xlog.c

Go to the documentation of this file.

/*-------------------------------------------------------------------------
 *
 * xlog.c
 *      PostgreSQL write-ahead log manager
 *
 *
 * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/backend/access/transam/xlog.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include <ctype.h>
#include <math.h>
#include <time.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <unistd.h>

#include "access/clog.h"
#include "access/commit_ts.h"
#include "access/heaptoast.h"
#include "access/multixact.h"
#include "access/rewriteheap.h"
#include "access/subtrans.h"
#include "access/timeline.h"
#include "access/transam.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog_internal.h"
#include "access/xlogarchive.h"
#include "access/xloginsert.h"
#include "access/xlogreader.h"
#include "access/xlogutils.h"
#include "catalog/catversion.h"
#include "catalog/pg_control.h"
#include "catalog/pg_database.h"
#include "commands/progress.h"
#include "commands/tablespace.h"
#include "common/controldata_utils.h"
#include "executor/instrument.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "port/atomics.h"
#include "port/pg_iovec.h"
#include "postmaster/bgwriter.h"
#include "postmaster/startup.h"
#include "postmaster/walwriter.h"
#include "replication/basebackup.h"
#include "replication/logical.h"
#include "replication/origin.h"
#include "replication/slot.h"
#include "replication/snapbuild.h"
#include "replication/walreceiver.h"
#include "replication/walsender.h"
#include "storage/bufmgr.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/large_object.h"
#include "storage/latch.h"
#include "storage/pmsignal.h"
#include "storage/predicate.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/reinit.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "storage/sync.h"
#include "utils/builtins.h"
#include "utils/guc.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/relmapper.h"
#include "utils/pg_rusage.h"
#include "utils/snapmgr.h"
#include "utils/timestamp.h"

extern uint32 bootstrap_data_checksum_version;

/* Unsupported old recovery command file names (relative to $PGDATA) */
#define RECOVERY_COMMAND_FILE   "recovery.conf"
#define RECOVERY_COMMAND_DONE   "recovery.done"

/* User-settable parameters */
int         max_wal_size_mb = 1024; /* 1 GB */
int         min_wal_size_mb = 80;   /* 80 MB */
int         wal_keep_size_mb = 0;
int         XLOGbuffers = -1;
int         XLogArchiveTimeout = 0;
int         XLogArchiveMode = ARCHIVE_MODE_OFF;
char       *XLogArchiveCommand = NULL;
bool        EnableHotStandby = false;
bool        fullPageWrites = true;
bool        wal_log_hints = false;
int         wal_compression = WAL_COMPRESSION_NONE;
char       *wal_consistency_checking_string = NULL;
bool       *wal_consistency_checking = NULL;
bool        wal_init_zero = true;
bool        wal_recycle = true;
bool        log_checkpoints = false;
int         sync_method = DEFAULT_SYNC_METHOD;
int         wal_level = WAL_LEVEL_MINIMAL;
int         CommitDelay = 0;    /* precommit delay in microseconds */
int         CommitSiblings = 5; /* # concurrent xacts needed to sleep */
int         wal_retrieve_retry_interval = 5000;
int         max_slot_wal_keep_size_mb = -1;
bool        track_wal_io_timing = false;

#ifdef WAL_DEBUG
bool        XLOG_DEBUG = false;
#endif

int         wal_segment_size = DEFAULT_XLOG_SEG_SIZE;

/*
 * Number of WAL insertion locks to use. A higher value allows more insertions
 * to happen concurrently, but adds some CPU overhead to flushing the WAL,
 * which needs to iterate all the locks.
 */
#define NUM_XLOGINSERT_LOCKS  8

/*
 * Max distance from last checkpoint, before triggering a new xlog-based
 * checkpoint.
 */
int         CheckPointSegments;

/* Estimated distance between checkpoints, in bytes */
static double CheckPointDistanceEstimate = 0;
static double PrevCheckPointDistance = 0;

/*
 * GUC support
 */
const struct config_enum_entry sync_method_options[] = {
    {"fsync", SYNC_METHOD_FSYNC, false},
#ifdef HAVE_FSYNC_WRITETHROUGH
    {"fsync_writethrough", SYNC_METHOD_FSYNC_WRITETHROUGH, false},
#endif
#ifdef HAVE_FDATASYNC
    {"fdatasync", SYNC_METHOD_FDATASYNC, false},
#endif
#ifdef OPEN_SYNC_FLAG
    {"open_sync", SYNC_METHOD_OPEN, false},
#endif
#ifdef OPEN_DATASYNC_FLAG
    {"open_datasync", SYNC_METHOD_OPEN_DSYNC, false},
#endif
    {NULL, 0, false}
};


/*
 * Although only "on", "off", and "always" are documented,
 * we accept all the likely variants of "on" and "off".
 */
const struct config_enum_entry archive_mode_options[] = {
    {"always", ARCHIVE_MODE_ALWAYS, false},
    {"on", ARCHIVE_MODE_ON, false},
    {"off", ARCHIVE_MODE_OFF, false},
    {"true", ARCHIVE_MODE_ON, true},
    {"false", ARCHIVE_MODE_OFF, true},
    {"yes", ARCHIVE_MODE_ON, true},
    {"no", ARCHIVE_MODE_OFF, true},
    {"1", ARCHIVE_MODE_ON, true},
    {"0", ARCHIVE_MODE_OFF, true},
    {NULL, 0, false}
};

const struct config_enum_entry recovery_target_action_options[] = {
    {"pause", RECOVERY_TARGET_ACTION_PAUSE, false},
    {"promote", RECOVERY_TARGET_ACTION_PROMOTE, false},
    {"shutdown", RECOVERY_TARGET_ACTION_SHUTDOWN, false},
    {NULL, 0, false}
};

/*
 * Statistics for current checkpoint are collected in this global struct.
 * Because only the checkpointer or a stand-alone backend can perform
 * checkpoints, this will be unused in normal backends.
 */
CheckpointStatsData CheckpointStats;

/*
 * ThisTimeLineID will be same in all backends --- it identifies current
 * WAL timeline for the database system.
 */
TimeLineID  ThisTimeLineID = 0;

static XLogRecPtr LastRec;

/* Local copy of WalRcv->flushedUpto */
static XLogRecPtr flushedUpto = 0;
static TimeLineID receiveTLI = 0;

/*
 * During recovery, lastFullPageWrites keeps track of full_page_writes that
 * the replayed WAL records indicate. It's initialized with full_page_writes
 * that the recovery starting checkpoint record indicates, and then updated
 * each time XLOG_FPW_CHANGE record is replayed.
 */
static bool lastFullPageWrites;

/*
 * Local copy of the state tracked by SharedRecoveryState in shared memory,
 * It is false if SharedRecoveryState is RECOVERY_STATE_DONE.  True actually
 * means "not known, need to check the shared state".
 */
static bool LocalRecoveryInProgress = true;

/*
 * Local copy of SharedHotStandbyActive variable. False actually means "not
 * known, need to check the shared state".
 */
static bool LocalHotStandbyActive = false;

/*
 * Local copy of SharedPromoteIsTriggered variable. False actually means "not
 * known, need to check the shared state".
 */
static bool LocalPromoteIsTriggered = false;

/*
 * Local state for XLogInsertAllowed():
 *      1: unconditionally allowed to insert XLOG
 *      0: unconditionally not allowed to insert XLOG
 *      -1: must check RecoveryInProgress(); disallow until it is false
 * Most processes start with -1 and transition to 1 after seeing that recovery
 * is not in progress.  But we can also force the value for special cases.
 * The coding in XLogInsertAllowed() depends on the first two of these states
 * being numerically the same as bool true and false.
 */
static int  LocalXLogInsertAllowed = -1;

/*
 * When ArchiveRecoveryRequested is set, archive recovery was requested,
 * ie. signal files were present. When InArchiveRecovery is set, we are
 * currently recovering using offline XLOG archives. These variables are only
 * valid in the startup process.
 *
 * When ArchiveRecoveryRequested is true, but InArchiveRecovery is false, we're
 * currently performing crash recovery using only XLOG files in pg_wal, but
 * will switch to using offline XLOG archives as soon as we reach the end of
 * WAL in pg_wal.
*/
bool        ArchiveRecoveryRequested = false;
bool        InArchiveRecovery = false;

static bool standby_signal_file_found = false;
static bool recovery_signal_file_found = false;

/* Buffers dedicated to consistency checks of size BLCKSZ */
static char *replay_image_masked = NULL;
static char *primary_image_masked = NULL;

/* options formerly taken from recovery.conf for archive recovery */
char       *recoveryRestoreCommand = NULL;
char       *recoveryEndCommand = NULL;
char       *archiveCleanupCommand = NULL;
RecoveryTargetType recoveryTarget = RECOVERY_TARGET_UNSET;
bool        recoveryTargetInclusive = true;
int         recoveryTargetAction = RECOVERY_TARGET_ACTION_PAUSE;
TransactionId recoveryTargetXid;
char       *recovery_target_time_string;
static TimestampTz recoveryTargetTime;
const char *recoveryTargetName;
XLogRecPtr  recoveryTargetLSN;
int         recovery_min_apply_delay = 0;

/* options formerly taken from recovery.conf for XLOG streaming */
bool        StandbyModeRequested = false;
char       *PrimaryConnInfo = NULL;
char       *PrimarySlotName = NULL;
char       *PromoteTriggerFile = NULL;
bool        wal_receiver_create_temp_slot = false;

/* are we currently in standby mode? */
bool        StandbyMode = false;

/*
 * if recoveryStopsBefore/After returns true, it saves information of the stop
 * point here
 */
static TransactionId recoveryStopXid;
static TimestampTz recoveryStopTime;
static XLogRecPtr recoveryStopLSN;
static char recoveryStopName[MAXFNAMELEN];
static bool recoveryStopAfter;

/*
 * During normal operation, the only timeline we care about is ThisTimeLineID.
 * During recovery, however, things are more complicated.  To simplify life
 * for rmgr code, we keep ThisTimeLineID set to the "current" timeline as we
 * scan through the WAL history (that is, it is the line that was active when
 * the currently-scanned WAL record was generated).  We also need these
 * timeline values:
 *
 * recoveryTargetTimeLineGoal: what the user requested, if any
 *
 * recoveryTargetTLIRequested: numeric value of requested timeline, if constant
 *
 * recoveryTargetTLI: the currently understood target timeline; changes
 *
 * expectedTLEs: a list of TimeLineHistoryEntries for recoveryTargetTLI and the timelines of
 * its known parents, newest first (so recoveryTargetTLI is always the
 * first list member).  Only these TLIs are expected to be seen in the WAL
 * segments we read, and indeed only these TLIs will be considered as
 * candidate WAL files to open at all.
 *
 * curFileTLI: the TLI appearing in the name of the current input WAL file.
 * (This is not necessarily the same as ThisTimeLineID, because we could
 * be scanning data that was copied from an ancestor timeline when the current
 * file was created.)  During a sequential scan we do not allow this value
 * to decrease.
 */
RecoveryTargetTimeLineGoal recoveryTargetTimeLineGoal = RECOVERY_TARGET_TIMELINE_LATEST;
TimeLineID  recoveryTargetTLIRequested = 0;
TimeLineID  recoveryTargetTLI = 0;
static List *expectedTLEs;
static TimeLineID curFileTLI;

/*
 * ProcLastRecPtr points to the start of the last XLOG record inserted by the
 * current backend.  It is updated for all inserts.  XactLastRecEnd points to
 * end+1 of the last record, and is reset when we end a top-level transaction,
 * or start a new one; so it can be used to tell if the current transaction has
 * created any XLOG records.
 *
 * While in parallel mode, this may not be fully up to date.  When committing,
 * a transaction can assume this covers all xlog records written either by the
 * user backend or by any parallel worker which was present at any point during
 * the transaction.  But when aborting, or when still in parallel mode, other
 * parallel backends may have written WAL records at later LSNs than the value
 * stored here.  The parallel leader advances its own copy, when necessary,
 * in WaitForParallelWorkersToFinish.
 */
XLogRecPtr  ProcLastRecPtr = InvalidXLogRecPtr;
XLogRecPtr  XactLastRecEnd = InvalidXLogRecPtr;
XLogRecPtr  XactLastCommitEnd = InvalidXLogRecPtr;

