This may not be the case + * if there was a crash during an online backup, which left a + * backup_label around that references a WAL segment that's + * already been archived. + */ + if (checkPoint.redo < CheckPointLoc) + { + XLogBeginRead(xlogreader, checkPoint.redo); + if (!ReadRecord(xlogreader, LOG, false, + checkPoint.ThisTimeLineID)) + ereport(FATAL, + (errmsg("could not find redo location referenced by checkpoint record"), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir))); + } + } + else + { + ereport(FATAL, + (errmsg("could not locate required checkpoint record"), + errhint("If you are restoring from a backup, touch \"%s/recovery.signal\" and add required recovery options.\n" + "If you are not restoring from a backup, try removing the file \"%s/backup_label\".\n" + "Be careful: removing \"%s/backup_label\" will result in a corrupt cluster if restoring from a backup.", + DataDir, DataDir, DataDir))); + wasShutdown = false; /* keep compiler quiet */ + } + + /* Read the tablespace_map file if present and create symlinks. */ + if (read_tablespace_map(&tablespaces)) + { + ListCell *lc; + + foreach(lc, tablespaces) + { + tablespaceinfo *ti = lfirst(lc); + char *linkloc; + + linkloc = psprintf("pg_tblspc/%s", ti->oid); + + /* + * Remove the existing symlink if any and Create the symlink + * under PGDATA. + */ + remove_tablespace_symlink(linkloc); + + if (symlink(ti->path, linkloc) < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not create symbolic link \"%s\": %m", + linkloc))); + + pfree(ti->oid); + pfree(ti->path); + pfree(ti); + } + + /* tell the caller to delete it later */ + haveTblspcMap = true; + } + + /* tell the caller to delete it later */ + haveBackupLabel = true; + } + else + { + /* + * If tablespace_map file is present without backup_label file, there + * is no use of such file. There is no harm in retaining it, but it + * is better to get rid of the map file so that we don't have any + * redundant file in data directory and it will avoid any sort of + * confusion. It seems prudent though to just rename the file out of + * the way rather than delete it completely, also we ignore any error + * that occurs in rename operation as even if map file is present + * without backup_label file, it is harmless. + */ + if (stat(TABLESPACE_MAP, &st) == 0) + { + unlink(TABLESPACE_MAP_OLD); + if (durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, DEBUG1) == 0) + ereport(LOG, + (errmsg("ignoring file \"%s\" because no file \"%s\" exists", + TABLESPACE_MAP, BACKUP_LABEL_FILE), + errdetail("File \"%s\" was renamed to \"%s\".", + TABLESPACE_MAP, TABLESPACE_MAP_OLD))); + else + ereport(LOG, + (errmsg("ignoring file \"%s\" because no file \"%s\" exists", + TABLESPACE_MAP, BACKUP_LABEL_FILE), + errdetail("Could not rename file \"%s\" to \"%s\": %m.", + TABLESPACE_MAP, TABLESPACE_MAP_OLD))); + } + + /* + * It's possible that archive recovery was requested, but we don't + * know how far we need to replay the WAL before we reach consistency. + * This can happen for example if a base backup is taken from a + * running server using an atomic filesystem snapshot, without calling + * pg_start/stop_backup. Or if you just kill a running primary server + * and put it into archive recovery by creating a recovery signal + * file. + * + * Our strategy in that case is to perform crash recovery first, + * replaying all the WAL present in pg_wal, and only enter archive + * recovery after that. + * + * But usually we already know how far we need to replay the WAL (up + * to minRecoveryPoint, up to backupEndPoint, or until we see an + * end-of-backup record), and we can enter archive recovery directly. + */ + if (ArchiveRecoveryRequested && + (ControlFile->minRecoveryPoint != InvalidXLogRecPtr || + ControlFile->backupEndRequired || + ControlFile->backupEndPoint != InvalidXLogRecPtr || + ControlFile->state == DB_SHUTDOWNED)) + { + InArchiveRecovery = true; + if (StandbyModeRequested) + StandbyMode = true; + } + + /* Get the last valid checkpoint record. */ + CheckPointLoc = ControlFile->checkPoint; + CheckPointTLI = ControlFile->checkPointCopy.ThisTimeLineID; + RedoStartLSN = ControlFile->checkPointCopy.redo; + RedoStartTLI = ControlFile->checkPointCopy.ThisTimeLineID; + record = ReadCheckpointRecord(xlogreader, CheckPointLoc, 1, true, + CheckPointTLI); + if (record != NULL) + { + ereport(DEBUG1, + (errmsg_internal("checkpoint record is at %X/%X", + LSN_FORMAT_ARGS(CheckPointLoc)))); + } + else + { + /* + * We used to attempt to go back to a secondary checkpoint record + * here, but only when not in standby mode. We now just fail if we + * can't read the last checkpoint because this allows us to + * simplify processing around checkpoints. + */ + ereport(PANIC, + (errmsg("could not locate a valid checkpoint record"))); + } + memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); + wasShutdown = ((record->xl_info & ~XLR_INFO_MASK) == XLOG_CHECKPOINT_SHUTDOWN); + } + + /* + * If the location of the checkpoint record is not on the expected + * timeline in the history of the requested timeline, we cannot proceed: + * the backup is not part of the history of the requested timeline. + */ + Assert(expectedTLEs); /* was initialized by reading checkpoint + * record */ + if (tliOfPointInHistory(CheckPointLoc, expectedTLEs) != + CheckPointTLI) + { + XLogRecPtr switchpoint; + + /* + * tliSwitchPoint will throw an error if the checkpoint's timeline is + * not in expectedTLEs at all. + */ + switchpoint = tliSwitchPoint(ControlFile->checkPointCopy.ThisTimeLineID, expectedTLEs, NULL); + ereport(FATAL, + (errmsg("requested timeline %u is not a child of this server's history", + recoveryTargetTLI), + errdetail("Latest checkpoint is at %X/%X on timeline %u, but in the history of the requested timeline, the server forked off from that timeline at %X/%X.", + LSN_FORMAT_ARGS(ControlFile->checkPoint), + ControlFile->checkPointCopy.ThisTimeLineID, + LSN_FORMAT_ARGS(switchpoint)))); + } + + /* + * The min recovery point should be part of the requested timeline's + * history, too. + */ + if (!XLogRecPtrIsInvalid(ControlFile->minRecoveryPoint) && + tliOfPointInHistory(ControlFile->minRecoveryPoint - 1, expectedTLEs) != + ControlFile->minRecoveryPointTLI) + ereport(FATAL, + (errmsg("requested timeline %u does not contain minimum recovery point %X/%X on timeline %u", + recoveryTargetTLI, + LSN_FORMAT_ARGS(ControlFile->minRecoveryPoint), + ControlFile->minRecoveryPointTLI))); + + ereport(DEBUG1, + (errmsg_internal("redo record is at %X/%X; shutdown %s", + LSN_FORMAT_ARGS(checkPoint.redo), + wasShutdown ? "true" : "false"))); + ereport(DEBUG1, + (errmsg_internal("next transaction ID: " UINT64_FORMAT "; next OID: %u", + U64FromFullTransactionId(checkPoint.nextXid), + checkPoint.nextOid))); + ereport(DEBUG1, + (errmsg_internal("next MultiXactId: %u; next MultiXactOffset: %u", + checkPoint.nextMulti, checkPoint.nextMultiOffset))); + ereport(DEBUG1, + (errmsg_internal("oldest unfrozen transaction ID: %u, in database %u", + checkPoint.oldestXid, checkPoint.oldestXidDB))); + ereport(DEBUG1, + (errmsg_internal("oldest MultiXactId: %u, in database %u", + checkPoint.oldestMulti, checkPoint.oldestMultiDB))); + ereport(DEBUG1, + (errmsg_internal("commit timestamp Xid oldest/newest: %u/%u", + checkPoint.oldestCommitTsXid, + checkPoint.newestCommitTsXid))); + if (!TransactionIdIsNormal(XidFromFullTransactionId(checkPoint.nextXid))) + ereport(PANIC, + (errmsg("invalid next transaction ID"))); + + /* sanity check */ + if (checkPoint.redo > CheckPointLoc) + ereport(PANIC, + (errmsg("invalid redo in checkpoint record"))); + + /* + * Check whether we need to force recovery from WAL. If it appears to + * have been a clean shutdown and we did not have a recovery signal file, + * then assume no recovery needed. + */ + if (checkPoint.redo < CheckPointLoc) + { + if (wasShutdown) + ereport(PANIC, + (errmsg("invalid redo record in shutdown checkpoint"))); + InRecovery = true; + } + else if (ControlFile->state != DB_SHUTDOWNED) + InRecovery = true; + else if (ArchiveRecoveryRequested) + { + /* force recovery due to presence of recovery signal file */ + InRecovery = true; + } + + /* + * Update pg_control to show that we are recovering and to show the + * selected checkpoint as the place we are starting from. We also mark + * pg_control with any minimum recovery stop point obtained from a backup + * history file. + */ + if (InArchiveRecovery) + { + ControlFile->state = DB_IN_ARCHIVE_RECOVERY; + } + else + { + ereport(LOG, + (errmsg("database system was not properly shut down; " + "automatic recovery in progress"))); + if (recoveryTargetTLI > ControlFile->checkPointCopy.ThisTimeLineID) + ereport(LOG, + (errmsg("crash recovery starts in timeline %u " + "and has target timeline %u", + ControlFile->checkPointCopy.ThisTimeLineID, + recoveryTargetTLI))); + ControlFile->state = DB_IN_CRASH_RECOVERY; + } + ControlFile->checkPoint = CheckPointLoc; + ControlFile->checkPointCopy = checkPoint; + if (InArchiveRecovery) + { + /* initialize minRecoveryPoint if not set yet */ + if (ControlFile->minRecoveryPoint < checkPoint.redo) + { + ControlFile->minRecoveryPoint = checkPoint.redo; + ControlFile->minRecoveryPointTLI = checkPoint.ThisTimeLineID; + } + } + + /* + * Set backupStartPoint if we're starting recovery from a base backup. + * + * Also set backupEndPoint and use minRecoveryPoint as the backup end + * location if we're starting recovery from a base backup which was taken + * from a standby. In this case, the database system status in pg_control + * must indicate that the database was already in recovery. Usually that + * will be DB_IN_ARCHIVE_RECOVERY but also can be + * DB_SHUTDOWNED_IN_RECOVERY if recovery previously was interrupted before + * reaching this point; e.g. because restore_command or primary_conninfo + * were faulty. + * + * Any other state indicates that the backup somehow became corrupted and + * we can't sensibly continue with recovery. + */ + if (haveBackupLabel) + { + ControlFile->backupStartPoint = checkPoint.redo; + ControlFile->backupEndRequired = backupEndRequired; + + if (backupFromStandby) + { + if (dbstate_at_startup != DB_IN_ARCHIVE_RECOVERY && + dbstate_at_startup != DB_SHUTDOWNED_IN_RECOVERY) + ereport(FATAL, + (errmsg("backup_label contains data inconsistent with control file"), + errhint("This means that the backup is corrupted and you will " + "have to use another backup for recovery."))); + ControlFile->backupEndPoint = ControlFile->minRecoveryPoint; + } + } + + /* remember these, so that we know when we have reached consistency */ + backupStartPoint = ControlFile->backupStartPoint; + backupEndRequired = ControlFile->backupEndRequired; + backupEndPoint = ControlFile->backupEndPoint; + if (InArchiveRecovery) + { + minRecoveryPoint = ControlFile->minRecoveryPoint; + minRecoveryPointTLI = ControlFile->minRecoveryPointTLI; + } + else + { + minRecoveryPoint = InvalidXLogRecPtr; + minRecoveryPointTLI = 0; + } + + /* + * Start recovery assuming that the final record isn't lost. + */ + abortedRecPtr = InvalidXLogRecPtr; + missingContrecPtr = InvalidXLogRecPtr; + + *wasShutdown_ptr = wasShutdown; + *haveBackupLabel_ptr = haveBackupLabel; + *haveTblspcMap_ptr = haveTblspcMap; +} + +/* + * See if there are any recovery signal files and if so, set state for + * recovery. + * + * See if there is a recovery command file (recovery.conf), and if so + * throw an ERROR since as of PG12 we no longer recognize that. + */ +static void +readRecoverySignalFile(void) +{ + struct stat stat_buf; + + if (IsBootstrapProcessingMode()) + return; + + /* + * Check for old recovery API file: recovery.conf + */ + if (stat(RECOVERY_COMMAND_FILE, &stat_buf) == 0) + ereport(FATAL, + (errcode_for_file_access(), + errmsg("using recovery command file \"%s\" is not supported", + RECOVERY_COMMAND_FILE))); + + /* + * Remove unused .done file, if present. Ignore if absent. + */ + unlink(RECOVERY_COMMAND_DONE); + + /* + * Check for recovery signal files and if found, fsync them since they + * represent server state information. We don't sweat too much about the + * possibility of fsync failure, however. + * + * If present, standby signal file takes precedence. If neither is present + * then we won't enter archive recovery. + */ + if (stat(STANDBY_SIGNAL_FILE, &stat_buf) == 0) + { + int fd; + + fd = BasicOpenFilePerm(STANDBY_SIGNAL_FILE, O_RDWR | PG_BINARY, + S_IRUSR | S_IWUSR); + if (fd >= 0) + { + (void) pg_fsync(fd); + close(fd); + } + standby_signal_file_found = true; + } + else if (stat(RECOVERY_SIGNAL_FILE, &stat_buf) == 0) + { + int fd; + + fd = BasicOpenFilePerm(RECOVERY_SIGNAL_FILE, O_RDWR | PG_BINARY, + S_IRUSR | S_IWUSR); + if (fd >= 0) + { + (void) pg_fsync(fd); + close(fd); + } + recovery_signal_file_found = true; + } + + StandbyModeRequested = false; + ArchiveRecoveryRequested = false; + if (standby_signal_file_found) + { + StandbyModeRequested = true; + ArchiveRecoveryRequested = true; + } + else if (recovery_signal_file_found) + { + StandbyModeRequested = false; + ArchiveRecoveryRequested = true; + } + else + return; + + /* + * We don't support standby mode in standalone backends; that requires + * other processes such as the WAL receiver to be alive. + */ + if (StandbyModeRequested && !IsUnderPostmaster) + ereport(FATAL, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("standby mode is not supported by single-user servers"))); +} + +static void +validateRecoveryParameters(void) +{ + if (!ArchiveRecoveryRequested) + return; + + /* + * Check for compulsory parameters + */ + if (StandbyModeRequested) + { + if ((PrimaryConnInfo == NULL || strcmp(PrimaryConnInfo, "") == 0) && + (recoveryRestoreCommand == NULL || strcmp(recoveryRestoreCommand, "") == 0)) + ereport(WARNING, + (errmsg("specified neither primary_conninfo nor restore_command"), + errhint("The database server will regularly poll the pg_wal subdirectory to check for files placed there."))); + } + else + { + if (recoveryRestoreCommand == NULL || + strcmp(recoveryRestoreCommand, "") == 0) + ereport(FATAL, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("must specify restore_command when standby mode is not enabled"))); + } + + /* + * Override any inconsistent requests. Note that this is a change of + * behaviour in 9.5; prior to this we simply ignored a request to pause if + * hot_standby = off, which was surprising behaviour. + */ + if (recoveryTargetAction == RECOVERY_TARGET_ACTION_PAUSE && + !EnableHotStandby) + recoveryTargetAction = RECOVERY_TARGET_ACTION_SHUTDOWN; + + /* + * Final parsing of recovery_target_time string; see also + * check_recovery_target_time(). + */ + if (recoveryTarget == RECOVERY_TARGET_TIME) + { + recoveryTargetTime = DatumGetTimestampTz(DirectFunctionCall3(timestamptz_in, + CStringGetDatum(recovery_target_time_string), + ObjectIdGetDatum(InvalidOid), + Int32GetDatum(-1))); + } + + /* + * If user specified recovery_target_timeline, validate it or compute the + * "latest" value. We can't do this until after we've gotten the restore + * command and set InArchiveRecovery, because we need to fetch timeline + * history files from the archive. + */ + if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_NUMERIC) + { + TimeLineID rtli = recoveryTargetTLIRequested; + + /* Timeline 1 does not have a history file, all else should */ + if (rtli != 1 && !existsTimeLineHistory(rtli)) + ereport(FATAL, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("recovery target timeline %u does not exist", + rtli))); + recoveryTargetTLI = rtli; + } + else if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_LATEST) + { + /* We start the "latest" search from pg_control's timeline */ + recoveryTargetTLI = findNewestTimeLine(recoveryTargetTLI); + } + else + { + /* + * else we just use the recoveryTargetTLI as already read from + * ControlFile + */ + Assert(recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_CONTROLFILE); + } +} + +/* + * read_backup_label: check to see if a backup_label file is present + * + * If we see a backup_label during recovery, we assume that we are recovering + * from a backup dump file, and we therefore roll