#include "access/xlogbackup.h"
#include "access/xlogdefs.h"
#include "datatype/timestamp.h"
#include "lib/stringinfo.h"
#include "nodes/pg_list.h"

Include dependency graph for xlog.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	CheckpointStatsData

Macros
#define	XLogArchivingActive() (AssertMacro(XLogArchiveMode == ARCHIVE_MODE_OFF \|\| wal_level >= WAL_LEVEL_REPLICA), XLogArchiveMode > ARCHIVE_MODE_OFF)

#define	XLogArchivingAlways() (AssertMacro(XLogArchiveMode == ARCHIVE_MODE_OFF \|\| wal_level >= WAL_LEVEL_REPLICA), XLogArchiveMode == ARCHIVE_MODE_ALWAYS)

#define	XLogIsNeeded() (wal_level >= WAL_LEVEL_REPLICA)

#define	XLogHintBitIsNeeded() (DataChecksumsEnabled() \|\| wal_log_hints)

#define	XLogStandbyInfoActive() (wal_level >= WAL_LEVEL_REPLICA)

#define	XLogLogicalInfoActive() (wal_level >= WAL_LEVEL_LOGICAL)

#define	CHECKPOINT_IS_SHUTDOWN 0x0001 /* Checkpoint is for shutdown */

#define	CHECKPOINT_END_OF_RECOVERY

#define	CHECKPOINT_IMMEDIATE 0x0004 /* Do it without delays */

#define	CHECKPOINT_FORCE 0x0008 /* Force even if no activity */

#define	CHECKPOINT_FLUSH_ALL

#define	CHECKPOINT_WAIT 0x0020 /* Wait for completion */

#define	CHECKPOINT_REQUESTED 0x0040 /* Checkpoint request has been made */

#define	CHECKPOINT_CAUSE_XLOG 0x0080 /* XLOG consumption */

#define	CHECKPOINT_CAUSE_TIME 0x0100 /* Elapsed time */

#define	XLOG_INCLUDE_ORIGIN 0x01 /* include the replication origin */

#define	XLOG_MARK_UNIMPORTANT 0x02 /* record not important for durability */

#define	RECOVERY_SIGNAL_FILE "recovery.signal"

#define	STANDBY_SIGNAL_FILE "standby.signal"

#define	BACKUP_LABEL_FILE "backup_label"

#define	BACKUP_LABEL_OLD "backup_label.old"

#define	TABLESPACE_MAP "tablespace_map"

#define	TABLESPACE_MAP_OLD "tablespace_map.old"

#define	PROMOTE_SIGNAL_FILE "promote"

Typedefs
typedef enum ArchiveMode	ArchiveMode

typedef enum WalLevel	WalLevel

typedef enum WalCompression	WalCompression

typedef enum RecoveryState	RecoveryState

typedef struct CheckpointStatsData	CheckpointStatsData

typedef enum WALAvailability	WALAvailability

typedef enum SessionBackupState	SessionBackupState

Enumerations
enum	WalSyncMethod { WAL_SYNC_METHOD_FSYNC = 0 , WAL_SYNC_METHOD_FDATASYNC , WAL_SYNC_METHOD_OPEN , WAL_SYNC_METHOD_FSYNC_WRITETHROUGH , WAL_SYNC_METHOD_OPEN_DSYNC }

enum	ArchiveMode { ARCHIVE_MODE_OFF = 0 , ARCHIVE_MODE_ON , ARCHIVE_MODE_ALWAYS }

enum	WalLevel { WAL_LEVEL_MINIMAL = 0 , WAL_LEVEL_REPLICA , WAL_LEVEL_LOGICAL }

enum	WalCompression { WAL_COMPRESSION_NONE = 0 , WAL_COMPRESSION_PGLZ , WAL_COMPRESSION_LZ4 , WAL_COMPRESSION_ZSTD }

enum	RecoveryState { RECOVERY_STATE_CRASH = 0 , RECOVERY_STATE_ARCHIVE , RECOVERY_STATE_DONE }

enum	WALAvailability { WALAVAIL_INVALID_LSN , WALAVAIL_RESERVED , WALAVAIL_EXTENDED , WALAVAIL_UNRESERVED , WALAVAIL_REMOVED }

enum	SessionBackupState { SESSION_BACKUP_NONE , SESSION_BACKUP_RUNNING }

Functions
XLogRecPtr	XLogInsertRecord (struct XLogRecData *rdata, XLogRecPtr fpw_lsn, uint8 flags, int num_fpi, bool topxid_included)

void	XLogFlush (XLogRecPtr record)

bool	XLogBackgroundFlush (void)

bool	XLogNeedsFlush (XLogRecPtr record)

int	XLogFileInit (XLogSegNo logsegno, TimeLineID logtli)

int	XLogFileOpen (XLogSegNo segno, TimeLineID tli)

void	CheckXLogRemoved (XLogSegNo segno, TimeLineID tli)

XLogSegNo	XLogGetLastRemovedSegno (void)

XLogSegNo	XLogGetOldestSegno (TimeLineID tli)

void	XLogSetAsyncXactLSN (XLogRecPtr asyncXactLSN)

void	XLogSetReplicationSlotMinimumLSN (XLogRecPtr lsn)

void	xlog_redo (struct XLogReaderState *record)

void	xlog_desc (StringInfo buf, struct XLogReaderState *record)

const char *	xlog_identify (uint8 info)

void	issue_xlog_fsync (int fd, XLogSegNo segno, TimeLineID tli)

bool	RecoveryInProgress (void)

RecoveryState	GetRecoveryState (void)

bool	XLogInsertAllowed (void)

XLogRecPtr	GetXLogInsertRecPtr (void)

XLogRecPtr	GetXLogWriteRecPtr (void)

uint64	GetSystemIdentifier (void)

char *	GetMockAuthenticationNonce (void)

bool	DataChecksumsEnabled (void)

bool	GetDefaultCharSignedness (void)

XLogRecPtr	GetFakeLSNForUnloggedRel (void)

Size	XLOGShmemSize (void)

void	XLOGShmemInit (void)

void	BootStrapXLOG (uint32 data_checksum_version)

void	InitializeWalConsistencyChecking (void)

void	LocalProcessControlFile (bool reset)

WalLevel	GetActiveWalLevelOnStandby (void)

void	StartupXLOG (void)

void	ShutdownXLOG (int code, Datum arg)

bool	CreateCheckPoint (int flags)

bool	CreateRestartPoint (int flags)

WALAvailability	GetWALAvailability (XLogRecPtr targetLSN)

void	XLogPutNextOid (Oid nextOid)

XLogRecPtr	XLogRestorePoint (const char *rpName)

void	UpdateFullPageWrites (void)

void	GetFullPageWriteInfo (XLogRecPtr RedoRecPtr_p, bool doPageWrites_p)

XLogRecPtr	GetRedoRecPtr (void)

XLogRecPtr	GetInsertRecPtr (void)

XLogRecPtr	GetFlushRecPtr (TimeLineID *insertTLI)

TimeLineID	GetWALInsertionTimeLine (void)

TimeLineID	GetWALInsertionTimeLineIfSet (void)

XLogRecPtr	GetLastImportantRecPtr (void)

void	SetWalWriterSleeping (bool sleeping)

Size	WALReadFromBuffers (char *dstbuf, XLogRecPtr startptr, Size count, TimeLineID tli)

void	RemoveNonParentXlogFiles (XLogRecPtr switchpoint, TimeLineID newTLI)

bool	XLogCheckpointNeeded (XLogSegNo new_segno)

void	SwitchIntoArchiveRecovery (XLogRecPtr EndRecPtr, TimeLineID replayTLI)

void	ReachedEndOfBackup (XLogRecPtr EndRecPtr, TimeLineID tli)

void	SetInstallXLogFileSegmentActive (void)

bool	IsInstallXLogFileSegmentActive (void)

void	XLogShutdownWalRcv (void)

void	do_pg_backup_start (const char backupidstr, bool fast, List tablespaces, BackupState state, StringInfo tblspcmapfile)

void	do_pg_backup_stop (BackupState *state, bool waitforarchive)

void	do_pg_abort_backup (int code, Datum arg)

void	register_persistent_abort_backup_handler (void)

SessionBackupState	get_backup_status (void)

Variables
PGDLLIMPORT int	wal_sync_method

PGDLLIMPORT XLogRecPtr	ProcLastRecPtr

PGDLLIMPORT XLogRecPtr	XactLastRecEnd

PGDLLIMPORT XLogRecPtr	XactLastCommitEnd

PGDLLIMPORT int	wal_segment_size

PGDLLIMPORT int	min_wal_size_mb

PGDLLIMPORT int	max_wal_size_mb

PGDLLIMPORT int	wal_keep_size_mb

PGDLLIMPORT int	max_slot_wal_keep_size_mb

PGDLLIMPORT int	XLOGbuffers

PGDLLIMPORT int	XLogArchiveTimeout

PGDLLIMPORT int	wal_retrieve_retry_interval

PGDLLIMPORT char *	XLogArchiveCommand

PGDLLIMPORT bool	EnableHotStandby

PGDLLIMPORT bool	fullPageWrites

PGDLLIMPORT bool	wal_log_hints

PGDLLIMPORT int	wal_compression

PGDLLIMPORT bool	wal_init_zero

PGDLLIMPORT bool	wal_recycle

PGDLLIMPORT bool *	wal_consistency_checking

PGDLLIMPORT char *	wal_consistency_checking_string

PGDLLIMPORT bool	log_checkpoints

PGDLLIMPORT int	CommitDelay

PGDLLIMPORT int	CommitSiblings

PGDLLIMPORT bool	track_wal_io_timing

PGDLLIMPORT int	wal_decode_buffer_size

PGDLLIMPORT int	CheckPointSegments

PGDLLIMPORT int	XLogArchiveMode

PGDLLIMPORT int	wal_level

PGDLLIMPORT CheckpointStatsData	CheckpointStats

Macro Definition Documentation

◆ BACKUP_LABEL_FILE

#define BACKUP_LABEL_FILE "backup_label"

Definition at line 303 of file xlog.h.

◆ BACKUP_LABEL_OLD

#define BACKUP_LABEL_OLD "backup_label.old"

Definition at line 304 of file xlog.h.

◆ CHECKPOINT_CAUSE_TIME

#define CHECKPOINT_CAUSE_TIME 0x0100 /* Elapsed time */

Definition at line 149 of file xlog.h.

◆ CHECKPOINT_CAUSE_XLOG

#define CHECKPOINT_CAUSE_XLOG 0x0080 /* XLOG consumption */

Definition at line 148 of file xlog.h.

◆ CHECKPOINT_END_OF_RECOVERY

#define CHECKPOINT_END_OF_RECOVERY

Value:

0x0002 /* Like shutdown checkpoint, but

* issued at end of WAL recovery */

Definition at line 140 of file xlog.h.

◆ CHECKPOINT_FLUSH_ALL

#define CHECKPOINT_FLUSH_ALL

Value:

0x0010 /* Flush all pages, including those

* belonging to unlogged tables */

Definition at line 143 of file xlog.h.

◆ CHECKPOINT_FORCE

#define CHECKPOINT_FORCE 0x0008 /* Force even if no activity */

Definition at line 142 of file xlog.h.

◆ CHECKPOINT_IMMEDIATE

#define CHECKPOINT_IMMEDIATE 0x0004 /* Do it without delays */

Definition at line 141 of file xlog.h.

◆ CHECKPOINT_IS_SHUTDOWN

#define CHECKPOINT_IS_SHUTDOWN 0x0001 /* Checkpoint is for shutdown */

Definition at line 139 of file xlog.h.

◆ CHECKPOINT_REQUESTED

#define CHECKPOINT_REQUESTED 0x0040 /* Checkpoint request has been made */

Definition at line 146 of file xlog.h.

◆ CHECKPOINT_WAIT

#define CHECKPOINT_WAIT 0x0020 /* Wait for completion */

Definition at line 145 of file xlog.h.

◆ PROMOTE_SIGNAL_FILE

#define PROMOTE_SIGNAL_FILE "promote"

Definition at line 310 of file xlog.h.

◆ RECOVERY_SIGNAL_FILE

#define RECOVERY_SIGNAL_FILE "recovery.signal"

Definition at line 301 of file xlog.h.

◆ STANDBY_SIGNAL_FILE

#define STANDBY_SIGNAL_FILE "standby.signal"

Definition at line 302 of file xlog.h.

◆ TABLESPACE_MAP

#define TABLESPACE_MAP "tablespace_map"

Definition at line 306 of file xlog.h.

◆ TABLESPACE_MAP_OLD

#define TABLESPACE_MAP_OLD "tablespace_map.old"

Definition at line 307 of file xlog.h.

◆ XLOG_INCLUDE_ORIGIN

#define XLOG_INCLUDE_ORIGIN 0x01 /* include the replication origin */

Definition at line 154 of file xlog.h.

◆ XLOG_MARK_UNIMPORTANT

#define XLOG_MARK_UNIMPORTANT 0x02 /* record not important for durability */

Definition at line 155 of file xlog.h.

◆ XLogArchivingActive

#define XLogArchivingActive ( ) (AssertMacro(XLogArchiveMode == ARCHIVE_MODE_OFF || wal_level >= WAL_LEVEL_REPLICA), XLogArchiveMode > ARCHIVE_MODE_OFF)

Definition at line 99 of file xlog.h.

◆ XLogArchivingAlways

#define XLogArchivingAlways ( ) (AssertMacro(XLogArchiveMode == ARCHIVE_MODE_OFF || wal_level >= WAL_LEVEL_REPLICA), XLogArchiveMode == ARCHIVE_MODE_ALWAYS)

Definition at line 102 of file xlog.h.

◆ XLogHintBitIsNeeded

#define XLogHintBitIsNeeded ( ) (DataChecksumsEnabled() || wal_log_hints)

Definition at line 120 of file xlog.h.

◆ XLogIsNeeded

#define XLogIsNeeded ( ) (wal_level >= WAL_LEVEL_REPLICA)

Definition at line 109 of file xlog.h.

◆ XLogLogicalInfoActive

#define XLogLogicalInfoActive ( ) (wal_level >= WAL_LEVEL_LOGICAL)

Definition at line 126 of file xlog.h.

◆ XLogStandbyInfoActive

#define XLogStandbyInfoActive ( ) (wal_level >= WAL_LEVEL_REPLICA)

Definition at line 123 of file xlog.h.

Typedef Documentation

◆ ArchiveMode

typedef enum ArchiveMode ArchiveMode

◆ CheckpointStatsData

typedef struct CheckpointStatsData CheckpointStatsData

◆ RecoveryState

typedef enum RecoveryState RecoveryState

◆ SessionBackupState

typedef enum SessionBackupState SessionBackupState

◆ WALAvailability

typedef enum WALAvailability WALAvailability

◆ WalCompression

typedef enum WalCompression WalCompression

◆ WalLevel

typedef enum WalLevel WalLevel

Enumeration Type Documentation

◆ ArchiveMode

enum ArchiveMode

Enumerator
ARCHIVE_MODE_OFF
ARCHIVE_MODE_ON
ARCHIVE_MODE_ALWAYS

Definition at line 63 of file xlog.h.

{
    ARCHIVE_MODE_OFF = 0,       /* disabled */
    ARCHIVE_MODE_ON,            /* enabled while server is running normally */
    ARCHIVE_MODE_ALWAYS,        /* enabled always (even during recovery) */
} ArchiveMode;

◆ RecoveryState

enum RecoveryState

Enumerator
RECOVERY_STATE_CRASH
RECOVERY_STATE_ARCHIVE
RECOVERY_STATE_DONE

Definition at line 89 of file xlog.h.

{
    RECOVERY_STATE_CRASH = 0,   /* crash recovery */
    RECOVERY_STATE_ARCHIVE,     /* archive recovery */
    RECOVERY_STATE_DONE,        /* currently in production */
} RecoveryState;

◆ SessionBackupState

enum SessionBackupState

Enumerator
SESSION_BACKUP_NONE
SESSION_BACKUP_RUNNING

Definition at line 286 of file xlog.h.

289{

290 SESSION_BACKUP_NONE,

SESSION_BACKUP_NONE

@ SESSION_BACKUP_NONE

Definition: xlog.h:288

◆ WALAvailability

enum WALAvailability

Enumerator
WALAVAIL_INVALID_LSN
WALAVAIL_RESERVED
WALAVAIL_EXTENDED
WALAVAIL_UNRESERVED
WALAVAIL_REMOVED

Definition at line 187 of file xlog.h.

{
    WALAVAIL_INVALID_LSN,       /* parameter error */
    WALAVAIL_RESERVED,          /* WAL segment is within max_wal_size */
    WALAVAIL_EXTENDED,          /* WAL segment is reserved by a slot or
                                 * wal_keep_size */
    WALAVAIL_UNRESERVED,        /* no longer reserved, but not removed yet */

◆ WalCompression

enum WalCompression

Enumerator
WAL_COMPRESSION_NONE
WAL_COMPRESSION_PGLZ
WAL_COMPRESSION_LZ4
WAL_COMPRESSION_ZSTD

Definition at line 80 of file xlog.h.

{
    WAL_COMPRESSION_NONE = 0,
    WAL_COMPRESSION_PGLZ,
    WAL_COMPRESSION_LZ4,
    WAL_COMPRESSION_ZSTD,
} WalCompression;

◆ WalLevel

enum WalLevel

Enumerator
WAL_LEVEL_MINIMAL
WAL_LEVEL_REPLICA
WAL_LEVEL_LOGICAL

Definition at line 72 of file xlog.h.

{
    WAL_LEVEL_MINIMAL = 0,
    WAL_LEVEL_REPLICA,
    WAL_LEVEL_LOGICAL,
} WalLevel;

◆ WalSyncMethod

enum WalSyncMethod

Enumerator
WAL_SYNC_METHOD_FSYNC
WAL_SYNC_METHOD_FDATASYNC
WAL_SYNC_METHOD_OPEN
WAL_SYNC_METHOD_FSYNC_WRITETHROUGH
WAL_SYNC_METHOD_OPEN_DSYNC

Definition at line 22 of file xlog.h.

{
    WAL_SYNC_METHOD_FSYNC = 0,
    WAL_SYNC_METHOD_FDATASYNC,
    WAL_SYNC_METHOD_OPEN,       /* for O_SYNC */
    WAL_SYNC_METHOD_FSYNC_WRITETHROUGH,
    WAL_SYNC_METHOD_OPEN_DSYNC  /* for O_DSYNC */
};

Function Documentation

◆ BootStrapXLOG()

void BootStrapXLOG ( uint32 data_checksum_version )

Definition at line 5218 of file xlog.c.

{
    CheckPoint  checkPoint;
    char       *buffer;
    XLogPageHeader page;
    XLogLongPageHeader longpage;
    XLogRecord *record;
    char       *recptr;
    uint64      sysidentifier;
    struct timeval tv;
    pg_crc32c   crc;
 
    /* allow ordinary WAL segment creation, like StartupXLOG() would */
    SetInstallXLogFileSegmentActive();
 
    /*
     * Select a hopefully-unique system identifier code for this installation.
     * We use the result of gettimeofday(), including the fractional seconds
     * field, as being about as unique as we can easily get.  (Think not to
     * use random(), since it hasn't been seeded and there's no portable way
     * to seed it other than the system clock value...)  The upper half of the
     * uint64 value is just the tv_sec part, while the lower half contains the
     * tv_usec part (which must fit in 20 bits), plus 12 bits from our current
     * PID for a little extra uniqueness.  A person knowing this encoding can
     * determine the initialization time of the installation, which could
     * perhaps be useful sometimes.
     */
    gettimeofday(&tv, NULL);
    sysidentifier = ((uint64) tv.tv_sec) << 32;
    sysidentifier |= ((uint64) tv.tv_usec) << 12;
    sysidentifier |= getpid() & 0xFFF;
 
    /* page buffer must be aligned suitably for O_DIRECT */
    buffer = (char *) palloc(XLOG_BLCKSZ + XLOG_BLCKSZ);
    page = (XLogPageHeader) TYPEALIGN(XLOG_BLCKSZ, buffer);
    memset(page, 0, XLOG_BLCKSZ);
 
    /*
     * Set up information for the initial checkpoint record
     *
     * The initial checkpoint record is written to the beginning of the WAL
     * segment with logid=0 logseg=1. The very first WAL segment, 0/0, is not
     * used, so that we can use 0/0 to mean "before any valid WAL segment".
     */
    checkPoint.redo = wal_segment_size + SizeOfXLogLongPHD;
    checkPoint.ThisTimeLineID = BootstrapTimeLineID;
    checkPoint.PrevTimeLineID = BootstrapTimeLineID;
    checkPoint.fullPageWrites = fullPageWrites;
    checkPoint.wal_level = wal_level;
    checkPoint.nextXid =
        FullTransactionIdFromEpochAndXid(0, FirstNormalTransactionId);
    checkPoint.nextOid = FirstGenbkiObjectId;
    checkPoint.nextMulti = FirstMultiXactId;
    checkPoint.nextMultiOffset = 0;
    checkPoint.oldestXid = FirstNormalTransactionId;
    checkPoint.oldestXidDB = Template1DbOid;
    checkPoint.oldestMulti = FirstMultiXactId;
    checkPoint.oldestMultiDB = Template1DbOid;
    checkPoint.oldestCommitTsXid = InvalidTransactionId;
    checkPoint.newestCommitTsXid = InvalidTransactionId;
    checkPoint.time = (pg_time_t) time(NULL);
    checkPoint.oldestActiveXid = InvalidTransactionId;
 
    TransamVariables->nextXid = checkPoint.nextXid;
    TransamVariables->nextOid = checkPoint.nextOid;
    TransamVariables->oidCount = 0;
    MultiXactSetNextMXact(checkPoint.nextMulti, checkPoint.nextMultiOffset);
    AdvanceOldestClogXid(checkPoint.oldestXid);
    SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);
    SetMultiXactIdLimit(checkPoint.oldestMulti, checkPoint.oldestMultiDB, true);
    SetCommitTsLimit(InvalidTransactionId, InvalidTransactionId);
 
    /* Set up the XLOG page header */
    page->xlp_magic = XLOG_PAGE_MAGIC;
    page->xlp_info = XLP_LONG_HEADER;
    page->xlp_tli = BootstrapTimeLineID;
    page->xlp_pageaddr = wal_segment_size;
    longpage = (XLogLongPageHeader) page;
    longpage->xlp_sysid = sysidentifier;
    longpage->xlp_seg_size = wal_segment_size;
    longpage->xlp_xlog_blcksz = XLOG_BLCKSZ;
 
    /* Insert the initial checkpoint record */
    recptr = ((char *) page + SizeOfXLogLongPHD);
    record = (XLogRecord *) recptr;
    record->xl_prev = 0;
    record->xl_xid = InvalidTransactionId;
    record->xl_tot_len = SizeOfXLogRecord + SizeOfXLogRecordDataHeaderShort + sizeof(checkPoint);
    record->xl_info = XLOG_CHECKPOINT_SHUTDOWN;
    record->xl_rmid = RM_XLOG_ID;
    recptr += SizeOfXLogRecord;
    /* fill the XLogRecordDataHeaderShort struct */
    *(recptr++) = (char) XLR_BLOCK_ID_DATA_SHORT;
    *(recptr++) = sizeof(checkPoint);
    memcpy(recptr, &checkPoint, sizeof(checkPoint));
    recptr += sizeof(checkPoint);
    Assert(recptr - (char *) record == record->xl_tot_len);
 
    INIT_CRC32C(crc);
    COMP_CRC32C(crc, ((char *) record) + SizeOfXLogRecord, record->xl_tot_len - SizeOfXLogRecord);
    COMP_CRC32C(crc, (char *) record, offsetof(XLogRecord, xl_crc));
    FIN_CRC32C(crc);
    record->xl_crc = crc;
 
    /* Create first XLOG segment file */
    openLogTLI = BootstrapTimeLineID;
    openLogFile = XLogFileInit(1, BootstrapTimeLineID);
 
    /*
     * We needn't bother with Reserve/ReleaseExternalFD here, since we'll
     * close the file again in a moment.
     */
 
    /* Write the first page with the initial record */
    errno = 0;
    pgstat_report_wait_start(WAIT_EVENT_WAL_BOOTSTRAP_WRITE);
    if (write(openLogFile, page, XLOG_BLCKSZ) != XLOG_BLCKSZ)
    {
        /* if write didn't set errno, assume problem is no disk space */
        if (errno == 0)
            errno = ENOSPC;
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not write bootstrap write-ahead log file: %m")));
    }
    pgstat_report_wait_end();
 
    pgstat_report_wait_start(WAIT_EVENT_WAL_BOOTSTRAP_SYNC);
    if (pg_fsync(openLogFile) != 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not fsync bootstrap write-ahead log file: %m")));
    pgstat_report_wait_end();
 
    if (close(openLogFile) != 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not close bootstrap write-ahead log file: %m")));
 
    openLogFile = -1;
 
    /* Now create pg_control */
    InitControlFile(sysidentifier, data_checksum_version);
    ControlFile->time = checkPoint.time;
    ControlFile->checkPoint = checkPoint.redo;
    ControlFile->checkPointCopy = checkPoint;
 
    /* some additional ControlFile fields are set in WriteControlFile() */
    WriteControlFile();
 
    /* Bootstrap the commit log, too */
    BootStrapCLOG();
    BootStrapCommitTs();
    BootStrapSUBTRANS();
    BootStrapMultiXact();
 
    pfree(buffer);
 
    /*
     * Force control file to be read - in contrast to normal processing we'd
     * otherwise never run the checks and GUC related initializations therein.
     */
    ReadControlFile();
}

References AdvanceOldestClogXid(), Assert(), BootStrapCLOG(), BootStrapCommitTs(), BootStrapMultiXact(), BootStrapSUBTRANS(), BootstrapTimeLineID, ControlFileData::checkPoint, ControlFileData::checkPointCopy, close, COMP_CRC32C, ControlFile, crc, ereport, errcode_for_file_access(), errmsg(), FIN_CRC32C, FirstGenbkiObjectId, FirstMultiXactId, FirstNormalTransactionId, fullPageWrites, CheckPoint::fullPageWrites, FullTransactionIdFromEpochAndXid(), gettimeofday(), INIT_CRC32C, InitControlFile(), InvalidTransactionId, MultiXactSetNextMXact(), CheckPoint::newestCommitTsXid, CheckPoint::nextMulti, CheckPoint::nextMultiOffset, TransamVariablesData::nextOid, CheckPoint::nextOid, TransamVariablesData::nextXid, CheckPoint::nextXid, TransamVariablesData::oidCount, CheckPoint::oldestActiveXid, CheckPoint::oldestCommitTsXid, CheckPoint::oldestMulti, CheckPoint::oldestMultiDB, CheckPoint::oldestXid, CheckPoint::oldestXidDB, openLogFile, openLogTLI, palloc(), PANIC, pfree(), pg_fsync(), pgstat_report_wait_end(), pgstat_report_wait_start(), CheckPoint::PrevTimeLineID, ReadControlFile(), CheckPoint::redo, SetCommitTsLimit(), SetInstallXLogFileSegmentActive(), SetMultiXactIdLimit(), SetTransactionIdLimit(), SizeOfXLogLongPHD, SizeOfXLogRecord, SizeOfXLogRecordDataHeaderShort, CheckPoint::ThisTimeLineID, CheckPoint::time, ControlFileData::time, TransamVariables, TYPEALIGN, wal_level, CheckPoint::wal_level, wal_segment_size, write, WriteControlFile(), XLogRecord::xl_crc, XLogRecord::xl_info, XLogRecord::xl_prev, XLogRecord::xl_rmid, XLogRecord::xl_tot_len, XLogRecord::xl_xid, XLOG_CHECKPOINT_SHUTDOWN, XLOG_PAGE_MAGIC, XLogFileInit(), XLogPageHeaderData::xlp_info, XLP_LONG_HEADER, XLogPageHeaderData::xlp_magic, XLogPageHeaderData::xlp_pageaddr, XLogLongPageHeaderData::xlp_seg_size, XLogLongPageHeaderData::xlp_sysid, XLogPageHeaderData::xlp_tli, XLogLongPageHeaderData::xlp_xlog_blcksz, and XLR_BLOCK_ID_DATA_SHORT.

Referenced by BootstrapModeMain().

◆ CheckXLogRemoved()

void CheckXLogRemoved	(	XLogSegNo	segno,
		TimeLineID	tli
	)

Definition at line 3866 of file xlog.c.

{
    int         save_errno = errno;
    XLogSegNo   lastRemovedSegNo;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    lastRemovedSegNo = XLogCtl->lastRemovedSegNo;
    SpinLockRelease(&XLogCtl->info_lck);
 
    if (segno <= lastRemovedSegNo)
    {
        char        filename[MAXFNAMELEN];
 
        XLogFileName(filename, tli, segno, wal_segment_size);
        errno = save_errno;
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("requested WAL segment %s has already been removed",
                        filename)));
    }
    errno = save_errno;
}

References ereport, errcode_for_file_access(), errmsg(), ERROR, filename, XLogCtlData::info_lck, XLogCtlData::lastRemovedSegNo, MAXFNAMELEN, SpinLockAcquire, SpinLockRelease, wal_segment_size, XLogCtl, and XLogFileName().