/*
 * RedoRecPtr is this backend's local copy of the REDO record pointer
 * (which is almost but not quite the same as a pointer to the most recent
 * CHECKPOINT record).  We update this from the shared-memory copy,
 * XLogCtl->Insert.RedoRecPtr, whenever we can safely do so (ie, when we
 * hold an insertion lock).  See XLogInsertRecord for details.  We are also
 * allowed to update from XLogCtl->RedoRecPtr if we hold the info_lck;
 * see GetRedoRecPtr.  A freshly spawned backend obtains the value during
 * InitXLOGAccess.
 */
static XLogRecPtr RedoRecPtr;

/*
 * doPageWrites is this backend's local copy of (forcePageWrites ||
 * fullPageWrites).  It is used together with RedoRecPtr to decide whether
 * a full-page image of a page need to be taken.
 */
static bool doPageWrites;

/* Has the recovery code requested a walreceiver wakeup? */
static bool doRequestWalReceiverReply;

/*
 * RedoStartLSN points to the checkpoint's REDO location which is specified
 * in a backup label file, backup history file or control file. In standby
 * mode, XLOG streaming usually starts from the position where an invalid
 * record was found. But if we fail to read even the initial checkpoint
 * record, we use the REDO location instead of the checkpoint location as
 * the start position of XLOG streaming. Otherwise we would have to jump
 * backwards to the REDO location after reading the checkpoint record,
 * because the REDO record can precede the checkpoint record.
 */
static XLogRecPtr RedoStartLSN = InvalidXLogRecPtr;

/*----------
 * Shared-memory data structures for XLOG control
 *
 * LogwrtRqst indicates a byte position that we need to write and/or fsync
 * the log up to (all records before that point must be written or fsynced).
 * LogwrtResult indicates the byte positions we have already written/fsynced.
 * These structs are identical but are declared separately to indicate their
 * slightly different functions.
 *
 * To read XLogCtl->LogwrtResult, you must hold either info_lck or
 * WALWriteLock.  To update it, you need to hold both locks.  The point of
 * this arrangement is that the value can be examined by code that already
 * holds WALWriteLock without needing to grab info_lck as well.  In addition
 * to the shared variable, each backend has a private copy of LogwrtResult,
 * which is updated when convenient.
 *
 * The request bookkeeping is simpler: there is a shared XLogCtl->LogwrtRqst
 * (protected by info_lck), but we don't need to cache any copies of it.
 *
 * info_lck is only held long enough to read/update the protected variables,
 * so it's a plain spinlock.  The other locks are held longer (potentially
 * over I/O operations), so we use LWLocks for them.  These locks are:
 *
 * WALBufMappingLock: must be held to replace a page in the WAL buffer cache.
 * It is only held while initializing and changing the mapping.  If the
 * contents of the buffer being replaced haven't been written yet, the mapping
 * lock is released while the write is done, and reacquired afterwards.
 *
 * WALWriteLock: must be held to write WAL buffers to disk (XLogWrite or
 * XLogFlush).
 *
 * ControlFileLock: must be held to read/update control file or create
 * new log file.
 *
 *----------
 */

typedef struct XLogwrtRqst
{
    XLogRecPtr  Write;          /* last byte + 1 to write out */
    XLogRecPtr  Flush;          /* last byte + 1 to flush */
} XLogwrtRqst;

typedef struct XLogwrtResult
{
    XLogRecPtr  Write;          /* last byte + 1 written out */
    XLogRecPtr  Flush;          /* last byte + 1 flushed */
} XLogwrtResult;

/*
 * Inserting to WAL is protected by a small fixed number of WAL insertion
 * locks. To insert to the WAL, you must hold one of the locks - it doesn't
 * matter which one. To lock out other concurrent insertions, you must hold
 * of them. Each WAL insertion lock consists of a lightweight lock, plus an
 * indicator of how far the insertion has progressed (insertingAt).
 *
 * The insertingAt values are read when a process wants to flush WAL from
 * the in-memory buffers to disk, to check that all the insertions to the
 * region the process is about to write out have finished. You could simply
 * wait for all currently in-progress insertions to finish, but the
 * insertingAt indicator allows you to ignore insertions to later in the WAL,
 * so that you only wait for the insertions that are modifying the buffers
 * you're about to write out.
 *
 * This isn't just an optimization. If all the WAL buffers are dirty, an
 * inserter that's holding a WAL insert lock might need to evict an old WAL
 * buffer, which requires flushing the WAL. If it's possible for an inserter
 * to block on another inserter unnecessarily, deadlock can arise when two
 * inserters holding a WAL insert lock wait for each other to finish their
 * insertion.
 *
 * Small WAL records that don't cross a page boundary never update the value,
 * the WAL record is just copied to the page and the lock is released. But
 * to avoid the deadlock-scenario explained above, the indicator is always
 * updated before sleeping while holding an insertion lock.
 *
 * lastImportantAt contains the LSN of the last important WAL record inserted
 * using a given lock. This value is used to detect if there has been
 * important WAL activity since the last time some action, like a checkpoint,
 * was performed - allowing to not repeat the action if not. The LSN is
 * updated for all insertions, unless the XLOG_MARK_UNIMPORTANT flag was
 * set. lastImportantAt is never cleared, only overwritten by the LSN of newer
 * records.  Tracking the WAL activity directly in WALInsertLock has the
 * advantage of not needing any additional locks to update the value.
 */
typedef struct
{
    LWLock      lock;
    XLogRecPtr  insertingAt;
    XLogRecPtr  lastImportantAt;
} WALInsertLock;

/*
 * All the WAL insertion locks are allocated as an array in shared memory. We
 * force the array stride to be a power of 2, which saves a few cycles in
 * indexing, but more importantly also ensures that individual slots don't
 * cross cache line boundaries. (Of course, we have to also ensure that the
 * array start address is suitably aligned.)
 */
typedef union WALInsertLockPadded
{
    WALInsertLock l;
    char        pad[PG_CACHE_LINE_SIZE];
} WALInsertLockPadded;

/*
 * State of an exclusive backup, necessary to control concurrent activities
 * across sessions when working on exclusive backups.
 *
 * EXCLUSIVE_BACKUP_NONE means that there is no exclusive backup actually
 * running, to be more precise pg_start_backup() is not being executed for
 * an exclusive backup and there is no exclusive backup in progress.
 * EXCLUSIVE_BACKUP_STARTING means that pg_start_backup() is starting an
 * exclusive backup.
 * EXCLUSIVE_BACKUP_IN_PROGRESS means that pg_start_backup() has finished
 * running and an exclusive backup is in progress. pg_stop_backup() is
 * needed to finish it.
 * EXCLUSIVE_BACKUP_STOPPING means that pg_stop_backup() is stopping an
 * exclusive backup.
 */
typedef enum ExclusiveBackupState
{
    EXCLUSIVE_BACKUP_NONE = 0,
    EXCLUSIVE_BACKUP_STARTING,
    EXCLUSIVE_BACKUP_IN_PROGRESS,
    EXCLUSIVE_BACKUP_STOPPING
} ExclusiveBackupState;

/*
 * Session status of running backup, used for sanity checks in SQL-callable
 * functions to start and stop backups.
 */
static SessionBackupState sessionBackupState = SESSION_BACKUP_NONE;

/*
 * Shared state data for WAL insertion.
 */
typedef struct XLogCtlInsert
{
    slock_t     insertpos_lck;  /* protects CurrBytePos and PrevBytePos */

    /*
     * CurrBytePos is the end of reserved WAL. The next record will be
     * inserted at that position. PrevBytePos is the start position of the
     * previously inserted (or rather, reserved) record - it is copied to the
     * prev-link of the next record. These are stored as "usable byte
     * positions" rather than XLogRecPtrs (see XLogBytePosToRecPtr()).
     */
    uint64      CurrBytePos;
    uint64      PrevBytePos;

    /*
     * Make sure the above heavily-contended spinlock and byte positions are
     * on their own cache line. In particular, the RedoRecPtr and full page
     * write variables below should be on a different cache line. They are
     * read on every WAL insertion, but updated rarely, and we don't want
     * those reads to steal the cache line containing Curr/PrevBytePos.
     */
    char        pad[PG_CACHE_LINE_SIZE];

    /*
     * fullPageWrites is the authoritative value used by all backends to
     * determine whether to write full-page image to WAL. This shared value,
     * instead of the process-local fullPageWrites, is required because, when
     * full_page_writes is changed by SIGHUP, we must WAL-log it before it
     * actually affects WAL-logging by backends.  Checkpointer sets at startup
     * or after SIGHUP.
     *
     * To read these fields, you must hold an insertion lock. To modify them,
     * you must hold ALL the locks.
     */
    XLogRecPtr  RedoRecPtr;     /* current redo point for insertions */
    bool        forcePageWrites;    /* forcing full-page writes for PITR? */
    bool        fullPageWrites;

    /*
     * exclusiveBackupState indicates the state of an exclusive backup (see
     * comments of ExclusiveBackupState for more details). nonExclusiveBackups
     * is a counter indicating the number of streaming base backups currently
     * in progress. forcePageWrites is set to true when either of these is
     * non-zero. lastBackupStart is the latest checkpoint redo location used
     * as a starting point for an online backup.
     */
    ExclusiveBackupState exclusiveBackupState;
    int         nonExclusiveBackups;
    XLogRecPtr  lastBackupStart;

    /*
     * WAL insertion locks.
     */
    WALInsertLockPadded *WALInsertLocks;
} XLogCtlInsert;

/*
 * Total shared-memory state for XLOG.
 */
typedef struct XLogCtlData
{
    XLogCtlInsert Insert;

    /* Protected by info_lck: */
    XLogwrtRqst LogwrtRqst;
    XLogRecPtr  RedoRecPtr;     /* a recent copy of Insert->RedoRecPtr */
    FullTransactionId ckptFullXid;  /* nextXid of latest checkpoint */
    XLogRecPtr  asyncXactLSN;   /* LSN of newest async commit/abort */
    XLogRecPtr  replicationSlotMinLSN;  /* oldest LSN needed by any slot */

    XLogSegNo   lastRemovedSegNo;   /* latest removed/recycled XLOG segment */

    /* Fake LSN counter, for unlogged relations. Protected by ulsn_lck. */
    XLogRecPtr  unloggedLSN;
    slock_t     ulsn_lck;

    /* Time and LSN of last xlog segment switch. Protected by WALWriteLock. */
    pg_time_t   lastSegSwitchTime;
    XLogRecPtr  lastSegSwitchLSN;

    /*
     * Protected by info_lck and WALWriteLock (you must hold either lock to
     * read it, but both to update)
     */
    XLogwrtResult LogwrtResult;

    /*
     * Latest initialized page in the cache (last byte position + 1).
     *
     * To change the identity of a buffer (and InitializedUpTo), you need to
     * hold WALBufMappingLock.  To change the identity of a buffer that's
     * still dirty, the old page needs to be written out first, and for that
     * you need WALWriteLock, and you need to ensure that there are no
     * in-progress insertions to the page by calling
     * WaitXLogInsertionsToFinish().
     */
    XLogRecPtr  InitializedUpTo;

    /*
     * These values do not change after startup, although the pointed-to pages
     * and xlblocks values certainly do.  xlblocks values are protected by
     * WALBufMappingLock.
     */
    char       *pages;          /* buffers for unwritten XLOG pages */
    XLogRecPtr *xlblocks;       /* 1st byte ptr-s + XLOG_BLCKSZ */
    int         XLogCacheBlck;  /* highest allocated xlog buffer index */

    /*
     * Shared copy of ThisTimeLineID. Does not change after end-of-recovery.
     * If we created a new timeline when the system was started up,
     * PrevTimeLineID is the old timeline's ID that we forked off from.
     * Otherwise it's equal to ThisTimeLineID.
     */
    TimeLineID  ThisTimeLineID;
    TimeLineID  PrevTimeLineID;

    /*
     * SharedRecoveryState indicates if we're still in crash or archive
     * recovery.  Protected by info_lck.
     */
    RecoveryState SharedRecoveryState;