forward from the checkpoint + * identified by the label file, NOT what pg_control says. This avoids the + * problem that pg_control might have been archived one or more checkpoints + * later than the start of the dump, and so if we rely on it as the start + * point, we will fail to restore a consistent database state. + * + * Returns true if a backup_label was found (and fills the checkpoint + * location and TLI into *checkPointLoc and *backupLabelTLI, respectively); + * returns false if not. If this backup_label came from a streamed backup, + * *backupEndRequired is set to true. If this backup_label was created during + * recovery, *backupFromStandby is set to true. + * + * Also sets the global variables RedoStartLSN and RedoStartTLI with the LSN + * and TLI read from the backup file. + */ +static bool +read_backup_label(XLogRecPtr *checkPointLoc, TimeLineID *backupLabelTLI, + bool *backupEndRequired, bool *backupFromStandby) +{ + char startxlogfilename[MAXFNAMELEN]; + TimeLineID tli_from_walseg, + tli_from_file; + FILE *lfp; + char ch; + char backuptype[20]; + char backupfrom[20]; + char backuplabel[MAXPGPATH]; + char backuptime[128]; + uint32 hi, + lo; + + /* suppress possible uninitialized-variable warnings */ + *checkPointLoc = InvalidXLogRecPtr; + *backupLabelTLI = 0; + *backupEndRequired = false; + *backupFromStandby = false; + + /* + * See if label file is present + */ + lfp = AllocateFile(BACKUP_LABEL_FILE, "r"); + if (!lfp) + { + if (errno != ENOENT) + ereport(FATAL, + (errcode_for_file_access(), + errmsg("could not read file \"%s\": %m", + BACKUP_LABEL_FILE))); + return false; /* it's not there, all is fine */ + } + + /* + * Read and parse the START WAL LOCATION and CHECKPOINT lines (this code + * is pretty crude, but we are not expecting any variability in the file + * format). + */ + if (fscanf(lfp, "START WAL LOCATION: %X/%X (file %08X%16s)%c", + &hi, &lo, &tli_from_walseg, startxlogfilename, &ch) != 5 || ch != '\n') + ereport(FATAL, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); + RedoStartLSN = ((uint64) hi) << 32 | lo; + RedoStartTLI = tli_from_walseg; + if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%X%c", + &hi, &lo, &ch) != 3 || ch != '\n') + ereport(FATAL, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE))); + *checkPointLoc = ((uint64) hi) << 32 | lo; + *backupLabelTLI = tli_from_walseg; + + /* + * BACKUP METHOD and BACKUP FROM lines are new in 9.2. We can't restore + * from an older backup anyway, but since the information on it is not + * strictly required, don't error out if it's missing for some reason. + */ + if (fscanf(lfp, "BACKUP METHOD: %19s\n", backuptype) == 1) + { + if (strcmp(backuptype, "streamed") == 0) + *backupEndRequired = true; + } + + if (fscanf(lfp, "BACKUP FROM: %19s\n", backupfrom) == 1) + { + if (strcmp(backupfrom, "standby") == 0) + *backupFromStandby = true; + } + + /* + * Parse START TIME and LABEL. Those are not mandatory fields for recovery + * but checking for their presence is useful for debugging and the next + * sanity checks. Cope also with the fact that the result buffers have a + * pre-allocated size, hence if the backup_label file has been generated + * with strings longer than the maximum assumed here an incorrect parsing + * happens. That's fine as only minor consistency checks are done + * afterwards. + */ + if (fscanf(lfp, "START TIME: %127[^\n]\n", backuptime) == 1) + ereport(DEBUG1, + (errmsg_internal("backup time %s in file \"%s\"", + backuptime, BACKUP_LABEL_FILE))); + + if (fscanf(lfp, "LABEL: %1023[^\n]\n", backuplabel) == 1) + ereport(DEBUG1, + (errmsg_internal("backup label %s in file \"%s\"", + backuplabel, BACKUP_LABEL_FILE))); + + /* + * START TIMELINE is new as of 11. Its parsing is not mandatory, still use + * it as a sanity check if present. + */ + if (fscanf(lfp, "START TIMELINE: %u\n", &tli_from_file) == 1) + { + if (tli_from_walseg != tli_from_file) + ereport(FATAL, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE), + errdetail("Timeline ID parsed is %u, but expected %u.", + tli_from_file, tli_from_walseg))); + + ereport(DEBUG1, + (errmsg_internal("backup timeline %u in file \"%s\"", + tli_from_file, BACKUP_LABEL_FILE))); + } + + if (ferror(lfp) || FreeFile(lfp)) + ereport(FATAL, + (errcode_for_file_access(), + errmsg("could not read file \"%s\": %m", + BACKUP_LABEL_FILE))); + + return true; +} + +/* + * read_tablespace_map: check to see if a tablespace_map file is present + * + * If we see a tablespace_map file during recovery, we assume that we are + * recovering from a backup dump file, and we therefore need to create symlinks + * as per the information present in tablespace_map file. + * + * Returns true if a tablespace_map file was found (and fills *tablespaces + * with a tablespaceinfo struct for each tablespace listed in the file); + * returns false if not. + */ +static bool +read_tablespace_map(List **tablespaces) +{ + tablespaceinfo *ti; + FILE *lfp; + char str[MAXPGPATH]; + int ch, + i, + n; + bool was_backslash; + + /* + * See if tablespace_map file is present + */ + lfp = AllocateFile(TABLESPACE_MAP, "r"); + if (!lfp) + { + if (errno != ENOENT) + ereport(FATAL, + (errcode_for_file_access(), + errmsg("could not read file \"%s\": %m", + TABLESPACE_MAP))); + return false; /* it's not there, all is fine */ + } + + /* + * Read and parse the link name and path lines from tablespace_map file + * (this code is pretty crude, but we are not expecting any variability in + * the file format). De-escape any backslashes that were inserted. + */ + i = 0; + was_backslash = false; + while ((ch = fgetc(lfp)) != EOF) + { + if (!was_backslash && (ch == '\n' || ch == '\r')) + { + if (i == 0) + continue; /* \r immediately followed by \n */ + + /* + * The de-escaped line should contain an OID followed by exactly + * one space followed by a path. The path might start with + * spaces, so don't be too liberal about parsing. + */ + str[i] = '\0'; + n = 0; + while (str[n] && str[n] != ' ') + n++; + if (n < 1 || n >= i - 1) + ereport(FATAL, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("invalid data in file \"%s\"", TABLESPACE_MAP))); + str[n++] = '\0'; + + ti = palloc0(sizeof(tablespaceinfo)); + ti->oid = pstrdup(str); + ti->path = pstrdup(str + n); + *tablespaces = lappend(*tablespaces, ti); + + i = 0; + continue; + } + else if (!was_backslash && ch == '\\') + was_backslash = true; + else + { + if (i < sizeof(str) - 1) + str[i++] = ch; + was_backslash = false; + } + } + + if (i != 0 || was_backslash) /* last line not terminated? */ + ereport(FATAL, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("invalid data in file \"%s\"", TABLESPACE_MAP))); + + if (ferror(lfp) || FreeFile(lfp)) + ereport(FATAL, + (errcode_for_file_access(), + errmsg("could not read file \"%s\": %m", + TABLESPACE_MAP))); + + return true; +} + +/* + * Finish WAL recovery. + * + * This does not close the 'xlogreader' yet, because in some cases the caller + * still wants to re-read the last checkpoint record by calling + * ReadCheckPointRecord(). + * + * Returns the position of the last valid or applied record, after which new + * WAL should be appended, information about why recovery was ended, and some + * other things. See the WalRecoveryResult struct for details. + */ +EndOfWalRecoveryInfo * +FinishWalRecovery(void) +{ + EndOfWalRecoveryInfo *result = palloc(sizeof(EndOfWalRecoveryInfo)); + XLogRecPtr lastRec; + TimeLineID lastRecTLI; + XLogRecPtr endOfLog; + + /* + * Kill WAL receiver, if it's still running, before we continue to write + * the startup checkpoint and aborted-contrecord records. It will trump + * over these records and subsequent ones if it's still alive when we + * start writing WAL. + */ + XLogShutdownWalRcv(); + + /* + * We are now done reading the xlog from stream. Turn off streaming + * recovery to force fetching the files (which would be required at end of + * recovery, e.g., timeline history file) from archive or pg_wal. + * + * Note that standby mode must be turned off after killing WAL receiver, + * i.e., calling XLogShutdownWalRcv(). + */ + Assert(!WalRcvStreaming()); + StandbyMode = false; + + /* + * Determine where to start writing WAL next. + * + * Re-fetch the last valid or last applied record, so we can identify the + * exact endpoint of what we consider the valid portion of WAL. There may + * be an incomplete continuation record after that, in which case + * 'abortedRecPtr' and 'missingContrecPtr' are set and the caller will + * write a special OVERWRITE_CONTRECORD message to mark that the rest of + * it is intentionally missing. See CreateOverwriteContrecordRecord(). + * + * An important side-effect of this is to load the last page into + * xlogreader. The caller uses it to initialize the WAL for writing. + */ + if (!InRecovery) + { + lastRec = CheckPointLoc; + lastRecTLI = CheckPointTLI; + } + else + { + lastRec = XLogRecoveryCtl->lastReplayedReadRecPtr; + lastRecTLI = XLogRecoveryCtl->lastReplayedTLI; + } + XLogBeginRead(xlogreader, lastRec); + (void) ReadRecord(xlogreader, PANIC, false, lastRecTLI); + endOfLog = xlogreader->EndRecPtr; + + /* + * Remember the TLI in the filename of the XLOG segment containing the + * end-of-log. It could be different from the timeline that endOfLog + * nominally belongs to, if there was a timeline switch in that segment, + * and we were reading the old WAL from a segment belonging to a higher + * timeline. + */ + result->endOfLogTLI = xlogreader->seg.ws_tli; + + if (ArchiveRecoveryRequested) + { + /* + * We are no longer in archive recovery state. + * + * We are now done reading the old WAL. Turn off archive fetching if + * it was active. + */ + Assert(InArchiveRecovery); + InArchiveRecovery = false; + + /* + * If the ending log segment is still open, close it (to avoid + * problems on Windows with trying to rename or delete an open file). + */ + if (readFile >= 0) + { + close(readFile); + readFile = -1; + } + } + + /* + * Copy the last partial block to the caller, for initializing the WAL + * buffer for appending new WAL. + */ + if (endOfLog % XLOG_BLCKSZ != 0) + { + char *page; + int len; + XLogRecPtr pageBeginPtr; + + pageBeginPtr = endOfLog - (endOfLog % XLOG_BLCKSZ); + Assert(readOff == XLogSegmentOffset(pageBeginPtr, wal_segment_size)); + + /* Copy the valid part of the last block */ + len = endOfLog % XLOG_BLCKSZ; + page = palloc(len); + memcpy(page, xlogreader->readBuf, len); + + result->lastPageBeginPtr = pageBeginPtr; + result->lastPage = page; + } + else + { + /* There is no partial block to copy. */ + result->lastPageBeginPtr = endOfLog; + result->lastPage = NULL; + } + + /* + * Create a comment for the history file to explain why and where timeline + * changed. + */ + result->recoveryStopReason = getRecoveryStopReason(); + + result->lastRec = lastRec; + result->lastRecTLI = lastRecTLI; + result->endOfLog = endOfLog; + + result->abortedRecPtr = abortedRecPtr; + result->missingContrecPtr = missingContrecPtr; + + result->standby_signal_file_found = standby_signal_file_found; + result->recovery_signal_file_found = recovery_signal_file_found; + + return result; +} + +/* + * Clean up the WAL reader and leftovers from restoring WAL from archive + */ +void +ShutdownWalRecovery(void) +{ + char recoveryPath[MAXPGPATH]; + + /* Shut down xlogreader */ + if (readFile >= 0) + { + close(readFile); + readFile = -1; + } + XLogReaderFree(xlogreader); + + if (ArchiveRecoveryRequested) + { + /* + * Since there might be a partial WAL segment named RECOVERYXLOG, get + * rid of it. + */ + snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYXLOG"); + unlink(recoveryPath); /* ignore any error */ + + /* Get rid of any remaining recovered timeline-history file, too */ + snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYHISTORY"); + unlink(recoveryPath); /* ignore any error */ + } + + /* + * We don't need the latch anymore. It's not strictly necessary to disown + * it, but let's do it for the sake of tidiness. + */ + if (ArchiveRecoveryRequested) + DisownLatch(&XLogRecoveryCtl->recoveryWakeupLatch); +} + +/* + * Perform WAL recovery. + * + * If the system was shut down cleanly, this is never called. + */ +void +PerformWalRecovery(void) +{ + int rmid; + XLogRecord *record; + bool reachedRecoveryTarget = false; + TimeLineID replayTLI; + + /* + * Initialize shared variables for tracking progress of WAL replay, as if + * we had just replayed the record before the REDO location (or the + * checkpoint record itself, if it's a shutdown checkpoint). + */ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + if (RedoStartLSN < CheckPointLoc) + { + XLogRecoveryCtl->lastReplayedReadRecPtr = InvalidXLogRecPtr; + XLogRecoveryCtl->lastReplayedEndRecPtr = RedoStartLSN; + XLogRecoveryCtl->lastReplayedTLI = RedoStartTLI; + } + else + { + XLogRecoveryCtl->lastReplayedReadRecPtr = xlogreader->ReadRecPtr; + XLogRecoveryCtl->lastReplayedEndRecPtr = xlogreader->EndRecPtr; + XLogRecoveryCtl->lastReplayedTLI = CheckPointTLI; + } + XLogRecoveryCtl->replayEndRecPtr = XLogRecoveryCtl->lastReplayedEndRecPtr; + XLogRecoveryCtl->replayEndTLI = XLogRecoveryCtl->lastReplayedTLI; + XLogRecoveryCtl->recoveryLastXTime = 0; + XLogRecoveryCtl->currentChunkStartTime = 0; + XLogRecoveryCtl->recoveryPauseState = RECOVERY_NOT_PAUSED; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + /* Also ensure XLogReceiptTime has a sane value */ + XLogReceiptTime = GetCurrentTimestamp(); + + /* + * Let postmaster know we've started redo now, so that it can launch the + * archiver if necessary. + */ + if (IsUnderPostmaster) + SendPostmasterSignal(PMSIGNAL_RECOVERY_STARTED); + + /* + * Allow read-only connections immediately if we're consistent already. + */ + CheckRecoveryConsistency(); + + /* + * Find the first record that logically follows the checkpoint --- it + * might physically precede it, though. + */ + if (RedoStartLSN < CheckPointLoc) + { + /* back up to find the record */ + replayTLI = RedoStartTLI; + XLogBeginRead(xlogreader, RedoStartLSN); + record = ReadRecord(xlogreader, PANIC, false, replayTLI); + } + else + { + /* just have to read next record after CheckPoint */ + Assert(xlogreader->ReadRecPtr == CheckPointLoc); + replayTLI = CheckPointTLI; + record = ReadRecord(xlogreader, LOG, false, replayTLI); + } + + if (record != NULL) + { + TimestampTz xtime; + PGRUsage ru0; + + pg_rusage_init(&ru0); + + InRedo = true; + + /* Initialize resource managers */ + for (rmid = 0; rmid <= RM_MAX_ID; rmid++) + { + if (RmgrTable[rmid].rm_startup != NULL) + RmgrTable[rmid].rm_startup(); + } + + ereport(LOG, + (errmsg("redo starts at %X/%X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)))); + + /* Prepare to report progress of the redo phase. */ + if (!StandbyMode) + begin_startup_progress_phase(); + + /* + * main redo apply loop + */ + do + { + if (!StandbyMode) + ereport_startup_progress("redo in progress, elapsed time: %ld.