Referenced by logical_read_xlog_page(), perform_base_backup(), and XLogSendPhysical().

◆ CreateCheckPoint()

bool CreateCheckPoint ( int flags )

Definition at line 7077 of file xlog.c.

{
    bool        shutdown;
    CheckPoint  checkPoint;
    XLogRecPtr  recptr;
    XLogSegNo   _logSegNo;
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    uint32      freespace;
    XLogRecPtr  PriorRedoPtr;
    XLogRecPtr  last_important_lsn;
    VirtualTransactionId *vxids;
    int         nvxids;
    int         oldXLogAllowed = 0;
 
    /*
     * An end-of-recovery checkpoint is really a shutdown checkpoint, just
     * issued at a different time.
     */
    if (flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY))
        shutdown = true;
    else
        shutdown = false;
 
    /* sanity check */
    if (RecoveryInProgress() && (flags & CHECKPOINT_END_OF_RECOVERY) == 0)
        elog(ERROR, "can't create a checkpoint during recovery");
 
    /*
     * Prepare to accumulate statistics.
     *
     * Note: because it is possible for log_checkpoints to change while a
     * checkpoint proceeds, we always accumulate stats, even if
     * log_checkpoints is currently off.
     */
    MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
    CheckpointStats.ckpt_start_t = GetCurrentTimestamp();
 
    /*
     * Let smgr prepare for checkpoint; this has to happen outside the
     * critical section and before we determine the REDO pointer.  Note that
     * smgr must not do anything that'd have to be undone if we decide no
     * checkpoint is needed.
     */
    SyncPreCheckpoint();
 
    /*
     * Use a critical section to force system panic if we have trouble.
     */
    START_CRIT_SECTION();
 
    if (shutdown)
    {
        LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
        ControlFile->state = DB_SHUTDOWNING;
        UpdateControlFile();
        LWLockRelease(ControlFileLock);
    }
 
    /* Begin filling in the checkpoint WAL record */
    MemSet(&checkPoint, 0, sizeof(checkPoint));
    checkPoint.time = (pg_time_t) time(NULL);
 
    /*
     * For Hot Standby, derive the oldestActiveXid before we fix the redo
     * pointer. This allows us to begin accumulating changes to assemble our
     * starting snapshot of locks and transactions.
     */
    if (!shutdown && XLogStandbyInfoActive())
        checkPoint.oldestActiveXid = GetOldestActiveTransactionId();
    else
        checkPoint.oldestActiveXid = InvalidTransactionId;
 
    /*
     * Get location of last important record before acquiring insert locks (as
     * GetLastImportantRecPtr() also locks WAL locks).
     */
    last_important_lsn = GetLastImportantRecPtr();
 
    /*
     * If this isn't a shutdown or forced checkpoint, and if there has been no
     * WAL activity requiring a checkpoint, skip it.  The idea here is to
     * avoid inserting duplicate checkpoints when the system is idle.
     */
    if ((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
                  CHECKPOINT_FORCE)) == 0)
    {
        if (last_important_lsn == ControlFile->checkPoint)
        {
            END_CRIT_SECTION();
            ereport(DEBUG1,
                    (errmsg_internal("checkpoint skipped because system is idle")));
            return false;
        }
    }
 
    /*
     * An end-of-recovery checkpoint is created before anyone is allowed to
     * write WAL. To allow us to write the checkpoint record, temporarily
     * enable XLogInsertAllowed.
     */
    if (flags & CHECKPOINT_END_OF_RECOVERY)
        oldXLogAllowed = LocalSetXLogInsertAllowed();
 
    checkPoint.ThisTimeLineID = XLogCtl->InsertTimeLineID;
    if (flags & CHECKPOINT_END_OF_RECOVERY)
        checkPoint.PrevTimeLineID = XLogCtl->PrevTimeLineID;
    else
        checkPoint.PrevTimeLineID = checkPoint.ThisTimeLineID;
 
    /*
     * We must block concurrent insertions while examining insert state.
     */
    WALInsertLockAcquireExclusive();
 
    checkPoint.fullPageWrites = Insert->fullPageWrites;
    checkPoint.wal_level = wal_level;
 
    if (shutdown)
    {
        XLogRecPtr  curInsert = XLogBytePosToRecPtr(Insert->CurrBytePos);
 
        /*
         * Compute new REDO record ptr = location of next XLOG record.
         *
         * Since this is a shutdown checkpoint, there can't be any concurrent
         * WAL insertion.
         */
        freespace = INSERT_FREESPACE(curInsert);
        if (freespace == 0)
        {
            if (XLogSegmentOffset(curInsert, wal_segment_size) == 0)
                curInsert += SizeOfXLogLongPHD;
            else
                curInsert += SizeOfXLogShortPHD;
        }
        checkPoint.redo = curInsert;
 
        /*
         * Here we update the shared RedoRecPtr for future XLogInsert calls;
         * this must be done while holding all the insertion locks.
         *
         * Note: if we fail to complete the checkpoint, RedoRecPtr will be
         * left pointing past where it really needs to point.  This is okay;
         * the only consequence is that XLogInsert might back up whole buffers
         * that it didn't really need to.  We can't postpone advancing
         * RedoRecPtr because XLogInserts that happen while we are dumping
         * buffers must assume that their buffer changes are not included in
         * the checkpoint.
         */
        RedoRecPtr = XLogCtl->Insert.RedoRecPtr = checkPoint.redo;
    }
 
    /*
     * Now we can release the WAL insertion locks, allowing other xacts to
     * proceed while we are flushing disk buffers.
     */
    WALInsertLockRelease();
 
    /*
     * If this is an online checkpoint, we have not yet determined the redo
     * point. We do so now by inserting the special XLOG_CHECKPOINT_REDO
     * record; the LSN at which it starts becomes the new redo pointer. We
     * don't do this for a shutdown checkpoint, because in that case no WAL
     * can be written between the redo point and the insertion of the
     * checkpoint record itself, so the checkpoint record itself serves to
     * mark the redo point.
     */
    if (!shutdown)
    {
        /* Include WAL level in record for WAL summarizer's benefit. */
        XLogBeginInsert();
        XLogRegisterData(&wal_level, sizeof(wal_level));
        (void) XLogInsert(RM_XLOG_ID, XLOG_CHECKPOINT_REDO);
 
        /*
         * XLogInsertRecord will have updated XLogCtl->Insert.RedoRecPtr in
         * shared memory and RedoRecPtr in backend-local memory, but we need
         * to copy that into the record that will be inserted when the
         * checkpoint is complete.
         */
        checkPoint.redo = RedoRecPtr;
    }
 
    /* Update the info_lck-protected copy of RedoRecPtr as well */
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->RedoRecPtr = checkPoint.redo;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * If enabled, log checkpoint start.  We postpone this until now so as not
     * to log anything if we decided to skip the checkpoint.
     */
    if (log_checkpoints)
        LogCheckpointStart(flags, false);
 
    /* Update the process title */
    update_checkpoint_display(flags, false, false);
 
    TRACE_POSTGRESQL_CHECKPOINT_START(flags);
 
    /*
     * Get the other info we need for the checkpoint record.
     *
     * We don't need to save oldestClogXid in the checkpoint, it only matters
     * for the short period in which clog is being truncated, and if we crash
     * during that we'll redo the clog truncation and fix up oldestClogXid
     * there.
     */
    LWLockAcquire(XidGenLock, LW_SHARED);
    checkPoint.nextXid = TransamVariables->nextXid;
    checkPoint.oldestXid = TransamVariables->oldestXid;
    checkPoint.oldestXidDB = TransamVariables->oldestXidDB;
    LWLockRelease(XidGenLock);
 
    LWLockAcquire(CommitTsLock, LW_SHARED);
    checkPoint.oldestCommitTsXid = TransamVariables->oldestCommitTsXid;
    checkPoint.newestCommitTsXid = TransamVariables->newestCommitTsXid;
    LWLockRelease(CommitTsLock);
 
    LWLockAcquire(OidGenLock, LW_SHARED);
    checkPoint.nextOid = TransamVariables->nextOid;
    if (!shutdown)
        checkPoint.nextOid += TransamVariables->oidCount;
    LWLockRelease(OidGenLock);
 
    MultiXactGetCheckptMulti(shutdown,
                             &checkPoint.nextMulti,
                             &checkPoint.nextMultiOffset,
                             &checkPoint.oldestMulti,
                             &checkPoint.oldestMultiDB);
 
    /*
     * Having constructed the checkpoint record, ensure all shmem disk buffers
     * and commit-log buffers are flushed to disk.
     *
     * This I/O could fail for various reasons.  If so, we will fail to
     * complete the checkpoint, but there is no reason to force a system
     * panic. Accordingly, exit critical section while doing it.
     */
    END_CRIT_SECTION();
 
    /*
     * In some cases there are groups of actions that must all occur on one
     * side or the other of a checkpoint record. Before flushing the
     * checkpoint record we must explicitly wait for any backend currently
     * performing those groups of actions.
     *
     * One example is end of transaction, so we must wait for any transactions
     * that are currently in commit critical sections.  If an xact inserted
     * its commit record into XLOG just before the REDO point, then a crash
     * restart from the REDO point would not replay that record, which means
     * that our flushing had better include the xact's update of pg_xact.  So
     * we wait till he's out of his commit critical section before proceeding.
     * See notes in RecordTransactionCommit().
     *
     * Because we've already released the insertion locks, this test is a bit
     * fuzzy: it is possible that we will wait for xacts we didn't really need
     * to wait for.  But the delay should be short and it seems better to make
     * checkpoint take a bit longer than to hold off insertions longer than
     * necessary. (In fact, the whole reason we have this issue is that xact.c
     * does commit record XLOG insertion and clog update as two separate steps
     * protected by different locks, but again that seems best on grounds of
     * minimizing lock contention.)
     *
     * A transaction that has not yet set delayChkptFlags when we look cannot
     * be at risk, since it has not inserted its commit record yet; and one
     * that's already cleared it is not at risk either, since it's done fixing
     * clog and we will correctly flush the update below.  So we cannot miss
     * any xacts we need to wait for.
     */
    vxids = GetVirtualXIDsDelayingChkpt(&nvxids, DELAY_CHKPT_START);
    if (nvxids > 0)
    {
        do
        {
            /*
             * Keep absorbing fsync requests while we wait. There could even
             * be a deadlock if we don't, if the process that prevents the
             * checkpoint is trying to add a request to the queue.
             */
            AbsorbSyncRequests();
 
            pgstat_report_wait_start(WAIT_EVENT_CHECKPOINT_DELAY_START);
            pg_usleep(10000L);  /* wait for 10 msec */
            pgstat_report_wait_end();
        } while (HaveVirtualXIDsDelayingChkpt(vxids, nvxids,
                                              DELAY_CHKPT_START));
    }
    pfree(vxids);
 
    CheckPointGuts(checkPoint.redo, flags);
 
    vxids = GetVirtualXIDsDelayingChkpt(&nvxids, DELAY_CHKPT_COMPLETE);
    if (nvxids > 0)
    {
        do
        {
            AbsorbSyncRequests();
 
            pgstat_report_wait_start(WAIT_EVENT_CHECKPOINT_DELAY_COMPLETE);
            pg_usleep(10000L);  /* wait for 10 msec */
            pgstat_report_wait_end();
        } while (HaveVirtualXIDsDelayingChkpt(vxids, nvxids,
                                              DELAY_CHKPT_COMPLETE));
    }
    pfree(vxids);
 
    /*
     * Take a snapshot of running transactions and write this to WAL. This
     * allows us to reconstruct the state of running transactions during
     * archive recovery, if required. Skip, if this info disabled.
     *
     * If we are shutting down, or Startup process is completing crash
     * recovery we don't need to write running xact data.
     */
    if (!shutdown && XLogStandbyInfoActive())
        LogStandbySnapshot();
 
    START_CRIT_SECTION();
 
    /*
     * Now insert the checkpoint record into XLOG.
     */
    XLogBeginInsert();
    XLogRegisterData(&checkPoint, sizeof(checkPoint));
    recptr = XLogInsert(RM_XLOG_ID,
                        shutdown ? XLOG_CHECKPOINT_SHUTDOWN :
                        XLOG_CHECKPOINT_ONLINE);
 
    XLogFlush(recptr);
 
    /*
     * We mustn't write any new WAL after a shutdown checkpoint, or it will be
     * overwritten at next startup.  No-one should even try, this just allows
     * sanity-checking.  In the case of an end-of-recovery checkpoint, we want
     * to just temporarily disable writing until the system has exited
     * recovery.
     */
    if (shutdown)
    {
        if (flags & CHECKPOINT_END_OF_RECOVERY)
            LocalXLogInsertAllowed = oldXLogAllowed;
        else
            LocalXLogInsertAllowed = 0; /* never again write WAL */
    }
 
    /*
     * We now have ProcLastRecPtr = start of actual checkpoint record, recptr
     * = end of actual checkpoint record.
     */
    if (shutdown && checkPoint.redo != ProcLastRecPtr)
        ereport(PANIC,
                (errmsg("concurrent write-ahead log activity while database system is shutting down")));
 
    /*
     * Remember the prior checkpoint's redo ptr for
     * UpdateCheckPointDistanceEstimate()
     */
    PriorRedoPtr = ControlFile->checkPointCopy.redo;
 
    /*
     * Update the control file.
     */
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    if (shutdown)
        ControlFile->state = DB_SHUTDOWNED;
    ControlFile->checkPoint = ProcLastRecPtr;
    ControlFile->checkPointCopy = checkPoint;
    /* crash recovery should always recover to the end of WAL */
    ControlFile->minRecoveryPoint = InvalidXLogRecPtr;
    ControlFile->minRecoveryPointTLI = 0;
 
    /*
     * Persist unloggedLSN value. It's reset on crash recovery, so this goes
     * unused on non-shutdown checkpoints, but seems useful to store it always
     * for debugging purposes.
     */
    ControlFile->unloggedLSN = pg_atomic_read_membarrier_u64(&XLogCtl->unloggedLSN);
 
    UpdateControlFile();
    LWLockRelease(ControlFileLock);
 
    /* Update shared-memory copy of checkpoint XID/epoch */
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->ckptFullXid = checkPoint.nextXid;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * We are now done with critical updates; no need for system panic if we
     * have trouble while fooling with old log segments.
     */
    END_CRIT_SECTION();
 
    /*
     * WAL summaries end when the next XLOG_CHECKPOINT_REDO or
     * XLOG_CHECKPOINT_SHUTDOWN record is reached. This is the first point
     * where (a) we're not inside of a critical section and (b) we can be
     * certain that the relevant record has been flushed to disk, which must
     * happen before it can be summarized.
     *
     * If this is a shutdown checkpoint, then this happens reasonably
     * promptly: we've only just inserted and flushed the
     * XLOG_CHECKPOINT_SHUTDOWN record. If this is not a shutdown checkpoint,
     * then this might not be very prompt at all: the XLOG_CHECKPOINT_REDO
     * record was written before we began flushing data to disk, and that
     * could be many minutes ago at this point. However, we don't XLogFlush()
     * after inserting that record, so we're not guaranteed that it's on disk
     * until after the above call that flushes the XLOG_CHECKPOINT_ONLINE
     * record.
     */
    WakeupWalSummarizer();
 
    /*
     * Let smgr do post-checkpoint cleanup (eg, deleting old files).
     */
    SyncPostCheckpoint();
 
    /*
     * Update the average distance between checkpoints if the prior checkpoint
     * exists.
     */
    if (PriorRedoPtr != InvalidXLogRecPtr)
        UpdateCheckPointDistanceEstimate(RedoRecPtr - PriorRedoPtr);
 
    /*
     * Delete old log files, those no longer needed for last checkpoint to
     * prevent the disk holding the xlog from growing full.
     */
    XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
    KeepLogSeg(recptr, &_logSegNo);
    if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED | RS_INVAL_IDLE_TIMEOUT,
                                           _logSegNo, InvalidOid,
                                           InvalidTransactionId))
    {
        /*
         * Some slots have been invalidated; recalculate the old-segment
         * horizon, starting again from RedoRecPtr.
         */
        XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
        KeepLogSeg(recptr, &_logSegNo);
    }
    _logSegNo--;
    RemoveOldXlogFiles(_logSegNo, RedoRecPtr, recptr,
                       checkPoint.ThisTimeLineID);
 
    /*
     * Make more log segments if needed.  (Do this after recycling old log
     * segments, since that may supply some of the needed files.)
     */
    if (!shutdown)
        PreallocXlogFiles(recptr, checkPoint.ThisTimeLineID);
 
    /*
     * Truncate pg_subtrans if possible.  We can throw away all data before
     * the oldest XMIN of any running transaction.  No future transaction will
     * attempt to reference any pg_subtrans entry older than that (see Asserts
     * in subtrans.c).  During recovery, though, we mustn't do this because
     * StartupSUBTRANS hasn't been called yet.
     */
    if (!RecoveryInProgress())
        TruncateSUBTRANS(GetOldestTransactionIdConsideredRunning());
 
    /* Real work is done; log and update stats. */
    LogCheckpointEnd(false);
 
    /* Reset the process title */
    update_checkpoint_display(flags, false, true);
 
    TRACE_POSTGRESQL_CHECKPOINT_DONE(CheckpointStats.ckpt_bufs_written,
                                     NBuffers,
                                     CheckpointStats.ckpt_segs_added,
                                     CheckpointStats.ckpt_segs_removed,
                                     CheckpointStats.ckpt_segs_recycled);
 
    return true;
}

References AbsorbSyncRequests(), ControlFileData::checkPoint, CHECKPOINT_END_OF_RECOVERY, CHECKPOINT_FORCE, CHECKPOINT_IS_SHUTDOWN, ControlFileData::checkPointCopy, CheckPointGuts(), CheckpointStats, CheckpointStatsData::ckpt_bufs_written, CheckpointStatsData::ckpt_segs_added, CheckpointStatsData::ckpt_segs_recycled, CheckpointStatsData::ckpt_segs_removed, CheckpointStatsData::ckpt_start_t, XLogCtlData::ckptFullXid, ControlFile, DB_SHUTDOWNED, DB_SHUTDOWNING, DEBUG1, DELAY_CHKPT_COMPLETE, DELAY_CHKPT_START, elog, END_CRIT_SECTION, ereport, errmsg(), errmsg_internal(), ERROR, CheckPoint::fullPageWrites, GetCurrentTimestamp(), GetLastImportantRecPtr(), GetOldestActiveTransactionId(), GetOldestTransactionIdConsideredRunning(), GetVirtualXIDsDelayingChkpt(), HaveVirtualXIDsDelayingChkpt(), XLogCtlData::info_lck, XLogCtlData::Insert, Insert(), INSERT_FREESPACE, XLogCtlData::InsertTimeLineID, InvalidateObsoleteReplicationSlots(), InvalidOid, InvalidTransactionId, InvalidXLogRecPtr, KeepLogSeg(), LocalSetXLogInsertAllowed(), LocalXLogInsertAllowed, log_checkpoints, LogCheckpointEnd(), LogCheckpointStart(), LogStandbySnapshot(), LW_EXCLUSIVE, LW_SHARED, LWLockAcquire(), LWLockRelease(), MemSet, ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, MultiXactGetCheckptMulti(), NBuffers, TransamVariablesData::newestCommitTsXid, CheckPoint::newestCommitTsXid, CheckPoint::nextMulti, CheckPoint::nextMultiOffset, TransamVariablesData::nextOid, CheckPoint::nextOid, TransamVariablesData::nextXid, CheckPoint::nextXid, TransamVariablesData::oidCount, CheckPoint::oldestActiveXid, TransamVariablesData::oldestCommitTsXid, CheckPoint::oldestCommitTsXid, CheckPoint::oldestMulti, CheckPoint::oldestMultiDB, TransamVariablesData::oldestXid, CheckPoint::oldestXid, TransamVariablesData::oldestXidDB, CheckPoint::oldestXidDB, PANIC, pfree(), pg_atomic_read_membarrier_u64(), pg_usleep(), pgstat_report_wait_end(), pgstat_report_wait_start(), PreallocXlogFiles(), XLogCtlData::PrevTimeLineID, CheckPoint::PrevTimeLineID, ProcLastRecPtr, RecoveryInProgress(), CheckPoint::redo, RedoRecPtr, XLogCtlInsert::RedoRecPtr, XLogCtlData::RedoRecPtr, RemoveOldXlogFiles(), RS_INVAL_IDLE_TIMEOUT, RS_INVAL_WAL_REMOVED, SizeOfXLogLongPHD, SizeOfXLogShortPHD, SpinLockAcquire, SpinLockRelease, START_CRIT_SECTION, ControlFileData::state, SyncPostCheckpoint(), SyncPreCheckpoint(), CheckPoint::ThisTimeLineID, CheckPoint::time, TransamVariables, TruncateSUBTRANS(), XLogCtlData::unloggedLSN, ControlFileData::unloggedLSN, update_checkpoint_display(), UpdateCheckPointDistanceEstimate(), UpdateControlFile(), WakeupWalSummarizer(), wal_level, CheckPoint::wal_level, wal_segment_size, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), XLByteToSeg, XLOG_CHECKPOINT_ONLINE, XLOG_CHECKPOINT_REDO, XLOG_CHECKPOINT_SHUTDOWN, XLogBeginInsert(), XLogBytePosToRecPtr(), XLogCtl, XLogFlush(), XLogInsert(), XLogRegisterData(), XLogSegmentOffset, and XLogStandbyInfoActive.

Referenced by CheckpointerMain(), RequestCheckpoint(), and ShutdownXLOG().

◆ CreateRestartPoint()

bool CreateRestartPoint ( int flags )

Definition at line 7779 of file xlog.c.

{
    XLogRecPtr  lastCheckPointRecPtr;
    XLogRecPtr  lastCheckPointEndPtr;
    CheckPoint  lastCheckPoint;
    XLogRecPtr  PriorRedoPtr;
    XLogRecPtr  receivePtr;
    XLogRecPtr  replayPtr;
    TimeLineID  replayTLI;
    XLogRecPtr  endptr;
    XLogSegNo   _logSegNo;
    TimestampTz xtime;
 
    /* Concurrent checkpoint/restartpoint cannot happen */
    Assert(!IsUnderPostmaster || MyBackendType == B_CHECKPOINTER);
 
    /* Get a local copy of the last safe checkpoint record. */
    SpinLockAcquire(&XLogCtl->info_lck);
    lastCheckPointRecPtr = XLogCtl->lastCheckPointRecPtr;
    lastCheckPointEndPtr = XLogCtl->lastCheckPointEndPtr;
    lastCheckPoint = XLogCtl->lastCheckPoint;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * Check that we're still in recovery mode. It's ok if we exit recovery
     * mode after this check, the restart point is valid anyway.
     */
    if (!RecoveryInProgress())
    {
        ereport(DEBUG2,
                (errmsg_internal("skipping restartpoint, recovery has already ended")));
        return false;
    }
 
    /*
     * If the last checkpoint record we've replayed is already our last
     * restartpoint, we can't perform a new restart point. We still update
     * minRecoveryPoint in that case, so that if this is a shutdown restart
     * point, we won't start up earlier than before. That's not strictly
     * necessary, but when hot standby is enabled, it would be rather weird if
     * the database opened up for read-only connections at a point-in-time
     * before the last shutdown. Such time travel is still possible in case of
     * immediate shutdown, though.
     *
     * We don't explicitly advance minRecoveryPoint when we do create a
     * restartpoint. It's assumed that flushing the buffers will do that as a
     * side-effect.
     */
    if (XLogRecPtrIsInvalid(lastCheckPointRecPtr) ||
        lastCheckPoint.redo <= ControlFile->checkPointCopy.redo)
    {
        ereport(DEBUG2,
                (errmsg_internal("skipping restartpoint, already performed at %X/%X",
                                 LSN_FORMAT_ARGS(lastCheckPoint.redo))));
 
        UpdateMinRecoveryPoint(InvalidXLogRecPtr, true);
        if (flags & CHECKPOINT_IS_SHUTDOWN)
        {
            LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
            ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
            UpdateControlFile();
            LWLockRelease(ControlFileLock);
        }
        return false;
    }
 
    /*
     * Update the shared RedoRecPtr so that the startup process can calculate
     * the number of segments replayed since last restartpoint, and request a
     * restartpoint if it exceeds CheckPointSegments.
     *
     * Like in CreateCheckPoint(), hold off insertions to update it, although
     * during recovery this is just pro forma, because no WAL insertions are
     * happening.
     */
    WALInsertLockAcquireExclusive();
    RedoRecPtr = XLogCtl->Insert.RedoRecPtr = lastCheckPoint.redo;
    WALInsertLockRelease();
 
    /* Also update the info_lck-protected copy */
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->RedoRecPtr = lastCheckPoint.redo;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * Prepare to accumulate statistics.
     *
     * Note: because it is possible for log_checkpoints to change while a
     * checkpoint proceeds, we always accumulate stats, even if
     * log_checkpoints is currently off.
     */
    MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
    CheckpointStats.ckpt_start_t = GetCurrentTimestamp();
 
    if (log_checkpoints)
        LogCheckpointStart(flags, true);
 
    /* Update the process title */
    update_checkpoint_display(flags, true, false);
 
    CheckPointGuts(lastCheckPoint.redo, flags);
 
    /*
     * This location needs to be after CheckPointGuts() to ensure that some
     * work has already happened during this checkpoint.
     */
    INJECTION_POINT("create-restart-point");
 
    /*
     * Remember the prior checkpoint's redo ptr for
     * UpdateCheckPointDistanceEstimate()
     */
    PriorRedoPtr = ControlFile->checkPointCopy.redo;
 
    /*
     * Update pg_control, using current time.  Check that it still shows an
     * older checkpoint, else do nothing; this is a quick hack to make sure
     * nothing really bad happens if somehow we get here after the
     * end-of-recovery checkpoint.
     */
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    if (ControlFile->checkPointCopy.redo < lastCheckPoint.redo)
    {
        /*
         * Update the checkpoint information.  We do this even if the cluster
         * does not show DB_IN_ARCHIVE_RECOVERY to match with the set of WAL
         * segments recycled below.
         */
        ControlFile->checkPoint = lastCheckPointRecPtr;
        ControlFile->checkPointCopy = lastCheckPoint;
 
        /*
         * Ensure minRecoveryPoint is past the checkpoint record and update it
         * if the control file still shows DB_IN_ARCHIVE_RECOVERY.  Normally,
         * this will have happened already while writing out dirty buffers,
         * but not necessarily - e.g. because no buffers were dirtied.  We do
         * this because a backup performed in recovery uses minRecoveryPoint
         * to determine which WAL files must be included in the backup, and
         * the file (or files) containing the checkpoint record must be
         * included, at a minimum.  Note that for an ordinary restart of
         * recovery there's no value in having the minimum recovery point any
         * earlier than this anyway, because redo will begin just after the
         * checkpoint record.
         */
        if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY)
        {
            if (ControlFile->minRecoveryPoint < lastCheckPointEndPtr)
            {
                ControlFile->minRecoveryPoint = lastCheckPointEndPtr;
                ControlFile->minRecoveryPointTLI = lastCheckPoint.ThisTimeLineID;
 
                /* update local copy */
                LocalMinRecoveryPoint = ControlFile->minRecoveryPoint;
                LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
            }
            if (flags & CHECKPOINT_IS_SHUTDOWN)
                ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
        }
        UpdateControlFile();
    }
    LWLockRelease(ControlFileLock);
 
    /*
     * Update the average distance between checkpoints/restartpoints if the
     * prior checkpoint exists.
     */
    if (PriorRedoPtr != InvalidXLogRecPtr)
        UpdateCheckPointDistanceEstimate(RedoRecPtr - PriorRedoPtr);
 
    /*
     * Delete old log files, those no longer needed for last restartpoint to
     * prevent the disk holding the xlog from growing full.
     */
    XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
 
    /*
     * Retreat _logSegNo using the current end of xlog replayed or received,
     * whichever is later.
     */
    receivePtr = GetWalRcvFlushRecPtr(NULL, NULL);
    replayPtr = GetXLogReplayRecPtr(&replayTLI);
    endptr = (receivePtr < replayPtr) ? replayPtr : receivePtr;
    KeepLogSeg(endptr, &_logSegNo);
    if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED | RS_INVAL_IDLE_TIMEOUT,
                                           _logSegNo, InvalidOid,
                                           InvalidTransactionId))
    {
        /*
         * Some slots have been invalidated; recalculate the old-segment
         * horizon, starting again from RedoRecPtr.
         */
        XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
        KeepLogSeg(endptr, &_logSegNo);
    }
    _logSegNo--;
 
    /*
     * Try to recycle segments on a useful timeline. If we've been promoted
     * since the beginning of this restartpoint, use the new timeline chosen
     * at end of recovery.  If we're still in recovery, use the timeline we're
     * currently replaying.
     *
     * There is no guarantee that the WAL segments will be useful on the
     * current timeline; if recovery proceeds to a new timeline right after
     * this, the pre-allocated WAL segments on this timeline will not be used,
     * and will go wasted until recycled on the next restartpoint. We'll live
     * with that.
     */
    if (!RecoveryInProgress())
        replayTLI = XLogCtl->InsertTimeLineID;
 
    RemoveOldXlogFiles(_logSegNo, RedoRecPtr, endptr, replayTLI);
 
    /*
     * Make more log segments if needed.  (Do this after recycling old log
     * segments, since that may supply some of the needed files.)
     */
    PreallocXlogFiles(endptr, replayTLI);
 
    /*
     * Truncate pg_subtrans if possible.  We can throw away all data before
     * the oldest XMIN of any running transaction.  No future transaction will
     * attempt to reference any pg_subtrans entry older than that (see Asserts
     * in subtrans.c).  When hot standby is disabled, though, we mustn't do
     * this because StartupSUBTRANS hasn't been called yet.
     */
    if (EnableHotStandby)
        TruncateSUBTRANS(GetOldestTransactionIdConsideredRunning());
 
    /* Real work is done; log and update stats. */
    LogCheckpointEnd(true);
 
    /* Reset the process title */
    update_checkpoint_display(flags, true, true);
 
    xtime = GetLatestXTime();
    ereport((log_checkpoints ? LOG : DEBUG2),
            (errmsg("recovery restart point at %X/%X",
                    LSN_FORMAT_ARGS(lastCheckPoint.redo)),
             xtime ? errdetail("Last completed transaction was at log time %s.",
                               timestamptz_to_str(xtime)) : 0));
 
    /*
     * Finally, execute archive_cleanup_command, if any.
     */
    if (archiveCleanupCommand && strcmp(archiveCleanupCommand, "") != 0)
        ExecuteRecoveryCommand(archiveCleanupCommand,
                               "archive_cleanup_command",
                               false,
                               WAIT_EVENT_ARCHIVE_CLEANUP_COMMAND);
 
    return true;
}

References archiveCleanupCommand, Assert(), B_CHECKPOINTER, ControlFileData::checkPoint, CHECKPOINT_IS_SHUTDOWN, ControlFileData::checkPointCopy, CheckPointGuts(), CheckpointStats, CheckpointStatsData::ckpt_start_t, ControlFile, DB_IN_ARCHIVE_RECOVERY, DB_SHUTDOWNED_IN_RECOVERY, DEBUG2, EnableHotStandby, ereport, errdetail(), errmsg(), errmsg_internal(), ExecuteRecoveryCommand(), GetCurrentTimestamp(), GetLatestXTime(), GetOldestTransactionIdConsideredRunning(), GetWalRcvFlushRecPtr(), GetXLogReplayRecPtr(), XLogCtlData::info_lck, INJECTION_POINT, XLogCtlData::Insert, XLogCtlData::InsertTimeLineID, InvalidateObsoleteReplicationSlots(), InvalidOid, InvalidTransactionId, InvalidXLogRecPtr, IsUnderPostmaster, KeepLogSeg(), XLogCtlData::lastCheckPoint, XLogCtlData::lastCheckPointEndPtr, XLogCtlData::lastCheckPointRecPtr, LocalMinRecoveryPoint, LocalMinRecoveryPointTLI, LOG, log_checkpoints, LogCheckpointEnd(), LogCheckpointStart(), LSN_FORMAT_ARGS, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MemSet, ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, MyBackendType, PreallocXlogFiles(), RecoveryInProgress(), CheckPoint::redo, RedoRecPtr, XLogCtlInsert::RedoRecPtr, XLogCtlData::RedoRecPtr, RemoveOldXlogFiles(), RS_INVAL_IDLE_TIMEOUT, RS_INVAL_WAL_REMOVED, SpinLockAcquire, SpinLockRelease, ControlFileData::state, CheckPoint::ThisTimeLineID, timestamptz_to_str(), TruncateSUBTRANS(), update_checkpoint_display(), UpdateCheckPointDistanceEstimate(), UpdateControlFile(), UpdateMinRecoveryPoint(), wal_segment_size, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), XLByteToSeg, XLogCtl, and XLogRecPtrIsInvalid.