    /*
     * SharedHotStandbyActive indicates if we allow hot standby queries to be
     * run.  Protected by info_lck.
     */
    bool        SharedHotStandbyActive;

    /*
     * InstallXLogFileSegmentActive indicates whether the checkpointer should
     * arrange for future segments by recycling and/or PreallocXlogFiles().
     * Protected by ControlFileLock.  Only the startup process changes it.  If
     * true, anyone can use InstallXLogFileSegment().  If false, the startup
     * process owns the exclusive right to install segments, by reading from
     * the archive and possibly replacing existing files.
     */
    bool        InstallXLogFileSegmentActive;

    /*
     * SharedPromoteIsTriggered indicates if a standby promotion has been
     * triggered.  Protected by info_lck.
     */
    bool        SharedPromoteIsTriggered;

    /*
     * WalWriterSleeping indicates whether the WAL writer is currently in
     * low-power mode (and hence should be nudged if an async commit occurs).
     * Protected by info_lck.
     */
    bool        WalWriterSleeping;

    /*
     * recoveryWakeupLatch is used to wake up the startup process to continue
     * WAL replay, if it is waiting for WAL to arrive or failover trigger file
     * to appear.
     *
     * Note that the startup process also uses another latch, its procLatch,
     * to wait for recovery conflict. If we get rid of recoveryWakeupLatch for
     * signaling the startup process in favor of using its procLatch, which
     * comports better with possible generic signal handlers using that latch.
     * But we should not do that because the startup process doesn't assume
     * that it's waken up by walreceiver process or SIGHUP signal handler
     * while it's waiting for recovery conflict. The separate latches,
     * recoveryWakeupLatch and procLatch, should be used for inter-process
     * communication for WAL replay and recovery conflict, respectively.
     */
    Latch       recoveryWakeupLatch;

    /*
     * During recovery, we keep a copy of the latest checkpoint record here.
     * lastCheckPointRecPtr points to start of checkpoint record and
     * lastCheckPointEndPtr points to end+1 of checkpoint record.  Used by the
     * checkpointer when it wants to create a restartpoint.
     *
     * Protected by info_lck.
     */
    XLogRecPtr  lastCheckPointRecPtr;
    XLogRecPtr  lastCheckPointEndPtr;
    CheckPoint  lastCheckPoint;

    /*
     * lastReplayedEndRecPtr points to end+1 of the last record successfully
     * replayed. When we're currently replaying a record, ie. in a redo
     * function, replayEndRecPtr points to the end+1 of the record being
     * replayed, otherwise it's equal to lastReplayedEndRecPtr.
     */
    XLogRecPtr  lastReplayedEndRecPtr;
    TimeLineID  lastReplayedTLI;
    XLogRecPtr  replayEndRecPtr;
    TimeLineID  replayEndTLI;
    /* timestamp of last COMMIT/ABORT record replayed (or being replayed) */
    TimestampTz recoveryLastXTime;

    /*
     * timestamp of when we started replaying the current chunk of WAL data,
     * only relevant for replication or archive recovery
     */
    TimestampTz currentChunkStartTime;
    /* Recovery pause state */
    RecoveryPauseState recoveryPauseState;
    ConditionVariable recoveryNotPausedCV;

    /*
     * lastFpwDisableRecPtr points to the start of the last replayed
     * XLOG_FPW_CHANGE record that instructs full_page_writes is disabled.
     */
    XLogRecPtr  lastFpwDisableRecPtr;

    slock_t     info_lck;       /* locks shared variables shown above */
} XLogCtlData;

static XLogCtlData *XLogCtl = NULL;

/* a private copy of XLogCtl->Insert.WALInsertLocks, for convenience */
static WALInsertLockPadded *WALInsertLocks = NULL;

/*
 * We maintain an image of pg_control in shared memory.
 */
static ControlFileData *ControlFile = NULL;

/*
 * Calculate the amount of space left on the page after 'endptr'. Beware
 * multiple evaluation!
 */
#define INSERT_FREESPACE(endptr)    \
    (((endptr) % XLOG_BLCKSZ == 0) ? 0 : (XLOG_BLCKSZ - (endptr) % XLOG_BLCKSZ))

/* Macro to advance to next buffer index. */
#define NextBufIdx(idx)     \
        (((idx) == XLogCtl->XLogCacheBlck) ? 0 : ((idx) + 1))

/*
 * XLogRecPtrToBufIdx returns the index of the WAL buffer that holds, or
 * would hold if it was in cache, the page containing 'recptr'.
 */
#define XLogRecPtrToBufIdx(recptr)  \
    (((recptr) / XLOG_BLCKSZ) % (XLogCtl->XLogCacheBlck + 1))

/*
 * These are the number of bytes in a WAL page usable for WAL data.
 */
#define UsableBytesInPage (XLOG_BLCKSZ - SizeOfXLogShortPHD)

/*
 * Convert values of GUCs measured in megabytes to equiv. segment count.
 * Rounds down.
 */
#define ConvertToXSegs(x, segsize)  XLogMBVarToSegs((x), (segsize))

/* The number of bytes in a WAL segment usable for WAL data. */
static int  UsableBytesInSegment;

/*
 * Private, possibly out-of-date copy of shared LogwrtResult.
 * See discussion above.
 */
static XLogwrtResult LogwrtResult = {0, 0};

/*
 * Codes indicating where we got a WAL file from during recovery, or where
 * to attempt to get one.
 */
typedef enum
{
    XLOG_FROM_ANY = 0,          /* request to read WAL from any source */
    XLOG_FROM_ARCHIVE,          /* restored using restore_command */
    XLOG_FROM_PG_WAL,           /* existing file in pg_wal */
    XLOG_FROM_STREAM            /* streamed from primary */
} XLogSource;

/* human-readable names for XLogSources, for debugging output */
static const char *const xlogSourceNames[] = {"any", "archive", "pg_wal", "stream"};

/*
 * openLogFile is -1 or a kernel FD for an open log file segment.
 * openLogSegNo identifies the segment.  These variables are only used to
 * write the XLOG, and so will normally refer to the active segment.
 * Note: call Reserve/ReleaseExternalFD to track consumption of this FD.
 */
static int  openLogFile = -1;
static XLogSegNo openLogSegNo = 0;

/*
 * These variables are used similarly to the ones above, but for reading
 * the XLOG.  readOff is the offset of the page just read, readLen
 * indicates how much of it has been read into readBuf, and readSource
 * indicates where we got the currently open file from.
 * Note: we could use Reserve/ReleaseExternalFD to track consumption of
 * this FD too; but it doesn't currently seem worthwhile, since the XLOG is
 * not read by general-purpose sessions.
 */
static int  readFile = -1;
static XLogSegNo readSegNo = 0;
static uint32 readOff = 0;
static uint32 readLen = 0;
static XLogSource readSource = XLOG_FROM_ANY;

/*
 * Keeps track of which source we're currently reading from. This is
 * different from readSource in that this is always set, even when we don't
 * currently have a WAL file open. If lastSourceFailed is set, our last
 * attempt to read from currentSource failed, and we should try another source
 * next.
 *
 * pendingWalRcvRestart is set when a config change occurs that requires a
 * walreceiver restart.  This is only valid in XLOG_FROM_STREAM state.
 */
static XLogSource currentSource = XLOG_FROM_ANY;
static bool lastSourceFailed = false;
static bool pendingWalRcvRestart = false;

typedef struct XLogPageReadPrivate
{
    int         emode;
    bool        fetching_ckpt;  /* are we fetching a checkpoint record? */
    bool        randAccess;
} XLogPageReadPrivate;

/*
 * These variables track when we last obtained some WAL data to process,
 * and where we got it from.  (XLogReceiptSource is initially the same as
 * readSource, but readSource gets reset to zero when we don't have data
 * to process right now.  It is also different from currentSource, which
 * also changes when we try to read from a source and fail, while
 * XLogReceiptSource tracks where we last successfully read some WAL.)
 */
static TimestampTz XLogReceiptTime = 0;
static XLogSource XLogReceiptSource = XLOG_FROM_ANY;

/* State information for XLOG reading */
static XLogRecPtr ReadRecPtr;   /* start of last record read */
static XLogRecPtr EndRecPtr;    /* end+1 of last record read */

/*
 * Local copies of equivalent fields in the control file.  When running
 * crash recovery, minRecoveryPoint is set to InvalidXLogRecPtr as we
 * expect to replay all the WAL available, and updateMinRecoveryPoint is
 * switched to false to prevent any updates while replaying records.
 * Those values are kept consistent as long as crash recovery runs.
 */
static XLogRecPtr minRecoveryPoint;
static TimeLineID minRecoveryPointTLI;
static bool updateMinRecoveryPoint = true;

/*
 * Have we reached a consistent database state? In crash recovery, we have
 * to replay all the WAL, so reachedConsistency is never set. During archive
 * recovery, the database is consistent once minRecoveryPoint is reached.
 */
bool        reachedConsistency = false;

static bool InRedo = false;

/* For WALInsertLockAcquire/Release functions */
static int  MyLockNo = 0;
static bool holdingAllLocks = false;

#ifdef WAL_DEBUG
static MemoryContext walDebugCxt = NULL;
#endif

static void readRecoverySignalFile(void);
static void validateRecoveryParameters(void);
static void exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog);
static bool recoveryStopsBefore(XLogReaderState *record);
static bool recoveryStopsAfter(XLogReaderState *record);
static char *getRecoveryStopReason(void);
static void ConfirmRecoveryPaused(void);
static void recoveryPausesHere(bool endOfRecovery);
static bool recoveryApplyDelay(XLogReaderState *record);
static void SetLatestXTime(TimestampTz xtime);
static void SetCurrentChunkStartTime(TimestampTz xtime);
static void CheckRequiredParameterValues(void);
static void XLogReportParameters(void);
static void checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI,
                                TimeLineID prevTLI);
static void LocalSetXLogInsertAllowed(void);
static void CreateEndOfRecoveryRecord(void);
static void CheckPointGuts(XLogRecPtr checkPointRedo, int flags);
static void KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo);
static XLogRecPtr XLogGetReplicationSlotMinimumLSN(void);

static void AdvanceXLInsertBuffer(XLogRecPtr upto, bool opportunistic);
static bool XLogCheckpointNeeded(XLogSegNo new_segno);
static void XLogWrite(XLogwrtRqst WriteRqst, bool flexible);
static bool InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
                                   bool find_free, XLogSegNo max_segno);
static int  XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli,
                         XLogSource source, bool notfoundOk);
static int  XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source);
static int  XLogPageRead(XLogReaderState *xlogreader, XLogRecPtr targetPagePtr,
                         int reqLen, XLogRecPtr targetRecPtr, char *readBuf);
static bool WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
                                        bool fetching_ckpt, XLogRecPtr tliRecPtr);
static void XLogShutdownWalRcv(void);
static int  emode_for_corrupt_record(int emode, XLogRecPtr RecPtr);
static void XLogFileClose(void);
static void PreallocXlogFiles(XLogRecPtr endptr);
static void RemoveTempXlogFiles(void);
static void RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr lastredoptr, XLogRecPtr endptr);
static void RemoveXlogFile(const char *segname, XLogSegNo recycleSegNo,
                           XLogSegNo *endlogSegNo);
static void UpdateLastRemovedPtr(char *filename);
static void ValidateXLOGDirectoryStructure(void);
static void CleanupBackupHistory(void);
static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force);
static XLogRecord *ReadRecord(XLogReaderState *xlogreader,
                              int emode, bool fetching_ckpt);
static void CheckRecoveryConsistency(void);
static XLogRecord *ReadCheckpointRecord(XLogReaderState *xlogreader,
                                        XLogRecPtr RecPtr, int whichChkpt, bool report);
static bool rescanLatestTimeLine(void);
static void InitControlFile(uint64 sysidentifier);
static void WriteControlFile(void);
static void ReadControlFile(void);
static char *str_time(pg_time_t tnow);
static void SetPromoteIsTriggered(void);
static bool CheckForStandbyTrigger(void);