%02d s, current LSN: %X/%X", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr)); + +#ifdef WAL_DEBUG + if (XLOG_DEBUG || + (rmid == RM_XACT_ID && trace_recovery_messages <= DEBUG2) || + (rmid != RM_XACT_ID && trace_recovery_messages <= DEBUG3)) + { + StringInfoData buf; + + initStringInfo(&buf); + appendStringInfo(&buf, "REDO @ %X/%X; LSN %X/%X: ", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), + LSN_FORMAT_ARGS(xlogreader->EndRecPtr)); + xlog_outrec(&buf, xlogreader); + appendStringInfoString(&buf, " - "); + xlog_outdesc(&buf, xlogreader); + elog(LOG, "%s", buf.data); + pfree(buf.data); + } +#endif + + /* Handle interrupt signals of startup process */ + HandleStartupProcInterrupts(); + + /* + * Pause WAL replay, if requested by a hot-standby session via + * SetRecoveryPause(). + * + * Note that we intentionally don't take the info_lck spinlock + * here. We might therefore read a slightly stale value of the + * recoveryPause flag, but it can't be very stale (no worse than + * the last spinlock we did acquire). Since a pause request is a + * pretty asynchronous thing anyway, possibly responding to it one + * WAL record later than we otherwise would is a minor issue, so + * it doesn't seem worth adding another spinlock cycle to prevent + * that. + */ + if (((volatile XLogRecoveryCtlData *) XLogRecoveryCtl)->recoveryPauseState != + RECOVERY_NOT_PAUSED) + recoveryPausesHere(false); + + /* + * Have we reached our recovery target? + */ + if (recoveryStopsBefore(xlogreader)) + { + reachedRecoveryTarget = true; + break; + } + + /* + * If we've been asked to lag the primary, wait on latch until + * enough time has passed. + */ + if (recoveryApplyDelay(xlogreader)) + { + /* + * We test for paused recovery again here. If user sets + * delayed apply, it may be because they expect to pause + * recovery in case of problems, so we must test again here + * otherwise pausing during the delay-wait wouldn't work. + */ + if (((volatile XLogRecoveryCtlData *) XLogRecoveryCtl)->recoveryPauseState != + RECOVERY_NOT_PAUSED) + recoveryPausesHere(false); + } + + /* + * Apply the record + */ + ApplyWalRecord(xlogreader, record, &replayTLI); + + /* Exit loop if we reached inclusive recovery target */ + if (recoveryStopsAfter(xlogreader)) + { + reachedRecoveryTarget = true; + break; + } + + /* Else, try to fetch the next WAL record */ + record = ReadRecord(xlogreader, LOG, false, replayTLI); + } while (record != NULL); + + /* + * end of main redo apply loop + */ + + if (reachedRecoveryTarget) + { + if (!reachedConsistency) + ereport(FATAL, + (errmsg("requested recovery stop point is before consistent recovery point"))); + + /* + * This is the last point where we can restart recovery with a new + * recovery target, if we shutdown and begin again. After this, + * Resource Managers may choose to do permanent corrective actions + * at end of recovery. + */ + switch (recoveryTargetAction) + { + case RECOVERY_TARGET_ACTION_SHUTDOWN: + + /* + * exit with special return code to request shutdown of + * postmaster. Log messages issued from postmaster. + */ + proc_exit(3); + + case RECOVERY_TARGET_ACTION_PAUSE: + SetRecoveryPause(true); + recoveryPausesHere(true); + + /* drop into promote */ + + case RECOVERY_TARGET_ACTION_PROMOTE: + break; + } + } + + /* Allow resource managers to do any required cleanup. */ + for (rmid = 0; rmid <= RM_MAX_ID; rmid++) + { + if (RmgrTable[rmid].rm_cleanup != NULL) + RmgrTable[rmid].rm_cleanup(); + } + + ereport(LOG, + (errmsg("redo done at %X/%X system usage: %s", + LSN_FORMAT_ARGS(xlogreader->ReadRecPtr), + pg_rusage_show(&ru0)))); + xtime = GetLatestXTime(); + if (xtime) + ereport(LOG, + (errmsg("last completed transaction was at log time %s", + timestamptz_to_str(xtime)))); + + InRedo = false; + } + else + { + /* there are no WAL records following the checkpoint */ + ereport(LOG, + (errmsg("redo is not required"))); + + } + + /* + * This check is intentionally after the above log messages that indicate + * how far recovery went. + */ + if (ArchiveRecoveryRequested && + recoveryTarget != RECOVERY_TARGET_UNSET && + !reachedRecoveryTarget) + ereport(FATAL, + (errmsg("recovery ended before configured recovery target was reached"))); +} + +/* + * Subroutine of PerformWalRecovery, to apply one WAL record. + */ +static void +ApplyWalRecord(XLogReaderState *xlogreader, XLogRecord *record, TimeLineID *replayTLI) +{ + ErrorContextCallback errcallback; + bool switchedTLI = false; + + /* Setup error traceback support for ereport() */ + errcallback.callback = rm_redo_error_callback; + errcallback.arg = (void *) xlogreader; + errcallback.previous = error_context_stack; + error_context_stack = &errcallback; + + /* + * ShmemVariableCache->nextXid must be beyond record's xid. + */ + AdvanceNextFullTransactionIdPastXid(record->xl_xid); + + /* + * Before replaying this record, check if this record causes the current + * timeline to change. The record is already considered to be part of the + * new timeline, so we update replayTLI before replaying it. That's + * important so that replayEndTLI, which is recorded as the minimum + * recovery point's TLI if recovery stops after this record, is set + * correctly. + */ + if (record->xl_rmid == RM_XLOG_ID) + { + TimeLineID newReplayTLI = *replayTLI; + TimeLineID prevReplayTLI = *replayTLI; + uint8 info = record->xl_info & ~XLR_INFO_MASK; + + if (info == XLOG_CHECKPOINT_SHUTDOWN) + { + CheckPoint checkPoint; + + memcpy(&checkPoint, XLogRecGetData(xlogreader), sizeof(CheckPoint)); + newReplayTLI = checkPoint.ThisTimeLineID; + prevReplayTLI = checkPoint.PrevTimeLineID; + } + else if (info == XLOG_END_OF_RECOVERY) + { + xl_end_of_recovery xlrec; + + memcpy(&xlrec, XLogRecGetData(xlogreader), sizeof(xl_end_of_recovery)); + newReplayTLI = xlrec.ThisTimeLineID; + prevReplayTLI = xlrec.PrevTimeLineID; + } + + if (newReplayTLI != *replayTLI) + { + /* Check that it's OK to switch to this TLI */ + checkTimeLineSwitch(xlogreader->EndRecPtr, + newReplayTLI, prevReplayTLI, *replayTLI); + + /* Following WAL records should be run with new TLI */ + *replayTLI = newReplayTLI; + switchedTLI = true; + } + } + + /* + * Update shared replayEndRecPtr before replaying this record, so that + * XLogFlush will update minRecoveryPoint correctly. + */ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->replayEndRecPtr = xlogreader->EndRecPtr; + XLogRecoveryCtl->replayEndTLI = *replayTLI; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + /* + * If we are attempting to enter Hot Standby mode, process XIDs we see + */ + if (standbyState >= STANDBY_INITIALIZED && + TransactionIdIsValid(record->xl_xid)) + RecordKnownAssignedTransactionIds(record->xl_xid); + + /* + * Some XLOG record types that are related to recovery are processed + * directly here, rather than in xlog_redo() + */ + if (record->xl_rmid == RM_XLOG_ID) + xlogrecovery_redo(xlogreader, *replayTLI); + + /* Now apply the WAL record itself */ + RmgrTable[record->xl_rmid].rm_redo(xlogreader); + + /* + * After redo, check whether the backup pages associated with the WAL + * record are consistent with the existing pages. This check is done only + * if consistency check is enabled for this record. + */ + if ((record->xl_info & XLR_CHECK_CONSISTENCY) != 0) + verifyBackupPageConsistency(xlogreader); + + /* Pop the error context stack */ + error_context_stack = errcallback.previous; + + /* + * Update lastReplayedEndRecPtr after this record has been successfully + * replayed. + */ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->lastReplayedReadRecPtr = xlogreader->ReadRecPtr; + XLogRecoveryCtl->lastReplayedEndRecPtr = xlogreader->EndRecPtr; + XLogRecoveryCtl->lastReplayedTLI = *replayTLI; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + /* + * If rm_redo called XLogRequestWalReceiverReply, then we wake up the + * receiver so that it notices the updated lastReplayedEndRecPtr and sends + * a reply to the primary. + */ + if (doRequestWalReceiverReply) + { + doRequestWalReceiverReply = false; + WalRcvForceReply(); + } + + /* Allow read-only connections if we're consistent now */ + CheckRecoveryConsistency(); + + /* Is this a timeline switch? */ + if (switchedTLI) + { + /* + * Before we continue on the new timeline, clean up any (possibly + * bogus) future WAL segments on the old timeline. + */ + RemoveNonParentXlogFiles(xlogreader->EndRecPtr, *replayTLI); + + /* + * Wake up any walsenders to notice that we are on a new timeline. + */ + if (AllowCascadeReplication()) + WalSndWakeup(); + } +} + +/* + * Some XLOG RM record types that are directly related to WAL recovery are + * handled here rather than in the xlog_redo() + */ +static void +xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) +{ + uint8 info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; + XLogRecPtr lsn = record->EndRecPtr; + + Assert(XLogRecGetRmid(record) == RM_XLOG_ID); + + if (info == XLOG_OVERWRITE_CONTRECORD) + { + /* Verify the payload of a XLOG_OVERWRITE_CONTRECORD record. */ + xl_overwrite_contrecord xlrec; + + memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_overwrite_contrecord)); + if (xlrec.overwritten_lsn != record->overwrittenRecPtr) + elog(FATAL, "mismatching overwritten LSN %X/%X -> %X/%X", + LSN_FORMAT_ARGS(xlrec.overwritten_lsn), + LSN_FORMAT_ARGS(record->overwrittenRecPtr)); + + ereport(LOG, + (errmsg("successfully skipped missing contrecord at %X/%X, overwritten at %s", + LSN_FORMAT_ARGS(xlrec.overwritten_lsn), + timestamptz_to_str(xlrec.overwrite_time)))); + + /* Verifying the record should only happen once */ + record->overwrittenRecPtr = InvalidXLogRecPtr; + } + else if (info == XLOG_BACKUP_END) + { + XLogRecPtr startpoint; + + memcpy(&startpoint, XLogRecGetData(record), sizeof(startpoint)); + + if (backupStartPoint == startpoint) + { + /* + * We have reached the end of base backup, the point where + * pg_stop_backup() was done. The data on disk is now consistent + * (assuming we have also reached minRecoveryPoint). Set + * backupEndPoint to the current LSN, so that the next call to + * CheckRecoveryConsistency() will notice it and do the + * end-of-backup processing. + */ + elog(DEBUG1, "end of backup record reached"); + + backupEndPoint = lsn; + } + else + elog(DEBUG1, "saw end-of-backup record for backup starting at %X/%X, waiting for %X/%X", + LSN_FORMAT_ARGS(startpoint), LSN_FORMAT_ARGS(backupStartPoint)); + } +} + +/* + * Checks if recovery has reached a consistent state. When consistency is + * reached and we have a valid starting standby snapshot, tell postmaster + * that it can start accepting read-only connections. + */ +static void +CheckRecoveryConsistency(void) +{ + XLogRecPtr lastReplayedEndRecPtr; + TimeLineID lastReplayedTLI; + + /* + * During crash recovery, we don't reach a consistent state until we've + * replayed all the WAL. + */ + if (XLogRecPtrIsInvalid(minRecoveryPoint)) + return; + + Assert(InArchiveRecovery); + + /* + * assume that we are called in the startup process, and hence don't need + * a lock to read lastReplayedEndRecPtr + */ + lastReplayedEndRecPtr = XLogRecoveryCtl->lastReplayedEndRecPtr; + lastReplayedTLI = XLogRecoveryCtl->lastReplayedTLI; + + /* + * Have we reached the point where our base backup was completed? + */ + if (!XLogRecPtrIsInvalid(backupEndPoint) && + backupEndPoint <= lastReplayedEndRecPtr) + { + elog(DEBUG1, "end of backup reached"); + + /* + * We have reached the end of base backup, as indicated by pg_control. + * Update the control file accordingly. + */ + ReachedEndOfBackup(lastReplayedEndRecPtr, lastReplayedTLI); + backupStartPoint = InvalidXLogRecPtr; + backupEndPoint = InvalidXLogRecPtr; + backupEndRequired = false; + } + + /* + * Have we passed our safe starting point? Note that minRecoveryPoint is + * known to be incorrectly set if ControlFile->backupEndRequired, until + * the XLOG_BACKUP_END arrives to advise us of the correct + * minRecoveryPoint. All we know prior to that is that we're not + * consistent yet. + */ + if (!reachedConsistency && !backupEndRequired && + minRecoveryPoint <= lastReplayedEndRecPtr) + { + /* + * Check to see if the XLOG sequence contained any unresolved + * references to uninitialized pages. + */ + XLogCheckInvalidPages(); + + reachedConsistency = true; + ereport(LOG, + (errmsg("consistent recovery state reached at %X/%X", + LSN_FORMAT_ARGS(lastReplayedEndRecPtr)))); + } + + /* + * Have we got a valid starting snapshot that will allow queries to be + * run? If so, we can tell postmaster that the database is consistent now, + * enabling connections. + */ + if (standbyState == STANDBY_SNAPSHOT_READY && + !LocalHotStandbyActive && + reachedConsistency && + IsUnderPostmaster) + { + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->SharedHotStandbyActive = true; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + LocalHotStandbyActive = true; + + SendPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY); + } +} + +/* + * Error context callback for errors occurring during rm_redo(). + */ +static void +rm_redo_error_callback(void *arg) +{ + XLogReaderState *record = (XLogReaderState *) arg; + StringInfoData buf; + + initStringInfo(&buf); + xlog_outdesc(&buf, record); + xlog_block_info(&buf, record); + + /* translator: %s is a WAL record description */ + errcontext("WAL redo at %X/%X for %s", + LSN_FORMAT_ARGS(record->ReadRecPtr), + buf.data); + + pfree(buf.data); +} + +/* + * Returns a string describing an XLogRecord, consisting of its identity + * optionally followed by a colon, a space, and a further description. + */ +void +xlog_outdesc(StringInfo buf, XLogReaderState *record) +{ + RmgrId rmid = XLogRecGetRmid(record); + uint8 info = XLogRecGetInfo(record); + const char *id; + + appendStringInfoString(buf, RmgrTable[rmid].rm_name); + appendStringInfoChar(buf, '/'); + + id = RmgrTable[rmid].rm_identify(info); + if (id == NULL) + appendStringInfo(buf, "UNKNOWN (%X): ", info & ~XLR_INFO_MASK); + else + appendStringInfo(buf, "%s: ", id); + + RmgrTable[rmid].rm_desc(buf, record); +} + +#ifdef WAL_DEBUG + +static void +xlog_outrec(StringInfo buf, XLogReaderState *record) +{ + appendStringInfo(buf, "prev %X/%X; xid %u", + LSN_FORMAT_ARGS(XLogRecGetPrev(record)), + XLogRecGetXid(record)); + + appendStringInfo(buf, "; len %u", + XLogRecGetDataLen(record)); + + xlog_block_info(buf, record); +} +#endif /* WAL_DEBUG */ + +/* + * Returns a string giving information about all the blocks in an + * XLogRecord. + */ +static void +xlog_block_info(StringInfo buf, XLogReaderState *record) +{ + int block_id; + + /* decode block references */ + for (block_id = 0; block_id <= record->max_block_id; block_id++) + { + RelFileNode rnode; + ForkNumber forknum; + BlockNumber blk; + + if (!XLogRecHasBlockRef(record, block_id)) + continue; + + XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blk); + if (forknum != MAIN_FORKNUM) + appendStringInfo(buf, "; blkref #%d: rel %u/%u/%u, fork %u, blk %u", + block_id, + rnode.spcNode, rnode.dbNode, rnode.relNode, + forknum, + blk); + else + appendStringInfo(buf, "; blkref #%d: rel %u/%u/%u, blk %u", + block_id, + rnode.spcNode, rnode.dbNode, rnode.relNode, + blk); + if (XLogRecHasBlockImage(record, block_id)) + appendStringInfoString(buf, " FPW"); + } +} + + +/* + * Check that it's OK to switch to new timeline during recovery. + * + * 'lsn' is the address of the shutdown checkpoint record we're about to + * replay. (Currently, timeline can only change at a shutdown checkpoint). + */ +static void +checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI, TimeLineID prevTLI, + TimeLineID replayTLI) +{ + /* Check that the record agrees on what the current (old) timeline is */ + if (prevTLI != replayTLI) + ereport(PANIC, + (errmsg("unexpected previous timeline ID %u (current timeline ID %u) in checkpoint record", + prevTLI, replayTLI))); + + /* + * The new timeline better be in the list of timelines we expect to see, + * according to the timeline history. It should also not decrease. + */ + if (newTLI < replayTLI || !tliInHistory(newTLI, expectedTLEs)) + ereport(PANIC, + (errmsg("unexpected timeline ID %u (after %u) in checkpoint record", + newTLI, replayTLI))); + + /* + * If we have not yet reached min recovery point, and we're about to + * switch to a timeline greater than the timeline of the min recovery + * point: trouble. After switching to the new timeline, we could not + * possibly visit the min recovery point on the correct timeline anymore. + * This can happen if there is a newer timeline in the archive that + * branched before the timeline the min recovery point is on, and you + * attempt to do PITR to the new timeline. + */ + if (!XLogRecPtrIsInvalid(minRecoveryPoint) && + lsn < minRecoveryPoint && + newTLI > minRecoveryPointTLI) + ereport(PANIC, + (errmsg("unexpected timeline ID %u in checkpoint record, before reaching minimum recovery point %X/%X on timeline %u", + newTLI, + LSN_FORMAT_ARGS(minRecoveryPoint), + minRecoveryPointTLI))); + + /* Looks good */ +} + + +/* + * Extract timestamp from WAL record. + * + * If the record contains a timestamp, returns true, and saves the timestamp + * in *recordXtime. If the record type has no timestamp, returns false. + * Currently, only transaction commit/abort records and restore points contain + * timestamps. + */ +static bool +getRecordTimestamp(XLogReaderState *record, TimestampTz *recordXtime) +{ + uint8 info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; + uint8 