Referenced by CheckpointerMain(), and ShutdownXLOG().

◆ DataChecksumsEnabled()

bool DataChecksumsEnabled ( void )

Definition at line 4754 of file xlog.c.

{
    Assert(ControlFile != NULL);
    return (ControlFile->data_checksum_version > 0);
}

References Assert(), ControlFile, and ControlFileData::data_checksum_version.

Referenced by PageIsVerified(), PageSetChecksumCopy(), PageSetChecksumInplace(), pg_stat_get_db_checksum_failures(), pg_stat_get_db_checksum_last_failure(), ReadControlFile(), and sendFile().

◆ do_pg_abort_backup()

void do_pg_abort_backup	(	int	code,
		Datum	arg
	)

Definition at line 9571 of file xlog.c.

{
    bool        during_backup_start = DatumGetBool(arg);
 
    /* If called during backup start, there shouldn't be one already running */
    Assert(!during_backup_start || sessionBackupState == SESSION_BACKUP_NONE);
 
    if (during_backup_start || sessionBackupState != SESSION_BACKUP_NONE)
    {
        WALInsertLockAcquireExclusive();
        Assert(XLogCtl->Insert.runningBackups > 0);
        XLogCtl->Insert.runningBackups--;
 
        sessionBackupState = SESSION_BACKUP_NONE;
        WALInsertLockRelease();
 
        if (!during_backup_start)
            ereport(WARNING,
                    errmsg("aborting backup due to backend exiting before pg_backup_stop was called"));
    }
}

References arg, Assert(), DatumGetBool(), ereport, errmsg(), XLogCtlData::Insert, XLogCtlInsert::runningBackups, SESSION_BACKUP_NONE, sessionBackupState, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), WARNING, and XLogCtl.

Referenced by do_pg_backup_start(), perform_base_backup(), and register_persistent_abort_backup_handler().

◆ do_pg_backup_start()

void do_pg_backup_start	(	const char *	backupidstr,
		bool	fast,
		List **	tablespaces,
		BackupState *	state,
		StringInfo	tblspcmapfile
	)

Definition at line 8969 of file xlog.c.

{
    bool        backup_started_in_recovery;
 
    Assert(state != NULL);
    backup_started_in_recovery = RecoveryInProgress();
 
    /*
     * During recovery, we don't need to check WAL level. Because, if WAL
     * level is not sufficient, it's impossible to get here during recovery.
     */
    if (!backup_started_in_recovery && !XLogIsNeeded())
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("WAL level not sufficient for making an online backup"),
                 errhint("\"wal_level\" must be set to \"replica\" or \"logical\" at server start.")));
 
    if (strlen(backupidstr) > MAXPGPATH)
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                 errmsg("backup label too long (max %d bytes)",
                        MAXPGPATH)));
 
    strlcpy(state->name, backupidstr, sizeof(state->name));
 
    /*
     * Mark backup active in shared memory.  We must do full-page WAL writes
     * during an on-line backup even if not doing so at other times, because
     * it's quite possible for the backup dump to obtain a "torn" (partially
     * written) copy of a database page if it reads the page concurrently with
     * our write to the same page.  This can be fixed as long as the first
     * write to the page in the WAL sequence is a full-page write. Hence, we
     * increment runningBackups then force a CHECKPOINT, to ensure there are
     * no dirty pages in shared memory that might get dumped while the backup
     * is in progress without having a corresponding WAL record.  (Once the
     * backup is complete, we need not force full-page writes anymore, since
     * we expect that any pages not modified during the backup interval must
     * have been correctly captured by the backup.)
     *
     * Note that forcing full-page writes has no effect during an online
     * backup from the standby.
     *
     * We must hold all the insertion locks to change the value of
     * runningBackups, to ensure adequate interlocking against
     * XLogInsertRecord().
     */
    WALInsertLockAcquireExclusive();
    XLogCtl->Insert.runningBackups++;
    WALInsertLockRelease();
 
    /*
     * Ensure we decrement runningBackups if we fail below. NB -- for this to
     * work correctly, it is critical that sessionBackupState is only updated
     * after this block is over.
     */
    PG_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, DatumGetBool(true));
    {
        bool        gotUniqueStartpoint = false;
        DIR        *tblspcdir;
        struct dirent *de;
        tablespaceinfo *ti;
        int         datadirpathlen;
 
        /*
         * Force an XLOG file switch before the checkpoint, to ensure that the
         * WAL segment the checkpoint is written to doesn't contain pages with
         * old timeline IDs.  That would otherwise happen if you called
         * pg_backup_start() right after restoring from a PITR archive: the
         * first WAL segment containing the startup checkpoint has pages in
         * the beginning with the old timeline ID.  That can cause trouble at
         * recovery: we won't have a history file covering the old timeline if
         * pg_wal directory was not included in the base backup and the WAL
         * archive was cleared too before starting the backup.
         *
         * This also ensures that we have emitted a WAL page header that has
         * XLP_BKP_REMOVABLE off before we emit the checkpoint record.
         * Therefore, if a WAL archiver (such as pglesslog) is trying to
         * compress out removable backup blocks, it won't remove any that
         * occur after this point.
         *
         * During recovery, we skip forcing XLOG file switch, which means that
         * the backup taken during recovery is not available for the special
         * recovery case described above.
         */
        if (!backup_started_in_recovery)
            RequestXLogSwitch(false);
 
        do
        {
            bool        checkpointfpw;
 
            /*
             * Force a CHECKPOINT.  Aside from being necessary to prevent torn
             * page problems, this guarantees that two successive backup runs
             * will have different checkpoint positions and hence different
             * history file names, even if nothing happened in between.
             *
             * During recovery, establish a restartpoint if possible. We use
             * the last restartpoint as the backup starting checkpoint. This
             * means that two successive backup runs can have same checkpoint
             * positions.
             *
             * Since the fact that we are executing do_pg_backup_start()
             * during recovery means that checkpointer is running, we can use
             * RequestCheckpoint() to establish a restartpoint.
             *
             * We use CHECKPOINT_IMMEDIATE only if requested by user (via
             * passing fast = true).  Otherwise this can take awhile.
             */
            RequestCheckpoint(CHECKPOINT_FORCE | CHECKPOINT_WAIT |
                              (fast ? CHECKPOINT_IMMEDIATE : 0));
 
            /*
             * Now we need to fetch the checkpoint record location, and also
             * its REDO pointer.  The oldest point in WAL that would be needed
             * to restore starting from the checkpoint is precisely the REDO
             * pointer.
             */
            LWLockAcquire(ControlFileLock, LW_SHARED);
            state->checkpointloc = ControlFile->checkPoint;
            state->startpoint = ControlFile->checkPointCopy.redo;
            state->starttli = ControlFile->checkPointCopy.ThisTimeLineID;
            checkpointfpw = ControlFile->checkPointCopy.fullPageWrites;
            LWLockRelease(ControlFileLock);
 
            if (backup_started_in_recovery)
            {
                XLogRecPtr  recptr;
 
                /*
                 * Check to see if all WAL replayed during online backup
                 * (i.e., since last restartpoint used as backup starting
                 * checkpoint) contain full-page writes.
                 */
                SpinLockAcquire(&XLogCtl->info_lck);
                recptr = XLogCtl->lastFpwDisableRecPtr;
                SpinLockRelease(&XLogCtl->info_lck);
 
                if (!checkpointfpw || state->startpoint <= recptr)
                    ereport(ERROR,
                            (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                             errmsg("WAL generated with \"full_page_writes=off\" was replayed "
                                    "since last restartpoint"),
                             errhint("This means that the backup being taken on the standby "
                                     "is corrupt and should not be used. "
                                     "Enable \"full_page_writes\" and run CHECKPOINT on the primary, "
                                     "and then try an online backup again.")));
 
                /*
                 * During recovery, since we don't use the end-of-backup WAL
                 * record and don't write the backup history file, the
                 * starting WAL location doesn't need to be unique. This means
                 * that two base backups started at the same time might use
                 * the same checkpoint as starting locations.
                 */
                gotUniqueStartpoint = true;
            }
 
            /*
             * If two base backups are started at the same time (in WAL sender
             * processes), we need to make sure that they use different
             * checkpoints as starting locations, because we use the starting
             * WAL location as a unique identifier for the base backup in the
             * end-of-backup WAL record and when we write the backup history
             * file. Perhaps it would be better generate a separate unique ID
             * for each backup instead of forcing another checkpoint, but
             * taking a checkpoint right after another is not that expensive
             * either because only few buffers have been dirtied yet.
             */
            WALInsertLockAcquireExclusive();
            if (XLogCtl->Insert.lastBackupStart < state->startpoint)
            {
                XLogCtl->Insert.lastBackupStart = state->startpoint;
                gotUniqueStartpoint = true;
            }
            WALInsertLockRelease();
        } while (!gotUniqueStartpoint);
 
        /*
         * Construct tablespace_map file.
         */
        datadirpathlen = strlen(DataDir);
 
        /* Collect information about all tablespaces */
        tblspcdir = AllocateDir(PG_TBLSPC_DIR);
        while ((de = ReadDir(tblspcdir, PG_TBLSPC_DIR)) != NULL)
        {
            char        fullpath[MAXPGPATH + sizeof(PG_TBLSPC_DIR)];
            char        linkpath[MAXPGPATH];
            char       *relpath = NULL;
            char       *s;
            PGFileType  de_type;
            char       *badp;
            Oid         tsoid;
 
            /*
             * Try to parse the directory name as an unsigned integer.
             *
             * Tablespace directories should be positive integers that can be
             * represented in 32 bits, with no leading zeroes or trailing
             * garbage. If we come across a name that doesn't meet those
             * criteria, skip it.
             */
            if (de->d_name[0] < '1' || de->d_name[1] > '9')
                continue;
            errno = 0;
            tsoid = strtoul(de->d_name, &badp, 10);
            if (*badp != '\0' || errno == EINVAL || errno == ERANGE)
                continue;
 
            snprintf(fullpath, sizeof(fullpath), "%s/%s", PG_TBLSPC_DIR, de->d_name);
 
            de_type = get_dirent_type(fullpath, de, false, ERROR);
 
            if (de_type == PGFILETYPE_LNK)
            {
                StringInfoData escapedpath;
                int         rllen;
 
                rllen = readlink(fullpath, linkpath, sizeof(linkpath));
                if (rllen < 0)
                {
                    ereport(WARNING,
                            (errmsg("could not read symbolic link \"%s\": %m",
                                    fullpath)));
                    continue;
                }
                else if (rllen >= sizeof(linkpath))
                {
                    ereport(WARNING,
                            (errmsg("symbolic link \"%s\" target is too long",
                                    fullpath)));
                    continue;
                }
                linkpath[rllen] = '\0';
 
                /*
                 * Relpath holds the relative path of the tablespace directory
                 * when it's located within PGDATA, or NULL if it's located
                 * elsewhere.
                 */
                if (rllen > datadirpathlen &&
                    strncmp(linkpath, DataDir, datadirpathlen) == 0 &&
                    IS_DIR_SEP(linkpath[datadirpathlen]))
                    relpath = pstrdup(linkpath + datadirpathlen + 1);
 
                /*
                 * Add a backslash-escaped version of the link path to the
                 * tablespace map file.
                 */
                initStringInfo(&escapedpath);
                for (s = linkpath; *s; s++)
                {
                    if (*s == '\n' || *s == '\r' || *s == '\\')
                        appendStringInfoChar(&escapedpath, '\\');
                    appendStringInfoChar(&escapedpath, *s);
                }
                appendStringInfo(tblspcmapfile, "%s %s\n",
                                 de->d_name, escapedpath.data);
                pfree(escapedpath.data);
            }
            else if (de_type == PGFILETYPE_DIR)
            {
                /*
                 * It's possible to use allow_in_place_tablespaces to create
                 * directories directly under pg_tblspc, for testing purposes
                 * only.
                 *
                 * In this case, we store a relative path rather than an
                 * absolute path into the tablespaceinfo.
                 */
                snprintf(linkpath, sizeof(linkpath), "%s/%s",
                         PG_TBLSPC_DIR, de->d_name);
                relpath = pstrdup(linkpath);
            }
            else
            {
                /* Skip any other file type that appears here. */
                continue;
            }
 
            ti = palloc(sizeof(tablespaceinfo));
            ti->oid = tsoid;
            ti->path = pstrdup(linkpath);
            ti->rpath = relpath;
            ti->size = -1;
 
            if (tablespaces)
                *tablespaces = lappend(*tablespaces, ti);
        }
        FreeDir(tblspcdir);
 
        state->starttime = (pg_time_t) time(NULL);
    }
    PG_END_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, DatumGetBool(true));
 
    state->started_in_recovery = backup_started_in_recovery;
 
    /*
     * Mark that the start phase has correctly finished for the backup.
     */
    sessionBackupState = SESSION_BACKUP_RUNNING;
}

References AllocateDir(), appendStringInfo(), appendStringInfoChar(), Assert(), backup_started_in_recovery, ControlFileData::checkPoint, CHECKPOINT_FORCE, CHECKPOINT_IMMEDIATE, CHECKPOINT_WAIT, ControlFileData::checkPointCopy, ControlFile, dirent::d_name, StringInfoData::data, DataDir, DatumGetBool(), do_pg_abort_backup(), ereport, errcode(), errhint(), errmsg(), ERROR, FreeDir(), CheckPoint::fullPageWrites, get_dirent_type(), XLogCtlData::info_lck, initStringInfo(), XLogCtlData::Insert, IS_DIR_SEP, lappend(), XLogCtlInsert::lastBackupStart, XLogCtlData::lastFpwDisableRecPtr, LW_SHARED, LWLockAcquire(), LWLockRelease(), MAXPGPATH, tablespaceinfo::oid, palloc(), tablespaceinfo::path, pfree(), PG_END_ENSURE_ERROR_CLEANUP, PG_ENSURE_ERROR_CLEANUP, PG_TBLSPC_DIR, PGFILETYPE_DIR, PGFILETYPE_LNK, pstrdup(), ReadDir(), readlink, RecoveryInProgress(), CheckPoint::redo, relpath, RequestCheckpoint(), RequestXLogSwitch(), tablespaceinfo::rpath, XLogCtlInsert::runningBackups, SESSION_BACKUP_RUNNING, sessionBackupState, tablespaceinfo::size, snprintf, SpinLockAcquire, SpinLockRelease, strlcpy(), CheckPoint::ThisTimeLineID, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), WARNING, XLogCtl, and XLogIsNeeded.

Referenced by perform_base_backup(), and pg_backup_start().

◆ do_pg_backup_stop()

void do_pg_backup_stop	(	BackupState *	state,
		bool	waitforarchive
	)

Definition at line 9297 of file xlog.c.

{
    bool        backup_stopped_in_recovery = false;
    char        histfilepath[MAXPGPATH];
    char        lastxlogfilename[MAXFNAMELEN];
    char        histfilename[MAXFNAMELEN];
    XLogSegNo   _logSegNo;
    FILE       *fp;
    int         seconds_before_warning;
    int         waits = 0;
    bool        reported_waiting = false;
 
    Assert(state != NULL);
 
    backup_stopped_in_recovery = RecoveryInProgress();
 
    /*
     * During recovery, we don't need to check WAL level. Because, if WAL
     * level is not sufficient, it's impossible to get here during recovery.
     */
    if (!backup_stopped_in_recovery && !XLogIsNeeded())
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("WAL level not sufficient for making an online backup"),
                 errhint("\"wal_level\" must be set to \"replica\" or \"logical\" at server start.")));
 
    /*
     * OK to update backup counter and session-level lock.
     *
     * Note that CHECK_FOR_INTERRUPTS() must not occur while updating them,
     * otherwise they can be updated inconsistently, which might cause
     * do_pg_abort_backup() to fail.
     */
    WALInsertLockAcquireExclusive();
 
    /*
     * It is expected that each do_pg_backup_start() call is matched by
     * exactly one do_pg_backup_stop() call.
     */
    Assert(XLogCtl->Insert.runningBackups > 0);
    XLogCtl->Insert.runningBackups--;
 
    /*
     * Clean up session-level lock.
     *
     * You might think that WALInsertLockRelease() can be called before
     * cleaning up session-level lock because session-level lock doesn't need
     * to be protected with WAL insertion lock. But since
     * CHECK_FOR_INTERRUPTS() can occur in it, session-level lock must be
     * cleaned up before it.
     */
    sessionBackupState = SESSION_BACKUP_NONE;
 
    WALInsertLockRelease();
 
    /*
     * If we are taking an online backup from the standby, we confirm that the
     * standby has not been promoted during the backup.
     */
    if (state->started_in_recovery && !backup_stopped_in_recovery)
        ereport(ERROR,
                (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                 errmsg("the standby was promoted during online backup"),
                 errhint("This means that the backup being taken is corrupt "
                         "and should not be used. "
                         "Try taking another online backup.")));
 
    /*
     * During recovery, we don't write an end-of-backup record. We assume that
     * pg_control was backed up last and its minimum recovery point can be
     * available as the backup end location. Since we don't have an
     * end-of-backup record, we use the pg_control value to check whether
     * we've reached the end of backup when starting recovery from this
     * backup. We have no way of checking if pg_control wasn't backed up last
     * however.
     *
     * We don't force a switch to new WAL file but it is still possible to
     * wait for all the required files to be archived if waitforarchive is
     * true. This is okay if we use the backup to start a standby and fetch
     * the missing WAL using streaming replication. But in the case of an
     * archive recovery, a user should set waitforarchive to true and wait for
     * them to be archived to ensure that all the required files are
     * available.
     *
     * We return the current minimum recovery point as the backup end
     * location. Note that it can be greater than the exact backup end
     * location if the minimum recovery point is updated after the backup of
     * pg_control. This is harmless for current uses.
     *
     * XXX currently a backup history file is for informational and debug
     * purposes only. It's not essential for an online backup. Furthermore,
     * even if it's created, it will not be archived during recovery because
     * an archiver is not invoked. So it doesn't seem worthwhile to write a
     * backup history file during recovery.
     */
    if (backup_stopped_in_recovery)
    {
        XLogRecPtr  recptr;
 
        /*
         * Check to see if all WAL replayed during online backup contain
         * full-page writes.
         */
        SpinLockAcquire(&XLogCtl->info_lck);
        recptr = XLogCtl->lastFpwDisableRecPtr;
        SpinLockRelease(&XLogCtl->info_lck);
 
        if (state->startpoint <= recptr)
            ereport(ERROR,
                    (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                     errmsg("WAL generated with \"full_page_writes=off\" was replayed "
                            "during online backup"),
                     errhint("This means that the backup being taken on the standby "
                             "is corrupt and should not be used. "
                             "Enable \"full_page_writes\" and run CHECKPOINT on the primary, "
                             "and then try an online backup again.")));
 
 
        LWLockAcquire(ControlFileLock, LW_SHARED);
        state->stoppoint = ControlFile->minRecoveryPoint;
        state->stoptli = ControlFile->minRecoveryPointTLI;
        LWLockRelease(ControlFileLock);
    }
    else
    {
        char       *history_file;
 
        /*
         * Write the backup-end xlog record
         */
        XLogBeginInsert();
        XLogRegisterData(&state->startpoint,
                         sizeof(state->startpoint));
        state->stoppoint = XLogInsert(RM_XLOG_ID, XLOG_BACKUP_END);
 
        /*
         * Given that we're not in recovery, InsertTimeLineID is set and can't
         * change, so we can read it without a lock.
         */
        state->stoptli = XLogCtl->InsertTimeLineID;
 
        /*
         * Force a switch to a new xlog segment file, so that the backup is
         * valid as soon as archiver moves out the current segment file.
         */
        RequestXLogSwitch(false);
 
        state->stoptime = (pg_time_t) time(NULL);
 
        /*
         * Write the backup history file
         */
        XLByteToSeg(state->startpoint, _logSegNo, wal_segment_size);
        BackupHistoryFilePath(histfilepath, state->stoptli, _logSegNo,
                              state->startpoint, wal_segment_size);
        fp = AllocateFile(histfilepath, "w");
        if (!fp)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not create file \"%s\": %m",
                            histfilepath)));
 
        /* Build and save the contents of the backup history file */
        history_file = build_backup_content(state, true);
        fprintf(fp, "%s", history_file);
        pfree(history_file);
 
        if (fflush(fp) || ferror(fp) || FreeFile(fp))
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not write file \"%s\": %m",
                            histfilepath)));
 
        /*
         * Clean out any no-longer-needed history files.  As a side effect,
         * this will post a .ready file for the newly created history file,
         * notifying the archiver that history file may be archived
         * immediately.
         */
        CleanupBackupHistory();
    }
 
    /*
     * If archiving is enabled, wait for all the required WAL files to be
     * archived before returning. If archiving isn't enabled, the required WAL
     * needs to be transported via streaming replication (hopefully with
     * wal_keep_size set high enough), or some more exotic mechanism like
     * polling and copying files from pg_wal with script. We have no knowledge
     * of those mechanisms, so it's up to the user to ensure that he gets all
     * the required WAL.
     *
     * We wait until both the last WAL file filled during backup and the
     * history file have been archived, and assume that the alphabetic sorting
     * property of the WAL files ensures any earlier WAL files are safely
     * archived as well.
     *
     * We wait forever, since archive_command is supposed to work and we
     * assume the admin wanted his backup to work completely. If you don't
     * wish to wait, then either waitforarchive should be passed in as false,
     * or you can set statement_timeout.  Also, some notices are issued to
     * clue in anyone who might be doing this interactively.
     */
 
    if (waitforarchive &&
        ((!backup_stopped_in_recovery && XLogArchivingActive()) ||
         (backup_stopped_in_recovery && XLogArchivingAlways())))
    {
        XLByteToPrevSeg(state->stoppoint, _logSegNo, wal_segment_size);
        XLogFileName(lastxlogfilename, state->stoptli, _logSegNo,
                     wal_segment_size);
 
        XLByteToSeg(state->startpoint, _logSegNo, wal_segment_size);
        BackupHistoryFileName(histfilename, state->stoptli, _logSegNo,
                              state->startpoint, wal_segment_size);
 
        seconds_before_warning = 60;
        waits = 0;
 
        while (XLogArchiveIsBusy(lastxlogfilename) ||
               XLogArchiveIsBusy(histfilename))
        {
            CHECK_FOR_INTERRUPTS();
 
            if (!reported_waiting && waits > 5)
            {
                ereport(NOTICE,
                        (errmsg("base backup done, waiting for required WAL segments to be archived")));
                reported_waiting = true;
            }
 
            (void) WaitLatch(MyLatch,
                             WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
                             1000L,
                             WAIT_EVENT_BACKUP_WAIT_WAL_ARCHIVE);
            ResetLatch(MyLatch);
 
            if (++waits >= seconds_before_warning)
            {
                seconds_before_warning *= 2;    /* This wraps in >10 years... */
                ereport(WARNING,
                        (errmsg("still waiting for all required WAL segments to be archived (%d seconds elapsed)",
                                waits),
                         errhint("Check that your \"archive_command\" is executing properly.  "
                                 "You can safely cancel this backup, "
                                 "but the database backup will not be usable without all the WAL segments.")));
            }
        }
 
        ereport(NOTICE,
                (errmsg("all required WAL segments have been archived")));
    }
    else if (waitforarchive)
        ereport(NOTICE,
                (errmsg("WAL archiving is not enabled; you must ensure that all required WAL segments are copied through other means to complete the backup")));
}

References AllocateFile(), Assert(), BackupHistoryFileName(), BackupHistoryFilePath(), build_backup_content(), CHECK_FOR_INTERRUPTS, CleanupBackupHistory(), ControlFile, ereport, errcode(), errcode_for_file_access(), errhint(), errmsg(), ERROR, fprintf, FreeFile(), XLogCtlData::info_lck, XLogCtlData::Insert, XLogCtlData::InsertTimeLineID, XLogCtlData::lastFpwDisableRecPtr, LW_SHARED, LWLockAcquire(), LWLockRelease(), MAXFNAMELEN, MAXPGPATH, ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, MyLatch, NOTICE, pfree(), RecoveryInProgress(), RequestXLogSwitch(), ResetLatch(), XLogCtlInsert::runningBackups, SESSION_BACKUP_NONE, sessionBackupState, SpinLockAcquire, SpinLockRelease, WaitLatch(), wal_segment_size, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), WARNING, WL_EXIT_ON_PM_DEATH, WL_LATCH_SET, WL_TIMEOUT, XLByteToPrevSeg, XLByteToSeg, XLOG_BACKUP_END, XLogArchiveIsBusy(), XLogArchivingActive, XLogArchivingAlways, XLogBeginInsert(), XLogCtl, XLogFileName(), XLogInsert(), XLogIsNeeded, and XLogRegisterData().

Referenced by perform_base_backup(), and pg_backup_stop().

◆ get_backup_status()

SessionBackupState get_backup_status ( void )

Definition at line 9278 of file xlog.c.

{
    return sessionBackupState;
}

References sessionBackupState.

Referenced by pg_backup_start(), pg_backup_stop(), and SendBaseBackup().

◆ GetActiveWalLevelOnStandby()

WalLevel GetActiveWalLevelOnStandby ( void )

Definition at line 5040 of file xlog.c.

{
    return ControlFile->wal_level;
}

References ControlFile, and ControlFileData::wal_level.