#ifdef WAL_DEBUG
static void xlog_outrec(StringInfo buf, XLogReaderState *record);
#endif
static void xlog_block_info(StringInfo buf, XLogReaderState *record);
static void xlog_outdesc(StringInfo buf, XLogReaderState *record);
static void pg_start_backup_callback(int code, Datum arg);
static void pg_stop_backup_callback(int code, Datum arg);
static bool read_backup_label(XLogRecPtr *checkPointLoc,
                              bool *backupEndRequired, bool *backupFromStandby);
static bool read_tablespace_map(List **tablespaces);

static void rm_redo_error_callback(void *arg);
static int  get_sync_bit(int method);

static void CopyXLogRecordToWAL(int write_len, bool isLogSwitch,
                                XLogRecData *rdata,
                                XLogRecPtr StartPos, XLogRecPtr EndPos);
static void ReserveXLogInsertLocation(int size, XLogRecPtr *StartPos,
                                      XLogRecPtr *EndPos, XLogRecPtr *PrevPtr);
static bool ReserveXLogSwitch(XLogRecPtr *StartPos, XLogRecPtr *EndPos,
                              XLogRecPtr *PrevPtr);
static XLogRecPtr WaitXLogInsertionsToFinish(XLogRecPtr upto);
static char *GetXLogBuffer(XLogRecPtr ptr);
static XLogRecPtr XLogBytePosToRecPtr(uint64 bytepos);
static XLogRecPtr XLogBytePosToEndRecPtr(uint64 bytepos);
static uint64 XLogRecPtrToBytePos(XLogRecPtr ptr);
static void checkXLogConsistency(XLogReaderState *record);

static void WALInsertLockAcquire(void);
static void WALInsertLockAcquireExclusive(void);
static void WALInsertLockRelease(void);
static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);

/*
 * Insert an XLOG record represented by an already-constructed chain of data
 * chunks.  This is a low-level routine; to construct the WAL record header
 * and data, use the higher-level routines in xloginsert.c.
 *
 * If 'fpw_lsn' is valid, it is the oldest LSN among the pages that this
 * WAL record applies to, that were not included in the record as full page
 * images.  If fpw_lsn <= RedoRecPtr, the function does not perform the
 * insertion and returns InvalidXLogRecPtr.  The caller can then recalculate
 * which pages need a full-page image, and retry.  If fpw_lsn is invalid, the
 * record is always inserted.
 *
 * 'flags' gives more in-depth control on the record being inserted. See
 * XLogSetRecordFlags() for details.
 *
 * The first XLogRecData in the chain must be for the record header, and its
 * data must be MAXALIGNed.  XLogInsertRecord fills in the xl_prev and
 * xl_crc fields in the header, the rest of the header must already be filled
 * by the caller.
 *
 * Returns XLOG pointer to end of record (beginning of next record).
 * This can be used as LSN for data pages affected by the logged action.
 * (LSN is the XLOG point up to which the XLOG must be flushed to disk
 * before the data page can be written out.  This implements the basic
 * WAL rule "write the log before the data".)
 */
XLogRecPtr
XLogInsertRecord(XLogRecData *rdata,
                 XLogRecPtr fpw_lsn,
                 uint8 flags,
                 int num_fpi)
{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    pg_crc32c   rdata_crc;
    bool        inserted;
    XLogRecord *rechdr = (XLogRecord *) rdata->data;
    uint8       info = rechdr->xl_info & ~XLR_INFO_MASK;
    bool        isLogSwitch = (rechdr->xl_rmid == RM_XLOG_ID &&
                               info == XLOG_SWITCH);
    XLogRecPtr  StartPos;
    XLogRecPtr  EndPos;
    bool        prevDoPageWrites = doPageWrites;

    /* 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");

    /*----------
     *
     * 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 grab WALBufMappingLock to
     * initialize it, but the WAL writer tries to do that ahead of insertions
     * to avoid that from happening in the critical path.
     *
     *----------
     */
    START_CRIT_SECTION();
    if (isLogSwitch)
        WALInsertLockAcquireExclusive();
    else
        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 or forcePageWrites was just turned
     * on; 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->forcePageWrites);

    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.
     */
    if (isLogSwitch)
        inserted = ReserveXLogSwitch(&StartPos, &EndPos, &rechdr->xl_prev);
    else
    {
        ReserveXLogInsertLocation(rechdr->xl_tot_len, &StartPos, &EndPos,
                                  &rechdr->xl_prev);
        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, isLogSwitch, rdata,
                            StartPos, EndPos);

        /*
         * 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();

    MarkCurrentTransactionIdLoggedIfAny();

    END_CRIT_SECTION();

    /*
     * 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;
        /* update local result copy while I have the chance */
        LogwrtResult = XLogCtl->LogwrtResult;
        SpinLockRelease(&XLogCtl->info_lck);
    }

    /*
     * 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 (isLogSwitch)
    {
        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;
        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);

        if (!debug_reader)
            debug_reader = XLogReaderAllocate(wal_segment_size, NULL,
                                              XL_ROUTINE(), NULL);

        if (!debug_reader)
        {
            appendStringInfoString(&buf, "error decoding record: out of memory");
        }
        else if (!DecodeXLogRecord(debug_reader, (XLogRecord *) recordBuf.data,
                                   &errormsg))
        {
            appendStringInfo(&buf, "error decoding record: %s",
                             errormsg ? errormsg : "no error message");
        }
        else
        {
            appendStringInfoString(&buf, " - ");
            xlog_outdesc(&buf, debug_reader);
        }
        elog(LOG, "%s", buf.data);

        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;
}

/*
 * Reserves the right amount of space for a record of given size from the WAL.
 * *StartPos is set to the beginning of the reserved section, *EndPos to
 * its end+1. *PrevPtr is set to the beginning of the previous record; it is
 * used to set the xl_prev of this record.
 *
 * This is the performance critical part of XLogInsert that must be serialized
 * across backends. The rest can happen mostly in parallel. Try to keep this
 * section as short as possible, insertpos_lck can be heavily contended on a
 * busy system.
 *
 * NB: The space calculation here must match the code in CopyXLogRecordToWAL,
 * where we actually copy the record to the reserved space.
 */
static void
ReserveXLogInsertLocation(int size, XLogRecPtr *StartPos, XLogRecPtr *EndPos,
                          XLogRecPtr *PrevPtr)
{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    uint64      startbytepos;
    uint64      endbytepos;
    uint64      prevbytepos;

    size = MAXALIGN(size);

    /* All (non xlog-switch) records should contain data. */
    Assert(size > SizeOfXLogRecord);

    /*
     * The duration the spinlock needs to be held is minimized by minimizing
     * the calculations that have to be done while holding the lock. The
     * current tip of reserved WAL is kept in CurrBytePos, as a byte position
     * that only counts "usable" bytes in WAL, that is, it excludes all WAL
     * page headers. The mapping between "usable" byte positions and physical
     * positions (XLogRecPtrs) can be done outside the locked region, and
     * because the usable byte position doesn't include any headers, reserving
     * X bytes from WAL is almost as simple as "CurrBytePos += X".
     */
    SpinLockAcquire(&Insert->insertpos_lck);

    startbytepos = Insert->CurrBytePos;
    endbytepos = startbytepos + size;
    prevbytepos = Insert->PrevBytePos;
    Insert->CurrBytePos = endbytepos;
    Insert->PrevBytePos = startbytepos;

    SpinLockRelease(&Insert->insertpos_lck);

    *StartPos = XLogBytePosToRecPtr(startbytepos);
    *EndPos = XLogBytePosToEndRecPtr(endbytepos);
    *PrevPtr = XLogBytePosToRecPtr(prevbytepos);

    /*
     * Check that the conversions between "usable byte positions" and
     * XLogRecPtrs work consistently in both directions.
     */
    Assert(XLogRecPtrToBytePos(*StartPos) == startbytepos);
    Assert(XLogRecPtrToBytePos(*EndPos) == endbytepos);
    Assert(XLogRecPtrToBytePos(*PrevPtr) == prevbytepos);
}

/*
 * Like ReserveXLogInsertLocation(), but for an xlog-switch record.
 *
 * A log-switch record is handled slightly differently. The rest of the
 * segment will be reserved for this insertion, as indicated by the returned
 * *EndPos value. However, if we are already at the beginning of the current
 * segment, *StartPos and *EndPos are set to the current location without
 * reserving any space, and the function returns false.
*/
static bool
ReserveXLogSwitch(XLogRecPtr *StartPos, XLogRecPtr *EndPos, XLogRecPtr *PrevPtr)
{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    uint64      startbytepos;
    uint64      endbytepos;
    uint64      prevbytepos;
    uint32      size = MAXALIGN(SizeOfXLogRecord);
    XLogRecPtr  ptr;
    uint32      segleft;

    /*
     * These calculations are a bit heavy-weight to be done while holding a
     * spinlock, but since we're holding all the WAL insertion locks, there
     * are no other inserters competing for it. GetXLogInsertRecPtr() does
     * compete for it, but that's not called very frequently.
     */
    SpinLockAcquire(&Insert->insertpos_lck);

    startbytepos = Insert->CurrBytePos;

    ptr = XLogBytePosToEndRecPtr(startbytepos);
    if (XLogSegmentOffset(ptr, wal_segment_size) == 0)
    {
        SpinLockRelease(&Insert->insertpos_lck);
        *EndPos = *StartPos = ptr;
        return false;
    }

    endbytepos = startbytepos + size;
    prevbytepos = Insert->PrevBytePos;

    *StartPos = XLogBytePosToRecPtr(startbytepos);
    *EndPos = XLogBytePosToEndRecPtr(endbytepos);

    segleft = wal_segment_size - XLogSegmentOffset(*EndPos, wal_segment_size);
    if (segleft != wal_segment_size)
    {
        /* consume the rest of the segment */
        *EndPos += segleft;
        endbytepos = XLogRecPtrToBytePos(*EndPos);
    }
    Insert->CurrBytePos = endbytepos;
    Insert->PrevBytePos = startbytepos;

    SpinLockRelease(&Insert->insertpos_lck);

    *PrevPtr = XLogBytePosToRecPtr(prevbytepos);

    Assert(XLogSegmentOffset(*EndPos, wal_segment_size) == 0);
    Assert(XLogRecPtrToBytePos(*EndPos) == endbytepos);
    Assert(XLogRecPtrToBytePos(*StartPos) == startbytepos);
    Assert(XLogRecPtrToBytePos(*PrevPtr) == prevbytepos);

    return true;
}

/*
 * Checks whether the current buffer page and backup page stored in the
 * WAL record are consistent or not. Before comparing the two pages, a
 * masking can be applied to the pages to ignore certain areas like hint bits,
 * unused space between pd_lower and pd_upper among other things. This
 * function should be called once WAL replay has been completed for a
 * given record.
 */
static void
checkXLogConsistency(XLogReaderState *record)
{
    RmgrId      rmid = XLogRecGetRmid(record);
    RelFileNode rnode;
    ForkNumber  forknum;
    BlockNumber blkno;
    int         block_id;

    /* Records with no backup blocks have no need for consistency checks. */
    if (!XLogRecHasAnyBlockRefs(record))
        return;

    Assert((XLogRecGetInfo(record) & XLR_CHECK_CONSISTENCY) != 0);

    for (block_id = 0; block_id <= record->max_block_id; block_id++)
    {
        Buffer      buf;
        Page        page;

        if (!XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blkno))
        {
            /*
             * WAL record doesn't contain a block reference with the given id.
             * Do nothing.
             */
            continue;
        }

        Assert(XLogRecHasBlockImage(record, block_id));

        if (XLogRecBlockImageApply(record, block_id))
        {
            /*
             * WAL record has already applied the page, so bypass the
             * consistency check as that would result in comparing the full
             * page stored in the record with itself.
             */
            continue;
        }

        /*
         * Read the contents from the current buffer and store it in a
         * temporary page.
         */
        buf = XLogReadBufferExtended(rnode, forknum, blkno,
                                     RBM_NORMAL_NO_LOG);
        if (!BufferIsValid(buf))
            continue;

        LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
        page = BufferGetPage(buf);

        /*
         * Take a copy of the local page where WAL has been applied to have a
         * comparison base before masking it...
         */
        memcpy(replay_image_masked, page, BLCKSZ);

        /* No need for this page anymore now that a copy is in. */
        UnlockReleaseBuffer(buf);