xact_info = info & XLOG_XACT_OPMASK; + uint8 rmid = XLogRecGetRmid(record); + + if (rmid == RM_XLOG_ID && info == XLOG_RESTORE_POINT) + { + *recordXtime = ((xl_restore_point *) XLogRecGetData(record))->rp_time; + return true; + } + if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_COMMIT || + xact_info == XLOG_XACT_COMMIT_PREPARED)) + { + *recordXtime = ((xl_xact_commit *) XLogRecGetData(record))->xact_time; + return true; + } + if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_ABORT || + xact_info == XLOG_XACT_ABORT_PREPARED)) + { + *recordXtime = ((xl_xact_abort *) XLogRecGetData(record))->xact_time; + return true; + } + return false; +} + +/* + * Checks whether the current buffer page and backup page stored in the + * WAL record are consistent or not. Before comparing the two pages, a + * masking can be applied to the pages to ignore certain areas like hint bits, + * unused space between pd_lower and pd_upper among other things. This + * function should be called once WAL replay has been completed for a + * given record. + */ +static void +verifyBackupPageConsistency(XLogReaderState *record) +{ + RmgrId rmid = XLogRecGetRmid(record); + RelFileNode rnode; + ForkNumber forknum; + BlockNumber blkno; + int block_id; + + /* Records with no backup blocks have no need for consistency checks. */ + if (!XLogRecHasAnyBlockRefs(record)) + return; + + Assert((XLogRecGetInfo(record) & XLR_CHECK_CONSISTENCY) != 0); + + for (block_id = 0; block_id <= record->max_block_id; block_id++) + { + Buffer buf; + Page page; + + if (!XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blkno)) + { + /* + * WAL record doesn't contain a block reference with the given id. + * Do nothing. + */ + continue; + } + + Assert(XLogRecHasBlockImage(record, block_id)); + + if (XLogRecBlockImageApply(record, block_id)) + { + /* + * WAL record has already applied the page, so bypass the + * consistency check as that would result in comparing the full + * page stored in the record with itself. + */ + continue; + } + + /* + * Read the contents from the current buffer and store it in a + * temporary page. + */ + buf = XLogReadBufferExtended(rnode, forknum, blkno, + RBM_NORMAL_NO_LOG); + if (!BufferIsValid(buf)) + continue; + + LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE); + page = BufferGetPage(buf); + + /* + * Take a copy of the local page where WAL has been applied to have a + * comparison base before masking it... + */ + memcpy(replay_image_masked, page, BLCKSZ); + + /* No need for this page anymore now that a copy is in. */ + UnlockReleaseBuffer(buf); + + /* + * If the block LSN is already ahead of this WAL record, we can't + * expect contents to match. This can happen if recovery is + * restarted. + */ + if (PageGetLSN(replay_image_masked) > record->EndRecPtr) + continue; + + /* + * Read the contents from the backup copy, stored in WAL record and + * store it in a temporary page. There is no need to allocate a new + * page here, a local buffer is fine to hold its contents and a mask + * can be directly applied on it. + */ + if (!RestoreBlockImage(record, block_id, primary_image_masked)) + elog(ERROR, "failed to restore block image"); + + /* + * If masking function is defined, mask both the primary and replay + * images + */ + if (RmgrTable[rmid].rm_mask != NULL) + { + RmgrTable[rmid].rm_mask(replay_image_masked, blkno); + RmgrTable[rmid].rm_mask(primary_image_masked, blkno); + } + + /* Time to compare the primary and replay images. */ + if (memcmp(replay_image_masked, primary_image_masked, BLCKSZ) != 0) + { + elog(FATAL, + "inconsistent page found, rel %u/%u/%u, forknum %u, blkno %u", + rnode.spcNode, rnode.dbNode, rnode.relNode, + forknum, blkno); + } + } +} + +/* + * For point-in-time recovery, this function decides whether we want to + * stop applying the XLOG before the current record. + * + * Returns true if we are stopping, false otherwise. If stopping, some + * information is saved in recoveryStopXid et al for use in annotating the + * new timeline's history file. + */ +static bool +recoveryStopsBefore(XLogReaderState *record) +{ + bool stopsHere = false; + uint8 xact_info; + bool isCommit; + TimestampTz recordXtime = 0; + TransactionId recordXid; + + /* + * Ignore recovery target settings when not in archive recovery (meaning + * we are in crash recovery). + */ + if (!ArchiveRecoveryRequested) + return false; + + /* Check if we should stop as soon as reaching consistency */ + if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE && reachedConsistency) + { + ereport(LOG, + (errmsg("recovery stopping after reaching consistency"))); + + recoveryStopAfter = false; + recoveryStopXid = InvalidTransactionId; + recoveryStopLSN = InvalidXLogRecPtr; + recoveryStopTime = 0; + recoveryStopName[0] = '\0'; + return true; + } + + /* Check if target LSN has been reached */ + if (recoveryTarget == RECOVERY_TARGET_LSN && + !recoveryTargetInclusive && + record->ReadRecPtr >= recoveryTargetLSN) + { + recoveryStopAfter = false; + recoveryStopXid = InvalidTransactionId; + recoveryStopLSN = record->ReadRecPtr; + recoveryStopTime = 0; + recoveryStopName[0] = '\0'; + ereport(LOG, + (errmsg("recovery stopping before WAL location (LSN) \"%X/%X\"", + LSN_FORMAT_ARGS(recoveryStopLSN)))); + return true; + } + + /* Otherwise we only consider stopping before COMMIT or ABORT records. */ + if (XLogRecGetRmid(record) != RM_XACT_ID) + return false; + + xact_info = XLogRecGetInfo(record) & XLOG_XACT_OPMASK; + + if (xact_info == XLOG_XACT_COMMIT) + { + isCommit = true; + recordXid = XLogRecGetXid(record); + } + else if (xact_info == XLOG_XACT_COMMIT_PREPARED) + { + xl_xact_commit *xlrec = (xl_xact_commit *) XLogRecGetData(record); + xl_xact_parsed_commit parsed; + + isCommit = true; + ParseCommitRecord(XLogRecGetInfo(record), + xlrec, + &parsed); + recordXid = parsed.twophase_xid; + } + else if (xact_info == XLOG_XACT_ABORT) + { + isCommit = false; + recordXid = XLogRecGetXid(record); + } + else if (xact_info == XLOG_XACT_ABORT_PREPARED) + { + xl_xact_abort *xlrec = (xl_xact_abort *) XLogRecGetData(record); + xl_xact_parsed_abort parsed; + + isCommit = false; + ParseAbortRecord(XLogRecGetInfo(record), + xlrec, + &parsed); + recordXid = parsed.twophase_xid; + } + else + return false; + + if (recoveryTarget == RECOVERY_TARGET_XID && !recoveryTargetInclusive) + { + /* + * There can be only one transaction end record with this exact + * transactionid + * + * when testing for an xid, we MUST test for equality only, since + * transactions are numbered in the order they start, not the order + * they complete. A higher numbered xid will complete before you about + * 50% of the time... + */ + stopsHere = (recordXid == recoveryTargetXid); + } + + if (recoveryTarget == RECOVERY_TARGET_TIME && + getRecordTimestamp(record, &recordXtime)) + { + /* + * There can be many transactions that share the same commit time, so + * we stop after the last one, if we are inclusive, or stop at the + * first one if we are exclusive + */ + if (recoveryTargetInclusive) + stopsHere = (recordXtime > recoveryTargetTime); + else + stopsHere = (recordXtime >= recoveryTargetTime); + } + + if (stopsHere) + { + recoveryStopAfter = false; + recoveryStopXid = recordXid; + recoveryStopTime = recordXtime; + recoveryStopLSN = InvalidXLogRecPtr; + recoveryStopName[0] = '\0'; + + if (isCommit) + { + ereport(LOG, + (errmsg("recovery stopping before commit of transaction %u, time %s", + recoveryStopXid, + timestamptz_to_str(recoveryStopTime)))); + } + else + { + ereport(LOG, + (errmsg("recovery stopping before abort of transaction %u, time %s", + recoveryStopXid, + timestamptz_to_str(recoveryStopTime)))); + } + } + + return stopsHere; +} + +/* + * Same as recoveryStopsBefore, but called after applying the record. + * + * We also track the timestamp of the latest applied COMMIT/ABORT + * record in XLogRecoveryCtl->recoveryLastXTime. + */ +static bool +recoveryStopsAfter(XLogReaderState *record) +{ + uint8 info; + uint8 xact_info; + uint8 rmid; + TimestampTz recordXtime; + + /* + * Ignore recovery target settings when not in archive recovery (meaning + * we are in crash recovery). + */ + if (!ArchiveRecoveryRequested) + return false; + + info = XLogRecGetInfo(record) & ~XLR_INFO_MASK; + rmid = XLogRecGetRmid(record); + + /* + * There can be many restore points that share the same name; we stop at + * the first one. + */ + if (recoveryTarget == RECOVERY_TARGET_NAME && + rmid == RM_XLOG_ID && info == XLOG_RESTORE_POINT) + { + xl_restore_point *recordRestorePointData; + + recordRestorePointData = (xl_restore_point *) XLogRecGetData(record); + + if (strcmp(recordRestorePointData->rp_name, recoveryTargetName) == 0) + { + recoveryStopAfter = true; + recoveryStopXid = InvalidTransactionId; + recoveryStopLSN = InvalidXLogRecPtr; + (void) getRecordTimestamp(record, &recoveryStopTime); + strlcpy(recoveryStopName, recordRestorePointData->rp_name, MAXFNAMELEN); + + ereport(LOG, + (errmsg("recovery stopping at restore point \"%s\", time %s", + recoveryStopName, + timestamptz_to_str(recoveryStopTime)))); + return true; + } + } + + /* Check if the target LSN has been reached */ + if (recoveryTarget == RECOVERY_TARGET_LSN && + recoveryTargetInclusive && + record->ReadRecPtr >= recoveryTargetLSN) + { + recoveryStopAfter = true; + recoveryStopXid = InvalidTransactionId; + recoveryStopLSN = record->ReadRecPtr; + recoveryStopTime = 0; + recoveryStopName[0] = '\0'; + ereport(LOG, + (errmsg("recovery stopping after WAL location (LSN) \"%X/%X\"", + LSN_FORMAT_ARGS(recoveryStopLSN)))); + return true; + } + + if (rmid != RM_XACT_ID) + return false; + + xact_info = info & XLOG_XACT_OPMASK; + + if (xact_info == XLOG_XACT_COMMIT || + xact_info == XLOG_XACT_COMMIT_PREPARED || + xact_info == XLOG_XACT_ABORT || + xact_info == XLOG_XACT_ABORT_PREPARED) + { + TransactionId recordXid; + + /* Update the last applied transaction timestamp */ + if (getRecordTimestamp(record, &recordXtime)) + SetLatestXTime(recordXtime); + + /* Extract the XID of the committed/aborted transaction */ + if (xact_info == XLOG_XACT_COMMIT_PREPARED) + { + xl_xact_commit *xlrec = (xl_xact_commit *) XLogRecGetData(record); + xl_xact_parsed_commit parsed; + + ParseCommitRecord(XLogRecGetInfo(record), + xlrec, + &parsed); + recordXid = parsed.twophase_xid; + } + else if (xact_info == XLOG_XACT_ABORT_PREPARED) + { + xl_xact_abort *xlrec = (xl_xact_abort *) XLogRecGetData(record); + xl_xact_parsed_abort parsed; + + ParseAbortRecord(XLogRecGetInfo(record), + xlrec, + &parsed); + recordXid = parsed.twophase_xid; + } + else + recordXid = XLogRecGetXid(record); + + /* + * There can be only one transaction end record with this exact + * transactionid + * + * when testing for an xid, we MUST test for equality only, since + * transactions are numbered in the order they start, not the order + * they complete. A higher numbered xid will complete before you about + * 50% of the time... + */ + if (recoveryTarget == RECOVERY_TARGET_XID && recoveryTargetInclusive && + recordXid == recoveryTargetXid) + { + recoveryStopAfter = true; + recoveryStopXid = recordXid; + recoveryStopTime = recordXtime; + recoveryStopLSN = InvalidXLogRecPtr; + recoveryStopName[0] = '\0'; + + if (xact_info == XLOG_XACT_COMMIT || + xact_info == XLOG_XACT_COMMIT_PREPARED) + { + ereport(LOG, + (errmsg("recovery stopping after commit of transaction %u, time %s", + recoveryStopXid, + timestamptz_to_str(recoveryStopTime)))); + } + else if (xact_info == XLOG_XACT_ABORT || + xact_info == XLOG_XACT_ABORT_PREPARED) + { + ereport(LOG, + (errmsg("recovery stopping after abort of transaction %u, time %s", + recoveryStopXid, + timestamptz_to_str(recoveryStopTime)))); + } + return true; + } + } + + /* Check if we should stop as soon as reaching consistency */ + if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE && reachedConsistency) + { + ereport(LOG, + (errmsg("recovery stopping after reaching consistency"))); + + recoveryStopAfter = true; + recoveryStopXid = InvalidTransactionId; + recoveryStopTime = 0; + recoveryStopLSN = InvalidXLogRecPtr; + recoveryStopName[0] = '\0'; + return true; + } + + return false; +} + +/* + * Create a comment for the history file to explain why and where + * timeline changed. + */ +static char * +getRecoveryStopReason(void) +{ + char reason[200]; + + if (recoveryTarget == RECOVERY_TARGET_XID) + snprintf(reason, sizeof(reason), + "%s transaction %u", + recoveryStopAfter ? "after" : "before", + recoveryStopXid); + else if (recoveryTarget == RECOVERY_TARGET_TIME) + snprintf(reason, sizeof(reason), + "%s %s\n", + recoveryStopAfter ? "after" : "before", + timestamptz_to_str(recoveryStopTime)); + else if (recoveryTarget == RECOVERY_TARGET_LSN) + snprintf(reason, sizeof(reason), + "%s LSN %X/%X\n", + recoveryStopAfter ? "after" : "before", + LSN_FORMAT_ARGS(recoveryStopLSN)); + else if (recoveryTarget == RECOVERY_TARGET_NAME) + snprintf(reason, sizeof(reason), + "at restore point \"%s\"", + recoveryStopName); + else if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE) + snprintf(reason, sizeof(reason), "reached consistency"); + else + snprintf(reason, sizeof(reason), "no recovery target specified"); + + return pstrdup(reason); +} + +/* + * Wait until shared recoveryPauseState is set to RECOVERY_NOT_PAUSED. + * + * endOfRecovery is true if the recovery target is reached and + * the paused state starts at the end of recovery because of + * recovery_target_action=pause, and false otherwise. + */ +static void +recoveryPausesHere(bool endOfRecovery) +{ + /* Don't pause unless users can connect! */ + if (!LocalHotStandbyActive) + return; + + /* Don't pause after standby promotion has been triggered */ + if (LocalPromoteIsTriggered) + return; + + if (endOfRecovery) + ereport(LOG, + (errmsg("pausing at the end of recovery"), + errhint("Execute pg_wal_replay_resume() to promote."))); + else + ereport(LOG, + (errmsg("recovery has paused"), + errhint("Execute pg_wal_replay_resume() to continue."))); + + /* loop until recoveryPauseState is set to RECOVERY_NOT_PAUSED */ + while (GetRecoveryPauseState() != RECOVERY_NOT_PAUSED) + { + HandleStartupProcInterrupts(); + if (CheckForStandbyTrigger()) + return; + + /* + * If recovery pause is requested then set it paused. While we are in + * the loop, user might resume and pause again so set this every time. + */ + ConfirmRecoveryPaused(); + + /* + * We wait on a condition variable that will wake us as soon as the + * pause ends, but we use a timeout so we can check the above exit + * condition periodically too. + */ + ConditionVariableTimedSleep(&XLogRecoveryCtl->recoveryNotPausedCV, 1000, + WAIT_EVENT_RECOVERY_PAUSE); + } + ConditionVariableCancelSleep(); +} + +/* + * When recovery_min_apply_delay is set, we wait long enough to make sure + * certain record types are applied at least that interval behind the primary. + * + * Returns true if we waited. + * + * Note that the delay is calculated between the WAL record log time and + * the current time on standby. We would prefer to keep track of when this + * standby received each WAL record, which would allow a more consistent + * approach and one not affected by time synchronisation issues, but that + * is significantly more effort and complexity for little actual gain in + * usability. + */ +static bool +recoveryApplyDelay(XLogReaderState *record) +{ + uint8 xact_info; + TimestampTz xtime; + TimestampTz delayUntil; + long msecs; + + /* nothing to do if no delay configured */ + if (recovery_min_apply_delay <= 0) + return false; + + /* no delay is applied on a database not yet consistent */ + if (!reachedConsistency) + return false; + + /* nothing to do if crash recovery is requested */ + if (!ArchiveRecoveryRequested) + return false; + + /* + * Is it a COMMIT record? + * + * We deliberately choose not to delay aborts since they have no effect on + * MVCC. We already allow replay of records that don't have a timestamp, + * so there is already opportunity for issues caused by early conflicts on + * standbys. + */ + if (XLogRecGetRmid(record) != RM_XACT_ID) + return false; + + xact_info = XLogRecGetInfo(record) & XLOG_XACT_OPMASK; + + if (xact_info != XLOG_XACT_COMMIT && + xact_info != XLOG_XACT_COMMIT_PREPARED) + return false; + + if (!getRecordTimestamp(record, &xtime)) + return false; + + delayUntil = TimestampTzPlusMilliseconds(xtime, recovery_min_apply_delay); + + /* + * Exit without arming the latch if it's already past time to apply this + * record + */ + msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(), delayUntil); + if (msecs <= 0) + return false; + + while (true) + { + ResetLatch(&XLogRecoveryCtl->recoveryWakeupLatch); + + /* + * This might change recovery_min_apply_delay or the trigger file's + * location. + */ + HandleStartupProcInterrupts(); + + if (CheckForStandbyTrigger()) + break; + + /* + * Recalculate delayUntil as recovery_min_apply_delay could have + * changed while waiting in this loop. + */ + delayUntil = TimestampTzPlusMilliseconds(xtime, recovery_min_apply_delay); + + /* + * Wait for difference between GetCurrentTimestamp() and delayUntil. + */ + msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(), + delayUntil); + + if (msecs <= 0) + break; + + elog(DEBUG2, "recovery apply delay %ld milliseconds", msecs); + + (void) WaitLatch(&XLogRecoveryCtl->recoveryWakeupLatch, + WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH, + msecs, + WAIT_EVENT_RECOVERY_APPLY_DELAY); + } + return true; +} + +/* + * Get the current state of the recovery pause request. + */ +RecoveryPauseState +GetRecoveryPauseState(void) +{ + RecoveryPauseState state; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + state = XLogRecoveryCtl->recoveryPauseState; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + return state; +} + +/* + * Set the recovery pause state. + * + * If recovery pause is requested then sets the recovery pause state to + * 'pause requested' if it is not already 'paused'. Otherwise, sets it + * to 'not paused' to resume the recovery. The recovery pause will be + * confirmed by the ConfirmRecoveryPaused. + */ +void +SetRecoveryPause(bool recoveryPause) +{ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + + if (!recoveryPause) + XLogRecoveryCtl->recoveryPauseState = RECOVERY_NOT_PAUSED; + else if (XLogRecoveryCtl->recoveryPauseState == RECOVERY_NOT_PAUSED) + XLogRecoveryCtl->recoveryPauseState = RECOVERY_PAUSE_REQUESTED; + + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + if (!recoveryPause) + ConditionVariableBroadcast(&XLogRecoveryCtl->recoveryNotPausedCV); +} + +/* + * Confirm the recovery pause by setting the recovery pause state to + * RECOVERY_PAUSED. + */ +static void +ConfirmRecoveryPaused(void) +{ + /* If recovery pause is requested then set it paused */ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + if (XLogRecoveryCtl->recoveryPauseState == RECOVERY_PAUSE_REQUESTED) + XLogRecoveryCtl->recoveryPauseState = RECOVERY_PAUSED; + SpinLockRelease(&XLogRecoveryCtl->info_lck); +} + + +/* + * Attempt to read the next XLOG record. + * + * Before first call, the reader needs to be positioned to the first record + * by calling XLogBeginRead(). + * + * If no valid record is available, returns NULL, or fails if emode is PANIC. + * (emode must be either PANIC, LOG). In standby mode, retries until a valid + * record is available. + */ +static XLogRecord * +ReadRecord(XLogReaderState *xlogreader, int emode, + bool fetching_ckpt, TimeLineID replayTLI) +{ + XLogRecord *record; + XLogPageReadPrivate *private = (XLogPageReadPrivate *) xlogreader->private_data; + + /* Pass through parameters to XLogPageRead */ + private->fetching_ckpt = fetching_ckpt; + private->emode = emode; + private->randAccess = (xlogreader->ReadRecPtr == InvalidXLogRecPtr); + private->replayTLI = replayTLI; + + /* This is the first attempt to read this page. */ + lastSourceFailed = false; + + for (;;) + { + char *errormsg; + + record = XLogReadRecord(xlogreader, &errormsg); + if (record == NULL) + { + /* + * When not in standby mode we find that WAL ends in an incomplete + * record, keep track of that record. After recovery is done, + * we'll write a record to indicate downstream WAL readers that + * that portion is to be ignored. + */ + if (!StandbyMode && + !XLogRecPtrIsInvalid(xlogreader->abortedRecPtr)) + { + abortedRecPtr = xlogreader->abortedRecPtr; + missingContrecPtr = xlogreader->missingContrecPtr; + } + + if (readFile >= 0) + { + close(readFile); + readFile = -1; + } + + /* + * We only end up here without a message when XLogPageRead() + * failed - in that case we already logged something. In + * StandbyMode that only happens if we have been triggered, so we + * shouldn't loop anymore in that case. + */ + if (errormsg) + ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), + (errmsg_internal("%s", errormsg) /* already translated */ )); + } + + /* + * Check page TLI is one of the expected values. + */ + else if (!tliInHistory(xlogreader->latestPageTLI, expectedTLEs)) + { + char fname[MAXFNAMELEN]; + XLogSegNo segno; + int32 offset; + + XLByteToSeg(xlogreader->latestPagePtr, segno, wal_segment_size); + offset = XLogSegmentOffset(xlogreader->latestPagePtr, + wal_segment_size); + XLogFileName(fname, xlogreader->seg.ws_tli, segno, + wal_segment_size); + ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), + (errmsg("unexpected timeline ID %u in log segment %s, offset %u", + xlogreader->latestPageTLI, + fname, + offset))); + record = NULL; + } + + if (record) + { + /* Great, got a record */ + return record; + } + else + { + /* No valid record available from this source */ + lastSourceFailed = true; + + /* + * If archive recovery was requested, but we were still doing + * crash recovery, switch to archive recovery and retry using the + * offline archive. We have now replayed all the valid WAL in + * pg_wal, so we are presumably now consistent. + * + * We require that there's at least some valid WAL present in + * pg_wal, however (!fetching_ckpt). We could recover using the + * WAL from the archive, even if pg_wal is completely empty, but + * we'd have no idea how far we'd have to replay to reach + * consistency. So err on the safe side and give up. + */ + if (!InArchiveRecovery && ArchiveRecoveryRequested && + !fetching_ckpt) + { + ereport(DEBUG1, + (errmsg_internal("reached end of WAL in pg_wal, entering archive recovery"))); + InArchiveRecovery = true; + if (StandbyModeRequested) + StandbyMode = true; + + SwitchIntoArchiveRecovery(xlogreader->EndRecPtr, replayTLI); + minRecoveryPoint = xlogreader->EndRecPtr; + minRecoveryPointTLI = replayTLI; + + CheckRecoveryConsistency(); + + /* + * Before we retry, reset lastSourceFailed and currentSource + * so that we will check the archive next. + */ + lastSourceFailed = false; + currentSource = XLOG_FROM_ANY; + + continue; + } + + /* In standby mode, loop back to retry. Otherwise, give up. */ + if (StandbyMode && !CheckForStandbyTrigger()) + continue; + else + return NULL; + } + } +} + +/* + * Read the XLOG page containing RecPtr into readBuf (if not read already). + * Returns number of bytes read, if the page is read successfully, or -1 + * in case of errors. When errors occur, they are ereport'ed, but only + * if they have not been previously reported. + * + * This is responsible for restoring files from archive as needed, as well + * as for waiting for the requested WAL record to arrive in standby mode. + * + * 'emode' specifies the log level used for reporting "file not found" or + * "end of WAL" situations in archive recovery, or in standby mode when a + * trigger file is found. If set to WARNING or below, XLogPageRead() returns + * false in those situations, on higher log levels the ereport() won't + * return. + * + * In standby mode, if after a successful return of XLogPageRead() the + * caller finds the record it's interested in to be broken, it should + * ereport the error with the level determined by + * emode_for_corrupt_record(), and then set lastSourceFailed + * and call XLogPageRead() again with the same arguments. This lets + * XLogPageRead() to try fetching the record from another source, or to + * sleep and retry. + */ +static int +XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr, int reqLen, + XLogRecPtr targetRecPtr, char *readBuf) +{ + XLogPageReadPrivate *private = + (XLogPageReadPrivate *) xlogreader->private_data; + int emode = private->emode; + uint32 targetPageOff; + XLogSegNo targetSegNo PG_USED_FOR_ASSERTS_ONLY; + int r; + + XLByteToSeg(targetPagePtr, targetSegNo, wal_segment_size); + targetPageOff = XLogSegmentOffset(targetPagePtr, wal_segment_size); + + /* + * See if we need to switch to a new segment because the requested record + * is not in the currently open one. + */ + if (readFile >= 0 && + !XLByteInSeg(targetPagePtr, readSegNo, wal_segment_size)) + { + /* + * Request a restartpoint if we've replayed too much xlog since the + * last one. + */ + if (ArchiveRecoveryRequested && IsUnderPostmaster) + { + if (XLogCheckpointNeeded(readSegNo)) + { + (void) GetRedoRecPtr(); + if (XLogCheckpointNeeded(readSegNo)) + RequestCheckpoint(CHECKPOINT_CAUSE_XLOG); + } + } + + close(readFile); + readFile = -1; + readSource = XLOG_FROM_ANY; + } + + XLByteToSeg(targetPagePtr, readSegNo, wal_segment_size); + +retry: + /* See if we need to retrieve more data */ + if (readFile < 0 || + (readSource == XLOG_FROM_STREAM && + flushedUpto < targetPagePtr + reqLen)) + { + if (!WaitForWALToBecomeAvailable(targetPagePtr + reqLen, + private->randAccess, + private->fetching_ckpt, + targetRecPtr, + private->replayTLI, + xlogreader->EndRecPtr)) + { + if (readFile >= 0) + close(readFile); + readFile = -1; + readLen = 0; + readSource = XLOG_FROM_ANY; + + return -1; + } + } + + /* + * At this point, we have the right segment open and if we're streaming we + * know the requested record is in it. + */ + Assert(readFile != -1); + + /* + * If the current segment is being streamed from the primary, calculate + * how much of the current page we have received already. We know the + * requested record has been received, but this is for the benefit of + * future calls, to allow quick exit at the top of this function. + */ + if (readSource == XLOG_FROM_STREAM) + { + if (((targetPagePtr) / XLOG_BLCKSZ) != (flushedUpto / XLOG_BLCKSZ)) + readLen = XLOG_BLCKSZ; + else + readLen = XLogSegmentOffset(flushedUpto, wal_segment_size) - + targetPageOff; + } + else + readLen = XLOG_BLCKSZ; + + /* Read the requested page */ + readOff = targetPageOff; + + pgstat_report_wait_start(WAIT_EVENT_WAL_READ); + r = pg_pread(readFile, readBuf, XLOG_BLCKSZ, (off_t) readOff); + if (r != XLOG_BLCKSZ) + { + char fname[MAXFNAMELEN]; + int save_errno = errno; + + pgstat_report_wait_end(); + XLogFileName(fname, curFileTLI, readSegNo, wal_segment_size); + if (r < 0) + { + errno = save_errno; + ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), + (errcode_for_file_access(), + errmsg("could not read from log segment %s, offset %u: %m", + fname, readOff))); + } + else + ereport(emode_for_corrupt_record(emode, targetPagePtr + reqLen), + (errcode(ERRCODE_DATA_CORRUPTED), + errmsg("could not read from log segment %s, offset %u: read %d of %zu", + fname, readOff, r, (Size) XLOG_BLCKSZ))); + goto next_record_is_invalid; + } + pgstat_report_wait_end(); + + Assert(targetSegNo == readSegNo); + Assert(targetPageOff == readOff); + Assert(reqLen <= readLen); + + xlogreader->seg.ws_tli = curFileTLI; + + /* + * Check the page header immediately, so that we can retry immediately if + * it's not valid. This may seem unnecessary, because ReadPageInternal() + * validates the page header anyway, and would propagate the failure up to + * ReadRecord(), which would retry. However, there's a corner case with + * continuation records, if a record is split across two pages such that + * we would need to read the two pages from different sources. For + * example, imagine a scenario where a streaming replica is started up, + * and replay reaches a record that's split across two WAL segments. The + * first page is only available locally, in pg_wal, because it's already + * been recycled on the primary. The second page, however, is not present + * in pg_wal, and we should stream it from the primary. There is a + * recycled WAL segment present in pg_wal, with garbage contents, however. + * We would read the first page from the local WAL segment, but when + * reading the second page, we would read the bogus, recycled, WAL + * segment. If we didn't catch that case here, we would never recover, + * because ReadRecord() would retry reading the whole record from the + * beginning. + * + * Of course, this only catches errors in the page header, which is what + * happens in the case of a recycled WAL segment. Other kinds of errors or + * corruption still has the same problem. But this at least fixes the + * common case, which can happen as part of normal operation. + * + * Validating the page header is cheap enough that doing it twice + * shouldn't be a big deal from a performance point of view. + * + * When not in standby mode, an invalid page header should cause recovery + * to end, not retry reading the page, so we don't need to validate the + * page header here for the retry. Instead, ReadPageInternal() is + * responsible for the validation. + */ + if (StandbyMode && + !XLogReaderValidatePageHeader(xlogreader, targetPagePtr, readBuf)) + { + /* + * Emit this error right now then retry this page immediately. Use + * errmsg_internal() because the message was already translated. + */ + if (xlogreader->errormsg_buf[0]) + ereport(emode_for_corrupt_record(emode, xlogreader->EndRecPtr), + (errmsg_internal("%s", xlogreader->errormsg_buf))); + + /* reset any error XLogReaderValidatePageHeader() might have set */ + xlogreader->errormsg_buf[0] = '\0'; + goto next_record_is_invalid; + } + + return readLen; + +next_record_is_invalid: + lastSourceFailed = true; + + if (readFile >= 0) + close(readFile); + readFile = -1; + readLen = 0; + readSource = XLOG_FROM_ANY; + + /* In standby-mode, keep trying */ + if (StandbyMode) + goto retry; + else + return -1; +} + +/* + * Open the WAL segment containing WAL location 'RecPtr'. + * + * The segment can be fetched via restore_command, or via walreceiver having + * streamed the record, or it can already be present in pg_wal. Checking + * pg_wal is mainly for crash recovery, but it will be polled in standby mode + * too, in case someone copies a new segment directly to pg_wal. That is not + * documented or recommended, though. + * + * If 'fetching_ckpt' is true, we're fetching a checkpoint record, and should + * prepare to read WAL starting from RedoStartLSN after this. + * + * 'RecPtr' might not point to the beginning of the record we're interested + * in, it might also point to the page or segment header. In that case, + * 'tliRecPtr' is the position of the WAL record we're interested in. It is + * used to decide which timeline to stream the requested WAL from. + * + * 'replayLSN' is the current replay LSN, so that if we scan for new + * timelines, we can reject a switch to a timeline that branched off before + * this point. + * + * If the record is not immediately available, the function returns false + * if we're not in standby mode. In standby mode, waits for it to become + * available. + * + * When the requested record becomes available, the function opens the file + * containing it (if not open already), and returns true. When end of standby + * mode is triggered by the user, and there is no more WAL available, returns + * false. + */ +static bool +WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess, + bool fetching_ckpt, XLogRecPtr tliRecPtr, + TimeLineID replayTLI, XLogRecPtr replayLSN) +{ + static TimestampTz last_fail_time = 0; + TimestampTz now; + bool streaming_reply_sent = false; + + /*------- + * Standby mode is implemented by a state machine: + * + * 1. Read from either archive or pg_wal (XLOG_FROM_ARCHIVE), or just + * pg_wal (XLOG_FROM_PG_WAL) + * 2. Check trigger file + * 3. Read from primary server via walreceiver (XLOG_FROM_STREAM) + * 4. Rescan timelines + * 5. Sleep wal_retrieve_retry_interval milliseconds, and loop back to 1. + * + * Failure to read from the current source advances the state machine to + * the