Referenced by CheckLogicalDecodingRequirements().

◆ GetDefaultCharSignedness()

bool GetDefaultCharSignedness ( void )

Definition at line 4768 of file xlog.c.

{
    return ControlFile->default_char_signedness;
}

References ControlFile, and ControlFileData::default_char_signedness.

Referenced by CMPTRGM_CHOOSE().

◆ GetFakeLSNForUnloggedRel()

XLogRecPtr GetFakeLSNForUnloggedRel ( void )

Definition at line 4783 of file xlog.c.

{
    return pg_atomic_fetch_add_u64(&XLogCtl->unloggedLSN, 1);
}

References pg_atomic_fetch_add_u64(), XLogCtlData::unloggedLSN, and XLogCtl.

Referenced by gistGetFakeLSN().

◆ GetFlushRecPtr()

XLogRecPtr GetFlushRecPtr ( TimeLineID * insertTLI )

Definition at line 6687 of file xlog.c.

{
    Assert(XLogCtl->SharedRecoveryState == RECOVERY_STATE_DONE);
 
    RefreshXLogWriteResult(LogwrtResult);
 
    /*
     * If we're writing and flushing WAL, the time line can't be changing, so
     * no lock is required.
     */
    if (insertTLI)
        *insertTLI = XLogCtl->InsertTimeLineID;
 
    return LogwrtResult.Flush;
}

References Assert(), XLogwrtResult::Flush, XLogCtlData::InsertTimeLineID, LogwrtResult, RECOVERY_STATE_DONE, RefreshXLogWriteResult, XLogCtlData::SharedRecoveryState, and XLogCtl.

Referenced by binary_upgrade_logical_slot_has_caught_up(), get_flush_position(), GetCurrentLSN(), GetLatestLSN(), IdentifySystem(), pg_current_wal_flush_lsn(), pg_logical_slot_get_changes_guts(), pg_replication_slot_advance(), read_local_xlog_page_guts(), StartReplication(), WalSndWaitForWal(), XLogSendLogical(), and XLogSendPhysical().

◆ GetFullPageWriteInfo()

void GetFullPageWriteInfo	(	XLogRecPtr *	RedoRecPtr_p,
		bool *	doPageWrites_p
	)

Definition at line 6655 of file xlog.c.

{
    *RedoRecPtr_p = RedoRecPtr;
    *doPageWrites_p = doPageWrites;
}

References doPageWrites, and RedoRecPtr.

Referenced by XLogCheckBufferNeedsBackup(), and XLogInsert().

◆ GetInsertRecPtr()

XLogRecPtr GetInsertRecPtr ( void )

Definition at line 6670 of file xlog.c.

{
    XLogRecPtr  recptr;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    recptr = XLogCtl->LogwrtRqst.Write;
    SpinLockRelease(&XLogCtl->info_lck);
 
    return recptr;
}

References XLogCtlData::info_lck, XLogCtlData::LogwrtRqst, SpinLockAcquire, SpinLockRelease, XLogwrtRqst::Write, and XLogCtl.

Referenced by CheckpointerMain(), gistvacuumscan(), IsCheckpointOnSchedule(), and LogStandbySnapshot().

◆ GetLastImportantRecPtr()

XLogRecPtr GetLastImportantRecPtr ( void )

Definition at line 6744 of file xlog.c.

{
    XLogRecPtr  res = InvalidXLogRecPtr;
    int         i;
 
    for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
    {
        XLogRecPtr  last_important;
 
        /*
         * Need to take a lock to prevent torn reads of the LSN, which are
         * possible on some of the supported platforms. WAL insert locks only
         * support exclusive mode, so we have to use that.
         */
        LWLockAcquire(&WALInsertLocks[i].l.lock, LW_EXCLUSIVE);
        last_important = WALInsertLocks[i].l.lastImportantAt;
        LWLockRelease(&WALInsertLocks[i].l.lock);
 
        if (res < last_important)
            res = last_important;
    }
 
    return res;
}

References i, InvalidXLogRecPtr, WALInsertLockPadded::l, WALInsertLock::lastImportantAt, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), NUM_XLOGINSERT_LOCKS, and WALInsertLocks.

Referenced by BackgroundWriterMain(), CheckArchiveTimeout(), and CreateCheckPoint().

◆ GetMockAuthenticationNonce()

char * GetMockAuthenticationNonce ( void )

Definition at line 4744 of file xlog.c.

{
    Assert(ControlFile != NULL);
    return ControlFile->mock_authentication_nonce;
}

References Assert(), ControlFile, and ControlFileData::mock_authentication_nonce.

Referenced by scram_mock_salt().

◆ GetRecoveryState()

RecoveryState GetRecoveryState ( void )

Definition at line 6558 of file xlog.c.

{
    RecoveryState retval;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    retval = XLogCtl->SharedRecoveryState;
    SpinLockRelease(&XLogCtl->info_lck);
 
    return retval;
}

References XLogCtlData::info_lck, XLogCtlData::SharedRecoveryState, SpinLockAcquire, SpinLockRelease, and XLogCtl.

Referenced by XLogArchiveCheckDone().

◆ GetRedoRecPtr()

XLogRecPtr GetRedoRecPtr ( void )

Definition at line 6625 of file xlog.c.

{
    XLogRecPtr  ptr;
 
    /*
     * The possibly not up-to-date copy in XlogCtl is enough. Even if we
     * grabbed a WAL insertion lock to read the authoritative value in
     * Insert->RedoRecPtr, someone might update it just after we've released
     * the lock.
     */
    SpinLockAcquire(&XLogCtl->info_lck);
    ptr = XLogCtl->RedoRecPtr;
    SpinLockRelease(&XLogCtl->info_lck);
 
    if (RedoRecPtr < ptr)
        RedoRecPtr = ptr;
 
    return RedoRecPtr;
}

References XLogCtlData::info_lck, RedoRecPtr, XLogCtlData::RedoRecPtr, SpinLockAcquire, SpinLockRelease, and XLogCtl.

Referenced by CheckPointLogicalRewriteHeap(), CheckPointSnapBuild(), MaybeRemoveOldWalSummaries(), nextval_internal(), ReplicationSlotReserveWal(), smgr_bulk_finish(), smgr_bulk_start_smgr(), XLogPageRead(), XLogSaveBufferForHint(), and XLogWrite().

◆ GetSystemIdentifier()

uint64 GetSystemIdentifier ( void )

Definition at line 4734 of file xlog.c.

{
    Assert(ControlFile != NULL);
    return ControlFile->system_identifier;
}

References Assert(), ControlFile, and ControlFileData::system_identifier.

Referenced by IdentifySystem(), InitializeBackupManifest(), manifest_process_system_identifier(), ReplicationSlotNameForTablesync(), and WalReceiverMain().

◆ GetWALAvailability()

WALAvailability GetWALAvailability ( XLogRecPtr targetLSN )

Definition at line 8057 of file xlog.c.

{
    XLogRecPtr  currpos;        /* current write LSN */
    XLogSegNo   currSeg;        /* segid of currpos */
    XLogSegNo   targetSeg;      /* segid of targetLSN */
    XLogSegNo   oldestSeg;      /* actual oldest segid */
    XLogSegNo   oldestSegMaxWalSize;    /* oldest segid kept by max_wal_size */
    XLogSegNo   oldestSlotSeg;  /* oldest segid kept by slot */
    uint64      keepSegs;
 
    /*
     * slot does not reserve WAL. Either deactivated, or has never been active
     */
    if (XLogRecPtrIsInvalid(targetLSN))
        return WALAVAIL_INVALID_LSN;
 
    /*
     * Calculate the oldest segment currently reserved by all slots,
     * considering wal_keep_size and max_slot_wal_keep_size.  Initialize
     * oldestSlotSeg to the current segment.
     */
    currpos = GetXLogWriteRecPtr();
    XLByteToSeg(currpos, oldestSlotSeg, wal_segment_size);
    KeepLogSeg(currpos, &oldestSlotSeg);
 
    /*
     * Find the oldest extant segment file. We get 1 until checkpoint removes
     * the first WAL segment file since startup, which causes the status being
     * wrong under certain abnormal conditions but that doesn't actually harm.
     */
    oldestSeg = XLogGetLastRemovedSegno() + 1;
 
    /* calculate oldest segment by max_wal_size */
    XLByteToSeg(currpos, currSeg, wal_segment_size);
    keepSegs = ConvertToXSegs(max_wal_size_mb, wal_segment_size) + 1;
 
    if (currSeg > keepSegs)
        oldestSegMaxWalSize = currSeg - keepSegs;
    else
        oldestSegMaxWalSize = 1;
 
    /* the segment we care about */
    XLByteToSeg(targetLSN, targetSeg, wal_segment_size);
 
    /*
     * No point in returning reserved or extended status values if the
     * targetSeg is known to be lost.
     */
    if (targetSeg >= oldestSlotSeg)
    {
        /* show "reserved" when targetSeg is within max_wal_size */
        if (targetSeg >= oldestSegMaxWalSize)
            return WALAVAIL_RESERVED;
 
        /* being retained by slots exceeding max_wal_size */
        return WALAVAIL_EXTENDED;
    }
 
    /* WAL segments are no longer retained but haven't been removed yet */
    if (targetSeg >= oldestSeg)
        return WALAVAIL_UNRESERVED;
 
    /* Definitely lost */
    return WALAVAIL_REMOVED;
}

References ConvertToXSegs, GetXLogWriteRecPtr(), KeepLogSeg(), max_wal_size_mb, wal_segment_size, WALAVAIL_EXTENDED, WALAVAIL_INVALID_LSN, WALAVAIL_REMOVED, WALAVAIL_RESERVED, WALAVAIL_UNRESERVED, XLByteToSeg, XLogGetLastRemovedSegno(), and XLogRecPtrIsInvalid.

Referenced by pg_get_replication_slots().

◆ GetWALInsertionTimeLine()

TimeLineID GetWALInsertionTimeLine ( void )

Definition at line 6708 of file xlog.c.

{
    Assert(XLogCtl->SharedRecoveryState == RECOVERY_STATE_DONE);
 
    /* Since the value can't be changing, no lock is required. */
    return XLogCtl->InsertTimeLineID;
}

References Assert(), XLogCtlData::InsertTimeLineID, RECOVERY_STATE_DONE, XLogCtlData::SharedRecoveryState, and XLogCtl.

Referenced by logical_read_xlog_page(), pg_walfile_name(), pg_walfile_name_offset(), ReadReplicationSlot(), WALReadFromBuffers(), and XLogSendPhysical().

◆ GetWALInsertionTimeLineIfSet()

TimeLineID GetWALInsertionTimeLineIfSet ( void )

Definition at line 6724 of file xlog.c.

{
    TimeLineID  insertTLI;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    insertTLI = XLogCtl->InsertTimeLineID;
    SpinLockRelease(&XLogCtl->info_lck);
 
    return insertTLI;
}

References XLogCtlData::info_lck, XLogCtlData::InsertTimeLineID, SpinLockAcquire, SpinLockRelease, and XLogCtl.

Referenced by GetLatestLSN().

◆ GetXLogInsertRecPtr()

XLogRecPtr GetXLogInsertRecPtr ( void )

Definition at line 9612 of file xlog.c.

{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    uint64      current_bytepos;
 
    SpinLockAcquire(&Insert->insertpos_lck);
    current_bytepos = Insert->CurrBytePos;
    SpinLockRelease(&Insert->insertpos_lck);
 
    return XLogBytePosToRecPtr(current_bytepos);
}

References XLogCtlData::Insert, Insert(), SpinLockAcquire, SpinLockRelease, XLogBytePosToRecPtr(), and XLogCtl.

Referenced by CreateOverwriteContrecordRecord(), gistGetFakeLSN(), logical_begin_heap_rewrite(), pg_current_wal_insert_lsn(), and ReplicationSlotReserveWal().

◆ GetXLogWriteRecPtr()

XLogRecPtr GetXLogWriteRecPtr ( void )

Definition at line 9628 of file xlog.c.

{
    RefreshXLogWriteResult(LogwrtResult);
 
    return LogwrtResult.Write;
}

References LogwrtResult, RefreshXLogWriteResult, and XLogwrtResult::Write.

Referenced by finish_sync_worker(), GetWALAvailability(), pg_current_wal_lsn(), and pg_get_replication_slots().

◆ InitializeWalConsistencyChecking()

void InitializeWalConsistencyChecking ( void )

Definition at line 4965 of file xlog.c.

{
    Assert(process_shared_preload_libraries_done);
 
    if (check_wal_consistency_checking_deferred)
    {
        struct config_generic *guc;
 
        guc = find_option("wal_consistency_checking", false, false, ERROR);
 
        check_wal_consistency_checking_deferred = false;
 
        set_config_option_ext("wal_consistency_checking",
                              wal_consistency_checking_string,
                              guc->scontext, guc->source, guc->srole,
                              GUC_ACTION_SET, true, ERROR, false);
 
        /* checking should not be deferred again */
        Assert(!check_wal_consistency_checking_deferred);
    }
}

References Assert(), check_wal_consistency_checking_deferred, ERROR, find_option(), GUC_ACTION_SET, process_shared_preload_libraries_done, config_generic::scontext, set_config_option_ext(), config_generic::source, config_generic::srole, and wal_consistency_checking_string.

Referenced by PostgresSingleUserMain(), and PostmasterMain().

◆ IsInstallXLogFileSegmentActive()

bool IsInstallXLogFileSegmentActive ( void )

Definition at line 9669 of file xlog.c.

{
    bool        result;
 
    LWLockAcquire(ControlFileLock, LW_SHARED);
    result = XLogCtl->InstallXLogFileSegmentActive;
    LWLockRelease(ControlFileLock);
 
    return result;
}

References XLogCtlData::InstallXLogFileSegmentActive, LW_SHARED, LWLockAcquire(), LWLockRelease(), and XLogCtl.

Referenced by XLogFileRead().

◆ issue_xlog_fsync()

void issue_xlog_fsync	(	int	fd,
		XLogSegNo	segno,
		TimeLineID	tli
	)

Definition at line 8871 of file xlog.c.

{
    char       *msg = NULL;
    instr_time  start;
 
    Assert(tli != 0);
 
    /*
     * Quick exit if fsync is disabled or write() has already synced the WAL
     * file.
     */
    if (!enableFsync ||
        wal_sync_method == WAL_SYNC_METHOD_OPEN ||
        wal_sync_method == WAL_SYNC_METHOD_OPEN_DSYNC)
        return;
 
    /*
     * Measure I/O timing to sync the WAL file for pg_stat_io.
     */
    start = pgstat_prepare_io_time(track_wal_io_timing);
 
    pgstat_report_wait_start(WAIT_EVENT_WAL_SYNC);
    switch (wal_sync_method)
    {
        case WAL_SYNC_METHOD_FSYNC:
            if (pg_fsync_no_writethrough(fd) != 0)
                msg = _("could not fsync file \"%s\": %m");
            break;
#ifdef HAVE_FSYNC_WRITETHROUGH
        case WAL_SYNC_METHOD_FSYNC_WRITETHROUGH:
            if (pg_fsync_writethrough(fd) != 0)
                msg = _("could not fsync write-through file \"%s\": %m");
            break;
#endif
        case WAL_SYNC_METHOD_FDATASYNC:
            if (pg_fdatasync(fd) != 0)
                msg = _("could not fdatasync file \"%s\": %m");
            break;
        case WAL_SYNC_METHOD_OPEN:
        case WAL_SYNC_METHOD_OPEN_DSYNC:
            /* not reachable */
            Assert(false);
            break;
        default:
            ereport(PANIC,
                    errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                    errmsg_internal("unrecognized \"wal_sync_method\": %d", wal_sync_method));
            break;
    }
 
    /* PANIC if failed to fsync */
    if (msg)
    {
        char        xlogfname[MAXFNAMELEN];
        int         save_errno = errno;
 
        XLogFileName(xlogfname, tli, segno, wal_segment_size);
        errno = save_errno;
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg(msg, xlogfname)));
    }
 
    pgstat_report_wait_end();
 
    pgstat_count_io_op_time(IOOBJECT_WAL, IOCONTEXT_NORMAL, IOOP_FSYNC,
                            start, 1, 0);
}

References _, Assert(), enableFsync, ereport, errcode(), errcode_for_file_access(), errmsg(), errmsg_internal(), fd(), IOCONTEXT_NORMAL, IOOBJECT_WAL, IOOP_FSYNC, MAXFNAMELEN, PANIC, pg_fdatasync(), pg_fsync_no_writethrough(), pg_fsync_writethrough(), pgstat_count_io_op_time(), pgstat_prepare_io_time(), pgstat_report_wait_end(), pgstat_report_wait_start(), start, track_wal_io_timing, wal_segment_size, wal_sync_method, WAL_SYNC_METHOD_FDATASYNC, WAL_SYNC_METHOD_FSYNC, WAL_SYNC_METHOD_FSYNC_WRITETHROUGH, WAL_SYNC_METHOD_OPEN, WAL_SYNC_METHOD_OPEN_DSYNC, and XLogFileName().

Referenced by XLogWalRcvFlush(), and XLogWrite().

◆ LocalProcessControlFile()

void LocalProcessControlFile ( bool reset )

Definition at line 5027 of file xlog.c.

{
    Assert(reset || ControlFile == NULL);
    ControlFile = palloc(sizeof(ControlFileData));
    ReadControlFile();
}

References Assert(), ControlFile, palloc(), ReadControlFile(), and reset().

Referenced by PostgresSingleUserMain(), PostmasterMain(), and PostmasterStateMachine().

◆ ReachedEndOfBackup()

void ReachedEndOfBackup	(	XLogRecPtr	EndRecPtr,
		TimeLineID	tli
	)

Definition at line 6435 of file xlog.c.

{
    /*
     * We have reached the end of base backup, as indicated by pg_control. The
     * data on disk is now consistent (unless minRecoveryPoint 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;
    }
 
    ControlFile->backupStartPoint = InvalidXLogRecPtr;
    ControlFile->backupEndPoint = InvalidXLogRecPtr;
    ControlFile->backupEndRequired = false;
    UpdateControlFile();
 
    LWLockRelease(ControlFileLock);
}

References ControlFileData::backupEndPoint, ControlFileData::backupEndRequired, ControlFileData::backupStartPoint, ControlFile, InvalidXLogRecPtr, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, and UpdateControlFile().

Referenced by CheckRecoveryConsistency().

◆ RecoveryInProgress()

bool RecoveryInProgress ( void )

Definition at line 6522 of file xlog.c.

{
    /*
     * We check shared state each time only until we leave recovery mode. We
     * can't re-enter recovery, so there's no need to keep checking after the
     * shared variable has once been seen false.
     */
    if (!LocalRecoveryInProgress)
        return false;
    else
    {
        /*
         * use volatile pointer to make sure we make a fresh read of the
         * shared variable.
         */
        volatile XLogCtlData *xlogctl = XLogCtl;
 
        LocalRecoveryInProgress = (xlogctl->SharedRecoveryState != RECOVERY_STATE_DONE);
 
        /*
         * Note: We don't need a memory barrier when we're still in recovery.
         * We might exit recovery immediately after return, so the caller
         * can't rely on 'true' meaning that we're still in recovery anyway.
         */
 
        return LocalRecoveryInProgress;
    }
}

References LocalRecoveryInProgress, RECOVERY_STATE_DONE, XLogCtlData::SharedRecoveryState, and XLogCtl.

Referenced by amcheck_index_mainfork_expected(), attribute_statistics_update(), BackgroundWriterMain(), BeginReportingGUCOptions(), brin_desummarize_range(), brin_summarize_range(), CanInvalidateIdleSlot(), check_transaction_isolation(), check_transaction_read_only(), CheckArchiveTimeout(), CheckLogicalDecodingRequirements(), CheckpointerMain(), ComputeXidHorizons(), CreateCheckPoint(), CreateDecodingContext(), CreateEndOfRecoveryRecord(), CreateOverwriteContrecordRecord(), CreateRestartPoint(), do_pg_backup_start(), do_pg_backup_stop(), error_commit_ts_disabled(), get_relation_info(), GetCurrentLSN(), GetLatestLSN(), GetNewMultiXactId(), GetNewObjectId(), GetNewTransactionId(), GetOldestActiveTransactionId(), GetOldestSafeDecodingTransactionId(), GetRunningTransactionData(), GetSerializableTransactionSnapshot(), GetSerializableTransactionSnapshotInt(), GetSnapshotData(), GetStrictOldestNonRemovableTransactionId(), gin_clean_pending_list(), GlobalVisHorizonKindForRel(), heap_force_common(), heap_page_prune_opt(), IdentifySystem(), InitTempTableNamespace(), InitWalSender(), IsCheckpointOnSchedule(), LockAcquireExtended(), logical_read_xlog_page(), MaintainLatestCompletedXid(), MarkBufferDirtyHint(), perform_base_backup(), pg_clear_attribute_stats(), pg_create_restore_point(), pg_current_wal_flush_lsn(), pg_current_wal_insert_lsn(), pg_current_wal_lsn(), pg_get_sequence_data(), pg_get_wal_replay_pause_state(), pg_is_in_recovery(), pg_is_wal_replay_paused(), pg_log_standby_snapshot(), pg_logical_slot_get_changes_guts(), pg_promote(), pg_replication_slot_advance(), pg_sequence_last_value(), pg_switch_wal(), pg_sync_replication_slots(), pg_wal_replay_pause(), pg_wal_replay_resume(), pg_walfile_name(), pg_walfile_name_offset(), PhysicalWakeupLogicalWalSnd(), PrepareRedoAdd(), PrepareRedoRemove(), PreventCommandDuringRecovery(), ProcSleep(), read_local_xlog_page_guts(), ReadReplicationSlot(), recovery_create_dbdir(), relation_statistics_update(), ReplicationSlotAlter(), ReplicationSlotCreate(), ReplicationSlotDrop(), ReplicationSlotReserveWal(), replorigin_check_prerequisites(), ReportChangedGUCOptions(), sendDir(), SerialSetActiveSerXmin(), show_in_hot_standby(), ShutdownXLOG(), SnapBuildWaitSnapshot(), standard_ProcessUtility(), StandbySlotsHaveCaughtup(), StartLogicalReplication(), StartReplication(), StartTransaction(), TransactionIdIsInProgress(), TruncateMultiXact(), UpdateFullPageWrites(), verify_heapam(), WALReadFromBuffers(), WalReceiverMain(), WalSndWaitForWal(), xlog_decode(), XLogBackgroundFlush(), XLogFlush(), XLogInsertAllowed(), XLogNeedsFlush(), and XLogSendPhysical().

◆ register_persistent_abort_backup_handler()

void register_persistent_abort_backup_handler ( void )

Definition at line 9598 of file xlog.c.

{
    static bool already_done = false;
 
    if (already_done)
        return;
    before_shmem_exit(do_pg_abort_backup, DatumGetBool(false));
    already_done = true;
}

References before_shmem_exit(), DatumGetBool(), and do_pg_abort_backup().

Referenced by pg_backup_start().

◆ RemoveNonParentXlogFiles()

void RemoveNonParentXlogFiles	(	XLogRecPtr	switchpoint,
		TimeLineID	newTLI
	)

Definition at line 4079 of file xlog.c.

{
    DIR        *xldir;
    struct dirent *xlde;
    char        switchseg[MAXFNAMELEN];
    XLogSegNo   endLogSegNo;
    XLogSegNo   switchLogSegNo;
    XLogSegNo   recycleSegNo;
 
    /*
     * Initialize info about where to begin the work.  This will recycle,
     * somewhat arbitrarily, 10 future segments.
     */
    XLByteToPrevSeg(switchpoint, switchLogSegNo, wal_segment_size);
    XLByteToSeg(switchpoint, endLogSegNo, wal_segment_size);
    recycleSegNo = endLogSegNo + 10;
 
    /*
     * Construct a filename of the last segment to be kept.
     */
    XLogFileName(switchseg, newTLI, switchLogSegNo, wal_segment_size);
 
    elog(DEBUG2, "attempting to remove WAL segments newer than log file %s",
         switchseg);
 
    xldir = AllocateDir(XLOGDIR);
 
    while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
    {
        /* Ignore files that are not XLOG segments */
        if (!IsXLogFileName(xlde->d_name))
            continue;
 
        /*
         * Remove files that are on a timeline older than the new one we're
         * switching to, but with a segment number >= the first segment on the
         * new timeline.
         */
        if (strncmp(xlde->d_name, switchseg, 8) < 0 &&
            strcmp(xlde->d_name + 8, switchseg + 8) > 0)
        {
            /*
             * If the file has already been marked as .ready, however, don't
             * remove it yet. It should be OK to remove it - files that are
             * not part of our timeline history are not required for recovery
             * - but seems safer to let them be archived and removed later.
             */
            if (!XLogArchiveIsReady(xlde->d_name))
                RemoveXlogFile(xlde, recycleSegNo, &endLogSegNo, newTLI);
        }
    }
 
    FreeDir(xldir);
}

References AllocateDir(), dirent::d_name, DEBUG2, elog, FreeDir(), IsXLogFileName(), MAXFNAMELEN, ReadDir(), RemoveXlogFile(), wal_segment_size, XLByteToPrevSeg, XLByteToSeg, XLogArchiveIsReady(), XLOGDIR, and XLogFileName().

Referenced by ApplyWalRecord(), and CleanupAfterArchiveRecovery().

◆ SetInstallXLogFileSegmentActive()

void SetInstallXLogFileSegmentActive ( void )

Definition at line 9661 of file xlog.c.

{
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    XLogCtl->InstallXLogFileSegmentActive = true;
    LWLockRelease(ControlFileLock);
}

References XLogCtlData::InstallXLogFileSegmentActive, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), and XLogCtl.

Referenced by BootStrapXLOG(), StartupXLOG(), and WaitForWALToBecomeAvailable().

◆ SetWalWriterSleeping()

void SetWalWriterSleeping ( bool sleeping )

Definition at line 9684 of file xlog.c.

{
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->WalWriterSleeping = sleeping;
    SpinLockRelease(&XLogCtl->info_lck);
}

References XLogCtlData::info_lck, SpinLockAcquire, SpinLockRelease, XLogCtlData::WalWriterSleeping, and XLogCtl.

Referenced by WalWriterMain().

◆ ShutdownXLOG()

void ShutdownXLOG	(	int	code,
		Datum	arg
	)

Definition at line 6790 of file xlog.c.

{
    /*
     * We should have an aux process resource owner to use, and we should not
     * be in a transaction that's installed some other resowner.
     */
    Assert(AuxProcessResourceOwner != NULL);
    Assert(CurrentResourceOwner == NULL ||
           CurrentResourceOwner == AuxProcessResourceOwner);
    CurrentResourceOwner = AuxProcessResourceOwner;
 
    /* Don't be chatty in standalone mode */
    ereport(IsPostmasterEnvironment ? LOG : NOTICE,
            (errmsg("shutting down")));
 
    /*
     * Signal walsenders to move to stopping state.
     */
    WalSndInitStopping();
 
    /*
     * Wait for WAL senders to be in stopping state.  This prevents commands
     * from writing new WAL.
     */
    WalSndWaitStopping();
 
    if (RecoveryInProgress())
        CreateRestartPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
    else
    {
        /*
         * If archiving is enabled, rotate the last XLOG file so that all the
         * remaining records are archived (postmaster wakes up the archiver
         * process one more time at the end of shutdown). The checkpoint
         * record will go to the next XLOG file and won't be archived (yet).
         */
        if (XLogArchivingActive())
            RequestXLogSwitch(false);
 
        CreateCheckPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
    }
}

References Assert(), AuxProcessResourceOwner, CHECKPOINT_IMMEDIATE, CHECKPOINT_IS_SHUTDOWN, CreateCheckPoint(), CreateRestartPoint(), CurrentResourceOwner, ereport, errmsg(), IsPostmasterEnvironment, LOG, NOTICE, RecoveryInProgress(), RequestXLogSwitch(), WalSndInitStopping(), WalSndWaitStopping(), and XLogArchivingActive.

Referenced by CheckpointerMain(), and InitPostgres().

◆ StartupXLOG()

void StartupXLOG ( void )

Definition at line 5614 of file xlog.c.