        /*
         * If the block LSN is already ahead of this WAL record, we can't
         * expect contents to match.  This can happen if recovery is
         * restarted.
         */
        if (PageGetLSN(replay_image_masked) > record->EndRecPtr)
            continue;

        /*
         * Read the contents from the backup copy, stored in WAL record and
         * store it in a temporary page. There is no need to allocate a new
         * page here, a local buffer is fine to hold its contents and a mask
         * can be directly applied on it.
         */
        if (!RestoreBlockImage(record, block_id, primary_image_masked))
            elog(ERROR, "failed to restore block image");

        /*
         * If masking function is defined, mask both the primary and replay
         * images
         */
        if (RmgrTable[rmid].rm_mask != NULL)
        {
            RmgrTable[rmid].rm_mask(replay_image_masked, blkno);
            RmgrTable[rmid].rm_mask(primary_image_masked, blkno);
        }

        /* Time to compare the primary and replay images. */
        if (memcmp(replay_image_masked, primary_image_masked, BLCKSZ) != 0)
        {
            elog(FATAL,
                 "inconsistent page found, rel %u/%u/%u, forknum %u, blkno %u",
                 rnode.spcNode, rnode.dbNode, rnode.relNode,
                 forknum, blkno);
        }
    }
}

/*
 * Subroutine of XLogInsertRecord.  Copies a WAL record to an already-reserved
 * area in the WAL.
 */
static void
CopyXLogRecordToWAL(int write_len, bool isLogSwitch, XLogRecData *rdata,
                    XLogRecPtr StartPos, XLogRecPtr EndPos)
{
    char       *currpos;
    int         freespace;
    int         written;
    XLogRecPtr  CurrPos;
    XLogPageHeader pagehdr;

    /*
     * Get a pointer to the right place in the right WAL buffer to start
     * inserting to.
     */
    CurrPos = StartPos;
    currpos = GetXLogBuffer(CurrPos);
    freespace = INSERT_FREESPACE(CurrPos);

    /*
     * there should be enough space for at least the first field (xl_tot_len)
     * on this page.
     */
    Assert(freespace >= sizeof(uint32));

    /* Copy record data */
    written = 0;
    while (rdata != NULL)
    {
        char       *rdata_data = rdata->data;
        int         rdata_len = rdata->len;

        while (rdata_len > freespace)
        {
            /*
             * Write what fits on this page, and continue on the next page.
             */
            Assert(CurrPos % XLOG_BLCKSZ >= SizeOfXLogShortPHD || freespace == 0);
            memcpy(currpos, rdata_data, freespace);
            rdata_data += freespace;
            rdata_len -= freespace;
            written += freespace;
            CurrPos += freespace;

            /*
             * Get pointer to beginning of next page, and set the xlp_rem_len
             * in the page header. Set XLP_FIRST_IS_CONTRECORD.
             *
             * It's safe to set the contrecord flag and xlp_rem_len without a
             * lock on the page. All the other flags were already set when the
             * page was initialized, in AdvanceXLInsertBuffer, and we're the
             * only backend that needs to set the contrecord flag.
             */
            currpos = GetXLogBuffer(CurrPos);
            pagehdr = (XLogPageHeader) currpos;
            pagehdr->xlp_rem_len = write_len - written;
            pagehdr->xlp_info |= XLP_FIRST_IS_CONTRECORD;

            /* skip over the page header */
            if (XLogSegmentOffset(CurrPos, wal_segment_size) == 0)
            {
                CurrPos += SizeOfXLogLongPHD;
                currpos += SizeOfXLogLongPHD;
            }
            else
            {
                CurrPos += SizeOfXLogShortPHD;
                currpos += SizeOfXLogShortPHD;
            }
            freespace = INSERT_FREESPACE(CurrPos);
        }

        Assert(CurrPos % XLOG_BLCKSZ >= SizeOfXLogShortPHD || rdata_len == 0);
        memcpy(currpos, rdata_data, rdata_len);
        currpos += rdata_len;
        CurrPos += rdata_len;
        freespace -= rdata_len;
        written += rdata_len;

        rdata = rdata->next;
    }
    Assert(written == write_len);

    /*
     * If this was an xlog-switch, it's not enough to write the switch record,
     * we also have to consume all the remaining space in the WAL segment.  We
     * have already reserved that space, but we need to actually fill it.
     */
    if (isLogSwitch && XLogSegmentOffset(CurrPos, wal_segment_size) != 0)
    {
        /* An xlog-switch record doesn't contain any data besides the header */
        Assert(write_len == SizeOfXLogRecord);

        /* Assert that we did reserve the right amount of space */
        Assert(XLogSegmentOffset(EndPos, wal_segment_size) == 0);

        /* Use up all the remaining space on the current page */
        CurrPos += freespace;

        /*
         * Cause all remaining pages in the segment to be flushed, leaving the
         * XLog position where it should be, at the start of the next segment.
         * We do this one page at a time, to make sure we don't deadlock
         * against ourselves if wal_buffers < wal_segment_size.
         */
        while (CurrPos < EndPos)
        {
            /*
             * The minimal action to flush the page would be to call
             * WALInsertLockUpdateInsertingAt(CurrPos) followed by
             * AdvanceXLInsertBuffer(...).  The page would be left initialized
             * mostly to zeros, except for the page header (always the short
             * variant, as this is never a segment's first page).
             *
             * The large vistas of zeros are good for compressibility, but the
             * headers interrupting them every XLOG_BLCKSZ (with values that
             * differ from page to page) are not.  The effect varies with
             * compression tool, but bzip2 for instance compresses about an
             * order of magnitude worse if those headers are left in place.
             *
             * Rather than complicating AdvanceXLInsertBuffer itself (which is
             * called in heavily-loaded circumstances as well as this lightly-
             * loaded one) with variant behavior, we just use GetXLogBuffer
             * (which itself calls the two methods we need) to get the pointer
             * and zero most of the page.  Then we just zero the page header.
             */
            currpos = GetXLogBuffer(CurrPos);
            MemSet(currpos, 0, SizeOfXLogShortPHD);

            CurrPos += XLOG_BLCKSZ;
        }
    }
    else
    {
        /* Align the end position, so that the next record starts aligned */
        CurrPos = MAXALIGN64(CurrPos);
    }

    if (CurrPos != EndPos)
        elog(PANIC, "space reserved for WAL record does not match what was written");
}

/*
 * Acquire a WAL insertion lock, for inserting to WAL.
 */
static void
WALInsertLockAcquire(void)
{
    bool        immed;

    /*
     * It doesn't matter which of the WAL insertion locks we acquire, so try
     * the one we used last time.  If the system isn't particularly busy, it's
     * a good bet that it's still available, and it's good to have some
     * affinity to a particular lock so that you don't unnecessarily bounce
     * cache lines between processes when there's no contention.
     *
     * If this is the first time through in this backend, pick a lock
     * (semi-)randomly.  This allows the locks to be used evenly if you have a
     * lot of very short connections.
     */
    static int  lockToTry = -1;

    if (lockToTry == -1)
        lockToTry = MyProc->pgprocno % NUM_XLOGINSERT_LOCKS;
    MyLockNo = lockToTry;

    /*
     * The insertingAt value is initially set to 0, as we don't know our
     * insert location yet.
     */
    immed = LWLockAcquire(&WALInsertLocks[MyLockNo].l.lock, LW_EXCLUSIVE);
    if (!immed)
    {
        /*
         * If we couldn't get the lock immediately, try another lock next
         * time.  On a system with more insertion locks than concurrent
         * inserters, this causes all the inserters to eventually migrate to a
         * lock that no-one else is using.  On a system with more inserters
         * than locks, it still helps to distribute the inserters evenly
         * across the locks.
         */
        lockToTry = (lockToTry + 1) % NUM_XLOGINSERT_LOCKS;
    }
}

/*
 * Acquire all WAL insertion locks, to prevent other backends from inserting
 * to WAL.
 */
static void
WALInsertLockAcquireExclusive(void)
{
    int         i;

    /*
     * When holding all the locks, all but the last lock's insertingAt
     * indicator is set to 0xFFFFFFFFFFFFFFFF, which is higher than any real
     * XLogRecPtr value, to make sure that no-one blocks waiting on those.
     */
    for (i = 0; i < NUM_XLOGINSERT_LOCKS - 1; i++)
    {
        LWLockAcquire(&WALInsertLocks[i].l.lock, LW_EXCLUSIVE);
        LWLockUpdateVar(&WALInsertLocks[i].l.lock,
                        &WALInsertLocks[i].l.insertingAt,
                        PG_UINT64_MAX);
    }
    /* Variable value reset to 0 at release */
    LWLockAcquire(&WALInsertLocks[i].l.lock, LW_EXCLUSIVE);

    holdingAllLocks = true;
}

/*
 * Release our insertion lock (or locks, if we're holding them all).
 *
 * NB: Reset all variables to 0, so they cause LWLockWaitForVar to block the
 * next time the lock is acquired.
 */
static void
WALInsertLockRelease(void)
{
    if (holdingAllLocks)
    {
        int         i;

        for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
            LWLockReleaseClearVar(&WALInsertLocks[i].l.lock,
                                  &WALInsertLocks[i].l.insertingAt,
                                  0);

        holdingAllLocks = false;
    }
    else
    {
        LWLockReleaseClearVar(&WALInsertLocks[MyLockNo].l.lock,
                              &WALInsertLocks[MyLockNo].l.insertingAt,
                              0);
    }
}

/*
 * Update our insertingAt value, to let others know that we've finished
 * inserting up to that point.
 */
static void
WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt)
{
    if (holdingAllLocks)
    {
        /*
         * We use the last lock to mark our actual position, see comments in
         * WALInsertLockAcquireExclusive.
         */
        LWLockUpdateVar(&WALInsertLocks[NUM_XLOGINSERT_LOCKS - 1].l.lock,
                        &WALInsertLocks[NUM_XLOGINSERT_LOCKS - 1].l.insertingAt,
                        insertingAt);
    }
    else
        LWLockUpdateVar(&WALInsertLocks[MyLockNo].l.lock,
                        &WALInsertLocks[MyLockNo].l.insertingAt,
                        insertingAt);
}

/*
 * Wait for any WAL insertions < upto to finish.
 *
 * Returns the location of the oldest insertion that is still in-progress.
 * Any WAL prior to that point has been fully copied into WAL buffers, and
 * can be flushed out to disk. Because this waits for any insertions older
 * than 'upto' to finish, the return value is always >= 'upto'.
 *
 * Note: When you are about to write out WAL, you must call this function
 * *before* acquiring WALWriteLock, to avoid deadlocks. This function might
 * need to wait for an insertion to finish (or at least advance to next
 * uninitialized page), and the inserter might need to evict an old WAL buffer
 * to make room for a new one, which in turn requires WALWriteLock.
 */
static XLogRecPtr
WaitXLogInsertionsToFinish(XLogRecPtr upto)
{
    uint64      bytepos;
    XLogRecPtr  reservedUpto;
    XLogRecPtr  finishedUpto;
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    int         i;

    if (MyProc == NULL)
        elog(PANIC, "cannot wait without a PGPROC structure");

    /* Read the current insert position */
    SpinLockAcquire(&Insert->insertpos_lck);
    bytepos = Insert->CurrBytePos;
    SpinLockRelease(&Insert->insertpos_lck);
    reservedUpto = XLogBytePosToEndRecPtr(bytepos);

    /*
     * No-one should request to flush a piece of WAL that hasn't even been
     * reserved yet. However, it can happen if there is a block with a bogus
     * LSN on disk, for example. XLogFlush checks for that situation and
     * complains, but only after the flush. Here we just assume that to mean
     * that all WAL that has been reserved needs to be finished. In this
     * corner-case, the return value can be smaller than 'upto' argument.
     */
    if (upto > reservedUpto)
    {
        ereport(LOG,
                (errmsg("request to flush past end of generated WAL; request %X/%X, current position %X/%X",
                        LSN_FORMAT_ARGS(upto), LSN_FORMAT_ARGS(reservedUpto))));
        upto = reservedUpto;
    }