next state. + * + * 'currentSource' indicates the current state. There are no currentSource + * values for "check trigger", "rescan timelines", and "sleep" states, + * those actions are taken when reading from the previous source fails, as + * part of advancing to the next state. + * + * If standby mode is turned off while reading WAL from stream, we move + * to XLOG_FROM_ARCHIVE and reset lastSourceFailed, to force fetching + * the files (which would be required at end of recovery, e.g., timeline + * history file) from archive or pg_wal. We don't need to kill WAL receiver + * here because it's already stopped when standby mode is turned off at + * the end of recovery. + *------- + */ + if (!InArchiveRecovery) + currentSource = XLOG_FROM_PG_WAL; + else if (currentSource == XLOG_FROM_ANY || + (!StandbyMode && currentSource == XLOG_FROM_STREAM)) + { + lastSourceFailed = false; + currentSource = XLOG_FROM_ARCHIVE; + } + + for (;;) + { + XLogSource oldSource = currentSource; + bool startWalReceiver = false; + + /* + * First check if we failed to read from the current source, and + * advance the state machine if so. The failure to read might've + * happened outside this function, e.g when a CRC check fails on a + * record, or within this loop. + */ + if (lastSourceFailed) + { + switch (currentSource) + { + case XLOG_FROM_ARCHIVE: + case XLOG_FROM_PG_WAL: + + /* + * Check to see if the trigger file exists. Note that we + * do this only after failure, so when you create the + * trigger file, we still finish replaying as much as we + * can from archive and pg_wal before failover. + */ + if (StandbyMode && CheckForStandbyTrigger()) + { + XLogShutdownWalRcv(); + return false; + } + + /* + * Not in standby mode, and we've now tried the archive + * and pg_wal. + */ + if (!StandbyMode) + return false; + + /* + * Move to XLOG_FROM_STREAM state, and set to start a + * walreceiver if necessary. + */ + currentSource = XLOG_FROM_STREAM; + startWalReceiver = true; + break; + + case XLOG_FROM_STREAM: + + /* + * Failure while streaming. Most likely, we got here + * because streaming replication was terminated, or + * promotion was triggered. But we also get here if we + * find an invalid record in the WAL streamed from the + * primary, in which case something is seriously wrong. + * There's little chance that the problem will just go + * away, but PANIC is not good for availability either, + * especially in hot standby mode. So, we treat that the + * same as disconnection, and retry from archive/pg_wal + * again. The WAL in the archive should be identical to + * what was streamed, so it's unlikely that it helps, but + * one can hope... + */ + + /* + * We should be able to move to XLOG_FROM_STREAM only in + * standby mode. + */ + Assert(StandbyMode); + + /* + * Before we leave XLOG_FROM_STREAM state, make sure that + * walreceiver is not active, so that it won't overwrite + * WAL that we restore from archive. + */ + if (WalRcvStreaming()) + XLogShutdownWalRcv(); + + /* + * Before we sleep, re-scan for possible new timelines if + * we were requested to recover to the latest timeline. + */ + if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_LATEST) + { + if (rescanLatestTimeLine(replayTLI, replayLSN)) + { + currentSource = XLOG_FROM_ARCHIVE; + break; + } + } + + /* + * XLOG_FROM_STREAM is the last state in our state + * machine, so we've exhausted all the options for + * obtaining the requested WAL. We're going to loop back + * and retry from the archive, but if it hasn't been long + * since last attempt, sleep wal_retrieve_retry_interval + * milliseconds to avoid busy-waiting. + */ + now = GetCurrentTimestamp(); + if (!TimestampDifferenceExceeds(last_fail_time, now, + wal_retrieve_retry_interval)) + { + long wait_time; + + wait_time = wal_retrieve_retry_interval - + TimestampDifferenceMilliseconds(last_fail_time, now); + + elog(LOG, "waiting for WAL to become available at %X/%X", + LSN_FORMAT_ARGS(RecPtr)); + + (void) WaitLatch(&XLogRecoveryCtl->recoveryWakeupLatch, + WL_LATCH_SET | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + wait_time, + WAIT_EVENT_RECOVERY_RETRIEVE_RETRY_INTERVAL); + ResetLatch(&XLogRecoveryCtl->recoveryWakeupLatch); + now = GetCurrentTimestamp(); + + /* Handle interrupt signals of startup process */ + HandleStartupProcInterrupts(); + } + last_fail_time = now; + currentSource = XLOG_FROM_ARCHIVE; + break; + + default: + elog(ERROR, "unexpected WAL source %d", currentSource); + } + } + else if (currentSource == XLOG_FROM_PG_WAL) + { + /* + * We just successfully read a file in pg_wal. We prefer files in + * the archive over ones in pg_wal, so try the next file again + * from the archive first. + */ + if (InArchiveRecovery) + currentSource = XLOG_FROM_ARCHIVE; + } + + if (currentSource != oldSource) + elog(DEBUG2, "switched WAL source from %s to %s after %s", + xlogSourceNames[oldSource], xlogSourceNames[currentSource], + lastSourceFailed ? "failure" : "success"); + + /* + * We've now handled possible failure. Try to read from the chosen + * source. + */ + lastSourceFailed = false; + + switch (currentSource) + { + case XLOG_FROM_ARCHIVE: + case XLOG_FROM_PG_WAL: + + /* + * WAL receiver must not be running when reading WAL from + * archive or pg_wal. + */ + Assert(!WalRcvStreaming()); + + /* Close any old file we might have open. */ + if (readFile >= 0) + { + close(readFile); + readFile = -1; + } + /* Reset curFileTLI if random fetch. */ + if (randAccess) + curFileTLI = 0; + + /* + * Try to restore the file from archive, or read an existing + * file from pg_wal. + */ + readFile = XLogFileReadAnyTLI(readSegNo, DEBUG2, + currentSource == XLOG_FROM_ARCHIVE ? XLOG_FROM_ANY : + currentSource); + if (readFile >= 0) + return true; /* success! */ + + /* + * Nope, not found in archive or pg_wal. + */ + lastSourceFailed = true; + break; + + case XLOG_FROM_STREAM: + { + bool havedata; + + /* + * We should be able to move to XLOG_FROM_STREAM only in + * standby mode. + */ + Assert(StandbyMode); + + /* + * First, shutdown walreceiver if its restart has been + * requested -- but no point if we're already slated for + * starting it. + */ + if (pendingWalRcvRestart && !startWalReceiver) + { + XLogShutdownWalRcv(); + + /* + * Re-scan for possible new timelines if we were + * requested to recover to the latest timeline. + */ + if (recoveryTargetTimeLineGoal == + RECOVERY_TARGET_TIMELINE_LATEST) + rescanLatestTimeLine(replayTLI, replayLSN); + + startWalReceiver = true; + } + pendingWalRcvRestart = false; + + /* + * Launch walreceiver if needed. + * + * If fetching_ckpt is true, RecPtr points to the initial + * checkpoint location. In that case, we use RedoStartLSN + * as the streaming start position instead of RecPtr, so + * that when we later jump backwards to start redo at + * RedoStartLSN, we will have the logs streamed already. + */ + if (startWalReceiver && + PrimaryConnInfo && strcmp(PrimaryConnInfo, "") != 0) + { + XLogRecPtr ptr; + TimeLineID tli; + + if (fetching_ckpt) + { + ptr = RedoStartLSN; + tli = RedoStartTLI; + } + else + { + ptr = RecPtr; + + /* + * Use the record begin position to determine the + * TLI, rather than the position we're reading. + */ + tli = tliOfPointInHistory(tliRecPtr, expectedTLEs); + + if (curFileTLI > 0 && tli < curFileTLI) + elog(ERROR, "according to history file, WAL location %X/%X belongs to timeline %u, but previous recovered WAL file came from timeline %u", + LSN_FORMAT_ARGS(tliRecPtr), + tli, curFileTLI); + } + curFileTLI = tli; + SetInstallXLogFileSegmentActive(); + RequestXLogStreaming(tli, ptr, PrimaryConnInfo, + PrimarySlotName, + wal_receiver_create_temp_slot); + flushedUpto = 0; + } + + /* + * Check if WAL receiver is active or wait to start up. + */ + if (!WalRcvStreaming()) + { + lastSourceFailed = true; + break; + } + + /* + * Walreceiver is active, so see if new data has arrived. + * + * We only advance XLogReceiptTime when we obtain fresh + * WAL from walreceiver and observe that we had already + * processed everything before the most recent "chunk" + * that it flushed to disk. In steady state where we are + * keeping up with the incoming data, XLogReceiptTime will + * be updated on each cycle. When we are behind, + * XLogReceiptTime will not advance, so the grace time + * allotted to conflicting queries will decrease. + */ + if (RecPtr < flushedUpto) + havedata = true; + else + { + XLogRecPtr latestChunkStart; + + flushedUpto = GetWalRcvFlushRecPtr(&latestChunkStart, &receiveTLI); + if (RecPtr < flushedUpto && receiveTLI == curFileTLI) + { + havedata = true; + if (latestChunkStart <= RecPtr) + { + XLogReceiptTime = GetCurrentTimestamp(); + SetCurrentChunkStartTime(XLogReceiptTime); + } + } + else + havedata = false; + } + if (havedata) + { + /* + * Great, streamed far enough. Open the file if it's + * not open already. Also read the timeline history + * file if we haven't initialized timeline history + * yet; it should be streamed over and present in + * pg_wal by now. Use XLOG_FROM_STREAM so that source + * info is set correctly and XLogReceiptTime isn't + * changed. + * + * NB: We must set readTimeLineHistory based on + * recoveryTargetTLI, not receiveTLI. Normally they'll + * be the same, but if recovery_target_timeline is + * 'latest' and archiving is configured, then it's + * possible that we managed to retrieve one or more + * new timeline history files from the archive, + * updating recoveryTargetTLI. + */ + if (readFile < 0) + { + if (!expectedTLEs) + expectedTLEs = readTimeLineHistory(recoveryTargetTLI); + readFile = XLogFileRead(readSegNo, PANIC, + receiveTLI, + XLOG_FROM_STREAM, false); + Assert(readFile >= 0); + } + else + { + /* just make sure source info is correct... */ + readSource = XLOG_FROM_STREAM; + XLogReceiptSource = XLOG_FROM_STREAM; + return true; + } + break; + } + + /* + * Data not here yet. Check for trigger, then wait for + * walreceiver to wake us up when new WAL arrives. + */ + if (CheckForStandbyTrigger()) + { + /* + * Note that we don't "return false" immediately here. + * After being triggered, we still want to replay all + * the WAL that was already streamed. It's in pg_wal + * now, so we just treat this as a failure, and the + * state machine will move on to replay the streamed + * WAL from pg_wal, and then recheck the trigger and + * exit replay. + */ + lastSourceFailed = true; + break; + } + + /* + * Since we have replayed everything we have received so + * far and are about to start waiting for more WAL, let's + * tell the upstream server our replay location now so + * that pg_stat_replication doesn't show stale + * information. + */ + if (!streaming_reply_sent) + { + WalRcvForceReply(); + streaming_reply_sent = true; + } + + /* + * Wait for more WAL to arrive. Time out after 5 seconds + * to react to a trigger file promptly and to check if the + * WAL receiver is still active. + */ + (void) WaitLatch(&XLogRecoveryCtl->recoveryWakeupLatch, + WL_LATCH_SET | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + 5000L, WAIT_EVENT_RECOVERY_WAL_STREAM); + ResetLatch(&XLogRecoveryCtl->recoveryWakeupLatch); + break; + } + + default: + elog(ERROR, "unexpected WAL source %d", currentSource); + } + + /* + * Check for recovery pause here so that we can confirm more quickly + * that a requested pause has actually taken effect. + */ + if (((volatile XLogRecoveryCtlData *) XLogRecoveryCtl)->recoveryPauseState != + RECOVERY_NOT_PAUSED) + recoveryPausesHere(false); + + /* + * This possibly-long loop needs to handle interrupts of startup + * process. + */ + HandleStartupProcInterrupts(); + } + + return false; /* not reached */ +} + + +/* + * Determine what log level should be used to report a corrupt WAL record + * in the current WAL page, previously read by XLogPageRead(). + * + * 'emode' is the error mode that would be used to report a file-not-found + * or legitimate end-of-WAL situation. Generally, we use it as-is, but if + * we're retrying the exact same record that we've tried previously, only + * complain the first time to keep the noise down. However, we only do when + * reading from pg_wal, because we don't expect any invalid records in archive + * or in records streamed from the primary. Files in the archive should be complete, + * and we should never hit the end of WAL because we stop and wait for more WAL + * to arrive before replaying it. + * + * NOTE: This function remembers the RecPtr value it was last called with, + * to suppress repeated messages about the same record. Only call this when + * you are about to ereport(), or you might cause a later message to be + * erroneously suppressed. + */ +static int +emode_for_corrupt_record(int emode, XLogRecPtr RecPtr) +{ + static XLogRecPtr lastComplaint = 0; + + if (readSource == XLOG_FROM_PG_WAL && emode == LOG) + { + if (RecPtr == lastComplaint) + emode = DEBUG1; + else + lastComplaint = RecPtr; + } + return emode; +} + + +/* + * Subroutine to try to fetch and validate a prior checkpoint record. + * + * whichChkpt identifies the checkpoint (merely for reporting purposes). + * 1 for "primary", 0 for "other" (backup_label) + */ +static XLogRecord * +ReadCheckpointRecord(XLogReaderState *xlogreader, XLogRecPtr RecPtr, + int whichChkpt, bool report, TimeLineID replayTLI) +{ + XLogRecord *record; + uint8 info; + + Assert(xlogreader != NULL); + + if (!XRecOffIsValid(RecPtr)) + { + if (!report) + return NULL; + + switch (whichChkpt) + { + case 1: + ereport(LOG, + (errmsg("invalid primary checkpoint link in control file"))); + break; + default: + ereport(LOG, + (errmsg("invalid checkpoint link in backup_label file"))); + break; + } + return NULL; + } + + XLogBeginRead(xlogreader, RecPtr); + record = ReadRecord(xlogreader, LOG, true, replayTLI); + + if (record == NULL) + { + if (!report) + return NULL; + + switch (whichChkpt) + { + case 1: + ereport(LOG, + (errmsg("invalid primary checkpoint record"))); + break; + default: + ereport(LOG, + (errmsg("invalid checkpoint record"))); + break; + } + return NULL; + } + if (record->xl_rmid != RM_XLOG_ID) + { + switch (whichChkpt) + { + case 1: + ereport(LOG, + (errmsg("invalid resource manager ID in primary checkpoint record"))); + break; + default: + ereport(LOG, + (errmsg("invalid resource manager ID in checkpoint record"))); + break; + } + return NULL; + } + info = record->xl_info & ~XLR_INFO_MASK; + if (info != XLOG_CHECKPOINT_SHUTDOWN && + info != XLOG_CHECKPOINT_ONLINE) + { + switch (whichChkpt) + { + case 1: + ereport(LOG, + (errmsg("invalid xl_info in primary checkpoint record"))); + break; + default: + ereport(LOG, + (errmsg("invalid xl_info in checkpoint record"))); + break; + } + return NULL; + } + if (record->xl_tot_len != SizeOfXLogRecord + SizeOfXLogRecordDataHeaderShort + sizeof(CheckPoint)) + { + switch (whichChkpt) + { + case 1: + ereport(LOG, + (errmsg("invalid length of primary checkpoint record"))); + break; + default: + ereport(LOG, + (errmsg("invalid length of checkpoint record"))); + break; + } + return NULL; + } + return record; +} + +/* + * Scan for new timelines that might have appeared in the archive since we + * started recovery. + * + * If there are any, the function changes recovery target TLI to the latest + * one and returns 'true'. + */ +static bool +rescanLatestTimeLine(TimeLineID replayTLI, XLogRecPtr replayLSN) +{ + List *newExpectedTLEs; + bool found; + ListCell *cell; + TimeLineID newtarget; + TimeLineID oldtarget = recoveryTargetTLI; + TimeLineHistoryEntry *currentTle = NULL; + + newtarget = findNewestTimeLine(recoveryTargetTLI); + if (newtarget == recoveryTargetTLI) + { + /* No new timelines found */ + return false; + } + + /* + * Determine the list of expected TLIs for the new TLI + */ + + newExpectedTLEs = readTimeLineHistory(newtarget); + + /* + * If the current timeline is not part of the history of the new timeline, + * we cannot proceed to it. + */ + found = false; + foreach(cell, newExpectedTLEs) + { + currentTle = (TimeLineHistoryEntry *) lfirst(cell); + + if (currentTle->tli == recoveryTargetTLI) + { + found = true; + break; + } + } + if (!found) + { + ereport(LOG, + (errmsg("new timeline %u is not a child of database system timeline %u", + newtarget, + replayTLI))); + return false; + } + + /* + * The current timeline was found in the history file, but check that the + * next timeline was forked off from it *after* the current recovery + * location. + */ + if (currentTle->end < replayLSN) + { + ereport(LOG, + (errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%X", + newtarget, + replayTLI, + LSN_FORMAT_ARGS(replayLSN)))); + return false; + } + + /* The new timeline history seems valid. Switch target */ + recoveryTargetTLI = newtarget; + list_free_deep(expectedTLEs); + expectedTLEs = newExpectedTLEs; + + /* + * As in StartupXLOG(), try to ensure we have all the history files + * between the old target and new target in pg_wal. + */ + restoreTimeLineHistoryFiles(oldtarget + 1, newtarget); + + ereport(LOG, + (errmsg("new target timeline is %u", + recoveryTargetTLI))); + + return true; +} + + +/* + * Open a logfile segment for reading (during recovery). + * + * If source == XLOG_FROM_ARCHIVE, the segment is retrieved from archive. + * Otherwise, it's assumed to be already available in pg_wal. + */ +static int +XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli, + XLogSource source, bool notfoundOk) +{ + char xlogfname[MAXFNAMELEN]; + char activitymsg[MAXFNAMELEN + 16]; + char path[MAXPGPATH]; + int fd; + + XLogFileName(xlogfname, tli, segno, wal_segment_size); + + switch (source) + { + case XLOG_FROM_ARCHIVE: + /* Report recovery progress in PS display */ + snprintf(activitymsg, sizeof(activitymsg), "waiting for %s", + xlogfname); + set_ps_display(activitymsg); + + if (!RestoreArchivedFile(path, xlogfname, + "RECOVERYXLOG", + wal_segment_size, + InRedo)) + return -1; + break; + + case XLOG_FROM_PG_WAL: + case XLOG_FROM_STREAM: + XLogFilePath(path, tli, segno, wal_segment_size); + break; + + default: + elog(ERROR, "invalid XLogFileRead source %d", source); + } + + /* + * If the segment was fetched from archival storage, replace the existing + * xlog segment (if any) with the archival version. + */ + if (source == XLOG_FROM_ARCHIVE) + { + Assert(!IsInstallXLogFileSegmentActive()); + KeepFileRestoredFromArchive(path, xlogfname); + + /* + * Set path to point at the new file in pg_wal. + */ + snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlogfname); + } + + fd = BasicOpenFile(path, O_RDONLY | PG_BINARY); + if (fd >= 0) + { + /* Success! */ + curFileTLI = tli; + + /* Report recovery progress in PS display */ + snprintf(activitymsg, sizeof(activitymsg), "recovering %s", + xlogfname); + set_ps_display(activitymsg); + + /* Track source of data in assorted state variables */ + readSource = source; + XLogReceiptSource = source; + /* In FROM_STREAM case, caller tracks receipt time, not me */ + if (source != XLOG_FROM_STREAM) + XLogReceiptTime = GetCurrentTimestamp(); + + return fd; + } + if (errno != ENOENT || !notfoundOk) /* unexpected failure? */ + ereport(PANIC, + (errcode_for_file_access(), + errmsg("could not open file \"%s\": %m", path))); + return -1; +} + +/* + * Open a logfile segment for reading (during recovery). + * + * This version searches for the segment with any TLI listed in expectedTLEs. + */ +static int +XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source) +{ + char path[MAXPGPATH]; + ListCell *cell; + int fd; + List *tles; + + /* + * Loop looking for a suitable timeline ID: we might need to read any of + * the timelines listed in expectedTLEs. + * + * We expect curFileTLI on entry to be the TLI of the preceding file in + * sequence, or 0 if there was no predecessor. We do not allow curFileTLI + * to go backwards; this prevents us from picking up the wrong file when a + * parent timeline extends to higher segment numbers than the child we + * want to read. + * + * If we haven't read the timeline history file yet, read it now, so that + * we know which TLIs to scan. We don't save the list in expectedTLEs, + * however, unless we actually find a valid segment. That way if there is + * neither a timeline history file nor a WAL segment in the archive, and + * streaming replication is set up, we'll read the timeline history file + * streamed from the primary when we start streaming, instead of + * recovering with a dummy history generated here. + */ + if (expectedTLEs) + tles = expectedTLEs; + else + tles = readTimeLineHistory(recoveryTargetTLI); + + foreach(cell, tles) + { + TimeLineHistoryEntry *hent = (TimeLineHistoryEntry *) lfirst(cell); + TimeLineID tli = hent->tli; + + if (tli < curFileTLI) + break; /* don't bother looking at too-old TLIs */ + + /* + * Skip scanning the timeline ID that the logfile segment to read + * doesn't belong to + */ + if (hent->begin != InvalidXLogRecPtr) + { + XLogSegNo beginseg = 0; + + XLByteToSeg(hent->begin, beginseg, wal_segment_size); + + /* + * The logfile segment that doesn't belong to the timeline is + * older or newer than the segment that the timeline started or + * ended at, respectively. It's sufficient to check only the + * starting segment of the timeline here. Since the timelines are + * scanned in descending order in this loop, any segments newer + * than the ending segment should belong to newer timeline and + * have already been read before. So it's not necessary to check + * the ending segment of the timeline here. + */ + if (segno < beginseg) + continue; + } + + if (source == XLOG_FROM_ANY || source == XLOG_FROM_ARCHIVE) + { + fd = XLogFileRead(segno, emode, tli, + XLOG_FROM_ARCHIVE, true); + if (fd != -1) + { + elog(DEBUG1, "got WAL segment from archive"); + if (!expectedTLEs) + expectedTLEs = tles; + return fd; + } + } + + if (source == XLOG_FROM_ANY || source == XLOG_FROM_PG_WAL) + { + fd = XLogFileRead(segno, emode, tli, + XLOG_FROM_PG_WAL, true); + if (fd != -1) + { + if (!expectedTLEs) + expectedTLEs = tles; + return fd; + } + } + } + + /* Couldn't find it. For simplicity, complain about front timeline */ + XLogFilePath(path, recoveryTargetTLI, segno, wal_segment_size); + errno = ENOENT; + ereport(emode, + (errcode_for_file_access(), + errmsg("could not open file \"%s\": %m", path))); + return -1; +} + +/* + * Set flag to signal the walreceiver to restart. (The startup process calls + * this on noticing a relevant configuration change.) + */ +void +StartupRequestWalReceiverRestart(void) +{ + if (currentSource == XLOG_FROM_STREAM && WalRcvRunning()) + { + ereport(LOG, + (errmsg("WAL receiver process shutdown requested"))); + + pendingWalRcvRestart = true; + } +} + + +/* + * Has a standby promotion already been triggered? + * + * Unlike CheckForStandbyTrigger(), this works in any process + * that's connected to shared memory. + */ +bool +PromoteIsTriggered(void) +{ + /* + * We check shared state each time only until a standby promotion is + * triggered. We can't trigger a promotion again, so there's no need to + * keep checking after the shared variable has once been seen true. + */ + if (LocalPromoteIsTriggered) + return true; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + LocalPromoteIsTriggered = XLogRecoveryCtl->SharedPromoteIsTriggered; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + return LocalPromoteIsTriggered; +} + +static void +SetPromoteIsTriggered(void) +{ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->SharedPromoteIsTriggered = true; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + /* + * Mark the recovery pause state as 'not paused' because the paused state + * ends and promotion continues if a promotion is triggered while recovery + * is paused. Otherwise pg_get_wal_replay_pause_state() can mistakenly + * return 'paused' while a promotion is ongoing. + */ + SetRecoveryPause(false); + + LocalPromoteIsTriggered = true; +} + +/* + * Check to see whether the user-specified trigger file exists and whether a + * promote request has arrived. If either condition holds, return true. + */ +static bool +CheckForStandbyTrigger(void) +{ + struct stat stat_buf; + + if (LocalPromoteIsTriggered) + return true; + + if (IsPromoteSignaled() && CheckPromoteSignal()) + { + ereport(LOG, (errmsg("received promote request"))); + RemovePromoteSignalFiles(); + ResetPromoteSignaled(); + SetPromoteIsTriggered(); + return true; + } + + if (PromoteTriggerFile == NULL || strcmp(PromoteTriggerFile, "") == 0) + return false; + + if (stat(PromoteTriggerFile, &stat_buf) == 0) + { + ereport(LOG, + (errmsg("promote trigger file found: %s", PromoteTriggerFile))); + unlink(PromoteTriggerFile); + SetPromoteIsTriggered(); + return true; + } + else if (errno != ENOENT) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not stat promote trigger file \"%s\": %m", + PromoteTriggerFile))); + + return false; +} + +/* + * Remove the files signaling a standby promotion request. + */ +void +RemovePromoteSignalFiles(void) +{ + unlink(PROMOTE_SIGNAL_FILE); +} + +/* + * Check to see if a promote request has arrived. + */ +bool +CheckPromoteSignal(void) +{ + struct stat stat_buf; + + if (stat(PROMOTE_SIGNAL_FILE, &stat_buf) == 0) + return true; + + return false; +} + +/* + * Wake up startup process to replay newly arrived WAL, or to notice that + * failover has been requested. + */ +void +WakeupRecovery(void) +{ + SetLatch(&XLogRecoveryCtl->recoveryWakeupLatch); +} + +/* + * Schedule a walreceiver wakeup in the main recovery loop. + */ +void +XLogRequestWalReceiverReply(void) +{ + doRequestWalReceiverReply = true; +} + +/* + * Is HotStandby active yet? This is only important in special backends + * since normal backends won't ever be able to connect until this returns + * true. Postmaster knows this by way of signal, not via shared memory. + * + * Unlike testing standbyState, this works in any process that's connected to + * shared memory. (And note that standbyState alone doesn't tell the truth + * anyway.) + */ +bool +HotStandbyActive(void) +{ + /* + * We check shared state each time only until Hot Standby is active. We + * can't de-activate Hot Standby, so there's no need to keep checking + * after the shared variable has once been seen true. + */ + if (LocalHotStandbyActive) + return true; + else + { + /* spinlock is essential on machines with weak memory ordering! */ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + LocalHotStandbyActive = XLogRecoveryCtl->SharedHotStandbyActive; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + return LocalHotStandbyActive; + } +} + +/* + * Like HotStandbyActive(), but to be used only in WAL replay code, + * where we don't need to ask any other process what the state is. + */ +static bool +HotStandbyActiveInReplay(void) +{ + Assert(AmStartupProcess() || !IsPostmasterEnvironment); + return LocalHotStandbyActive; +} + +/* + * Get latest redo apply position. + * + * Exported to allow WALReceiver to read the pointer directly. + */ +XLogRecPtr +GetXLogReplayRecPtr(TimeLineID *replayTLI) +{ + XLogRecPtr recptr; + TimeLineID tli; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + recptr = XLogRecoveryCtl->lastReplayedEndRecPtr; + tli = XLogRecoveryCtl->lastReplayedTLI; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + if (replayTLI) + *replayTLI = tli; + return recptr; +} + + +/* + * Get position of last applied, or the record being applied. + * + * This is different from GetLogReplayRecPtr() in that if a WAL + * record is currently being applied, this includes that record. + */ +XLogRecPtr +GetCurrentReplayRecPtr(TimeLineID *replayEndTLI) +{ + XLogRecPtr recptr; + TimeLineID tli; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + recptr = XLogRecoveryCtl->replayEndRecPtr; + tli = XLogRecoveryCtl->replayEndTLI; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + if (replayEndTLI) + *replayEndTLI = tli; + return recptr; +} + +/* + * Save timestamp of latest processed commit/abort record. + * + * We keep this in XLogRecoveryCtl, not a simple static variable, so that it can be + * seen by processes other than the startup process. Note in particular + * that CreateRestartPoint is executed in the checkpointer. + */ +static void +SetLatestXTime(TimestampTz xtime) +{ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->recoveryLastXTime = xtime; + SpinLockRelease(&XLogRecoveryCtl->info_lck); +} + +/* + * Fetch timestamp of latest processed commit/abort record. + */ +TimestampTz +GetLatestXTime(void) +{ + TimestampTz xtime; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + xtime = XLogRecoveryCtl->recoveryLastXTime; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + return xtime; +} + +/* + * Save timestamp of the next chunk of WAL records to apply. + * + * We keep this in XLogRecoveryCtl, not a simple static variable, so that it can be + * seen by all backends. + */ +static void +SetCurrentChunkStartTime(TimestampTz xtime) +{ + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + XLogRecoveryCtl->currentChunkStartTime = xtime; + SpinLockRelease(&XLogRecoveryCtl->info_lck); +} + +/* + * Fetch timestamp of latest processed commit/abort record. + * Startup process maintains an accurate local copy in XLogReceiptTime + */ +TimestampTz +GetCurrentChunkReplayStartTime(void) +{ + TimestampTz xtime; + + SpinLockAcquire(&XLogRecoveryCtl->info_lck); + xtime = XLogRecoveryCtl->currentChunkStartTime; + SpinLockRelease(&XLogRecoveryCtl->info_lck); + + return xtime; +} + +/* + * Returns time of receipt of current chunk of XLOG data, as well as + * whether it was received from streaming replication or from archives. + */ +void +GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream) +{ + /* + * This must be executed in the startup process, since we don't export the + * relevant state to shared memory. + */ + Assert(InRecovery); + + *rtime = XLogReceiptTime; + *fromStream = (XLogReceiptSource == XLOG_FROM_STREAM); +} + +/* + * Note that text field supplied is a parameter name and does not require + * translation + */ +void +RecoveryRequiresIntParameter(const char *param_name, int currValue, int minValue) +{ + if (currValue < minValue) + { + if (HotStandbyActiveInReplay()) + { + bool warned_for_promote = false; + + ereport(WARNING, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("hot standby is not possible because of insufficient parameter settings"), + errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", + param_name, + currValue, + minValue))); + + SetRecoveryPause(true); + + ereport(LOG, + (errmsg("recovery has paused"), + errdetail("If recovery is unpaused, the server will shut down."), + errhint("You can then restart the server after making the necessary configuration changes."))); + + while (GetRecoveryPauseState() != RECOVERY_NOT_PAUSED) + { + HandleStartupProcInterrupts(); + + if (CheckForStandbyTrigger()) + { + if (!warned_for_promote) + ereport(WARNING, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("promotion is not possible because of insufficient parameter settings"), + + /* + * Repeat the detail from above so it's easy to find + * in the log. + */ + errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", + param_name, + currValue, + minValue), + errhint("Restart the server after making the necessary configuration changes."))); + warned_for_promote = true; + } + + /* + * If recovery pause is requested then set it paused. While + * we are in the loop, user might resume and pause again so + * set this every time. + */ + ConfirmRecoveryPaused(); + + /* + * We wait on a condition variable that will wake us as soon + * as the pause ends, but we use a timeout so we can check the + * above conditions periodically too. + */ + ConditionVariableTimedSleep(&XLogRecoveryCtl->recoveryNotPausedCV, 1000, + WAIT_EVENT_RECOVERY_PAUSE); + } + ConditionVariableCancelSleep(); + } + + ereport(FATAL, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("recovery aborted because of insufficient parameter settings"), + /* Repeat the detail from above so it's easy to find in the log. */ + errdetail("%s = %d is a lower setting than on the primary server, where its value was %d.", + param_name, + currValue, + minValue), + errhint("You can restart the server after making the necessary configuration changes."))); + } +} diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c index 90e1c48390..54d5f20734 100644 --- a/src/backend/access/transam/xlogutils.c +++ b/src/backend/access/transam/xlogutils.c @@ -20,7 +20,7 @@ #include #include "access/timeline.h" -#include "access/xlog.h" +#include "access/xlogrecovery.h" #include "access/xlog_internal.h" #include "access/xlogutils.h" #include "miscadmin.h" @@ -46,8 +46,8 @@ bool ignore_invalid_pages = false; * process you're running in, use RecoveryInProgress() but only after shared * memory startup and lock initialization. * - * This is updated from xlog.c, but lives here because it's mostly read by - * WAL redo functions. + * This is updated from xlog.c and xlogrecovery.c, but lives here because + * it's mostly read by WAL redo functions. */ bool InRecovery = false; diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c index 23f691cd47..4488e3a443 100644 --- a/src/backend/postmaster/checkpointer.c +++ b/src/backend/postmaster/checkpointer.c @@ -38,6 +38,7 @@ #include "access/xlog.h" #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c index 32992bafa0..735fed490b 100644 --- a/src/backend/postmaster/postmaster.c +++ b/src/backend/postmaster/postmaster.c @@ -95,6 +95,7 @@ #include "access/transam.h" #include "access/xlog.h" +#include "access/xlogrecovery.h" #include "catalog/pg_control.h" #include "common/file_perm.h" #include "common/ip.h" diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c index 9bae16bfc7..29cf8f18e1 100644 --- a/src/backend/postmaster/startup.c +++ b/src/backend/postmaster/startup.c @@ -20,6 +20,7 @@ #include "postgres.h" #include "access/xlog.