{
    XLogCtlInsert *Insert;
    CheckPoint  checkPoint;
    bool        wasShutdown;
    bool        didCrash;
    bool        haveTblspcMap;
    bool        haveBackupLabel;
    XLogRecPtr  EndOfLog;
    TimeLineID  EndOfLogTLI;
    TimeLineID  newTLI;
    bool        performedWalRecovery;
    EndOfWalRecoveryInfo *endOfRecoveryInfo;
    XLogRecPtr  abortedRecPtr;
    XLogRecPtr  missingContrecPtr;
    TransactionId oldestActiveXID;
    bool        promoted = false;
 
    /*
     * We should have an aux process resource owner to use, and we should not
     * be in a transaction that's installed some other resowner.
     */
    Assert(AuxProcessResourceOwner != NULL);
    Assert(CurrentResourceOwner == NULL ||
           CurrentResourceOwner == AuxProcessResourceOwner);
    CurrentResourceOwner = AuxProcessResourceOwner;
 
    /*
     * Check that contents look valid.
     */
    if (!XRecOffIsValid(ControlFile->checkPoint))
        ereport(FATAL,
                (errcode(ERRCODE_DATA_CORRUPTED),
                 errmsg("control file contains invalid checkpoint location")));
 
    switch (ControlFile->state)
    {
        case DB_SHUTDOWNED:
 
            /*
             * This is the expected case, so don't be chatty in standalone
             * mode
             */
            ereport(IsPostmasterEnvironment ? LOG : NOTICE,
                    (errmsg("database system was shut down at %s",
                            str_time(ControlFile->time))));
            break;
 
        case DB_SHUTDOWNED_IN_RECOVERY:
            ereport(LOG,
                    (errmsg("database system was shut down in recovery at %s",
                            str_time(ControlFile->time))));
            break;
 
        case DB_SHUTDOWNING:
            ereport(LOG,
                    (errmsg("database system shutdown was interrupted; last known up at %s",
                            str_time(ControlFile->time))));
            break;
 
        case DB_IN_CRASH_RECOVERY:
            ereport(LOG,
                    (errmsg("database system was interrupted while in recovery at %s",
                            str_time(ControlFile->time)),
                     errhint("This probably means that some data is corrupted and"
                             " you will have to use the last backup for recovery.")));
            break;
 
        case DB_IN_ARCHIVE_RECOVERY:
            ereport(LOG,
                    (errmsg("database system was interrupted while in recovery at log time %s",
                            str_time(ControlFile->checkPointCopy.time)),
                     errhint("If this has occurred more than once some data might be corrupted"
                             " and you might need to choose an earlier recovery target.")));
            break;
 
        case DB_IN_PRODUCTION:
            ereport(LOG,
                    (errmsg("database system was interrupted; last known up at %s",
                            str_time(ControlFile->time))));
            break;
 
        default:
            ereport(FATAL,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg("control file contains invalid database cluster state")));
    }
 
    /* This is just to allow attaching to startup process with a debugger */
#ifdef XLOG_REPLAY_DELAY
    if (ControlFile->state != DB_SHUTDOWNED)
        pg_usleep(60000000L);
#endif
 
    /*
     * Verify that pg_wal, pg_wal/archive_status, and pg_wal/summaries exist.
     * In cases where someone has performed a copy for PITR, these directories
     * may have been excluded and need to be re-created.
     */
    ValidateXLOGDirectoryStructure();
 
    /* Set up timeout handler needed to report startup progress. */
    if (!IsBootstrapProcessingMode())
        RegisterTimeout(STARTUP_PROGRESS_TIMEOUT,
                        startup_progress_timeout_handler);
 
    /*----------
     * If we previously crashed, perform a couple of actions:
     *
     * - The pg_wal directory may still include some temporary WAL segments
     *   used when creating a new segment, so perform some clean up to not
     *   bloat this path.  This is done first as there is no point to sync
     *   this temporary data.
     *
     * - There might be data which we had written, intending to fsync it, but
     *   which we had not actually fsync'd yet.  Therefore, a power failure in
     *   the near future might cause earlier unflushed writes to be lost, even
     *   though more recent data written to disk from here on would be
     *   persisted.  To avoid that, fsync the entire data directory.
     */
    if (ControlFile->state != DB_SHUTDOWNED &&
        ControlFile->state != DB_SHUTDOWNED_IN_RECOVERY)
    {
        RemoveTempXlogFiles();
        SyncDataDirectory();
        didCrash = true;
    }
    else
        didCrash = false;
 
    /*
     * Prepare for WAL recovery if needed.
     *
     * 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.
     */
    InitWalRecovery(ControlFile, &wasShutdown,
                    &haveBackupLabel, &haveTblspcMap);
    checkPoint = ControlFile->checkPointCopy;
 
    /* initialize shared memory variables from the checkpoint record */
    TransamVariables->nextXid = checkPoint.nextXid;
    TransamVariables->nextOid = checkPoint.nextOid;
    TransamVariables->oidCount = 0;
    MultiXactSetNextMXact(checkPoint.nextMulti, checkPoint.nextMultiOffset);
    AdvanceOldestClogXid(checkPoint.oldestXid);
    SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);
    SetMultiXactIdLimit(checkPoint.oldestMulti, checkPoint.oldestMultiDB, true);
    SetCommitTsLimit(checkPoint.oldestCommitTsXid,
                     checkPoint.newestCommitTsXid);
    XLogCtl->ckptFullXid = checkPoint.nextXid;
 
    /*
     * Clear out any old relcache cache files.  This is *necessary* if we do
     * any WAL replay, since that would probably result in the cache files
     * being out of sync with database reality.  In theory we could leave them
     * in place if the database had been cleanly shut down, but it seems
     * safest to just remove them always and let them be rebuilt during the
     * first backend startup.  These files needs to be removed from all
     * directories including pg_tblspc, however the symlinks are created only
     * after reading tablespace_map file in case of archive recovery from
     * backup, so needs to clear old relcache files here after creating
     * symlinks.
     */
    RelationCacheInitFileRemove();
 
    /*
     * Initialize replication slots, before there's a chance to remove
     * required resources.
     */
    StartupReplicationSlots();
 
    /*
     * Startup logical state, needs to be setup now so we have proper data
     * during crash recovery.
     */
    StartupReorderBuffer();
 
    /*
     * Startup CLOG. This must be done after TransamVariables->nextXid has
     * been initialized and before we accept connections or begin WAL replay.
     */
    StartupCLOG();
 
    /*
     * Startup MultiXact. We need to do this early to be able to replay
     * truncations.
     */
    StartupMultiXact();
 
    /*
     * Ditto for commit timestamps.  Activate the facility if the setting is
     * enabled in the control file, as there should be no tracking of commit
     * timestamps done when the setting was disabled.  This facility can be
     * started or stopped when replaying a XLOG_PARAMETER_CHANGE record.
     */
    if (ControlFile->track_commit_timestamp)
        StartupCommitTs();
 
    /*
     * Recover knowledge about replay progress of known replication partners.
     */
    StartupReplicationOrigin();
 
    /*
     * Initialize unlogged LSN. On a clean shutdown, it's restored from the
     * control file. On recovery, all unlogged relations are blown away, so
     * the unlogged LSN counter can be reset too.
     */
    if (ControlFile->state == DB_SHUTDOWNED)
        pg_atomic_write_membarrier_u64(&XLogCtl->unloggedLSN,
                                       ControlFile->unloggedLSN);
    else
        pg_atomic_write_membarrier_u64(&XLogCtl->unloggedLSN,
                                       FirstNormalUnloggedLSN);
 
    /*
     * 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
     * ourselves - the history file of the recovery target timeline covers all
     * the previous timelines in the history too - a cascading standby server
     * might be interested in them. Or, if you archive the WAL from this
     * server to a different archive than the primary, it'd be good for all
     * the history files to get archived there after failover, so that you can
     * use one of the old timelines as a PITR target. Timeline history files
     * are small, so it's better to copy them unnecessarily than not copy them
     * and regret later.
     */
    restoreTimeLineHistoryFiles(checkPoint.ThisTimeLineID, recoveryTargetTLI);
 
    /*
     * Before running in recovery, scan pg_twophase and fill in its status to
     * be able to work on entries generated by redo.  Doing a scan before
     * taking any recovery action has the merit to discard any 2PC files that
     * are newer than the first record to replay, saving from any conflicts at
     * replay.  This avoids as well any subsequent scans when doing recovery
     * of the on-disk two-phase data.
     */
    restoreTwoPhaseData();
 
    /*
     * When starting with crash recovery, reset pgstat data - it might not be
     * valid. Otherwise restore pgstat data. It's safe to do this here,
     * because postmaster will not yet have started any other processes.
     *
     * NB: Restoring replication slot stats relies on slot state to have
     * already been restored from disk.
     *
     * TODO: With a bit of extra work we could just start with a pgstat file
     * associated with the checkpoint redo location we're starting from.
     */
    if (didCrash)
        pgstat_discard_stats();
    else
        pgstat_restore_stats();
 
    lastFullPageWrites = checkPoint.fullPageWrites;
 
    RedoRecPtr = XLogCtl->RedoRecPtr = XLogCtl->Insert.RedoRecPtr = checkPoint.redo;
    doPageWrites = lastFullPageWrites;
 
    /* REDO */
    if (InRecovery)
    {
        /* Initialize state for RecoveryInProgress() */
        SpinLockAcquire(&XLogCtl->info_lck);
        if (InArchiveRecovery)
            XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;
        else
            XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
        SpinLockRelease(&XLogCtl->info_lck);
 
        /*
         * 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.
         *
         * No need to hold ControlFileLock yet, we aren't up far enough.
         */
        UpdateControlFile();
 
        /*
         * If there was a backup label file, it's done its job and the info
         * has now been propagated into pg_control.  We must get rid of the
         * label file so that if we crash during recovery, we'll pick up at
         * the latest recovery restartpoint instead of going all the way back
         * to the backup start point.  It seems prudent though to just rename
         * the file out of the way rather than delete it completely.
         */
        if (haveBackupLabel)
        {
            unlink(BACKUP_LABEL_OLD);
            durable_rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD, FATAL);
        }
 
        /*
         * If there was a tablespace_map file, it's done its job and the
         * symlinks have been created.  We must get rid of the map file so
         * that if we crash during recovery, we don't create symlinks again.
         * It seems prudent though to just rename the file out of the way
         * rather than delete it completely.
         */
        if (haveTblspcMap)
        {
            unlink(TABLESPACE_MAP_OLD);
            durable_rename(TABLESPACE_MAP, TABLESPACE_MAP_OLD, FATAL);
        }
 
        /*
         * Initialize our local copy of minRecoveryPoint.  When doing crash
         * recovery we want to replay up to the end of WAL.  Particularly, in
         * the case of a promoted standby minRecoveryPoint value in the
         * control file is only updated after the first checkpoint.  However,
         * if the instance crashes before the first post-recovery checkpoint
         * is completed then recovery will use a stale location causing the
         * startup process to think that there are still invalid page
         * references when checking for data consistency.
         */
        if (InArchiveRecovery)
        {
            LocalMinRecoveryPoint = ControlFile->minRecoveryPoint;
            LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
        }
        else
        {
            LocalMinRecoveryPoint = InvalidXLogRecPtr;
            LocalMinRecoveryPointTLI = 0;
        }
 
        /* Check that the GUCs used to generate the WAL allow recovery */
        CheckRequiredParameterValues();
 
        /*
         * We're in recovery, so unlogged relations may be trashed and must be
         * reset.  This should be done BEFORE allowing Hot Standby
         * connections, so that read-only backends don't try to read whatever
         * garbage is left over from before.
         */
        ResetUnloggedRelations(UNLOGGED_RELATION_CLEANUP);
 
        /*
         * Likewise, delete any saved transaction snapshot files that got left
         * behind by crashed backends.
         */
        DeleteAllExportedSnapshotFiles();
 
        /*
         * Initialize for Hot Standby, if enabled. We won't let backends in
         * yet, not until we've reached the min recovery point specified in
         * control file and we've established a recovery snapshot from a
         * running-xacts WAL record.
         */
        if (ArchiveRecoveryRequested && EnableHotStandby)
        {
            TransactionId *xids;
            int         nxids;
 
            ereport(DEBUG1,
                    (errmsg_internal("initializing for hot standby")));
 
            InitRecoveryTransactionEnvironment();
 
            if (wasShutdown)
                oldestActiveXID = PrescanPreparedTransactions(&xids, &nxids);
            else
                oldestActiveXID = checkPoint.oldestActiveXid;
            Assert(TransactionIdIsValid(oldestActiveXID));
 
            /* Tell procarray about the range of xids it has to deal with */
            ProcArrayInitRecovery(XidFromFullTransactionId(TransamVariables->nextXid));
 
            /*
             * Startup subtrans only.  CLOG, MultiXact and commit timestamp
             * have already been started up and other SLRUs are not maintained
             * during recovery and need not be started yet.
             */
            StartupSUBTRANS(oldestActiveXID);
 
            /*
             * If we're beginning at a shutdown checkpoint, we know that
             * nothing was running on the primary at this point. So fake-up an
             * empty running-xacts record and use that here and now. Recover
             * additional standby state for prepared transactions.
             */
            if (wasShutdown)
            {
                RunningTransactionsData running;
                TransactionId latestCompletedXid;
 
                /* Update pg_subtrans entries for any prepared transactions */
                StandbyRecoverPreparedTransactions();
 
                /*
                 * Construct a RunningTransactions snapshot representing a
                 * shut down server, with only prepared transactions still
                 * alive. We're never overflowed at this point because all
                 * subxids are listed with their parent prepared transactions.
                 */
                running.xcnt = nxids;
                running.subxcnt = 0;
                running.subxid_status = SUBXIDS_IN_SUBTRANS;
                running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
                running.oldestRunningXid = oldestActiveXID;
                latestCompletedXid = XidFromFullTransactionId(checkPoint.nextXid);
                TransactionIdRetreat(latestCompletedXid);
                Assert(TransactionIdIsNormal(latestCompletedXid));
                running.latestCompletedXid = latestCompletedXid;
                running.xids = xids;
 
                ProcArrayApplyRecoveryInfo(&running);
            }
        }
 
        /*
         * We're all set for replaying the WAL now. Do it.
         */
        PerformWalRecovery();
        performedWalRecovery = true;
    }
    else
        performedWalRecovery = false;
 
    /*
     * Finish WAL recovery.
     */
    endOfRecoveryInfo = FinishWalRecovery();
    EndOfLog = endOfRecoveryInfo->endOfLog;
    EndOfLogTLI = endOfRecoveryInfo->endOfLogTLI;
    abortedRecPtr = endOfRecoveryInfo->abortedRecPtr;
    missingContrecPtr = endOfRecoveryInfo->missingContrecPtr;
 
    /*
     * Reset ps status display, so as no information related to recovery shows
     * up.
     */
    set_ps_display("");
 
    /*
     * When recovering from a backup (we are in recovery, and archive recovery
     * was requested), complain if we did not roll forward far enough to reach
     * the point where the database is consistent.  For regular online
     * backup-from-primary, that means reaching the end-of-backup WAL record
     * (at which point we reset backupStartPoint to be Invalid), for
     * backup-from-replica (which can't inject records into the WAL stream),
     * that point is when we reach the minRecoveryPoint in pg_control (which
     * we purposefully copy last when backing up from a replica).  For
     * pg_rewind (which creates a backup_label with a method of "pg_rewind")
     * or snapshot-style backups (which don't), backupEndRequired will be set
     * to false.
     *
     * Note: it is indeed okay to look at the local variable
     * LocalMinRecoveryPoint here, even though ControlFile->minRecoveryPoint
     * might be further ahead --- ControlFile->minRecoveryPoint cannot have
     * been advanced beyond the WAL we processed.
     */
    if (InRecovery &&
        (EndOfLog < LocalMinRecoveryPoint ||
         !XLogRecPtrIsInvalid(ControlFile->backupStartPoint)))
    {
        /*
         * Ran off end of WAL before reaching end-of-backup WAL record, or
         * minRecoveryPoint. That's a bad sign, indicating that you tried to
         * recover from an online backup but never called pg_backup_stop(), or
         * you didn't archive all the WAL needed.
         */
        if (ArchiveRecoveryRequested || ControlFile->backupEndRequired)
        {
            if (!XLogRecPtrIsInvalid(ControlFile->backupStartPoint) || ControlFile->backupEndRequired)
                ereport(FATAL,
                        (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                         errmsg("WAL ends before end of online backup"),
                         errhint("All WAL generated while online backup was taken must be available at recovery.")));
            else
                ereport(FATAL,
                        (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
                         errmsg("WAL ends before consistent recovery point")));
        }
    }
 
    /*
     * Reset unlogged relations to the contents of their INIT fork. This is
     * done AFTER recovery is complete so as to include any unlogged relations
     * created during recovery, but BEFORE recovery is marked as having
     * completed successfully. Otherwise we'd not retry if any of the post
     * end-of-recovery steps fail.
     */
    if (InRecovery)
        ResetUnloggedRelations(UNLOGGED_RELATION_INIT);
 
    /*
     * Pre-scan prepared transactions to find out the range of XIDs present.
     * This information is not quite needed yet, but it is positioned here so
     * as potential problems are detected before any on-disk change is done.
     */
    oldestActiveXID = PrescanPreparedTransactions(NULL, NULL);
 
    /*
     * Allow ordinary WAL segment creation before possibly switching to a new
     * timeline, which creates a new segment, and after the last ReadRecord().
     */
    SetInstallXLogFileSegmentActive();
 
    /*
     * Consider whether we need to assign a new timeline ID.
     *
     * If we did archive recovery, we always assign a new ID.  This handles a
     * couple of issues.  If we stopped short of the end of WAL during
     * recovery, then we are clearly generating a new timeline and must assign
     * it a unique new ID.  Even if we ran to the end, modifying the current
     * last segment is problematic because it may result in trying to
     * overwrite an already-archived copy of that segment, and we encourage
     * DBAs to make their archive_commands reject that.  We can dodge the
     * problem by making the new active segment have a new timeline ID.
     *
     * In a normal crash recovery, we can just extend the timeline we were in.
     */
    newTLI = endOfRecoveryInfo->lastRecTLI;
    if (ArchiveRecoveryRequested)
    {
        newTLI = findNewestTimeLine(recoveryTargetTLI) + 1;
        ereport(LOG,
                (errmsg("selected new timeline ID: %u", newTLI)));
 
        /*
         * 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
         * endOfRecovery->lastPage; we will use that below.)
         */
        XLogInitNewTimeline(EndOfLogTLI, EndOfLog, newTLI);
 
        /*
         * Remove the signal files out of the way, so that we don't
         * accidentally re-enter archive recovery mode in a subsequent crash.
         */
        if (endOfRecoveryInfo->standby_signal_file_found)
            durable_unlink(STANDBY_SIGNAL_FILE, FATAL);
 
        if (endOfRecoveryInfo->recovery_signal_file_found)
            durable_unlink(RECOVERY_SIGNAL_FILE, FATAL);
 
        /*
         * Write the timeline history file, and have it archived. After this
         * point (or rather, as soon as the file is archived), the timeline
         * will appear as "taken" in the WAL archive and to any standby
         * servers.  If we crash before actually switching to the new
         * timeline, standby servers will nevertheless think that we switched
         * to the new timeline, and will try to connect to the new timeline.
         * To minimize the window for that, try to do as little as possible
         * between here and writing the end-of-recovery record.
         */
        writeTimeLineHistory(newTLI, recoveryTargetTLI,
                             EndOfLog, endOfRecoveryInfo->recoveryStopReason);
 
        ereport(LOG,
                (errmsg("archive recovery complete")));
    }
 
    /* Save the selected TimeLineID in shared memory, too */
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->InsertTimeLineID = newTLI;
    XLogCtl->PrevTimeLineID = endOfRecoveryInfo->lastRecTLI;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * Actually, if WAL ended in an incomplete record, skip the parts that
     * made it through and start writing after the portion that persisted.
     * (It's critical to first write an OVERWRITE_CONTRECORD message, which
     * we'll do as soon as we're open for writing new WAL.)
     */
    if (!XLogRecPtrIsInvalid(missingContrecPtr))
    {
        /*
         * We should only have a missingContrecPtr if we're not switching to a
         * new timeline. When a timeline switch occurs, WAL is copied from the
         * old timeline to the new only up to the end of the last complete
         * record, so there can't be an incomplete WAL record that we need to
         * disregard.
         */
        Assert(newTLI == endOfRecoveryInfo->lastRecTLI);
        Assert(!XLogRecPtrIsInvalid(abortedRecPtr));
        EndOfLog = missingContrecPtr;
    }
 
    /*
     * Prepare to write WAL starting at EndOfLog location, and init xlog
     * buffer cache using the block containing the last record from the
     * previous incarnation.
     */
    Insert = &XLogCtl->Insert;
    Insert->PrevBytePos = XLogRecPtrToBytePos(endOfRecoveryInfo->lastRec);
    Insert->CurrBytePos = XLogRecPtrToBytePos(EndOfLog);
 
    /*
     * 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.
     */
    if (EndOfLog % XLOG_BLCKSZ != 0)
    {
        char       *page;
        int         len;
        int         firstIdx;
 
        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];
        memcpy(page, endOfRecoveryInfo->lastPage, len);
        memset(page + len, 0, XLOG_BLCKSZ - len);
 
        pg_atomic_write_u64(&XLogCtl->xlblocks[firstIdx], endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ);
        pg_atomic_write_u64(&XLogCtl->InitializedUpTo, endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ);
        XLogCtl->InitializedFrom = endOfRecoveryInfo->lastPageBeginPtr;
    }
    else
    {
        /*
         * There is no partial block to copy. Just set InitializedUpTo, and
         * let the first attempt to insert a log record to initialize the next
         * buffer.
         */
        pg_atomic_write_u64(&XLogCtl->InitializedUpTo, EndOfLog);
        XLogCtl->InitializedFrom = EndOfLog;
    }
    pg_atomic_write_u64(&XLogCtl->InitializeReserved, pg_atomic_read_u64(&XLogCtl->InitializedUpTo));
 
    /*
     * Update local and shared status.  This is OK to do without any locks
     * because no other process can be reading or writing WAL yet.
     */
    LogwrtResult.Write = LogwrtResult.Flush = EndOfLog;
    pg_atomic_write_u64(&XLogCtl->logInsertResult, EndOfLog);
    pg_atomic_write_u64(&XLogCtl->logWriteResult, EndOfLog);
    pg_atomic_write_u64(&XLogCtl->logFlushResult, EndOfLog);
    XLogCtl->LogwrtRqst.Write = EndOfLog;
    XLogCtl->LogwrtRqst.Flush = EndOfLog;
 
    /*
     * Preallocate additional log files, if wanted.
     */
    PreallocXlogFiles(EndOfLog, newTLI);
 
    /*
     * Okay, we're officially UP.
     */
    InRecovery = false;
 
    /* start the archive_timeout timer and LSN running */
    XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL);
    XLogCtl->lastSegSwitchLSN = EndOfLog;
 
    /* also initialize latestCompletedXid, to nextXid - 1 */
    LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
    TransamVariables->latestCompletedXid = TransamVariables->nextXid;
    FullTransactionIdRetreat(&TransamVariables->latestCompletedXid);
    LWLockRelease(ProcArrayLock);
 
    /*
     * Start up subtrans, if not already done for hot standby.  (commit
     * timestamps are started below, if necessary.)
     */
    if (standbyState == STANDBY_DISABLED)
        StartupSUBTRANS(oldestActiveXID);
 
    /*
     * Perform end of recovery actions for any SLRUs that need it.
     */
    TrimCLOG();
    TrimMultiXact();
 
    /*
     * Reload shared-memory state for prepared transactions.  This needs to
     * happen before renaming the last partial segment of the old timeline as
     * it may be possible that we have to recover some transactions from it.
     */
    RecoverPreparedTransactions();
 
    /* Shut down xlogreader */
    ShutdownWalRecovery();
 
    /* Enable WAL writes for this backend only. */
    LocalSetXLogInsertAllowed();
 
    /* If necessary, write overwrite-contrecord before doing anything else */
    if (!XLogRecPtrIsInvalid(abortedRecPtr))
    {
        Assert(!XLogRecPtrIsInvalid(missingContrecPtr));
        CreateOverwriteContrecordRecord(abortedRecPtr, missingContrecPtr, newTLI);
    }
 
    /*
     * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE
     * record before resource manager writes cleanup WAL records or checkpoint
     * record is written.
     */
    Insert->fullPageWrites = lastFullPageWrites;
    UpdateFullPageWrites();
 
    /*
     * Emit checkpoint or end-of-recovery record in XLOG, if required.
     */
    if (performedWalRecovery)
        promoted = PerformRecoveryXLogAction();
 
    /*
     * If any of the critical GUCs have changed, log them before we allow
     * backends to write WAL.
     */
    XLogReportParameters();
 
    /* If this is archive recovery, perform post-recovery cleanup actions. */
    if (ArchiveRecoveryRequested)
        CleanupAfterArchiveRecovery(EndOfLogTLI, EndOfLog, newTLI);
 
    /*
     * Local WAL inserts enabled, so it's time to finish initialization of
     * commit timestamp.
     */
    CompleteCommitTsInitialization();
 
    /*
     * All done with end-of-recovery actions.
     *
     * Now allow backends to write WAL and update the control file status in
     * consequence.  SharedRecoveryState, that controls if backends can write
     * WAL, is updated while holding ControlFileLock to prevent other backends
     * to look at an inconsistent state of the control file in shared memory.
     * There is still a small window during which backends can write WAL and
     * the control file is still referring to a system not in DB_IN_PRODUCTION
     * state while looking at the on-disk control file.
     *
     * Also, we use info_lck to update SharedRecoveryState to ensure that
     * there are no race conditions concerning visibility of other recent
     * updates to shared memory.
     */
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    ControlFile->state = DB_IN_PRODUCTION;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->SharedRecoveryState = RECOVERY_STATE_DONE;
    SpinLockRelease(&XLogCtl->info_lck);
 
    UpdateControlFile();
    LWLockRelease(ControlFileLock);
 
    /*
     * Shutdown the recovery environment.  This must occur after
     * RecoverPreparedTransactions() (see notes in lock_twophase_recover())
     * and after switching SharedRecoveryState to RECOVERY_STATE_DONE so as
     * any session building a snapshot will not rely on KnownAssignedXids as
     * RecoveryInProgress() would return false at this stage.  This is
     * particularly critical for prepared 2PC transactions, that would still
     * need to be included in snapshots once recovery has ended.
     */
    if (standbyState != STANDBY_DISABLED)
        ShutdownRecoveryTransactionEnvironment();
 
    /*
     * If there were cascading standby servers connected to us, nudge any wal
     * sender processes to notice that we've been promoted.
     */
    WalSndWakeup(true, true);
 
    /*
     * If this was a promotion, request an (online) checkpoint now. This isn't
     * required for consistency, but the last restartpoint might be far back,
     * and in case of a crash, recovering from it might take a longer than is
     * appropriate now that we're not in standby mode anymore.
     */
    if (promoted)
        RequestCheckpoint(CHECKPOINT_FORCE);
}

Referenced by InitPostgres(), and StartupProcessMain().

◆ SwitchIntoArchiveRecovery()

void SwitchIntoArchiveRecovery	(	XLogRecPtr	EndRecPtr,
		TimeLineID	replayTLI
	)

Definition at line 6397 of file xlog.c.

{
    /* initialize minRecoveryPoint to this record */
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
    if (ControlFile->minRecoveryPoint < EndRecPtr)
    {
        ControlFile->minRecoveryPoint = EndRecPtr;
        ControlFile->minRecoveryPointTLI = replayTLI;
    }
    /* update local copy */
    LocalMinRecoveryPoint = ControlFile->minRecoveryPoint;
    LocalMinRecoveryPointTLI = 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);
}

References ControlFile, DB_IN_ARCHIVE_RECOVERY, XLogCtlData::info_lck, LocalMinRecoveryPoint, LocalMinRecoveryPointTLI, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, RECOVERY_STATE_ARCHIVE, XLogCtlData::SharedRecoveryState, SpinLockAcquire, SpinLockRelease, ControlFileData::state, UpdateControlFile(), updateMinRecoveryPoint, and XLogCtl.

Referenced by ReadRecord().

◆ UpdateFullPageWrites()

void UpdateFullPageWrites ( void )

Definition at line 8354 of file xlog.c.

{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    bool        recoveryInProgress;
 
    /*
     * Do nothing if full_page_writes has not been changed.
     *
     * It's safe to check the shared full_page_writes without the lock,
     * because we assume that there is no concurrently running process which
     * can update it.
     */
    if (fullPageWrites == Insert->fullPageWrites)
        return;
 
    /*
     * Perform this outside critical section so that the WAL insert
     * initialization done by RecoveryInProgress() doesn't trigger an
     * assertion failure.
     */
    recoveryInProgress = RecoveryInProgress();
 
    START_CRIT_SECTION();
 
    /*
     * It's always safe to take full page images, even when not strictly
     * required, but not the other round. So if we're setting full_page_writes
     * to true, first set it true and then write the WAL record. If we're
     * setting it to false, first write the WAL record and then set the global
     * flag.
     */
    if (fullPageWrites)
    {
        WALInsertLockAcquireExclusive();
        Insert->fullPageWrites = true;
        WALInsertLockRelease();
    }
 
    /*
     * Write an XLOG_FPW_CHANGE record. This allows us to keep track of
     * full_page_writes during archive recovery, if required.
     */
    if (XLogStandbyInfoActive() && !recoveryInProgress)
    {
        XLogBeginInsert();
        XLogRegisterData(&fullPageWrites, sizeof(bool));
 
        XLogInsert(RM_XLOG_ID, XLOG_FPW_CHANGE);
    }
 
    if (!fullPageWrites)
    {
        WALInsertLockAcquireExclusive();
        Insert->fullPageWrites = false;
        WALInsertLockRelease();
    }
    END_CRIT_SECTION();
}

References END_CRIT_SECTION, fullPageWrites, XLogCtlData::Insert, Insert(), RecoveryInProgress(), START_CRIT_SECTION, WALInsertLockAcquireExclusive(), WALInsertLockRelease(), XLOG_FPW_CHANGE, XLogBeginInsert(), XLogCtl, XLogInsert(), XLogRegisterData(), and XLogStandbyInfoActive.