    /*
     * Loop through all the locks, sleeping on any in-progress insert older
     * than 'upto'.
     *
     * finishedUpto is our return value, indicating the point upto which all
     * the WAL insertions have been finished. Initialize it to the head of
     * reserved WAL, and as we iterate through the insertion locks, back it
     * out for any insertion that's still in progress.
     */
    finishedUpto = reservedUpto;
    for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
    {
        XLogRecPtr  insertingat = InvalidXLogRecPtr;

        do
        {
            /*
             * See if this insertion is in progress.  LWLockWaitForVar will
             * wait for the lock to be released, or for the 'value' to be set
             * by a LWLockUpdateVar call.  When a lock is initially acquired,
             * its value is 0 (InvalidXLogRecPtr), which means that we don't
             * know where it's inserting yet.  We will have to wait for it. If
             * it's a small insertion, the record will most likely fit on the
             * same page and the inserter will release the lock without ever
             * calling LWLockUpdateVar.  But if it has to sleep, it will
             * advertise the insertion point with LWLockUpdateVar before
             * sleeping.
             */
            if (LWLockWaitForVar(&WALInsertLocks[i].l.lock,
                                 &WALInsertLocks[i].l.insertingAt,
                                 insertingat, &insertingat))
            {
                /* the lock was free, so no insertion in progress */
                insertingat = InvalidXLogRecPtr;
                break;
            }

            /*
             * This insertion is still in progress. Have to wait, unless the
             * inserter has proceeded past 'upto'.
             */
        } while (insertingat < upto);

        if (insertingat != InvalidXLogRecPtr && insertingat < finishedUpto)
            finishedUpto = insertingat;
    }
    return finishedUpto;
}

/*
 * Get a pointer to the right location in the WAL buffer containing the
 * given XLogRecPtr.
 *
 * If the page is not initialized yet, it is initialized. That might require
 * evicting an old dirty buffer from the buffer cache, which means I/O.
 *
 * The caller must ensure that the page containing the requested location
 * isn't evicted yet, and won't be evicted. The way to ensure that is to
 * hold onto a WAL insertion lock with the insertingAt position set to
 * something <= ptr. GetXLogBuffer() will update insertingAt if it needs
 * to evict an old page from the buffer. (This means that once you call
 * GetXLogBuffer() with a given 'ptr', you must not access anything before
 * that point anymore, and must not call GetXLogBuffer() with an older 'ptr'
 * later, because older buffers might be recycled already)
 */
static char *
GetXLogBuffer(XLogRecPtr ptr)
{
    int         idx;
    XLogRecPtr  endptr;
    static uint64 cachedPage = 0;
    static char *cachedPos = NULL;
    XLogRecPtr  expectedEndPtr;

    /*
     * Fast path for the common case that we need to access again the same
     * page as last time.
     */
    if (ptr / XLOG_BLCKSZ == cachedPage)
    {
        Assert(((XLogPageHeader) cachedPos)->xlp_magic == XLOG_PAGE_MAGIC);
        Assert(((XLogPageHeader) cachedPos)->xlp_pageaddr == ptr - (ptr % XLOG_BLCKSZ));
        return cachedPos + ptr % XLOG_BLCKSZ;
    }

    /*
     * The XLog buffer cache is organized so that a page is always loaded to a
     * particular buffer.  That way we can easily calculate the buffer a given
     * page must be loaded into, from the XLogRecPtr alone.
     */
    idx = XLogRecPtrToBufIdx(ptr);

    /*
     * See what page is loaded in the buffer at the moment. It could be the
     * page we're looking for, or something older. It can't be anything newer
     * - that would imply the page we're looking for has already been written
     * out to disk and evicted, and the caller is responsible for making sure
     * that doesn't happen.
     *
     * However, we don't hold a lock while we read the value. If someone has
     * just initialized the page, it's possible that we get a "torn read" of
     * the XLogRecPtr if 64-bit fetches are not atomic on this platform. In
     * that case we will see a bogus value. That's ok, we'll grab the mapping
     * lock (in AdvanceXLInsertBuffer) and retry if we see anything else than
     * the page we're looking for. But it means that when we do this unlocked
     * read, we might see a value that appears to be ahead of the page we're
     * looking for. Don't PANIC on that, until we've verified the value while
     * holding the lock.
     */
    expectedEndPtr = ptr;
    expectedEndPtr += XLOG_BLCKSZ - ptr % XLOG_BLCKSZ;

    endptr = XLogCtl->xlblocks[idx];
    if (expectedEndPtr != endptr)
    {
        XLogRecPtr  initializedUpto;

        /*
         * Before calling AdvanceXLInsertBuffer(), which can block, let others
         * know how far we're finished with inserting the record.
         *
         * NB: If 'ptr' points to just after the page header, advertise a
         * position at the beginning of the page rather than 'ptr' itself. If
         * there are no other insertions running, someone might try to flush
         * up to our advertised location. If we advertised a position after
         * the page header, someone might try to flush the page header, even
         * though page might actually not be initialized yet. As the first
         * inserter on the page, we are effectively responsible for making
         * sure that it's initialized, before we let insertingAt to move past
         * the page header.
         */
        if (ptr % XLOG_BLCKSZ == SizeOfXLogShortPHD &&
            XLogSegmentOffset(ptr, wal_segment_size) > XLOG_BLCKSZ)
            initializedUpto = ptr - SizeOfXLogShortPHD;
        else if (ptr % XLOG_BLCKSZ == SizeOfXLogLongPHD &&
                 XLogSegmentOffset(ptr, wal_segment_size) < XLOG_BLCKSZ)
            initializedUpto = ptr - SizeOfXLogLongPHD;
        else
            initializedUpto = ptr;

        WALInsertLockUpdateInsertingAt(initializedUpto);

        AdvanceXLInsertBuffer(ptr, false);
        endptr = XLogCtl->xlblocks[idx];

        if (expectedEndPtr != endptr)
            elog(PANIC, "could not find WAL buffer for %X/%X",
                 LSN_FORMAT_ARGS(ptr));
    }
    else
    {
        /*
         * Make sure the initialization of the page is visible to us, and
         * won't arrive later to overwrite the WAL data we write on the page.
         */
        pg_memory_barrier();
    }

    /*
     * Found the buffer holding this page. Return a pointer to the right
     * offset within the page.
     */
    cachedPage = ptr / XLOG_BLCKSZ;
    cachedPos = XLogCtl->pages + idx * (Size) XLOG_BLCKSZ;

    Assert(((XLogPageHeader) cachedPos)->xlp_magic == XLOG_PAGE_MAGIC);
    Assert(((XLogPageHeader) cachedPos)->xlp_pageaddr == ptr - (ptr % XLOG_BLCKSZ));

    return cachedPos + ptr % XLOG_BLCKSZ;
}

/*
 * Converts a "usable byte position" to XLogRecPtr. A usable byte position
 * is the position starting from the beginning of WAL, excluding all WAL
 * page headers.
 */
static XLogRecPtr
XLogBytePosToRecPtr(uint64 bytepos)
{
    uint64      fullsegs;
    uint64      fullpages;
    uint64      bytesleft;
    uint32      seg_offset;
    XLogRecPtr  result;

    fullsegs = bytepos / UsableBytesInSegment;
    bytesleft = bytepos % UsableBytesInSegment;

    if (bytesleft < XLOG_BLCKSZ - SizeOfXLogLongPHD)
    {
        /* fits on first page of segment */
        seg_offset = bytesleft + SizeOfXLogLongPHD;
    }
    else
    {
        /* account for the first page on segment with long header */
        seg_offset = XLOG_BLCKSZ;
        bytesleft -= XLOG_BLCKSZ - SizeOfXLogLongPHD;

        fullpages = bytesleft / UsableBytesInPage;
        bytesleft = bytesleft % UsableBytesInPage;

        seg_offset += fullpages * XLOG_BLCKSZ + bytesleft + SizeOfXLogShortPHD;
    }

    XLogSegNoOffsetToRecPtr(fullsegs, seg_offset, wal_segment_size, result);

    return result;
}

/*
 * Like XLogBytePosToRecPtr, but if the position is at a page boundary,
 * returns a pointer to the beginning of the page (ie. before page header),
 * not to where the first xlog record on that page would go to. This is used
 * when converting a pointer to the end of a record.
 */
static XLogRecPtr
XLogBytePosToEndRecPtr(uint64 bytepos)
{
    uint64      fullsegs;
    uint64      fullpages;
    uint64      bytesleft;
    uint32      seg_offset;
    XLogRecPtr  result;

    fullsegs = bytepos / UsableBytesInSegment;
    bytesleft = bytepos % UsableBytesInSegment;

    if (bytesleft < XLOG_BLCKSZ - SizeOfXLogLongPHD)
    {
        /* fits on first page of segment */
        if (bytesleft == 0)
            seg_offset = 0;
        else
            seg_offset = bytesleft + SizeOfXLogLongPHD;
    }
    else
    {
        /* account for the first page on segment with long header */
        seg_offset = XLOG_BLCKSZ;
        bytesleft -= XLOG_BLCKSZ - SizeOfXLogLongPHD;

        fullpages = bytesleft / UsableBytesInPage;
        bytesleft = bytesleft % UsableBytesInPage;

        if (bytesleft == 0)
            seg_offset += fullpages * XLOG_BLCKSZ + bytesleft;
        else
            seg_offset += fullpages * XLOG_BLCKSZ + bytesleft + SizeOfXLogShortPHD;
    }

    XLogSegNoOffsetToRecPtr(fullsegs, seg_offset, wal_segment_size, result);

    return result;
}

/*
 * Convert an XLogRecPtr to a "usable byte position".
 */
static uint64
XLogRecPtrToBytePos(XLogRecPtr ptr)
{
    uint64      fullsegs;
    uint32      fullpages;
    uint32      offset;
    uint64      result;

    XLByteToSeg(ptr, fullsegs, wal_segment_size);

    fullpages = (XLogSegmentOffset(ptr, wal_segment_size)) / XLOG_BLCKSZ;
    offset = ptr % XLOG_BLCKSZ;

    if (fullpages == 0)
    {
        result = fullsegs * UsableBytesInSegment;
        if (offset > 0)
        {
            Assert(offset >= SizeOfXLogLongPHD);
            result += offset - SizeOfXLogLongPHD;
        }
    }
    else
    {
        result = fullsegs * UsableBytesInSegment +
            (XLOG_BLCKSZ - SizeOfXLogLongPHD) + /* account for first page */
            (fullpages - 1) * UsableBytesInPage;    /* full pages */
        if (offset > 0)
        {
            Assert(offset >= SizeOfXLogShortPHD);
            result += offset - SizeOfXLogShortPHD;
        }
    }

    return result;
}

/*
 * Initialize XLOG buffers, writing out old buffers if they still contain
 * unwritten data, upto the page containing 'upto'. Or if 'opportunistic' is
 * true, initialize as many pages as we can without having to write out
 * unwritten data. Any new pages are initialized to zeros, with pages headers
 * initialized properly.
 */
static void
AdvanceXLInsertBuffer(XLogRecPtr upto, bool opportunistic)
{
    XLogCtlInsert *Insert = &XLogCtl->Insert;
    int         nextidx;
    XLogRecPtr  OldPageRqstPtr;
    XLogwrtRqst WriteRqst;
    XLogRecPtr  NewPageEndPtr = InvalidXLogRecPtr;
    XLogRecPtr  NewPageBeginPtr;
    XLogPageHeader NewPage;
    int         npages = 0;

    LWLockAcquire(WALBufMappingLock, LW_EXCLUSIVE);

    /*
     * Now that we have the lock, check if someone initialized the page
     * already.
     */
    while (upto >= XLogCtl->InitializedUpTo || opportunistic)
    {
        nextidx = XLogRecPtrToBufIdx(XLogCtl->InitializedUpTo);

        /*
         * Get ending-offset of the buffer page we need to replace (this may
         * be zero if the buffer hasn't been used yet).  Fall through if it's
         * already written out.
         */
        OldPageRqstPtr = XLogCtl->xlblocks[nextidx];
        if (LogwrtResult.Write < OldPageRqstPtr)
        {
            /*
             * Nope, got work to do. If we just want to pre-initialize as much
             * as we can without flushing, give up now.
             */
            if (opportunistic)
                break;