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "libpq/pqsignal.h" #include "miscadmin.h" diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c index 4d71e71f68..c29e82307f 100644 --- a/src/backend/replication/logical/logicalfuncs.c +++ b/src/backend/replication/logical/logicalfuncs.c @@ -19,6 +19,7 @@ #include "access/xact.h" #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "catalog/pg_type.h" #include "fmgr.h" diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index ae6316d908..5149ebccb0 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -14,6 +14,7 @@ #include "access/htup_details.h" #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "funcapi.h" #include "miscadmin.h" diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c index b39fce8c23..ceaff097b9 100644 --- a/src/backend/replication/walreceiver.c +++ b/src/backend/replication/walreceiver.c @@ -56,6 +56,7 @@ #include "access/transam.h" #include "access/xlog_internal.h" #include "access/xlogarchive.h" +#include "access/xlogrecovery.h" #include "catalog/pg_authid.h" #include "catalog/pg_type.h" #include "common/ip.h" diff --git a/src/backend/replication/walreceiverfuncs.c b/src/backend/replication/walreceiverfuncs.c index c50728ea22..90798b9d53 100644 --- a/src/backend/replication/walreceiverfuncs.c +++ b/src/backend/replication/walreceiverfuncs.c @@ -23,6 +23,7 @@ #include #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "pgstat.h" #include "postmaster/startup.h" #include "replication/walreceiver.h" diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 655760fee3..a1dadd4c6a 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -55,6 +55,7 @@ #include "access/xact.h" #include "access/xlog_internal.h" #include "access/xlogreader.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "catalog/pg_authid.h" #include "catalog/pg_type.h" diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 9f26e41c46..cd4ebe2fc5 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -22,6 +22,7 @@ #include "access/subtrans.h" #include "access/syncscan.h" #include "access/twophase.h" +#include "access/xlogrecovery.h" #include "commands/async.h" #include "miscadmin.h" #include "pgstat.h" @@ -119,6 +120,7 @@ CalculateShmemSize(int *num_semaphores) size = add_size(size, PredicateLockShmemSize()); size = add_size(size, ProcGlobalShmemSize()); size = add_size(size, XLOGShmemSize()); + size = add_size(size, XLogRecoveryShmemSize()); size = add_size(size, CLOGShmemSize()); size = add_size(size, CommitTsShmemSize()); size = add_size(size, SUBTRANSShmemSize()); @@ -241,6 +243,7 @@ CreateSharedMemoryAndSemaphores(void) * Set up xlog, clog, and buffers */ XLOGShmemInit(); + XLogRecoveryShmemInit(); CLOGShmemInit(); CommitTsShmemInit(); SUBTRANSShmemInit(); diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index 87ac0f74b2..27361ac861 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -20,6 +20,7 @@ #include "access/twophase.h" #include "access/xact.h" #include "access/xloginsert.h" +#include "access/xlogrecovery.h" #include "access/xlogutils.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/storage/sync/sync.c b/src/backend/storage/sync/sync.c index 543f691f2d..e161d57761 100644 --- a/src/backend/storage/sync/sync.c +++ b/src/backend/storage/sync/sync.c @@ -29,6 +29,7 @@ #include "portability/instr_time.h" #include "postmaster/bgwriter.h" #include "storage/bufmgr.h" +#include "storage/fd.h" #include "storage/ipc.h" #include "storage/md.h" #include "utils/hsearch.h" diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index e2fe219aa8..568ac62c2a 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -41,6 +41,7 @@ #include "access/twophase.h" #include "access/xact.h" #include "access/xlog_internal.h" +#include "access/xlogrecovery.h" #include "catalog/namespace.h" #include "catalog/pg_authid.h" #include "catalog/storage.h" diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index a4b1c1286f..4b45ac64db 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -11,13 +11,11 @@ #ifndef XLOG_H #define XLOG_H -#include "access/rmgr.h" #include "access/xlogdefs.h" #include "access/xlogreader.h" #include "datatype/timestamp.h" #include "lib/stringinfo.h" #include "nodes/pg_list.h" -#include "storage/fd.h" /* Sync methods */ @@ -28,36 +26,10 @@ #define SYNC_METHOD_OPEN_DSYNC 4 /* for O_DSYNC */ extern int sync_method; -/* - * Recovery target type. - * Only set during a Point in Time recovery, not when in standby mode. - */ -typedef enum -{ - RECOVERY_TARGET_UNSET, - RECOVERY_TARGET_XID, - RECOVERY_TARGET_TIME, - RECOVERY_TARGET_NAME, - RECOVERY_TARGET_LSN, - RECOVERY_TARGET_IMMEDIATE -} RecoveryTargetType; - -/* - * Recovery target TimeLine goal - */ -typedef enum -{ - RECOVERY_TARGET_TIMELINE_CONTROLFILE, - RECOVERY_TARGET_TIMELINE_LATEST, - RECOVERY_TARGET_TIMELINE_NUMERIC -} RecoveryTargetTimeLineGoal; - extern XLogRecPtr ProcLastRecPtr; extern XLogRecPtr XactLastRecEnd; extern PGDLLIMPORT XLogRecPtr XactLastCommitEnd; -extern bool reachedConsistency; - /* these variables are GUC parameters related to XLOG */ extern int wal_segment_size; extern int min_wal_size_mb; @@ -77,34 +49,10 @@ extern bool wal_recycle; extern bool *wal_consistency_checking; extern char *wal_consistency_checking_string; extern bool log_checkpoints; -extern char *recoveryRestoreCommand; -extern char *recoveryEndCommand; -extern char *archiveCleanupCommand; -extern bool recoveryTargetInclusive; -extern int recoveryTargetAction; -extern int recovery_min_apply_delay; -extern char *PrimaryConnInfo; -extern char *PrimarySlotName; -extern bool wal_receiver_create_temp_slot; extern bool track_wal_io_timing; -/* indirectly set via GUC system */ -extern TransactionId recoveryTargetXid; -extern char *recovery_target_time_string; -extern const char *recoveryTargetName; -extern XLogRecPtr recoveryTargetLSN; -extern RecoveryTargetType recoveryTarget; -extern char *PromoteTriggerFile; -extern RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal; -extern TimeLineID recoveryTargetTLIRequested; -extern TimeLineID recoveryTargetTLI; - extern int CheckPointSegments; -/* option set locally in startup process only when signal files exist */ -extern bool StandbyModeRequested; -extern bool StandbyMode; - /* Archive modes */ typedef enum ArchiveMode { @@ -138,14 +86,6 @@ typedef enum RecoveryState RECOVERY_STATE_DONE /* currently in production */ } RecoveryState; -/* Recovery pause states */ -typedef enum RecoveryPauseState -{ - RECOVERY_NOT_PAUSED, /* pause not requested */ - RECOVERY_PAUSE_REQUESTED, /* pause requested, but not yet paused */ - RECOVERY_PAUSED /* recovery is paused */ -} RecoveryPauseState; - extern PGDLLIMPORT int wal_level; /* Is WAL archiving enabled (always or only while server is running normally)? */ @@ -274,19 +214,10 @@ extern void issue_xlog_fsync(int fd, XLogSegNo segno, TimeLineID tli); extern bool RecoveryInProgress(void); extern RecoveryState GetRecoveryState(void); -extern bool HotStandbyActive(void); -extern bool HotStandbyActiveInReplay(void); extern bool XLogInsertAllowed(void); -extern void GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream); -extern XLogRecPtr GetXLogReplayRecPtr(TimeLineID *replayTLI); extern XLogRecPtr GetXLogInsertRecPtr(void); extern XLogRecPtr GetXLogWriteRecPtr(void); -extern RecoveryPauseState GetRecoveryPauseState(void); -extern void SetRecoveryPause(bool recoveryPause); -extern TimestampTz GetLatestXTime(void); -extern TimestampTz GetCurrentChunkReplayStartTime(void); -extern void UpdateControlFile(void); extern uint64 GetSystemIdentifier(void); extern char *GetMockAuthenticationNonce(void); extern bool DataChecksumsEnabled(void); @@ -310,19 +241,23 @@ extern XLogRecPtr GetInsertRecPtr(void); extern XLogRecPtr GetFlushRecPtr(TimeLineID *insertTLI); extern TimeLineID GetWALInsertionTimeLine(void); extern XLogRecPtr GetLastImportantRecPtr(void); -extern void RemovePromoteSignalFiles(void); -extern bool PromoteIsTriggered(void); -extern bool CheckPromoteSignal(void); -extern void WakeupRecovery(void); extern void SetWalWriterSleeping(bool sleeping); -extern void StartupRequestWalReceiverRestart(void); -extern void XLogRequestWalReceiverReply(void); - extern void assign_max_wal_size(int newval, void *extra); extern void assign_checkpoint_completion_target(double newval, void *extra); +/* + * Routines used by xlogrecovery.c to call back into xlog.c during recovery. + */ +extern void RemoveNonParentXlogFiles(XLogRecPtr switchpoint, TimeLineID newTLI); +extern bool XLogCheckpointNeeded(XLogSegNo new_segno); +extern void SwitchIntoArchiveRecovery(XLogRecPtr EndRecPtr, TimeLineID replayTLI); +extern void ReachedEndOfBackup(XLogRecPtr EndRecPtr, TimeLineID tli); +extern void SetInstallXLogFileSegmentActive(void); +extern bool IsInstallXLogFileSegmentActive(void); +extern void XLogShutdownWalRcv(void); + /* * Routines to start, stop, and get status of a base backup. */ diff --git a/src/include/access/xlogrecovery.h b/src/include/access/xlogrecovery.h new file mode 100644 index 0000000000..75a0f5fe5e --- /dev/null +++ b/src/include/access/xlogrecovery.h @@ -0,0 +1,157 @@ +/* + * xlogrecovery.h + * + * Functions for WAL recovery and standby mode + * + * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/access/xlogrecovery.h + */ +#ifndef XLOGRECOVERY_H +#define XLOGRECOVERY_H + +#include "access/xlogreader.h" +#include "catalog/pg_control.h" +#include "lib/stringinfo.h" +#include "utils/timestamp.h" + +/* + * Recovery target type. + * Only set during a Point in Time recovery, not when in standby mode. + */ +typedef enum +{ + RECOVERY_TARGET_UNSET, + RECOVERY_TARGET_XID, + RECOVERY_TARGET_TIME, + RECOVERY_TARGET_NAME, + RECOVERY_TARGET_LSN, + RECOVERY_TARGET_IMMEDIATE +} RecoveryTargetType; + +/* + * Recovery target TimeLine goal + */ +typedef enum +{ + RECOVERY_TARGET_TIMELINE_CONTROLFILE, + RECOVERY_TARGET_TIMELINE_LATEST, + RECOVERY_TARGET_TIMELINE_NUMERIC +} RecoveryTargetTimeLineGoal; + +/* Recovery pause states */ +typedef enum RecoveryPauseState +{ + RECOVERY_NOT_PAUSED, /* pause not requested */ + RECOVERY_PAUSE_REQUESTED, /* pause requested, but not yet paused */ + RECOVERY_PAUSED /* recovery is paused */ +} RecoveryPauseState; + +/* User-settable GUC parameters */ +extern bool recoveryTargetInclusive; +extern int recoveryTargetAction; +extern int recovery_min_apply_delay; +extern char *PrimaryConnInfo; +extern char *PrimarySlotName; +extern char *recoveryRestoreCommand; +extern char *recoveryEndCommand; +extern char *archiveCleanupCommand; + +/* indirectly set via GUC system */ +extern TransactionId recoveryTargetXid; +extern char *recovery_target_time_string; +extern TimestampTz recoveryTargetTime; +extern const char *recoveryTargetName; +extern XLogRecPtr recoveryTargetLSN; +extern RecoveryTargetType recoveryTarget; +extern char *PromoteTriggerFile; +extern bool wal_receiver_create_temp_slot; +extern RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal; +extern TimeLineID recoveryTargetTLIRequested; +extern TimeLineID recoveryTargetTLI; + +/* Have we already reached a consistent database state? */ +extern bool reachedConsistency; + +/* Are we currently in standby mode? */ +extern bool StandbyMode; + +extern Size XLogRecoveryShmemSize(void); +extern void XLogRecoveryShmemInit(void); + +extern void InitWalRecovery(ControlFileData *ControlFile, bool *wasShutdownPtr, bool *haveBackupLabel, bool *haveTblspcMap); +extern void PerformWalRecovery(void); + +/* + * FinishWalRecovery() returns this. It contains information about the point + * where recovery ended, and why it ended. + */ +typedef struct +{ + /* + * Information about the last valid or applied record, after which new WAL + * can be appended. 'lastRec' is the position where the last record + * starts, and 'endOfLog' is its end. 'lastPage' is a copy of the last + * partial page that contains endOfLog (or NULL if endOfLog is exactly at + * page boundary). 'lastPageBeginPtr' is the position where the last page + * begins. + * + * endOfLogTLI is the TLI in the filename of the XLOG segment containing + * the last applied record. It could be different from lastRecTLI, if + * there was a timeline switch in that segment, and we were reading the + * old WAL from a segment belonging to a higher timeline. + */ + XLogRecPtr lastRec; /* start of last valid or applied record */ + TimeLineID lastRecTLI; + XLogRecPtr endOfLog; /* end of last valid or applied record */ + TimeLineID endOfLogTLI; + + XLogRecPtr lastPageBeginPtr; /* LSN of page that contains endOfLog */ + char *lastPage; /* copy of the last page, up to endOfLog */ + + /* + * abortedRecPtr is the start pointer of a broken record at end of WAL + * when recovery completes; missingContrecPtr is the location of the first + * contrecord that went missing. See CreateOverwriteContrecordRecord for + * details. + */ + XLogRecPtr abortedRecPtr; + XLogRecPtr missingContrecPtr; + + /* short human-readable string describing why recovery ended */ + char *recoveryStopReason; + + /* + * If standby or recovery signal file was found, these flags are set + * accordingly. + */ + bool standby_signal_file_found; + bool recovery_signal_file_found; +} EndOfWalRecoveryInfo; + +extern EndOfWalRecoveryInfo *FinishWalRecovery(void); +extern void ShutdownWalRecovery(void); +extern void RemovePromoteSignalFiles(void); + +extern bool HotStandbyActive(void); +extern XLogRecPtr GetXLogReplayRecPtr(TimeLineID *replayTLI); +extern RecoveryPauseState GetRecoveryPauseState(void); +extern void SetRecoveryPause(bool recoveryPause); +extern void GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream); +extern TimestampTz GetLatestXTime(void); +extern TimestampTz GetCurrentChunkReplayStartTime(void); +extern XLogRecPtr GetCurrentReplayRecPtr(TimeLineID *replayEndTLI); + +extern bool PromoteIsTriggered(void); +extern bool CheckPromoteSignal(void); +extern void WakeupRecovery(void); + +extern void StartupRequestWalReceiverRestart(void); +extern void XLogRequestWalReceiverReply(void); + +extern void RecoveryRequiresIntParameter(const char *param_name, int currValue, int minValue); + +extern void xlog_outdesc(StringInfo buf, XLogReaderState *record); + +#endif /* XLOGRECOVERY_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index bfb7802f2d..15684f53ba 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -607,6 +607,7 @@ EndDirectModify_function EndForeignInsert_function EndForeignModify_function EndForeignScan_function +EndOfWalRecoveryInfo EndSampleScan_function EnumItem EolType @@ -2945,6 +2946,7 @@ XLogRecordBlockCompressHeader XLogRecordBlockHeader XLogRecordBlockImageHeader XLogRecordBuffer +XLogRecoveryCtlData XLogRedoAction XLogSegNo XLogSource