Referenced by StartupXLOG(), and UpdateSharedMemoryConfig().

◆ WALReadFromBuffers()

Size WALReadFromBuffers	(	char *	dstbuf,
		XLogRecPtr	startptr,
		Size	count,
		TimeLineID	tli
	)

Definition at line 1759 of file xlog.c.

{
    char       *pdst = dstbuf;
    XLogRecPtr  recptr = startptr;
    XLogRecPtr  inserted;
    Size        nbytes = count;
 
    if (RecoveryInProgress() || tli != GetWALInsertionTimeLine())
        return 0;
 
    Assert(!XLogRecPtrIsInvalid(startptr));
 
    /*
     * Caller should ensure that the requested data has been inserted into WAL
     * buffers before we try to read it.
     */
    inserted = pg_atomic_read_u64(&XLogCtl->logInsertResult);
    if (startptr + count > inserted)
        ereport(ERROR,
                errmsg("cannot read past end of generated WAL: requested %X/%X, current position %X/%X",
                       LSN_FORMAT_ARGS(startptr + count),
                       LSN_FORMAT_ARGS(inserted)));
 
    /*
     * Loop through the buffers without a lock. For each buffer, atomically
     * read and verify the end pointer, then copy the data out, and finally
     * re-read and re-verify the end pointer.
     *
     * Once a page is evicted, it never returns to the WAL buffers, so if the
     * end pointer matches the expected end pointer before and after we copy
     * the data, then the right page must have been present during the data
     * copy. Read barriers are necessary to ensure that the data copy actually
     * happens between the two verification steps.
     *
     * If either verification fails, we simply terminate the loop and return
     * with the data that had been already copied out successfully.
     */
    while (nbytes > 0)
    {
        uint32      offset = recptr % XLOG_BLCKSZ;
        int         idx = XLogRecPtrToBufIdx(recptr);
        XLogRecPtr  expectedEndPtr;
        XLogRecPtr  endptr;
        const char *page;
        const char *psrc;
        Size        npagebytes;
 
        /*
         * Calculate the end pointer we expect in the xlblocks array if the
         * correct page is present.
         */
        expectedEndPtr = recptr + (XLOG_BLCKSZ - offset);
 
        /*
         * First verification step: check that the correct page is present in
         * the WAL buffers.
         */
        endptr = pg_atomic_read_u64(&XLogCtl->xlblocks[idx]);
        if (expectedEndPtr != endptr)
            break;
 
        /*
         * The correct page is present (or was at the time the endptr was
         * read; must re-verify later). Calculate pointer to source data and
         * determine how much data to read from this page.
         */
        page = XLogCtl->pages + idx * (Size) XLOG_BLCKSZ;
        psrc = page + offset;
        npagebytes = Min(nbytes, XLOG_BLCKSZ - offset);
 
        /*
         * Ensure that the data copy and the first verification step are not
         * reordered.
         */
        pg_read_barrier();
 
        /* data copy */
        memcpy(pdst, psrc, npagebytes);
 
        /*
         * Ensure that the data copy and the second verification step are not
         * reordered.
         */
        pg_read_barrier();
 
        /*
         * Second verification step: check that the page we read from wasn't
         * evicted while we were copying the data.
         */
        endptr = pg_atomic_read_u64(&XLogCtl->xlblocks[idx]);
        if (expectedEndPtr != endptr)
            break;
 
        pdst += npagebytes;
        recptr += npagebytes;
        nbytes -= npagebytes;
    }
 
    Assert(pdst - dstbuf <= count);
 
    return pdst - dstbuf;
}

References Assert(), ereport, errmsg(), ERROR, GetWALInsertionTimeLine(), idx(), XLogCtlData::logInsertResult, LSN_FORMAT_ARGS, Min, XLogCtlData::pages, pg_atomic_read_u64(), pg_read_barrier, RecoveryInProgress(), XLogCtlData::xlblocks, XLogCtl, XLogRecPtrIsInvalid, and XLogRecPtrToBufIdx.

Referenced by XLogSendPhysical().

◆ xlog_desc()

void xlog_desc	(	StringInfo	buf,
		struct XLogReaderState *	record
	)

Definition at line 58 of file xlogdesc.c.

{
    char       *rec = XLogRecGetData(record);
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
 
    if (info == XLOG_CHECKPOINT_SHUTDOWN ||
        info == XLOG_CHECKPOINT_ONLINE)
    {
        CheckPoint *checkpoint = (CheckPoint *) rec;
 
        appendStringInfo(buf, "redo %X/%X; "
                         "tli %u; prev tli %u; fpw %s; wal_level %s; xid %u:%u; oid %u; multi %u; offset %u; "
                         "oldest xid %u in DB %u; oldest multi %u in DB %u; "
                         "oldest/newest commit timestamp xid: %u/%u; "
                         "oldest running xid %u; %s",
                         LSN_FORMAT_ARGS(checkpoint->redo),
                         checkpoint->ThisTimeLineID,
                         checkpoint->PrevTimeLineID,
                         checkpoint->fullPageWrites ? "true" : "false",
                         get_wal_level_string(checkpoint->wal_level),
                         EpochFromFullTransactionId(checkpoint->nextXid),
                         XidFromFullTransactionId(checkpoint->nextXid),
                         checkpoint->nextOid,
                         checkpoint->nextMulti,
                         checkpoint->nextMultiOffset,
                         checkpoint->oldestXid,
                         checkpoint->oldestXidDB,
                         checkpoint->oldestMulti,
                         checkpoint->oldestMultiDB,
                         checkpoint->oldestCommitTsXid,
                         checkpoint->newestCommitTsXid,
                         checkpoint->oldestActiveXid,
                         (info == XLOG_CHECKPOINT_SHUTDOWN) ? "shutdown" : "online");
    }
    else if (info == XLOG_NEXTOID)
    {
        Oid         nextOid;
 
        memcpy(&nextOid, rec, sizeof(Oid));
        appendStringInfo(buf, "%u", nextOid);
    }
    else if (info == XLOG_RESTORE_POINT)
    {
        xl_restore_point *xlrec = (xl_restore_point *) rec;
 
        appendStringInfoString(buf, xlrec->rp_name);
    }
    else if (info == XLOG_FPI || info == XLOG_FPI_FOR_HINT)
    {
        /* no further information to print */
    }
    else if (info == XLOG_BACKUP_END)
    {
        XLogRecPtr  startpoint;
 
        memcpy(&startpoint, rec, sizeof(XLogRecPtr));
        appendStringInfo(buf, "%X/%X", LSN_FORMAT_ARGS(startpoint));
    }
    else if (info == XLOG_PARAMETER_CHANGE)
    {
        xl_parameter_change xlrec;
        const char *wal_level_str;
 
        memcpy(&xlrec, rec, sizeof(xl_parameter_change));
        wal_level_str = get_wal_level_string(xlrec.wal_level);
 
        appendStringInfo(buf, "max_connections=%d max_worker_processes=%d "
                         "max_wal_senders=%d max_prepared_xacts=%d "
                         "max_locks_per_xact=%d wal_level=%s "
                         "wal_log_hints=%s track_commit_timestamp=%s",
                         xlrec.MaxConnections,
                         xlrec.max_worker_processes,
                         xlrec.max_wal_senders,
                         xlrec.max_prepared_xacts,
                         xlrec.max_locks_per_xact,
                         wal_level_str,
                         xlrec.wal_log_hints ? "on" : "off",
                         xlrec.track_commit_timestamp ? "on" : "off");
    }
    else if (info == XLOG_FPW_CHANGE)
    {
        bool        fpw;
 
        memcpy(&fpw, rec, sizeof(bool));
        appendStringInfoString(buf, fpw ? "true" : "false");
    }
    else if (info == XLOG_END_OF_RECOVERY)
    {
        xl_end_of_recovery xlrec;
 
        memcpy(&xlrec, rec, sizeof(xl_end_of_recovery));
        appendStringInfo(buf, "tli %u; prev tli %u; time %s; wal_level %s",
                         xlrec.ThisTimeLineID, xlrec.PrevTimeLineID,
                         timestamptz_to_str(xlrec.end_time),
                         get_wal_level_string(xlrec.wal_level));
    }
    else if (info == XLOG_OVERWRITE_CONTRECORD)
    {
        xl_overwrite_contrecord xlrec;
 
        memcpy(&xlrec, rec, sizeof(xl_overwrite_contrecord));
        appendStringInfo(buf, "lsn %X/%X; time %s",
                         LSN_FORMAT_ARGS(xlrec.overwritten_lsn),
                         timestamptz_to_str(xlrec.overwrite_time));
    }
    else if (info == XLOG_CHECKPOINT_REDO)
    {
        int         wal_level;
 
        memcpy(&wal_level, rec, sizeof(int));
        appendStringInfo(buf, "wal_level %s", get_wal_level_string(wal_level));
    }
}

References appendStringInfo(), appendStringInfoString(), buf, xl_end_of_recovery::end_time, EpochFromFullTransactionId, CheckPoint::fullPageWrites, get_wal_level_string(), LSN_FORMAT_ARGS, xl_parameter_change::max_locks_per_xact, xl_parameter_change::max_prepared_xacts, xl_parameter_change::max_wal_senders, xl_parameter_change::max_worker_processes, xl_parameter_change::MaxConnections, CheckPoint::newestCommitTsXid, CheckPoint::nextMulti, CheckPoint::nextMultiOffset, CheckPoint::nextOid, CheckPoint::nextXid, CheckPoint::oldestActiveXid, CheckPoint::oldestCommitTsXid, CheckPoint::oldestMulti, CheckPoint::oldestMultiDB, CheckPoint::oldestXid, CheckPoint::oldestXidDB, xl_overwrite_contrecord::overwrite_time, xl_overwrite_contrecord::overwritten_lsn, xl_end_of_recovery::PrevTimeLineID, CheckPoint::PrevTimeLineID, CheckPoint::redo, xl_restore_point::rp_name, xl_end_of_recovery::ThisTimeLineID, CheckPoint::ThisTimeLineID, timestamptz_to_str(), xl_parameter_change::track_commit_timestamp, wal_level, xl_parameter_change::wal_level, xl_end_of_recovery::wal_level, CheckPoint::wal_level, wal_level_str(), xl_parameter_change::wal_log_hints, XidFromFullTransactionId, XLOG_BACKUP_END, XLOG_CHECKPOINT_ONLINE, XLOG_CHECKPOINT_REDO, XLOG_CHECKPOINT_SHUTDOWN, XLOG_END_OF_RECOVERY, XLOG_FPI, XLOG_FPI_FOR_HINT, XLOG_FPW_CHANGE, XLOG_NEXTOID, XLOG_OVERWRITE_CONTRECORD, XLOG_PARAMETER_CHANGE, XLOG_RESTORE_POINT, XLogRecGetData, and XLogRecGetInfo.

◆ xlog_identify()

const char * xlog_identify ( uint8 info )

Definition at line 173 of file xlogdesc.c.

{
    const char *id = NULL;
 
    switch (info & ~XLR_INFO_MASK)
    {
        case XLOG_CHECKPOINT_SHUTDOWN:
            id = "CHECKPOINT_SHUTDOWN";
            break;
        case XLOG_CHECKPOINT_ONLINE:
            id = "CHECKPOINT_ONLINE";
            break;
        case XLOG_NOOP:
            id = "NOOP";
            break;
        case XLOG_NEXTOID:
            id = "NEXTOID";
            break;
        case XLOG_SWITCH:
            id = "SWITCH";
            break;
        case XLOG_BACKUP_END:
            id = "BACKUP_END";
            break;
        case XLOG_PARAMETER_CHANGE:
            id = "PARAMETER_CHANGE";
            break;
        case XLOG_RESTORE_POINT:
            id = "RESTORE_POINT";
            break;
        case XLOG_FPW_CHANGE:
            id = "FPW_CHANGE";
            break;
        case XLOG_END_OF_RECOVERY:
            id = "END_OF_RECOVERY";
            break;
        case XLOG_OVERWRITE_CONTRECORD:
            id = "OVERWRITE_CONTRECORD";
            break;
        case XLOG_FPI:
            id = "FPI";
            break;
        case XLOG_FPI_FOR_HINT:
            id = "FPI_FOR_HINT";
            break;
        case XLOG_CHECKPOINT_REDO:
            id = "CHECKPOINT_REDO";
            break;
    }
 
    return id;
}

References XLOG_BACKUP_END, XLOG_CHECKPOINT_ONLINE, XLOG_CHECKPOINT_REDO, XLOG_CHECKPOINT_SHUTDOWN, XLOG_END_OF_RECOVERY, XLOG_FPI, XLOG_FPI_FOR_HINT, XLOG_FPW_CHANGE, XLOG_NEXTOID, XLOG_NOOP, XLOG_OVERWRITE_CONTRECORD, XLOG_PARAMETER_CHANGE, XLOG_RESTORE_POINT, XLOG_SWITCH, and XLR_INFO_MASK.

◆ xlog_redo()

void xlog_redo ( struct XLogReaderState * record )

Definition at line 8423 of file xlog.c.

{
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
    XLogRecPtr  lsn = record->EndRecPtr;
 
    /*
     * In XLOG rmgr, backup blocks are only used by XLOG_FPI and
     * XLOG_FPI_FOR_HINT records.
     */
    Assert(info == XLOG_FPI || info == XLOG_FPI_FOR_HINT ||
           !XLogRecHasAnyBlockRefs(record));
 
    if (info == XLOG_NEXTOID)
    {
        Oid         nextOid;
 
        /*
         * We used to try to take the maximum of TransamVariables->nextOid and
         * the recorded nextOid, but that fails if the OID counter wraps
         * around.  Since no OID allocation should be happening during replay
         * anyway, better to just believe the record exactly.  We still take
         * OidGenLock while setting the variable, just in case.
         */
        memcpy(&nextOid, XLogRecGetData(record), sizeof(Oid));
        LWLockAcquire(OidGenLock, LW_EXCLUSIVE);
        TransamVariables->nextOid = nextOid;
        TransamVariables->oidCount = 0;
        LWLockRelease(OidGenLock);
    }
    else if (info == XLOG_CHECKPOINT_SHUTDOWN)
    {
        CheckPoint  checkPoint;
        TimeLineID  replayTLI;
 
        memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
        /* In a SHUTDOWN checkpoint, believe the counters exactly */
        LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
        TransamVariables->nextXid = checkPoint.nextXid;
        LWLockRelease(XidGenLock);
        LWLockAcquire(OidGenLock, LW_EXCLUSIVE);
        TransamVariables->nextOid = checkPoint.nextOid;
        TransamVariables->oidCount = 0;
        LWLockRelease(OidGenLock);
        MultiXactSetNextMXact(checkPoint.nextMulti,
                              checkPoint.nextMultiOffset);
 
        MultiXactAdvanceOldest(checkPoint.oldestMulti,
                               checkPoint.oldestMultiDB);
 
        /*
         * No need to set oldestClogXid here as well; it'll be set when we
         * redo an xl_clog_truncate if it changed since initialization.
         */
        SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);
 
        /*
         * If we see a shutdown checkpoint while waiting for an end-of-backup
         * record, the backup was canceled and the end-of-backup record will
         * never arrive.
         */
        if (ArchiveRecoveryRequested &&
            !XLogRecPtrIsInvalid(ControlFile->backupStartPoint) &&
            XLogRecPtrIsInvalid(ControlFile->backupEndPoint))
            ereport(PANIC,
                    (errmsg("online backup was canceled, recovery cannot continue")));
 
        /*
         * If we see a shutdown checkpoint, we know that nothing was running
         * on the primary at this point. So fake-up an empty running-xacts
         * record and use that here and now. Recover additional standby state
         * for prepared transactions.
         */
        if (standbyState >= STANDBY_INITIALIZED)
        {
            TransactionId *xids;
            int         nxids;
            TransactionId oldestActiveXID;
            TransactionId latestCompletedXid;
            RunningTransactionsData running;
 
            oldestActiveXID = PrescanPreparedTransactions(&xids, &nxids);
 
            /* Update pg_subtrans entries for any prepared transactions */
            StandbyRecoverPreparedTransactions();
 
            /*
             * Construct a RunningTransactions snapshot representing a shut
             * down server, with only prepared transactions still alive. We're
             * never overflowed at this point because all subxids are listed
             * with their parent prepared transactions.
             */
            running.xcnt = nxids;
            running.subxcnt = 0;
            running.subxid_status = SUBXIDS_IN_SUBTRANS;
            running.nextXid = XidFromFullTransactionId(checkPoint.nextXid);
            running.oldestRunningXid = oldestActiveXID;
            latestCompletedXid = XidFromFullTransactionId(checkPoint.nextXid);
            TransactionIdRetreat(latestCompletedXid);
            Assert(TransactionIdIsNormal(latestCompletedXid));
            running.latestCompletedXid = latestCompletedXid;
            running.xids = xids;
 
            ProcArrayApplyRecoveryInfo(&running);
        }
 
        /* ControlFile->checkPointCopy always tracks the latest ckpt XID */
        LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
        ControlFile->checkPointCopy.nextXid = checkPoint.nextXid;
        LWLockRelease(ControlFileLock);
 
        /* Update shared-memory copy of checkpoint XID/epoch */
        SpinLockAcquire(&XLogCtl->info_lck);
        XLogCtl->ckptFullXid = checkPoint.nextXid;
        SpinLockRelease(&XLogCtl->info_lck);
 
        /*
         * 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",
                            checkPoint.ThisTimeLineID, replayTLI)));
 
        RecoveryRestartPoint(&checkPoint, 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 */
        LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
        if (FullTransactionIdPrecedes(TransamVariables->nextXid,
                                      checkPoint.nextXid))
            TransamVariables->nextXid = checkPoint.nextXid;
        LWLockRelease(XidGenLock);
 
        /*
         * We ignore the nextOid counter in an ONLINE checkpoint, preferring
         * to track OID assignment through XLOG_NEXTOID records.  The nextOid
         * counter is from the start of the checkpoint and might well be stale
         * compared to later XLOG_NEXTOID records.  We could try to take the
         * maximum of the nextOid counter and our latest value, but since
         * there's no particular guarantee about the speed with which the OID
         * counter wraps around, that's a risky thing to do.  In any case,
         * users of the nextOid counter are required to avoid assignment of
         * duplicates, so that a somewhat out-of-date value should be safe.
         */
 
        /* Handle multixact */
        MultiXactAdvanceNextMXact(checkPoint.nextMulti,
                                  checkPoint.nextMultiOffset);
 
        /*
         * NB: This may perform multixact truncation when replaying WAL
         * generated by an older primary.
         */
        MultiXactAdvanceOldest(checkPoint.oldestMulti,
                               checkPoint.oldestMultiDB);
        if (TransactionIdPrecedes(TransamVariables->oldestXid,
                                  checkPoint.oldestXid))
            SetTransactionIdLimit(checkPoint.oldestXid,
                                  checkPoint.oldestXidDB);
        /* ControlFile->checkPointCopy always tracks the latest ckpt XID */
        LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
        ControlFile->checkPointCopy.nextXid = checkPoint.nextXid;
        LWLockRelease(ControlFileLock);
 
        /* Update shared-memory copy of checkpoint XID/epoch */
        SpinLockAcquire(&XLogCtl->info_lck);
        XLogCtl->ckptFullXid = checkPoint.nextXid;
        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",
                            checkPoint.ThisTimeLineID, replayTLI)));
 
        RecoveryRestartPoint(&checkPoint, record);
    }
    else if (info == XLOG_OVERWRITE_CONTRECORD)
    {
        /* 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));
 
        /*
         * For Hot Standby, we could treat this like a Shutdown Checkpoint,
         * but this case is rarer and harder to test, so the benefit doesn't
         * outweigh the potential extra cost of maintenance.
         */
 
        /*
         * 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",
                            xlrec.ThisTimeLineID, replayTLI)));
    }
    else if (info == XLOG_NOOP)
    {
        /* nothing to do here */
    }
    else if (info == XLOG_SWITCH)
    {
        /* nothing to do here */
    }
    else if (info == XLOG_RESTORE_POINT)
    {
        /* nothing to do here, handled in xlogrecovery.c */
    }
    else if (info == XLOG_FPI || info == XLOG_FPI_FOR_HINT)
    {
        /*
         * XLOG_FPI records contain nothing else but one or more block
         * references. Every block reference must include a full-page image
         * even if full_page_writes was disabled when the record was generated
         * - otherwise there would be no point in this record.
         *
         * XLOG_FPI_FOR_HINT records are generated when a page needs to be
         * WAL-logged because of a hint bit update. They are only generated
         * when checksums and/or wal_log_hints are enabled. They may include
         * no full-page images if full_page_writes was disabled when they were
         * generated. In this case there is nothing to do here.
         *
         * No recovery conflicts are generated by these generic records - if a
         * resource manager needs to generate conflicts, it has to define a
         * separate WAL record type and redo routine.
         */
        for (uint8 block_id = 0; block_id <= XLogRecMaxBlockId(record); block_id++)
        {
            Buffer      buffer;
 
            if (!XLogRecHasBlockImage(record, block_id))
            {
                if (info == XLOG_FPI)
                    elog(ERROR, "XLOG_FPI record did not contain a full-page image");
                continue;
            }
 
            if (XLogReadBufferForRedo(record, block_id, &buffer) != BLK_RESTORED)
                elog(ERROR, "unexpected XLogReadBufferForRedo result when restoring backup block");
            UnlockReleaseBuffer(buffer);
        }
    }
    else if (info == XLOG_BACKUP_END)
    {
        /* nothing to do here, handled in xlogrecovery_redo() */
    }
    else if (info == XLOG_PARAMETER_CHANGE)
    {
        xl_parameter_change xlrec;
 
        /* Update our copy of the parameters in pg_control */
        memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_parameter_change));
 
        /*
         * Invalidate logical slots if we are in hot standby and the primary
         * does not have a WAL level sufficient for logical decoding. No need
         * to search for potentially conflicting logically slots if standby is
         * running with wal_level lower than logical, because in that case, we
         * would have either disallowed creation of logical slots or
         * invalidated existing ones.
         */
        if (InRecovery && InHotStandby &&
            xlrec.wal_level < WAL_LEVEL_LOGICAL &&
            wal_level >= WAL_LEVEL_LOGICAL)
            InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_LEVEL,
                                               0, InvalidOid,
                                               InvalidTransactionId);
 
        LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
        ControlFile->MaxConnections = xlrec.MaxConnections;
        ControlFile->max_worker_processes = xlrec.max_worker_processes;
        ControlFile->max_wal_senders = xlrec.max_wal_senders;
        ControlFile->max_prepared_xacts = xlrec.max_prepared_xacts;
        ControlFile->max_locks_per_xact = xlrec.max_locks_per_xact;
        ControlFile->wal_level = xlrec.wal_level;
        ControlFile->wal_log_hints = xlrec.wal_log_hints;
 
        /*
         * Update minRecoveryPoint to ensure that if recovery is aborted, we
         * recover back up to this point before allowing hot standby again.
         * This is important if the max_* settings are decreased, to ensure
         * you don't run queries against the WAL preceding the change. The
         * local copies cannot be updated as long as crash recovery is
         * happening and we expect all the WAL to be replayed.
         */
        if (InArchiveRecovery)
        {
            LocalMinRecoveryPoint = ControlFile->minRecoveryPoint;
            LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
        }
        if (LocalMinRecoveryPoint != InvalidXLogRecPtr && LocalMinRecoveryPoint < lsn)
        {
            TimeLineID  replayTLI;
 
            (void) GetCurrentReplayRecPtr(&replayTLI);
            ControlFile->minRecoveryPoint = lsn;
            ControlFile->minRecoveryPointTLI = replayTLI;
        }
 
        CommitTsParameterChange(xlrec.track_commit_timestamp,
                                ControlFile->track_commit_timestamp);
        ControlFile->track_commit_timestamp = xlrec.track_commit_timestamp;
 
        UpdateControlFile();
        LWLockRelease(ControlFileLock);
 
        /* Check to see if any parameter change gives a problem on recovery */
        CheckRequiredParameterValues();
    }
    else if (info == XLOG_FPW_CHANGE)
    {
        bool        fpw;
 
        memcpy(&fpw, XLogRecGetData(record), sizeof(bool));
 
        /*
         * Update the LSN of the last replayed XLOG_FPW_CHANGE record so that
         * do_pg_backup_start() and do_pg_backup_stop() can check whether
         * full_page_writes has been disabled during online backup.
         */
        if (!fpw)
        {
            SpinLockAcquire(&XLogCtl->info_lck);
            if (XLogCtl->lastFpwDisableRecPtr < record->ReadRecPtr)
                XLogCtl->lastFpwDisableRecPtr = record->ReadRecPtr;
            SpinLockRelease(&XLogCtl->info_lck);
        }
 
        /* Keep track of full_page_writes */
        lastFullPageWrites = fpw;
    }
    else if (info == XLOG_CHECKPOINT_REDO)
    {
        /* nothing to do here, just for informational purposes */
    }
}

◆ XLogBackgroundFlush()

bool XLogBackgroundFlush ( void )

Definition at line 3111 of file xlog.c.

{
    XLogwrtRqst WriteRqst;
    bool        flexible = true;
    static TimestampTz lastflush;
    TimestampTz now;
    int         flushblocks;
    TimeLineID  insertTLI;
 
    /* XLOG doesn't need flushing during recovery */
    if (RecoveryInProgress())
        return false;
 
    /*
     * Since we're not in recovery, InsertTimeLineID is set and can't change,
     * so we can read it without a lock.
     */
    insertTLI = XLogCtl->InsertTimeLineID;
 
    /* read updated LogwrtRqst */
    SpinLockAcquire(&XLogCtl->info_lck);
    WriteRqst = XLogCtl->LogwrtRqst;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /* back off to last completed page boundary */
    WriteRqst.Write -= WriteRqst.Write % XLOG_BLCKSZ;
 
    /* if we have already flushed that far, consider async commit records */
    RefreshXLogWriteResult(LogwrtResult);
    if (WriteRqst.Write <= LogwrtResult.Flush)
    {
        SpinLockAcquire(&XLogCtl->info_lck);
        WriteRqst.Write = XLogCtl->asyncXactLSN;
        SpinLockRelease(&XLogCtl->info_lck);
        flexible = false;       /* ensure it all gets written */
    }
 
    /*
     * If already known flushed, we're done. Just need to check if we are
     * holding an open file handle to a logfile that's no longer in use,
     * preventing the file from being deleted.
     */
    if (WriteRqst.Write <= LogwrtResult.Flush)
    {
        if (openLogFile >= 0)
        {
            if (!XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo,
                                 wal_segment_size))
            {
                XLogFileClose();
            }
        }
        return false;
    }
 
    /*
     * Determine how far to flush WAL, based on the wal_writer_delay and
     * wal_writer_flush_after GUCs.
     *
     * Note that XLogSetAsyncXactLSN() performs similar calculation based on
     * wal_writer_flush_after, to decide when to wake us up.  Make sure the
     * logic is the same in both places if you change this.
     */
    now = GetCurrentTimestamp();
    flushblocks =
        WriteRqst.Write / XLOG_BLCKSZ - LogwrtResult.Flush / XLOG_BLCKSZ;
 
    if (WalWriterFlushAfter == 0 || lastflush == 0)
    {
        /* first call, or block based limits disabled */
        WriteRqst.Flush = WriteRqst.Write;
        lastflush = now;
    }
    else if (TimestampDifferenceExceeds(lastflush, now, WalWriterDelay))
    {
        /*
         * Flush the writes at least every WalWriterDelay ms. This is
         * important to bound the amount of time it takes for an asynchronous
         * commit to hit disk.
         */
        WriteRqst.Flush = WriteRqst.Write;
        lastflush = now;
    }
    else if (flushblocks >= WalWriterFlushAfter)
    {
        /* exceeded wal_writer_flush_after blocks, flush */
        WriteRqst.Flush = WriteRqst.Write;
        lastflush = now;
    }
    else
    {
        /* no flushing, this time round */
        WriteRqst.Flush = 0;
    }
 
#ifdef WAL_DEBUG
    if (XLOG_DEBUG)
        elog(LOG, "xlog bg flush request write %X/%X; flush: %X/%X, current is write %X/%X; flush %X/%X",
             LSN_FORMAT_ARGS(WriteRqst.Write),
             LSN_FORMAT_ARGS(WriteRqst.Flush),
             LSN_FORMAT_ARGS(LogwrtResult.Write),
             LSN_FORMAT_ARGS(LogwrtResult.Flush));
#endif
 
    START_CRIT_SECTION();
 
    /* now wait for any in-progress insertions to finish and get write lock */
    WaitXLogInsertionsToFinish(WriteRqst.Write);
    LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);
    RefreshXLogWriteResult(LogwrtResult);
    if (WriteRqst.Write > LogwrtResult.Write ||
        WriteRqst.Flush > LogwrtResult.Flush)
    {
        XLogWrite(WriteRqst, insertTLI, flexible);
    }
    LWLockRelease(WALWriteLock);
 
    END_CRIT_SECTION();
 
    /* wake up walsenders now that we've released heavily contended locks */
    WalSndWakeupProcessRequests(true, !RecoveryInProgress());
 
    /*
     * Great, done. To take some work off the critical path, try to initialize
     * as many of the no-longer-needed WAL buffers for future use as we can.
     */
    AdvanceXLInsertBuffer(InvalidXLogRecPtr, insertTLI, true);
 
    /*
     * If we determined that we need to write data, but somebody else
     * wrote/flushed already, it should be considered as being active, to
     * avoid hibernating too early.
     */
    return true;
}

References AdvanceXLInsertBuffer(), XLogCtlData::asyncXactLSN, elog, END_CRIT_SECTION, XLogwrtRqst::Flush, XLogwrtResult::Flush, GetCurrentTimestamp(), XLogCtlData::info_lck, XLogCtlData::InsertTimeLineID, InvalidXLogRecPtr, LOG, LogwrtResult, XLogCtlData::LogwrtRqst, LSN_FORMAT_ARGS, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), now(), openLogFile, openLogSegNo, RecoveryInProgress(), RefreshXLogWriteResult, SpinLockAcquire, SpinLockRelease, START_CRIT_SECTION, TimestampDifferenceExceeds(), WaitXLogInsertionsToFinish(), wal_segment_size, WalSndWakeupProcessRequests(), WalWriterDelay, WalWriterFlushAfter, XLogwrtRqst::Write, XLogwrtResult::Write, XLByteInPrevSeg, XLogCtl, XLogFileClose(), and XLogWrite().