            /* Before waiting, get info_lck and update LogwrtResult */
            SpinLockAcquire(&XLogCtl->info_lck);
            if (XLogCtl->LogwrtRqst.Write < OldPageRqstPtr)
                XLogCtl->LogwrtRqst.Write = OldPageRqstPtr;
            LogwrtResult = XLogCtl->LogwrtResult;
            SpinLockRelease(&XLogCtl->info_lck);

            /*
             * Now that we have an up-to-date LogwrtResult value, see if we
             * still need to write it or if someone else already did.
             */
            if (LogwrtResult.Write < OldPageRqstPtr)
            {
                /*
                 * Must acquire write lock. Release WALBufMappingLock first,
                 * to make sure that all insertions that we need to wait for
                 * can finish (up to this same position). Otherwise we risk
                 * deadlock.
                 */
                LWLockRelease(WALBufMappingLock);

                WaitXLogInsertionsToFinish(OldPageRqstPtr);

                LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);

                LogwrtResult = XLogCtl->LogwrtResult;
                if (LogwrtResult.Write >= OldPageRqstPtr)
                {
                    /* OK, someone wrote it already */
                    LWLockRelease(WALWriteLock);
                }
                else
                {
                    /* Have to write it ourselves */
                    TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_START();
                    WriteRqst.Write = OldPageRqstPtr;
                    WriteRqst.Flush = 0;
                    XLogWrite(WriteRqst, false);
                    LWLockRelease(WALWriteLock);
                    WalStats.m_wal_buffers_full++;
                    TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
                }
                /* Re-acquire WALBufMappingLock and retry */
                LWLockAcquire(WALBufMappingLock, LW_EXCLUSIVE);
                continue;
            }
        }

        /*
         * Now the next buffer slot is free and we can set it up to be the
         * next output page.
         */
        NewPageBeginPtr = XLogCtl->InitializedUpTo;
        NewPageEndPtr = NewPageBeginPtr + XLOG_BLCKSZ;

        Assert(XLogRecPtrToBufIdx(NewPageBeginPtr) == nextidx);

        NewPage = (XLogPageHeader) (XLogCtl->pages + nextidx * (Size) XLOG_BLCKSZ);

        /*
         * Be sure to re-zero the buffer so that bytes beyond what we've
         * written will look like zeroes and not valid XLOG records...
         */
        MemSet((char *) NewPage, 0, XLOG_BLCKSZ);

        /*
         * Fill the new page's header
         */
        NewPage->xlp_magic = XLOG_PAGE_MAGIC;

        /* NewPage->xlp_info = 0; */    /* done by memset */
        NewPage->xlp_tli = ThisTimeLineID;
        NewPage->xlp_pageaddr = NewPageBeginPtr;

        /* NewPage->xlp_rem_len = 0; */ /* done by memset */

        /*
         * If online backup is not in progress, mark the header to indicate
         * that WAL records beginning in this page have removable backup
         * blocks.  This allows the WAL archiver to know whether it is safe to
         * compress archived WAL data by transforming full-block records into
         * the non-full-block format.  It is sufficient to record this at the
         * page level because we force a page switch (in fact a segment
         * switch) when starting a backup, so the flag will be off before any
         * records can be written during the backup.  At the end of a backup,
         * the last page will be marked as all unsafe when perhaps only part
         * is unsafe, but at worst the archiver would miss the opportunity to
         * compress a few records.
         */
        if (!Insert->forcePageWrites)
            NewPage->xlp_info |= XLP_BKP_REMOVABLE;

        /*
         * If first page of an XLOG segment file, make it a long header.
         */
        if ((XLogSegmentOffset(NewPage->xlp_pageaddr, wal_segment_size)) == 0)
        {
            XLogLongPageHeader NewLongPage = (XLogLongPageHeader) NewPage;

            NewLongPage->xlp_sysid = ControlFile->system_identifier;
            NewLongPage->xlp_seg_size = wal_segment_size;
            NewLongPage->xlp_xlog_blcksz = XLOG_BLCKSZ;
            NewPage->xlp_info |= XLP_LONG_HEADER;
        }

        /*
         * Make sure the initialization of the page becomes visible to others
         * before the xlblocks update. GetXLogBuffer() reads xlblocks without
         * holding a lock.
         */
        pg_write_barrier();

        *((volatile XLogRecPtr *) &XLogCtl->xlblocks[nextidx]) = NewPageEndPtr;

        XLogCtl->InitializedUpTo = NewPageEndPtr;

        npages++;
    }
    LWLockRelease(WALBufMappingLock);

#ifdef WAL_DEBUG
    if (XLOG_DEBUG && npages > 0)
    {
        elog(DEBUG1, "initialized %d pages, up to %X/%X",
             npages, LSN_FORMAT_ARGS(NewPageEndPtr));
    }
#endif
}

/*
 * Calculate CheckPointSegments based on max_wal_size_mb and
 * checkpoint_completion_target.
 */
static void
CalculateCheckpointSegments(void)
{
    double      target;

    /*-------
     * Calculate the distance at which to trigger a checkpoint, to avoid
     * exceeding max_wal_size_mb. This is based on two assumptions:
     *
     * a) we keep WAL for only one checkpoint cycle (prior to PG11 we kept
     *    WAL for two checkpoint cycles to allow us to recover from the
     *    secondary checkpoint if the first checkpoint failed, though we
     *    only did this on the primary anyway, not on standby. Keeping just
     *    one checkpoint simplifies processing and reduces disk space in
     *    many smaller databases.)
     * b) during checkpoint, we consume checkpoint_completion_target *
     *    number of segments consumed between checkpoints.
     *-------
     */
    target = (double) ConvertToXSegs(max_wal_size_mb, wal_segment_size) /
        (1.0 + CheckPointCompletionTarget);

    /* round down */
    CheckPointSegments = (int) target;

    if (CheckPointSegments < 1)
        CheckPointSegments = 1;
}

void
assign_max_wal_size(int newval, void *extra)
{
    max_wal_size_mb = newval;
    CalculateCheckpointSegments();
}

void
assign_checkpoint_completion_target(double newval, void *extra)
{
    CheckPointCompletionTarget = newval;
    CalculateCheckpointSegments();
}

/*
 * At a checkpoint, how many WAL segments to recycle as preallocated future
 * XLOG segments? Returns the highest segment that should be preallocated.
 */
static XLogSegNo
XLOGfileslop(XLogRecPtr lastredoptr)
{
    XLogSegNo   minSegNo;
    XLogSegNo   maxSegNo;
    double      distance;
    XLogSegNo   recycleSegNo;

    /*
     * Calculate the segment numbers that min_wal_size_mb and max_wal_size_mb
     * correspond to. Always recycle enough segments to meet the minimum, and
     * remove enough segments to stay below the maximum.
     */
    minSegNo = lastredoptr / wal_segment_size +
        ConvertToXSegs(min_wal_size_mb, wal_segment_size) - 1;
    maxSegNo = lastredoptr / wal_segment_size +
        ConvertToXSegs(max_wal_size_mb, wal_segment_size) - 1;

    /*
     * Between those limits, recycle enough segments to get us through to the
     * estimated end of next checkpoint.
     *
     * To estimate where the next checkpoint will finish, assume that the
     * system runs steadily consuming CheckPointDistanceEstimate bytes between
     * every checkpoint.
     */
    distance = (1.0 + CheckPointCompletionTarget) * CheckPointDistanceEstimate;
    /* add 10% for good measure. */
    distance *= 1.10;

    recycleSegNo = (XLogSegNo) ceil(((double) lastredoptr + distance) /
                                    wal_segment_size);

    if (recycleSegNo < minSegNo)
        recycleSegNo = minSegNo;
    if (recycleSegNo > maxSegNo)
        recycleSegNo = maxSegNo;

    return recycleSegNo;
}

/*
 * Check whether we've consumed enough xlog space that a checkpoint is needed.
 *
 * new_segno indicates a log file that has just been filled up (or read
 * during recovery). We measure the distance from RedoRecPtr to new_segno
 * and see if that exceeds CheckPointSegments.
 *
 * Note: it is caller's responsibility that RedoRecPtr is up-to-date.
 */
static bool
XLogCheckpointNeeded(XLogSegNo new_segno)
{
    XLogSegNo   old_segno;

    XLByteToSeg(RedoRecPtr, old_segno, wal_segment_size);

    if (new_segno >= old_segno + (uint64) (CheckPointSegments - 1))
        return true;
    return false;
}

/*
 * Write and/or fsync the log at least as far as WriteRqst indicates.
 *
 * If flexible == true, we don't have to write as far as WriteRqst, but
 * may stop at any convenient boundary (such as a cache or logfile boundary).
 * This option allows us to avoid uselessly issuing multiple writes when a
 * single one would do.
 *
 * Must be called with WALWriteLock held. WaitXLogInsertionsToFinish(WriteRqst)
 * must be called before grabbing the lock, to make sure the data is ready to
 * write.
 */
static void
XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
{
    bool        ispartialpage;
    bool        last_iteration;
    bool        finishing_seg;
    int         curridx;
    int         npages;
    int         startidx;
    uint32      startoffset;

    /* We should always be inside a critical section here */
    Assert(CritSectionCount > 0);

    /*
     * Update local LogwrtResult (caller probably did this already, but...)
     */
    LogwrtResult = XLogCtl->LogwrtResult;

    /*
     * Since successive pages in the xlog cache are consecutively allocated,
     * we can usually gather multiple pages together and issue just one
     * write() call.  npages is the number of pages we have determined can be
     * written together; startidx is the cache block index of the first one,
     * and startoffset is the file offset at which it should go. The latter
     * two variables are only valid when npages > 0, but we must initialize
     * all of them to keep the compiler quiet.
     */
    npages = 0;
    startidx = 0;
    startoffset = 0;

    /*
     * Within the loop, curridx is the cache block index of the page to
     * consider writing.  Begin at the buffer containing the next unwritten
     * page, or last partially written page.
     */
    curridx = XLogRecPtrToBufIdx(LogwrtResult.Write);

    while (LogwrtResult.Write < WriteRqst.Write)
    {
        /*
         * Make sure we're not ahead of the insert process.  This could happen
         * if we're passed a bogus WriteRqst.Write that is past the end of the
         * last page that's been initialized by AdvanceXLInsertBuffer.
         */
        XLogRecPtr  EndPtr = XLogCtl->xlblocks[curridx];

        if (LogwrtResult.Write >= EndPtr)
            elog(PANIC, "xlog write request %X/%X is past end of log %X/%X",
                 LSN_FORMAT_ARGS(LogwrtResult.Write),
                 LSN_FORMAT_ARGS(EndPtr));

        /* Advance LogwrtResult.Write to end of current buffer page */
        LogwrtResult.Write = EndPtr;
        ispartialpage = WriteRqst.Write < LogwrtResult.Write;

        if (!XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo,
                             wal_segment_size))
        {
            /*
             * Switch to new logfile segment.  We cannot have any pending
             * pages here (since we dump what we have at segment end).
             */
            Assert(npages == 0);
            if (openLogFile >= 0)
                XLogFileClose();
            XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo,
                            wal_segment_size);

            /* create/use new log file */
            openLogFile = XLogFileInit(openLogSegNo);
            ReserveExternalFD();
        }

        /* Make sure we have the current logfile open */
        if (openLogFile < 0)
        {
            XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo,
                            wal_segment_size);
            openLogFile = XLogFileOpen(openLogSegNo);
            ReserveExternalFD();
        }

        /* Add current page to the set of pending pages-to-dump */
        if (npages == 0)
        {
            /* first of group */
            startidx = curridx;
            startoffset = XLogSegmentOffset(LogwrtResult.Write - XLOG_BLCKSZ,
                                            wal_segment_size);
        }
        npages++;

        /*
         * Dump the set if this will be the last loop iteration, or if we are
         * at the last page of the cache area (since the next page won't be
         * contiguous in memory), or if we are at the end of the logfile
         * segment.
         */
        last_iteration = WriteRqst.Write <= LogwrtResult.Write;

        finishing_seg = !ispartialpage &&
            (startoffset + npages * XLOG_BLCKSZ) >= wal_segment_size;

        if (last_iteration ||
            curridx == XLogCtl->XLogCacheBlck ||
            finishing_seg)
        {
            char       *from;
            Size        nbytes;
            Size        nleft;
            int         written;
            instr_time  start;