Referenced by WalSndWaitForWal(), and WalWriterMain().

◆ XLogCheckpointNeeded()

bool XLogCheckpointNeeded ( XLogSegNo new_segno )

Definition at line 2423 of file xlog.c.

{
    XLogSegNo   old_segno;
 
    XLByteToSeg(RedoRecPtr, old_segno, wal_segment_size);
 
    if (new_segno >= old_segno + (uint64) (CheckPointSegments - 1))
        return true;
    return false;
}

References CheckPointSegments, RedoRecPtr, wal_segment_size, and XLByteToSeg.

Referenced by XLogPageRead(), and XLogWrite().

◆ XLogFileInit()

int XLogFileInit	(	XLogSegNo	logsegno,
		TimeLineID	logtli
	)

Definition at line 3519 of file xlog.c.

{
    bool        ignore_added;
    char        path[MAXPGPATH];
    int         fd;
 
    Assert(logtli != 0);
 
    fd = XLogFileInitInternal(logsegno, logtli, &ignore_added, path);
    if (fd >= 0)
        return fd;
 
    /* Now open original target segment (might not be file I just made) */
    fd = BasicOpenFile(path, O_RDWR | PG_BINARY | O_CLOEXEC |
                       get_sync_bit(wal_sync_method));
    if (fd < 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));
    return fd;
}

References Assert(), BasicOpenFile(), ereport, errcode_for_file_access(), errmsg(), ERROR, fd(), get_sync_bit(), MAXPGPATH, O_CLOEXEC, PG_BINARY, wal_sync_method, and XLogFileInitInternal().

Referenced by BootStrapXLOG(), XLogInitNewTimeline(), XLogWalRcvWrite(), and XLogWrite().

◆ XLogFileOpen()

int XLogFileOpen	(	XLogSegNo	segno,
		TimeLineID	tli
	)

Definition at line 3757 of file xlog.c.

{
    char        path[MAXPGPATH];
    int         fd;
 
    XLogFilePath(path, tli, segno, wal_segment_size);
 
    fd = BasicOpenFile(path, O_RDWR | PG_BINARY | O_CLOEXEC |
                       get_sync_bit(wal_sync_method));
    if (fd < 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));
 
    return fd;
}

References BasicOpenFile(), ereport, errcode_for_file_access(), errmsg(), fd(), get_sync_bit(), MAXPGPATH, O_CLOEXEC, PANIC, PG_BINARY, wal_segment_size, wal_sync_method, and XLogFilePath().

Referenced by XLogWrite().

◆ XLogFlush()

void XLogFlush ( XLogRecPtr record )

Definition at line 2923 of file xlog.c.

{
    XLogRecPtr  WriteRqstPtr;
    XLogwrtRqst WriteRqst;
    TimeLineID  insertTLI = XLogCtl->InsertTimeLineID;
 
    /*
     * During REDO, we are reading not writing WAL.  Therefore, instead of
     * trying to flush the WAL, we should update minRecoveryPoint instead. We
     * test XLogInsertAllowed(), not InRecovery, because we need checkpointer
     * to act this way too, and because when it tries to write the
     * end-of-recovery checkpoint, it should indeed flush.
     */
    if (!XLogInsertAllowed())
    {
        UpdateMinRecoveryPoint(record, false);
        return;
    }
 
    /* Quick exit if already known flushed */
    if (record <= LogwrtResult.Flush)
        return;
 
#ifdef WAL_DEBUG
    if (XLOG_DEBUG)
        elog(LOG, "xlog flush request %X/%X; write %X/%X; flush %X/%X",
             LSN_FORMAT_ARGS(record),
             LSN_FORMAT_ARGS(LogwrtResult.Write),
             LSN_FORMAT_ARGS(LogwrtResult.Flush));
#endif
 
    START_CRIT_SECTION();
 
    /*
     * Since fsync is usually a horribly expensive operation, we try to
     * piggyback as much data as we can on each fsync: if we see any more data
     * entered into the xlog buffer, we'll write and fsync that too, so that
     * the final value of LogwrtResult.Flush is as large as possible. This
     * gives us some chance of avoiding another fsync immediately after.
     */
 
    /* initialize to given target; may increase below */
    WriteRqstPtr = record;
 
    /*
     * Now wait until we get the write lock, or someone else does the flush
     * for us.
     */
    for (;;)
    {
        XLogRecPtr  insertpos;
 
        /* done already? */
        RefreshXLogWriteResult(LogwrtResult);
        if (record <= LogwrtResult.Flush)
            break;
 
        /*
         * Before actually performing the write, wait for all in-flight
         * insertions to the pages we're about to write to finish.
         */
        SpinLockAcquire(&XLogCtl->info_lck);
        if (WriteRqstPtr < XLogCtl->LogwrtRqst.Write)
            WriteRqstPtr = XLogCtl->LogwrtRqst.Write;
        SpinLockRelease(&XLogCtl->info_lck);
        insertpos = WaitXLogInsertionsToFinish(WriteRqstPtr);
 
        /*
         * Try to get the write lock. If we can't get it immediately, wait
         * until it's released, and recheck if we still need to do the flush
         * or if the backend that held the lock did it for us already. This
         * helps to maintain a good rate of group committing when the system
         * is bottlenecked by the speed of fsyncing.
         */
        if (!LWLockAcquireOrWait(WALWriteLock, LW_EXCLUSIVE))
        {
            /*
             * The lock is now free, but we didn't acquire it yet. Before we
             * do, loop back to check if someone else flushed the record for
             * us already.
             */
            continue;
        }
 
        /* Got the lock; recheck whether request is satisfied */
        RefreshXLogWriteResult(LogwrtResult);
        if (record <= LogwrtResult.Flush)
        {
            LWLockRelease(WALWriteLock);
            break;
        }
 
        /*
         * Sleep before flush! By adding a delay here, we may give further
         * backends the opportunity to join the backlog of group commit
         * followers; this can significantly improve transaction throughput,
         * at the risk of increasing transaction latency.
         *
         * We do not sleep if enableFsync is not turned on, nor if there are
         * fewer than CommitSiblings other backends with active transactions.
         */
        if (CommitDelay > 0 && enableFsync &&
            MinimumActiveBackends(CommitSiblings))
        {
            pg_usleep(CommitDelay);
 
            /*
             * Re-check how far we can now flush the WAL. It's generally not
             * safe to call WaitXLogInsertionsToFinish while holding
             * WALWriteLock, because an in-progress insertion might need to
             * also grab WALWriteLock to make progress. But we know that all
             * the insertions up to insertpos have already finished, because
             * that's what the earlier WaitXLogInsertionsToFinish() returned.
             * We're only calling it again to allow insertpos to be moved
             * further forward, not to actually wait for anyone.
             */
            insertpos = WaitXLogInsertionsToFinish(insertpos);
        }
 
        /* try to write/flush later additions to XLOG as well */
        WriteRqst.Write = insertpos;
        WriteRqst.Flush = insertpos;
 
        XLogWrite(WriteRqst, insertTLI, false);
 
        LWLockRelease(WALWriteLock);
        /* done */
        break;
    }
 
    END_CRIT_SECTION();
 
    /* wake up walsenders now that we've released heavily contended locks */
    WalSndWakeupProcessRequests(true, !RecoveryInProgress());
 
    /*
     * If we still haven't flushed to the request point then we have a
     * problem; most likely, the requested flush point is past end of XLOG.
     * This has been seen to occur when a disk page has a corrupted LSN.
     *
     * Formerly we treated this as a PANIC condition, but that hurts the
     * system's robustness rather than helping it: we do not want to take down
     * the whole system due to corruption on one data page.  In particular, if
     * the bad page is encountered again during recovery then we would be
     * unable to restart the database at all!  (This scenario actually
     * happened in the field several times with 7.1 releases.)  As of 8.4, bad
     * LSNs encountered during recovery are UpdateMinRecoveryPoint's problem;
     * the only time we can reach here during recovery is while flushing the
     * end-of-recovery checkpoint record, and we don't expect that to have a
     * bad LSN.
     *
     * Note that for calls from xact.c, the ERROR will be promoted to PANIC
     * since xact.c calls this routine inside a critical section.  However,
     * calls from bufmgr.c are not within critical sections and so we will not
     * force a restart for a bad LSN on a data page.
     */
    if (LogwrtResult.Flush < record)
        elog(ERROR,
             "xlog flush request %X/%X is not satisfied --- flushed only to %X/%X",
             LSN_FORMAT_ARGS(record),
             LSN_FORMAT_ARGS(LogwrtResult.Flush));
}

References CommitDelay, CommitSiblings, elog, enableFsync, END_CRIT_SECTION, ERROR, XLogwrtRqst::Flush, XLogwrtResult::Flush, XLogCtlData::info_lck, XLogCtlData::InsertTimeLineID, LOG, LogwrtResult, XLogCtlData::LogwrtRqst, LSN_FORMAT_ARGS, LW_EXCLUSIVE, LWLockAcquireOrWait(), LWLockRelease(), MinimumActiveBackends(), pg_usleep(), RecoveryInProgress(), RefreshXLogWriteResult, SpinLockAcquire, SpinLockRelease, START_CRIT_SECTION, UpdateMinRecoveryPoint(), WaitXLogInsertionsToFinish(), WalSndWakeupProcessRequests(), XLogwrtRqst::Write, XLogwrtResult::Write, XLogCtl, XLogInsertAllowed(), and XLogWrite().

Referenced by CheckPointReplicationOrigin(), CreateCheckPoint(), CreateEndOfRecoveryRecord(), CreateOverwriteContrecordRecord(), dropdb(), EndPrepare(), finish_sync_worker(), FlushBuffer(), LogLogicalMessage(), pg_truncate_visibility_map(), RecordTransactionAbortPrepared(), RecordTransactionCommit(), RecordTransactionCommitPrepared(), RelationTruncate(), ReplicationSlotReserveWal(), replorigin_get_progress(), replorigin_session_get_progress(), SlruPhysicalWritePage(), smgr_redo(), write_relmap_file(), WriteMTruncateXlogRec(), WriteTruncateXlogRec(), xact_redo_abort(), xact_redo_commit(), XLogInsertRecord(), and XLogReportParameters().

◆ XLogGetLastRemovedSegno()

XLogSegNo XLogGetLastRemovedSegno ( void )

Definition at line 3897 of file xlog.c.

{
    XLogSegNo   lastRemovedSegNo;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    lastRemovedSegNo = XLogCtl->lastRemovedSegNo;
    SpinLockRelease(&XLogCtl->info_lck);
 
    return lastRemovedSegNo;
}

References XLogCtlData::info_lck, XLogCtlData::lastRemovedSegNo, SpinLockAcquire, SpinLockRelease, and XLogCtl.

Referenced by copy_replication_slot(), GetWALAvailability(), ReplicationSlotReserveWal(), and reserve_wal_for_local_slot().

◆ XLogGetOldestSegno()

XLogSegNo XLogGetOldestSegno ( TimeLineID tli )

Definition at line 3913 of file xlog.c.

{
    DIR        *xldir;
    struct dirent *xlde;
    XLogSegNo   oldest_segno = 0;
 
    xldir = AllocateDir(XLOGDIR);
    while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
    {
        TimeLineID  file_tli;
        XLogSegNo   file_segno;
 
        /* Ignore files that are not XLOG segments. */
        if (!IsXLogFileName(xlde->d_name))
            continue;
 
        /* Parse filename to get TLI and segno. */
        XLogFromFileName(xlde->d_name, &file_tli, &file_segno,
                         wal_segment_size);
 
        /* Ignore anything that's not from the TLI of interest. */
        if (tli != file_tli)
            continue;
 
        /* If it's the oldest so far, update oldest_segno. */
        if (oldest_segno == 0 || file_segno < oldest_segno)
            oldest_segno = file_segno;
    }
 
    FreeDir(xldir);
    return oldest_segno;
}

References AllocateDir(), dirent::d_name, FreeDir(), IsXLogFileName(), ReadDir(), wal_segment_size, XLOGDIR, and XLogFromFileName().

Referenced by GetOldestUnsummarizedLSN(), MaybeRemoveOldWalSummaries(), and reserve_wal_for_local_slot().

◆ XLogInsertAllowed()

bool XLogInsertAllowed ( void )

Definition at line 6577 of file xlog.c.

{
    /*
     * If value is "unconditionally true" or "unconditionally false", just
     * return it.  This provides the normal fast path once recovery is known
     * done.
     */
    if (LocalXLogInsertAllowed >= 0)
        return (bool) LocalXLogInsertAllowed;
 
    /*
     * Else, must check to see if we're still in recovery.
     */
    if (RecoveryInProgress())
        return false;
 
    /*
     * On exit from recovery, reset to "unconditionally true", since there is
     * no need to keep checking.
     */
    LocalXLogInsertAllowed = 1;
    return true;
}

References LocalXLogInsertAllowed, and RecoveryInProgress().

Referenced by XLogBeginInsert(), XLogFlush(), and XLogInsertRecord().

◆ XLogInsertRecord()

XLogRecPtr XLogInsertRecord	(	struct XLogRecData *	rdata,
		XLogRecPtr	fpw_lsn,
		uint8	flags,
		int	num_fpi,
		bool	topxid_included
	)

Definition at line 759 of file xlog.c.

{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    pg_crc32c   rdata_crc;
    bool        inserted;
    XLogRecord *rechdr = (XLogRecord *) rdata->data;
    uint8       info = rechdr->xl_info & ~XLR_INFO_MASK;
    WalInsertClass class = WALINSERT_NORMAL;
    XLogRecPtr  StartPos;
    XLogRecPtr  EndPos;
    bool        prevDoPageWrites = doPageWrites;
    TimeLineID  insertTLI;
 
    /* Does this record type require special handling? */
    if (unlikely(rechdr->xl_rmid == RM_XLOG_ID))
    {
        if (info == XLOG_SWITCH)
            class = WALINSERT_SPECIAL_SWITCH;
        else if (info == XLOG_CHECKPOINT_REDO)
            class = WALINSERT_SPECIAL_CHECKPOINT;
    }
 
    /* we assume that all of the record header is in the first chunk */
    Assert(rdata->len >= SizeOfXLogRecord);
 
    /* cross-check on whether we should be here or not */
    if (!XLogInsertAllowed())
        elog(ERROR, "cannot make new WAL entries during recovery");
 
    /*
     * Given that we're not in recovery, InsertTimeLineID is set and can't
     * change, so we can read it without a lock.
     */
    insertTLI = XLogCtl->InsertTimeLineID;
 
    /*----------
     *
     * We have now done all the preparatory work we can without holding a
     * lock or modifying shared state. From here on, inserting the new WAL
     * record to the shared WAL buffer cache is a two-step process:
     *
     * 1. Reserve the right amount of space from the WAL. The current head of
     *    reserved space is kept in Insert->CurrBytePos, and is protected by
     *    insertpos_lck.
     *
     * 2. Copy the record to the reserved WAL space. This involves finding the
     *    correct WAL buffer containing the reserved space, and copying the
     *    record in place. This can be done concurrently in multiple processes.
     *
     * To keep track of which insertions are still in-progress, each concurrent
     * inserter acquires an insertion lock. In addition to just indicating that
     * an insertion is in progress, the lock tells others how far the inserter
     * has progressed. There is a small fixed number of insertion locks,
     * determined by NUM_XLOGINSERT_LOCKS. When an inserter crosses a page
     * boundary, it updates the value stored in the lock to the how far it has
     * inserted, to allow the previous buffer to be flushed.
     *
     * Holding onto an insertion lock also protects RedoRecPtr and
     * fullPageWrites from changing until the insertion is finished.
     *
     * Step 2 can usually be done completely in parallel. If the required WAL
     * page is not initialized yet, you have to go through AdvanceXLInsertBuffer,
     * which will ensure it is initialized. But the WAL writer tries to do that
     * ahead of insertions to avoid that from happening in the critical path.
     *
     *----------
     */
    START_CRIT_SECTION();
 
    if (likely(class == WALINSERT_NORMAL))
    {
        WALInsertLockAcquire();
 
        /*
         * Check to see if my copy of RedoRecPtr is out of date. If so, may
         * have to go back and have the caller recompute everything. This can
         * only happen just after a checkpoint, so it's better to be slow in
         * this case and fast otherwise.
         *
         * Also check to see if fullPageWrites was just turned on or there's a
         * running backup (which forces full-page writes); if we weren't
         * already doing full-page writes then go back and recompute.
         *
         * If we aren't doing full-page writes then RedoRecPtr doesn't
         * actually affect the contents of the XLOG record, so we'll update
         * our local copy but not force a recomputation.  (If doPageWrites was
         * just turned off, we could recompute the record without full pages,
         * but we choose not to bother.)
         */
        if (RedoRecPtr != Insert->RedoRecPtr)
        {
            Assert(RedoRecPtr < Insert->RedoRecPtr);
            RedoRecPtr = Insert->RedoRecPtr;
        }
        doPageWrites = (Insert->fullPageWrites || Insert->runningBackups > 0);
 
        if (doPageWrites &&
            (!prevDoPageWrites ||
             (fpw_lsn != InvalidXLogRecPtr && fpw_lsn <= RedoRecPtr)))
        {
            /*
             * Oops, some buffer now needs to be backed up that the caller
             * didn't back up.  Start over.
             */
            WALInsertLockRelease();
            END_CRIT_SECTION();
            return InvalidXLogRecPtr;
        }
 
        /*
         * Reserve space for the record in the WAL. This also sets the xl_prev
         * pointer.
         */
        ReserveXLogInsertLocation(rechdr->xl_tot_len, &StartPos, &EndPos,
                                  &rechdr->xl_prev);
 
        /* Normal records are always inserted. */
        inserted = true;
    }
    else if (class == WALINSERT_SPECIAL_SWITCH)
    {
        /*
         * In order to insert an XLOG_SWITCH record, we need to hold all of
         * the WAL insertion locks, not just one, so that no one else can
         * begin inserting a record until we've figured out how much space
         * remains in the current WAL segment and claimed all of it.
         *
         * Nonetheless, this case is simpler than the normal cases handled
         * below, which must check for changes in doPageWrites and RedoRecPtr.
         * Those checks are only needed for records that can contain buffer
         * references, and an XLOG_SWITCH record never does.
         */
        Assert(fpw_lsn == InvalidXLogRecPtr);
        WALInsertLockAcquireExclusive();
        inserted = ReserveXLogSwitch(&StartPos, &EndPos, &rechdr->xl_prev);
    }
    else
    {
        Assert(class == WALINSERT_SPECIAL_CHECKPOINT);
 
        /*
         * We need to update both the local and shared copies of RedoRecPtr,
         * which means that we need to hold all the WAL insertion locks.
         * However, there can't be any buffer references, so as above, we need
         * not check RedoRecPtr before inserting the record; we just need to
         * update it afterwards.
         */
        Assert(fpw_lsn == InvalidXLogRecPtr);
        WALInsertLockAcquireExclusive();
        ReserveXLogInsertLocation(rechdr->xl_tot_len, &StartPos, &EndPos,
                                  &rechdr->xl_prev);
        RedoRecPtr = Insert->RedoRecPtr = StartPos;
        inserted = true;
    }
 
    if (inserted)
    {
        /*
         * Now that xl_prev has been filled in, calculate CRC of the record
         * header.
         */
        rdata_crc = rechdr->xl_crc;
        COMP_CRC32C(rdata_crc, rechdr, offsetof(XLogRecord, xl_crc));
        FIN_CRC32C(rdata_crc);
        rechdr->xl_crc = rdata_crc;
 
        /*
         * All the record data, including the header, is now ready to be
         * inserted. Copy the record in the space reserved.
         */
        CopyXLogRecordToWAL(rechdr->xl_tot_len,
                            class == WALINSERT_SPECIAL_SWITCH, rdata,
                            StartPos, EndPos, insertTLI);
 
        /*
         * Unless record is flagged as not important, update LSN of last
         * important record in the current slot. When holding all locks, just
         * update the first one.
         */
        if ((flags & XLOG_MARK_UNIMPORTANT) == 0)
        {
            int         lockno = holdingAllLocks ? 0 : MyLockNo;
 
            WALInsertLocks[lockno].l.lastImportantAt = StartPos;
        }
    }
    else
    {
        /*
         * This was an xlog-switch record, but the current insert location was
         * already exactly at the beginning of a segment, so there was no need
         * to do anything.
         */
    }
 
    /*
     * Done! Let others know that we're finished.
     */
    WALInsertLockRelease();
 
    END_CRIT_SECTION();
 
    MarkCurrentTransactionIdLoggedIfAny();
 
    /*
     * Mark top transaction id is logged (if needed) so that we should not try
     * to log it again with the next WAL record in the current subtransaction.
     */
    if (topxid_included)
        MarkSubxactTopXidLogged();
 
    /*
     * Update shared LogwrtRqst.Write, if we crossed page boundary.
     */
    if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ)
    {
        SpinLockAcquire(&XLogCtl->info_lck);
        /* advance global request to include new block(s) */
        if (XLogCtl->LogwrtRqst.Write < EndPos)
            XLogCtl->LogwrtRqst.Write = EndPos;
        SpinLockRelease(&XLogCtl->info_lck);
        RefreshXLogWriteResult(LogwrtResult);
    }
 
    /*
     * If this was an XLOG_SWITCH record, flush the record and the empty
     * padding space that fills the rest of the segment, and perform
     * end-of-segment actions (eg, notifying archiver).
     */
    if (class == WALINSERT_SPECIAL_SWITCH)
    {
        TRACE_POSTGRESQL_WAL_SWITCH();
        XLogFlush(EndPos);
 
        /*
         * Even though we reserved the rest of the segment for us, which is
         * reflected in EndPos, we return a pointer to just the end of the
         * xlog-switch record.
         */
        if (inserted)
        {
            EndPos = StartPos + SizeOfXLogRecord;
            if (StartPos / XLOG_BLCKSZ != EndPos / XLOG_BLCKSZ)
            {
                uint64      offset = XLogSegmentOffset(EndPos, wal_segment_size);
 
                if (offset == EndPos % XLOG_BLCKSZ)
                    EndPos += SizeOfXLogLongPHD;
                else
                    EndPos += SizeOfXLogShortPHD;
            }
        }
    }
 
#ifdef WAL_DEBUG
    if (XLOG_DEBUG)
    {
        static XLogReaderState *debug_reader = NULL;
        XLogRecord *record;
        DecodedXLogRecord *decoded;
        StringInfoData buf;
        StringInfoData recordBuf;
        char       *errormsg = NULL;
        MemoryContext oldCxt;
 
        oldCxt = MemoryContextSwitchTo(walDebugCxt);
 
        initStringInfo(&buf);
        appendStringInfo(&buf, "INSERT @ %X/%X: ", LSN_FORMAT_ARGS(EndPos));
 
        /*
         * We have to piece together the WAL record data from the XLogRecData
         * entries, so that we can pass it to the rm_desc function as one
         * contiguous chunk.
         */
        initStringInfo(&recordBuf);
        for (; rdata != NULL; rdata = rdata->next)
            appendBinaryStringInfo(&recordBuf, rdata->data, rdata->len);
 
        /* We also need temporary space to decode the record. */
        record = (XLogRecord *) recordBuf.data;
        decoded = (DecodedXLogRecord *)
            palloc(DecodeXLogRecordRequiredSpace(record->xl_tot_len));
 
        if (!debug_reader)
            debug_reader = XLogReaderAllocate(wal_segment_size, NULL,
                                              XL_ROUTINE(.page_read = NULL,
                                                         .segment_open = NULL,
                                                         .segment_close = NULL),
                                              NULL);
        if (!debug_reader)
        {
            appendStringInfoString(&buf, "error decoding record: out of memory while allocating a WAL reading processor");
        }
        else if (!DecodeXLogRecord(debug_reader,
                                   decoded,
                                   record,
                                   EndPos,
                                   &errormsg))
        {
            appendStringInfo(&buf, "error decoding record: %s",
                             errormsg ? errormsg : "no error message");
        }
        else
        {
            appendStringInfoString(&buf, " - ");
 
            debug_reader->record = decoded;
            xlog_outdesc(&buf, debug_reader);
            debug_reader->record = NULL;
        }
        elog(LOG, "%s", buf.data);
 
        pfree(decoded);
        pfree(buf.data);
        pfree(recordBuf.data);
        MemoryContextSwitchTo(oldCxt);
    }
#endif
 
    /*
     * Update our global variables
     */
    ProcLastRecPtr = StartPos;
    XactLastRecEnd = EndPos;
 
    /* Report WAL traffic to the instrumentation. */
    if (inserted)
    {
        pgWalUsage.wal_bytes += rechdr->xl_tot_len;
        pgWalUsage.wal_records++;
        pgWalUsage.wal_fpi += num_fpi;
    }
 
    return EndPos;
}

References appendBinaryStringInfo(), appendStringInfo(), appendStringInfoString(), Assert(), buf, COMP_CRC32C, CopyXLogRecordToWAL(), XLogRecData::data, StringInfoData::data, DecodeXLogRecord(), DecodeXLogRecordRequiredSpace(), doPageWrites, elog, END_CRIT_SECTION, ERROR, FIN_CRC32C, holdingAllLocks, if(), XLogCtlData::info_lck, initStringInfo(), XLogCtlData::Insert, Insert(), XLogCtlData::InsertTimeLineID, InvalidXLogRecPtr, WALInsertLockPadded::l, WALInsertLock::lastImportantAt, XLogRecData::len, likely, LOG, LogwrtResult, XLogCtlData::LogwrtRqst, LSN_FORMAT_ARGS, MarkCurrentTransactionIdLoggedIfAny(), MarkSubxactTopXidLogged(), MemoryContextSwitchTo(), MyLockNo, XLogRecData::next, palloc(), pfree(), pgWalUsage, ProcLastRecPtr, XLogReaderState::record, RedoRecPtr, RefreshXLogWriteResult, ReserveXLogInsertLocation(), ReserveXLogSwitch(), SizeOfXLogLongPHD, SizeOfXLogRecord, SizeOfXLogShortPHD, SpinLockAcquire, SpinLockRelease, START_CRIT_SECTION, unlikely, WalUsage::wal_bytes, WalUsage::wal_fpi, WalUsage::wal_records, wal_segment_size, WALINSERT_NORMAL, WALINSERT_SPECIAL_CHECKPOINT, WALINSERT_SPECIAL_SWITCH, WALInsertLockAcquire(), WALInsertLockAcquireExclusive(), WALInsertLockRelease(), WALInsertLocks, XLogwrtRqst::Write, XactLastRecEnd, XLogRecord::xl_crc, XLogRecord::xl_info, XLogRecord::xl_prev, XLogRecord::xl_rmid, XL_ROUTINE, XLogRecord::xl_tot_len, XLOG_CHECKPOINT_REDO, XLOG_MARK_UNIMPORTANT, xlog_outdesc(), XLOG_SWITCH, XLogCtl, XLogFlush(), XLogInsertAllowed(), XLogReaderAllocate(), XLogSegmentOffset, and XLR_INFO_MASK.

Referenced by XLogInsert().

◆ XLogNeedsFlush()

bool XLogNeedsFlush ( XLogRecPtr record )

Definition at line 3254 of file xlog.c.

{
    /*
     * During recovery, we don't flush WAL but update minRecoveryPoint
     * instead. So "needs flush" is taken to mean whether minRecoveryPoint
     * would need to be updated.
     */
    if (RecoveryInProgress())
    {
        /*
         * An invalid minRecoveryPoint means that we need to recover all the
         * WAL, i.e., we're doing crash recovery.  We never modify the control
         * file's value in that case, so we can short-circuit future checks
         * here too.  This triggers a quick exit path for the startup process,
         * which cannot update its local copy of minRecoveryPoint as long as
         * it has not replayed all WAL available when doing crash recovery.
         */
        if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint) && InRecovery)
            updateMinRecoveryPoint = false;
 
        /* Quick exit if already known to be updated or cannot be updated */
        if (record <= LocalMinRecoveryPoint || !updateMinRecoveryPoint)
            return false;
 
        /*
         * Update local copy of minRecoveryPoint. But if the lock is busy,
         * just return a conservative guess.
         */
        if (!LWLockConditionalAcquire(ControlFileLock, LW_SHARED))
            return true;
        LocalMinRecoveryPoint = ControlFile->minRecoveryPoint;
        LocalMinRecoveryPointTLI = ControlFile->minRecoveryPointTLI;
        LWLockRelease(ControlFileLock);
 
        /*
         * Check minRecoveryPoint for any other process than the startup
         * process doing crash recovery, which should not update the control
         * file value if crash recovery is still running.
         */
        if (XLogRecPtrIsInvalid(LocalMinRecoveryPoint))
            updateMinRecoveryPoint = false;
 
        /* check again */
        if (record <= LocalMinRecoveryPoint || !updateMinRecoveryPoint)
            return false;
        else
            return true;
    }
 
    /* Quick exit if already known flushed */
    if (record <= LogwrtResult.Flush)
        return false;
 
    /* read LogwrtResult and update local state */
    RefreshXLogWriteResult(LogwrtResult);
 
    /* check again */
    if (record <= LogwrtResult.Flush)
        return false;
 
    return true;
}

References ControlFile, XLogwrtResult::Flush, InRecovery, LocalMinRecoveryPoint, LocalMinRecoveryPointTLI, LogwrtResult, LW_SHARED, LWLockConditionalAcquire(), LWLockRelease(), ControlFileData::minRecoveryPoint, ControlFileData::minRecoveryPointTLI, RecoveryInProgress(), RefreshXLogWriteResult, updateMinRecoveryPoint, and XLogRecPtrIsInvalid.

Referenced by GetVictimBuffer(), and SetHintBits().

◆ XLogPutNextOid()

void XLogPutNextOid ( Oid nextOid )

Definition at line 8211 of file xlog.c.

{
    XLogBeginInsert();
    XLogRegisterData(&nextOid, sizeof(Oid));
    (void) XLogInsert(RM_XLOG_ID, XLOG_NEXTOID);
 
    /*
     * We need not flush the NEXTOID record immediately, because any of the
     * just-allocated OIDs could only reach disk as part of a tuple insert or
     * update that would have its own XLOG record that must follow the NEXTOID
     * record.  Therefore, the standard buffer LSN interlock applied to those
     * records will ensure no such OID reaches disk before the NEXTOID record
     * does.
     *
     * Note, however, that the above statement only covers state "within" the
     * database.  When we use a generated OID as a file or directory name, we
     * are in a sense violating the basic WAL rule, because that filesystem
     * change may reach disk before the NEXTOID WAL record does.  The impact
     * of this is that if a database crash occurs immediately afterward, we
     * might after restart re-generate the same OID and find that it conflicts
     * with the leftover file or directory.  But since for safety's sake we
     * always loop until finding a nonconflicting filename, this poses no real
     * problem in practice. See pgsql-hackers discussion 27-Sep-2006.
     */
}

References XLOG_NEXTOID, XLogBeginInsert(), XLogInsert(), and XLogRegisterData().

Referenced by GetNewObjectId().

◆ XLogRestorePoint()

XLogRecPtr XLogRestorePoint ( const char * rpName )

Definition at line 8266 of file xlog.c.

{
    XLogRecPtr  RecPtr;
    xl_restore_point xlrec;
 
    xlrec.rp_time = GetCurrentTimestamp();
    strlcpy(xlrec.rp_name, rpName, MAXFNAMELEN);
 
    XLogBeginInsert();
    XLogRegisterData(&xlrec, sizeof(xl_restore_point));
 
    RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT);
 
    ereport(LOG,
            (errmsg("restore point \"%s\" created at %X/%X",
                    rpName, LSN_FORMAT_ARGS(RecPtr))));
 
    return RecPtr;
}

References ereport, errmsg(), GetCurrentTimestamp(), LOG, LSN_FORMAT_ARGS, MAXFNAMELEN, xl_restore_point::rp_name, xl_restore_point::rp_time, strlcpy(), XLOG_RESTORE_POINT, XLogBeginInsert(), XLogInsert(), and XLogRegisterData().

Referenced by pg_create_restore_point().

◆ XLogSetAsyncXactLSN()

void XLogSetAsyncXactLSN ( XLogRecPtr asyncXactLSN )

Definition at line 2752 of file xlog.c.

{
    XLogRecPtr  WriteRqstPtr = asyncXactLSN;
    bool        sleeping;
    bool        wakeup = false;
    XLogRecPtr  prevAsyncXactLSN;
 
    SpinLockAcquire(&XLogCtl->info_lck);
    sleeping = XLogCtl->WalWriterSleeping;
    prevAsyncXactLSN = XLogCtl->asyncXactLSN;
    if (XLogCtl->asyncXactLSN < asyncXactLSN)
        XLogCtl->asyncXactLSN = asyncXactLSN;
    SpinLockRelease(&XLogCtl->info_lck);
 
    /*
     * If somebody else already called this function with a more aggressive
     * LSN, they will have done what we needed (and perhaps more).
     */
    if (asyncXactLSN <= prevAsyncXactLSN)
        return;
 
    /*
     * If the WALWriter is sleeping, kick it to make it come out of low-power
     * mode, so that this async commit will reach disk within the expected
     * amount of time.  Otherwise, determine whether it has enough WAL
     * available to flush, the same way that XLogBackgroundFlush() does.
     */
    if (sleeping)
        wakeup = true;
    else
    {
        int         flushblocks;
 
        RefreshXLogWriteResult(LogwrtResult);
 
        flushblocks =
            WriteRqstPtr / XLOG_BLCKSZ - LogwrtResult.Flush / XLOG_BLCKSZ;
 
        if (WalWriterFlushAfter == 0 || flushblocks >= WalWriterFlushAfter)
            wakeup = true;
    }
 
    if (wakeup)
    {
        volatile PROC_HDR *procglobal = ProcGlobal;
        ProcNumber  walwriterProc = procglobal->walwriterProc;
 
        if (walwriterProc != INVALID_PROC_NUMBER)
            SetLatch(&GetPGProcByNumber(walwriterProc)->procLatch);
    }
}

References XLogCtlData::asyncXactLSN, XLogwrtResult::Flush, GetPGProcByNumber, XLogCtlData::info_lck, INVALID_PROC_NUMBER, LogwrtResult, ProcGlobal, RefreshXLogWriteResult, SetLatch(), SpinLockAcquire, SpinLockRelease, wakeup, WalWriterFlushAfter, PROC_HDR::walwriterProc, XLogCtlData::WalWriterSleeping, and XLogCtl.

Referenced by AbortTransaction(), LogCurrentRunningXacts(), RecordTransactionAbort(), and RecordTransactionCommit().

◆ XLogSetReplicationSlotMinimumLSN()

void XLogSetReplicationSlotMinimumLSN ( XLogRecPtr lsn )

Definition at line 2809 of file xlog.c.

{
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->replicationSlotMinLSN = lsn;
    SpinLockRelease(&XLogCtl->info_lck);
}

References XLogCtlData::info_lck, XLogCtlData::replicationSlotMinLSN, SpinLockAcquire, SpinLockRelease, and XLogCtl.

Referenced by ReplicationSlotsComputeRequiredLSN().

◆ XLOGShmemInit()

void XLOGShmemInit ( void )

Definition at line 5099 of file xlog.c.

{
    bool        foundCFile,
                foundXLog;
    char       *allocptr;
    int         i;
    ControlFileData *localControlFile;
 
#ifdef WAL_DEBUG
 
    /*
     * Create a memory context for WAL debugging that's exempt from the normal
     * "no pallocs in critical section" rule. Yes, that can lead to a PANIC if
     * an allocation fails, but wal_debug is not for production use anyway.
     */
    if (walDebugCxt == NULL)
    {
        walDebugCxt = AllocSetContextCreate(TopMemoryContext,
                                            "WAL Debug",
                                            ALLOCSET_DEFAULT_SIZES);
        MemoryContextAllowInCriticalSection(walDebugCxt, true);
    }
#endif
 
 
    XLogCtl = (XLogCtlData *)
        ShmemInitStruct("XLOG Ctl", XLOGShmemSize(), &foundXLog);
 
    localControlFile = ControlFile;
    ControlFile = (ControlFileData *)
        ShmemInitStruct("Control File", sizeof(ControlFileData), &foundCFile);
 
    if (foundCFile || foundXLog)
    {
        /* both should be present or neither */
        Assert(foundCFile && foundXLog);
 
        /* Initialize local copy of WALInsertLocks */
        WALInsertLocks = XLogCtl->Insert.WALInsertLocks;
 
        if (localControlFile)
            pfree(localControlFile);
        return;
    }
    memset(XLogCtl, 0, sizeof(XLogCtlData));
 
    /*
     * Already have read control file locally, unless in bootstrap mode. Move
     * contents into shared memory.
     */
    if (localControlFile)
    {
        memcpy(ControlFile, localControlFile, sizeof(ControlFileData));
        pfree(localControlFile);
    }
 
    /*
     * Since XLogCtlData contains XLogRecPtr fields, its sizeof should be a
     * multiple of the alignment for same, so no extra alignment padding is
     * needed here.
     */
    allocptr = ((char *) XLogCtl) + sizeof(XLogCtlData);
    XLogCtl->xlblocks = (pg_atomic_uint64 *) allocptr;
    allocptr += sizeof(pg_atomic_uint64) * XLOGbuffers;
 
    for (i = 0; i < XLOGbuffers; i++)
    {
        pg_atomic_init_u64(&XLogCtl->xlblocks[i], InvalidXLogRecPtr);
    }
 
    /* WAL insertion locks. Ensure they're aligned to the full padded size */
    allocptr += sizeof(WALInsertLockPadded) -
        ((uintptr_t) allocptr) % sizeof(WALInsertLockPadded);
    WALInsertLocks = XLogCtl->Insert.WALInsertLocks =
        (WALInsertLockPadded *) allocptr;
    allocptr += sizeof(WALInsertLockPadded) * NUM_XLOGINSERT_LOCKS;
 
    for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
    {
        LWLockInitialize(&WALInsertLocks[i].l.lock, LWTRANCHE_WAL_INSERT);
        pg_atomic_init_u64(&WALInsertLocks[i].l.insertingAt, InvalidXLogRecPtr);
        WALInsertLocks[i].l.lastImportantAt = InvalidXLogRecPtr;
    }
 
    /*
     * Align the start of the page buffers to a full xlog block size boundary.
     * This simplifies some calculations in XLOG insertion. It is also
     * required for O_DIRECT.
     */
    allocptr = (char *) TYPEALIGN(XLOG_BLCKSZ, allocptr);
    XLogCtl->pages = allocptr;
    memset(XLogCtl->pages, 0, (Size) XLOG_BLCKSZ * XLOGbuffers);
 
    /*
     * Do basic initialization of XLogCtl shared data. (StartupXLOG will fill
     * in additional info.)
     */
    XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
    XLogCtl->SharedRecoveryState = RECOVERY_STATE_CRASH;
    XLogCtl->InstallXLogFileSegmentActive = false;
    XLogCtl->WalWriterSleeping = false;
 
    SpinLockInit(&XLogCtl->Insert.insertpos_lck);
    SpinLockInit(&XLogCtl->info_lck);
    pg_atomic_init_u64(&XLogCtl->logInsertResult, InvalidXLogRecPtr);
    pg_atomic_init_u64(&XLogCtl->logWriteResult, InvalidXLogRecPtr);
    pg_atomic_init_u64(&XLogCtl->logFlushResult, InvalidXLogRecPtr);
    pg_atomic_init_u64(&XLogCtl->unloggedLSN, InvalidXLogRecPtr);
 
    pg_atomic_init_u64(&XLogCtl->InitializeReserved, InvalidXLogRecPtr);
    pg_atomic_init_u64(&XLogCtl->InitializedUpTo, InvalidXLogRecPtr);
    ConditionVariableInit(&XLogCtl->InitializedUpToCondVar);
}

References ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate, Assert(), ConditionVariableInit(), ControlFile, i, XLogCtlData::info_lck, XLogCtlData::InitializedUpTo, XLogCtlData::InitializedUpToCondVar, XLogCtlData::InitializeReserved, XLogCtlData::Insert, XLogCtlInsert::insertpos_lck, XLogCtlData::InstallXLogFileSegmentActive, InvalidXLogRecPtr, WALInsertLockPadded::l, WALInsertLock::lastImportantAt, XLogCtlData::logFlushResult, XLogCtlData::logInsertResult, XLogCtlData::logWriteResult, LWLockInitialize(), LWTRANCHE_WAL_INSERT, MemoryContextAllowInCriticalSection(), NUM_XLOGINSERT_LOCKS, XLogCtlData::pages, pfree(), pg_atomic_init_u64(), RECOVERY_STATE_CRASH, XLogCtlData::SharedRecoveryState, ShmemInitStruct(), SpinLockInit, TopMemoryContext, TYPEALIGN, XLogCtlData::unloggedLSN, XLogCtlInsert::WALInsertLocks, WALInsertLocks, XLogCtlData::WalWriterSleeping, XLogCtlData::xlblocks, XLOGbuffers, XLogCtlData::XLogCacheBlck, XLogCtl, and XLOGShmemSize().

Referenced by CreateOrAttachShmemStructs().

◆ XLOGShmemSize()

Size XLOGShmemSize ( void )

Definition at line 5049 of file xlog.c.

{
    Size        size;
 
    /*
     * If the value of wal_buffers is -1, use the preferred auto-tune value.
     * This isn't an amazingly clean place to do this, but we must wait till
     * NBuffers has received its final value, and must do it before using the
     * value of XLOGbuffers to do anything important.
     *
     * We prefer to report this value's source as PGC_S_DYNAMIC_DEFAULT.
     * However, if the DBA explicitly set wal_buffers = -1 in the config file,
     * then PGC_S_DYNAMIC_DEFAULT will fail to override that and we must force
     * the matter with PGC_S_OVERRIDE.
     */
    if (XLOGbuffers == -1)
    {
        char        buf[32];
 
        snprintf(buf, sizeof(buf), "%d", XLOGChooseNumBuffers());
        SetConfigOption("wal_buffers", buf, PGC_POSTMASTER,
                        PGC_S_DYNAMIC_DEFAULT);
        if (XLOGbuffers == -1)  /* failed to apply it? */
            SetConfigOption("wal_buffers", buf, PGC_POSTMASTER,
                            PGC_S_OVERRIDE);
    }
    Assert(XLOGbuffers > 0);
 
    /* XLogCtl */
    size = sizeof(XLogCtlData);
 
    /* WAL insertion locks, plus alignment */
    size = add_size(size, mul_size(sizeof(WALInsertLockPadded), NUM_XLOGINSERT_LOCKS + 1));
    /* xlblocks array */
    size = add_size(size, mul_size(sizeof(pg_atomic_uint64), XLOGbuffers));
    /* extra alignment padding for XLOG I/O buffers */
    size = add_size(size, Max(XLOG_BLCKSZ, PG_IO_ALIGN_SIZE));
    /* and the buffers themselves */
    size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers));
 
    /*
     * Note: we don't count ControlFileData, it comes out of the "slop factor"
     * added by CreateSharedMemoryAndSemaphores.  This lets us use this
     * routine again below to compute the actual allocation size.
     */
 
    return size;
}

References add_size(), Assert(), buf, Max, mul_size(), NUM_XLOGINSERT_LOCKS, PG_IO_ALIGN_SIZE, PGC_POSTMASTER, PGC_S_DYNAMIC_DEFAULT, PGC_S_OVERRIDE, SetConfigOption(), snprintf, XLOGbuffers, and XLOGChooseNumBuffers().

Referenced by CalculateShmemSize(), and XLOGShmemInit().

◆ XLogShutdownWalRcv()

void XLogShutdownWalRcv ( void )

Definition at line 9650 of file xlog.c.

{
    ShutdownWalRcv();
 
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    XLogCtl->InstallXLogFileSegmentActive = false;
    LWLockRelease(ControlFileLock);
}

References XLogCtlData::InstallXLogFileSegmentActive, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), ShutdownWalRcv(), and XLogCtl.

Referenced by FinishWalRecovery(), and WaitForWALToBecomeAvailable().

Variable Documentation

◆ CheckPointSegments

PGDLLIMPORT int CheckPointSegments

extern

Definition at line 156 of file xlog.c.

Referenced by CalculateCheckpointSegments(), IsCheckpointOnSchedule(), XLogCheckpointNeeded(), and XLogFileInitInternal().

◆ CheckpointStats

PGDLLIMPORT CheckpointStatsData CheckpointStats

extern

Definition at line 209 of file xlog.c.

Referenced by BufferSync(), CheckPointGuts(), CreateCheckPoint(), CreateRestartPoint(), LogCheckpointEnd(), PreallocXlogFiles(), ProcessSyncRequests(), RemoveXlogFile(), and SlruInternalWritePage().

◆ CommitDelay

PGDLLIMPORT int CommitDelay

extern

Definition at line 132 of file xlog.c.

Referenced by XLogFlush().

◆ CommitSiblings

PGDLLIMPORT int CommitSiblings

extern

Definition at line 133 of file xlog.c.

Referenced by XLogFlush().

◆ EnableHotStandby

PGDLLIMPORT bool EnableHotStandby

extern

Definition at line 121 of file xlog.c.

Referenced by BackendInitialize(), CheckRequiredParameterValues(), CreateRestartPoint(), ProcArrayShmemInit(), ProcArrayShmemSize(), process_pm_pmsignal(), RestoreSlotFromDisk(), StartupXLOG(), and validateRecoveryParameters().

◆ fullPageWrites

PGDLLIMPORT bool fullPageWrites

extern

Definition at line 122 of file xlog.c.

Referenced by BootStrapXLOG(), and UpdateFullPageWrites().

◆ log_checkpoints

PGDLLIMPORT bool log_checkpoints

extern

Definition at line 129 of file xlog.c.

Referenced by CheckPointTwoPhase(), CreateCheckPoint(), CreateRestartPoint(), LogCheckpointEnd(), and ProcessSyncRequests().

◆ max_slot_wal_keep_size_mb

PGDLLIMPORT int max_slot_wal_keep_size_mb

extern

Definition at line 135 of file xlog.c.

Referenced by KeepLogSeg(), and pg_get_replication_slots().

◆ max_wal_size_mb

PGDLLIMPORT int max_wal_size_mb

extern

Definition at line 114 of file xlog.c.

Referenced by assign_max_wal_size(), CalculateCheckpointSegments(), GetWALAvailability(), ReadControlFile(), and XLOGfileslop().

◆ min_wal_size_mb

PGDLLIMPORT int min_wal_size_mb

extern

Definition at line 115 of file xlog.c.

Referenced by ReadControlFile(), and XLOGfileslop().

◆ ProcLastRecPtr

PGDLLIMPORT XLogRecPtr ProcLastRecPtr

extern

Definition at line 253 of file xlog.c.

Referenced by CreateCheckPoint(), CreateOverwriteContrecordRecord(), EndPrepare(), and XLogInsertRecord().

◆ track_wal_io_timing

PGDLLIMPORT bool track_wal_io_timing

extern

Definition at line 137 of file xlog.c.

Referenced by issue_xlog_fsync(), pgstat_count_backend_io_op_time(), WALRead(), XLogFileInitInternal(), XLogPageRead(), XLogWalRcvWrite(), and XLogWrite().

◆ wal_compression

PGDLLIMPORT int wal_compression

extern

Definition at line 124 of file xlog.c.

Referenced by XLogCompressBackupBlock(), and XLogRecordAssemble().

◆ wal_consistency_checking

PGDLLIMPORT bool* wal_consistency_checking

extern

Definition at line 126 of file xlog.c.

Referenced by assign_wal_consistency_checking(), and XLogRecordAssemble().

◆ wal_consistency_checking_string

PGDLLIMPORT char* wal_consistency_checking_string

extern

Definition at line 125 of file xlog.c.

Referenced by InitializeWalConsistencyChecking().

◆ wal_decode_buffer_size

PGDLLIMPORT int wal_decode_buffer_size

extern

Definition at line 136 of file xlog.c.

Referenced by InitWalRecovery().

◆ wal_init_zero

PGDLLIMPORT bool wal_init_zero

extern

Definition at line 127 of file xlog.c.

Referenced by XLogFileInitInternal().

◆ wal_keep_size_mb

PGDLLIMPORT int wal_keep_size_mb

extern

Definition at line 116 of file xlog.c.

Referenced by KeepLogSeg(), and pg_get_replication_slots().

◆ wal_level

PGDLLIMPORT int wal_level

extern

◆ wal_log_hints

PGDLLIMPORT bool wal_log_hints

extern

Definition at line 123 of file xlog.c.

Referenced by InitControlFile(), and XLogReportParameters().

◆ wal_recycle

PGDLLIMPORT bool wal_recycle

extern

Definition at line 128 of file xlog.c.

Referenced by RemoveXlogFile().

◆ wal_retrieve_retry_interval

PGDLLIMPORT int wal_retrieve_retry_interval

extern

Definition at line 134 of file xlog.c.

Referenced by ApplyLauncherMain(), process_syncing_tables_for_apply(), and WaitForWALToBecomeAvailable().

◆ wal_segment_size

PGDLLIMPORT int wal_segment_size

extern

Definition at line 143 of file xlog.c.

Referenced by AdvanceXLInsertBuffer(), assign_wal_sync_method(), BootStrapXLOG(), build_backup_content(), CalculateCheckpointSegments(), CheckArchiveTimeout(), CheckXLogRemoved(), CleanupAfterArchiveRecovery(), copy_replication_slot(), CopyXLogRecordToWAL(), CreateCheckPoint(), CreateOverwriteContrecordRecord(), CreateRestartPoint(), do_pg_backup_stop(), ExecuteRecoveryCommand(), FinishWalRecovery(), GetOldestUnsummarizedLSN(), GetWALAvailability(), GetXLogBuffer(), InitWalRecovery(), InitXLogReaderState(), InstallXLogFileSegment(), InvalidateObsoleteReplicationSlots(), IsCheckpointOnSchedule(), issue_xlog_fsync(), KeepLogSeg(), MaybeRemoveOldWalSummaries(), perform_base_backup(), pg_control_checkpoint(), pg_get_replication_slots(), pg_split_walfile_name(), pg_walfile_name(), pg_walfile_name_offset(), PreallocXlogFiles(), ReadControlFile(), ReadRecord(), RemoveNonParentXlogFiles(), RemoveOldXlogFiles(), ReorderBufferRestoreChanges(), ReorderBufferRestoreCleanup(), ReorderBufferSerializedPath(), ReorderBufferSerializeTXN(), ReplicationSlotReserveWal(), RequestXLogStreaming(), reserve_wal_for_local_slot(), ReserveXLogSwitch(), RestoreArchivedFile(), StartReplication(), StartupDecodingContext(), SummarizeWAL(), UpdateLastRemovedPtr(), WALReadRaiseError(), WalReceiverMain(), WalSndSegmentOpen(), WriteControlFile(), XLogArchiveNotifySeg(), XLogBackgroundFlush(), XLogBytePosToEndRecPtr(), XLogBytePosToRecPtr(), XLogCheckpointNeeded(), XLOGChooseNumBuffers(), XLogFileClose(), XLogFileCopy(), XLogFileInitInternal(), XLogFileOpen(), XLogFileRead(), XLogFileReadAnyTLI(), XLOGfileslop(), XLogGetOldestSegno(), XLogInitNewTimeline(), XLogInsertRecord(), XLogPageRead(), XLogReaderAllocate(), XlogReadTwoPhaseData(), XLogRecPtrToBytePos(), XLogWalRcvClose(), XLogWalRcvWrite(), and XLogWrite().

◆ wal_sync_method

PGDLLIMPORT int wal_sync_method

extern

Definition at line 130 of file xlog.c.

Referenced by assign_wal_sync_method(), issue_xlog_fsync(), pg_fsync(), XLogFileInit(), XLogFileInitInternal(), XLogFileOpen(), and XLogWrite().

◆ XactLastCommitEnd

PGDLLIMPORT XLogRecPtr XactLastCommitEnd

extern

Definition at line 255 of file xlog.c.

Referenced by apply_handle_commit_internal(), apply_handle_commit_prepared(), apply_handle_stream_commit(), and RecordTransactionCommit().

◆ XactLastRecEnd

PGDLLIMPORT XLogRecPtr XactLastRecEnd

extern

Definition at line 254 of file xlog.c.

Referenced by AbortTransaction(), CommitTransaction(), dropdb(), PrepareTransaction(), RecordTransactionAbort(), RecordTransactionAbortPrepared(), RecordTransactionCommit(), RecordTransactionCommitPrepared(), WaitForParallelWorkersToFinish(), and XLogInsertRecord().

◆ XLogArchiveCommand

PGDLLIMPORT char* XLogArchiveCommand

extern

Definition at line 120 of file xlog.c.

Referenced by LoadArchiveLibrary(), ProcessPgArchInterrupts(), shell_archive_configured(), shell_archive_file(), and show_archive_command().

◆ XLogArchiveMode

PGDLLIMPORT int XLogArchiveMode

extern

Definition at line 119 of file xlog.c.

Referenced by KeepFileRestoredFromArchive(), PostmasterMain(), WalRcvFetchTimeLineHistoryFiles(), WalReceiverMain(), and XLogWalRcvClose().

◆ XLogArchiveTimeout

PGDLLIMPORT int XLogArchiveTimeout

extern

Definition at line 118 of file xlog.c.

Referenced by CheckArchiveTimeout(), and CheckpointerMain().

◆ XLOGbuffers

PGDLLIMPORT int XLOGbuffers

extern

Definition at line 117 of file xlog.c.

Referenced by AdvanceXLInsertBuffer(), check_wal_buffers(), XLOGShmemInit(), and XLOGShmemSize().

Data Structures

Macros

Typedefs

Enumerations

Functions

Variables

Macro Definition Documentation

◆ BACKUP_LABEL_FILE

◆ BACKUP_LABEL_OLD

◆ CHECKPOINT_CAUSE_TIME

◆ CHECKPOINT_CAUSE_XLOG

◆ CHECKPOINT_END_OF_RECOVERY

◆ CHECKPOINT_FLUSH_ALL

◆ CHECKPOINT_FORCE

◆ CHECKPOINT_IMMEDIATE

◆ CHECKPOINT_IS_SHUTDOWN

◆ CHECKPOINT_REQUESTED

◆ CHECKPOINT_WAIT

◆ PROMOTE_SIGNAL_FILE

◆ RECOVERY_SIGNAL_FILE

◆ STANDBY_SIGNAL_FILE

◆ TABLESPACE_MAP

◆ TABLESPACE_MAP_OLD

◆ XLOG_INCLUDE_ORIGIN

◆ XLOG_MARK_UNIMPORTANT

◆ XLogArchivingActive

◆ XLogArchivingAlways

◆ XLogHintBitIsNeeded

◆ XLogIsNeeded

◆ XLogLogicalInfoActive

◆ XLogStandbyInfoActive

Typedef Documentation

◆ ArchiveMode

◆ CheckpointStatsData

◆ RecoveryState

◆ SessionBackupState

◆ WALAvailability

◆ WalCompression

◆ WalLevel

Enumeration Type Documentation

◆ ArchiveMode

◆ RecoveryState

◆ SessionBackupState

◆ WALAvailability

◆ WalCompression

◆ WalLevel

◆ WalSyncMethod

Function Documentation

◆ BootStrapXLOG()

◆ CheckXLogRemoved()

◆ CreateCheckPoint()

◆ CreateRestartPoint()

◆ DataChecksumsEnabled()

◆ do_pg_abort_backup()

◆ do_pg_backup_start()

◆ do_pg_backup_stop()

◆ get_backup_status()

◆ GetActiveWalLevelOnStandby()

◆ GetDefaultCharSignedness()

◆ GetFakeLSNForUnloggedRel()

◆ GetFlushRecPtr()

◆ GetFullPageWriteInfo()

◆ GetInsertRecPtr()

◆ GetLastImportantRecPtr()

◆ GetMockAuthenticationNonce()

◆ GetRecoveryState()

◆ GetRedoRecPtr()

◆ GetSystemIdentifier()

◆ GetWALAvailability()

◆ GetWALInsertionTimeLine()

◆ GetWALInsertionTimeLineIfSet()

◆ GetXLogInsertRecPtr()

◆ GetXLogWriteRecPtr()

◆ InitializeWalConsistencyChecking()

◆ IsInstallXLogFileSegmentActive()

◆ issue_xlog_fsync()

◆ LocalProcessControlFile()

◆ ReachedEndOfBackup()

◆ RecoveryInProgress()

◆ register_persistent_abort_backup_handler()