            /* OK to write the page(s) */
            from = XLogCtl->pages + startidx * (Size) XLOG_BLCKSZ;
            nbytes = npages * (Size) XLOG_BLCKSZ;
            nleft = nbytes;
            do
            {
                errno = 0;

                /* Measure I/O timing to write WAL data */
                if (track_wal_io_timing)
                    INSTR_TIME_SET_CURRENT(start);

                pgstat_report_wait_start(WAIT_EVENT_WAL_WRITE);
                written = pg_pwrite(openLogFile, from, nleft, startoffset);
                pgstat_report_wait_end();

                /*
                 * Increment the I/O timing and the number of times WAL data
                 * were written out to disk.
                 */
                if (track_wal_io_timing)
                {
                    instr_time  duration;

                    INSTR_TIME_SET_CURRENT(duration);
                    INSTR_TIME_SUBTRACT(duration, start);
                    WalStats.m_wal_write_time += INSTR_TIME_GET_MICROSEC(duration);
                }

                WalStats.m_wal_write++;

                if (written <= 0)
                {
                    char        xlogfname[MAXFNAMELEN];
                    int         save_errno;

                    if (errno == EINTR)
                        continue;

                    save_errno = errno;
                    XLogFileName(xlogfname, ThisTimeLineID, openLogSegNo,
                                 wal_segment_size);
                    errno = save_errno;
                    ereport(PANIC,
                            (errcode_for_file_access(),
                             errmsg("could not write to log file %s "
                                    "at offset %u, length %zu: %m",
                                    xlogfname, startoffset, nleft)));
                }
                nleft -= written;
                from += written;
                startoffset += written;
            } while (nleft > 0);

            npages = 0;

            /*
             * If we just wrote the whole last page of a logfile segment,
             * fsync the segment immediately.  This avoids having to go back
             * and re-open prior segments when an fsync request comes along
             * later. Doing it here ensures that one and only one backend will
             * perform this fsync.
             *
             * This is also the right place to notify the Archiver that the
             * segment is ready to copy to archival storage, and to update the
             * timer for archive_timeout, and to signal for a checkpoint if
             * too many logfile segments have been used since the last
             * checkpoint.
             */
            if (finishing_seg)
            {
                issue_xlog_fsync(openLogFile, openLogSegNo);

                /* signal that we need to wakeup walsenders later */
                WalSndWakeupRequest();

                LogwrtResult.Flush = LogwrtResult.Write;    /* end of page */

                if (XLogArchivingActive())
                    XLogArchiveNotifySeg(openLogSegNo);

                XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL);
                XLogCtl->lastSegSwitchLSN = LogwrtResult.Flush;

                /*
                 * Request a checkpoint if we've consumed too much xlog since
                 * the last one.  For speed, we first check using the local
                 * copy of RedoRecPtr, which might be out of date; if it looks
                 * like a checkpoint is needed, forcibly update RedoRecPtr and
                 * recheck.
                 */
                if (IsUnderPostmaster && XLogCheckpointNeeded(openLogSegNo))
                {
                    (void) GetRedoRecPtr();
                    if (XLogCheckpointNeeded(openLogSegNo))
                        RequestCheckpoint(CHECKPOINT_CAUSE_XLOG);
                }
            }
        }

        if (ispartialpage)
        {
            /* Only asked to write a partial page */
            LogwrtResult.Write = WriteRqst.Write;
            break;
        }
        curridx = NextBufIdx(curridx);

        /* If flexible, break out of loop as soon as we wrote something */
        if (flexible && npages == 0)
            break;
    }

    Assert(npages == 0);

    /*
     * If asked to flush, do so
     */
    if (LogwrtResult.Flush < WriteRqst.Flush &&
        LogwrtResult.Flush < LogwrtResult.Write)

    {
        /*
         * Could get here without iterating above loop, in which case we might
         * have no open file or the wrong one.  However, we do not need to
         * fsync more than one file.
         */
        if (sync_method != SYNC_METHOD_OPEN &&
            sync_method != SYNC_METHOD_OPEN_DSYNC)
        {
            if (openLogFile >= 0 &&
                !XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo,
                                 wal_segment_size))
                XLogFileClose();
            if (openLogFile < 0)
            {
                XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo,
                                wal_segment_size);
                openLogFile = XLogFileOpen(openLogSegNo);
                ReserveExternalFD();
            }

            issue_xlog_fsync(openLogFile, openLogSegNo);
        }

        /* signal that we need to wakeup walsenders later */
        WalSndWakeupRequest();

        LogwrtResult.Flush = LogwrtResult.Write;
    }

    /*
     * Update shared-memory status
     *
     * We make sure that the shared 'request' values do not fall behind the
     * 'result' values.  This is not absolutely essential, but it saves some
     * code in a couple of places.
     */
    {
        SpinLockAcquire(&XLogCtl->info_lck);
        XLogCtl->LogwrtResult = LogwrtResult;
        if (XLogCtl->LogwrtRqst.Write < LogwrtResult.Write)
            XLogCtl->LogwrtRqst.Write = LogwrtResult.Write;
        if (XLogCtl->LogwrtRqst.Flush < LogwrtResult.Flush)
            XLogCtl->LogwrtRqst.Flush = LogwrtResult.Flush;
        SpinLockRelease(&XLogCtl->info_lck);
    }
}

/*
 * Record the LSN for an asynchronous transaction commit/abort
 * and nudge the WALWriter if there is work for it to do.
 * (This should not be called for synchronous commits.)
 */
void
XLogSetAsyncXactLSN(XLogRecPtr asyncXactLSN)
{
    XLogRecPtr  WriteRqstPtr = asyncXactLSN;
    bool        sleeping;

    SpinLockAcquire(&XLogCtl->info_lck);
    LogwrtResult = XLogCtl->LogwrtResult;
    sleeping = XLogCtl->WalWriterSleeping;
    if (XLogCtl->asyncXactLSN < asyncXactLSN)
        XLogCtl->asyncXactLSN = asyncXactLSN;
    SpinLockRelease(&XLogCtl->info_lck);

    /*
     * If the WALWriter is sleeping, we should kick it to make it come out of
     * low-power mode.  Otherwise, determine whether there's a full page of
     * WAL available to write.
     */
    if (!sleeping)
    {
        /* back off to last completed page boundary */
        WriteRqstPtr -= WriteRqstPtr % XLOG_BLCKSZ;

        /* if we have already flushed that far, we're done */
        if (WriteRqstPtr <= LogwrtResult.Flush)
            return;
    }

    /*
     * Nudge the WALWriter: it has a full page of WAL to write, or we want it
     * to come out of low-power mode so that this async commit will reach disk
     * within the expected amount of time.
     */
    if (ProcGlobal->walwriterLatch)
        SetLatch(ProcGlobal->walwriterLatch);
}

/*
 * Record the LSN up to which we can remove WAL because it's not required by
 * any replication slot.
 */
void
XLogSetReplicationSlotMinimumLSN(XLogRecPtr lsn)
{
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->replicationSlotMinLSN = lsn;
    SpinLockRelease(&XLogCtl->info_lck);
}


/*
 * Return the oldest LSN we must retain to satisfy the needs of some
 * replication slot.
 */
static XLogRecPtr
XLogGetReplicationSlotMinimumLSN(void)
{
    XLogRecPtr  retval;

    SpinLockAcquire(&XLogCtl->info_lck);
    retval = XLogCtl->replicationSlotMinLSN;
    SpinLockRelease(&XLogCtl->info_lck);

    return retval;
}

/*
 * Advance minRecoveryPoint in control file.
 *
 * If we crash during recovery, we must reach this point again before the
 * database is consistent.
 *
 * If 'force' is true, 'lsn' argument is ignored. Otherwise, minRecoveryPoint
 * is only updated if it's not already greater than or equal to 'lsn'.
 */
static void
UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force)
{
    /* Quick check using our local copy of the variable */
    if (!updateMinRecoveryPoint || (!force && lsn <= minRecoveryPoint))
        return;

    /*
     * 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. The
     * local values of minRecoveryPoint and minRecoveryPointTLI should not be
     * updated until crash recovery finishes.  We only do this for the startup
     * process as it should not update its own reference of minRecoveryPoint
     * until it has finished crash recovery to make sure that all WAL
     * available is replayed in this case.  This also saves from extra locks
     * taken on the control file from the startup process.
     */
    if (XLogRecPtrIsInvalid(minRecoveryPoint) && InRecovery)
    {
        updateMinRecoveryPoint = false;
        return;
    }

    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

    /* update local copy */
    minRecoveryPoint = ControlFile->minRecoveryPoint;
    minRecoveryPointTLI = ControlFile->minRecoveryPointTLI;

    if (XLogRecPtrIsInvalid(minRecoveryPoint))
        updateMinRecoveryPoint = false;
    else if (force || minRecoveryPoint < lsn)
    {
        XLogRecPtr  newMinRecoveryPoint;
        TimeLineID  newMinRecoveryPointTLI;

        /*
         * To avoid having to update the control file too often, we update it
         * all the way to the last record being replayed, even though 'lsn'
         * would suffice for correctness.  This also allows the 'force' case
         * to not need a valid 'lsn' value.
         *
         * Another important reason for doing it this way is that the passed
         * 'lsn' value could be bogus, i.e., past the end of available WAL, if
         * the caller got it from a corrupted heap page.  Accepting such a
         * value as the min recovery point would prevent us from coming up at
         * all.  Instead, we just log a warning and continue with recovery.
         * (See also the comments about corrupt LSNs in XLogFlush.)
         */
        SpinLockAcquire(&XLogCtl->info_lck);
        newMinRecoveryPoint = XLogCtl->replayEndRecPtr;
        newMinRecoveryPointTLI = XLogCtl->replayEndTLI;
        SpinLockRelease(&XLogCtl->info_lck);

        if (!force && newMinRecoveryPoint < lsn)
            elog(WARNING,
                 "xlog min recovery request %X/%X is past current point %X/%X",
                 LSN_FORMAT_ARGS(lsn), LSN_FORMAT_ARGS(newMinRecoveryPoint));

        /* update control file */
        if (ControlFile->minRecoveryPoint < newMinRecoveryPoint)
        {
            ControlFile->minRecoveryPoint = newMinRecoveryPoint;
            ControlFile->minRecoveryPointTLI = newMinRecoveryPointTLI;
            UpdateControlFile();
            minRecoveryPoint = newMinRecoveryPoint;
            minRecoveryPointTLI = newMinRecoveryPointTLI;

            ereport(DEBUG2,
                    (errmsg_internal("updated min recovery point to %X/%X on timeline %u",
                                     LSN_FORMAT_ARGS(minRecoveryPoint),
                                     newMinRecoveryPointTLI)));
        }
    }
    LWLockRelease(ControlFileLock);
}

/*
 * Ensure that all XLOG data through the given position is flushed to disk.
 *
 * NOTE: this differs from XLogWrite mainly in that the WALWriteLock is not
 * already held, and we try to avoid acquiring it if possible.
 */
void
XLogFlush(XLogRecPtr record)
{
    XLogRecPtr  WriteRqstPtr;
    XLogwrtRqst WriteRqst;

    /*
     * 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;

        /* read LogwrtResult and update local state */
        SpinLockAcquire(&XLogCtl->info_lck);
        if (WriteRqstPtr < XLogCtl->LogwrtRqst.Write)
            WriteRqstPtr = XLogCtl->LogwrtRqst.Write;
        LogwrtResult = XLogCtl->LogwrtResult;
        SpinLockRelease(&XLogCtl->info_lck);

        /* done already? */
        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.
         */
        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 */
        LogwrtResult = XLogCtl->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, false);

        LWLockRelease(WALWriteLock);
        /* done */
        break;
    }

    END_CRIT_SECTION();

    /* wake up walsenders now that we've released heavily contended locks */
    WalSndWakeupProcessRequests();

    /*
     * 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));
}

/*
 * Write & flush xlog, but without specifying exactly where to.
 *
 * We normally write only completed blocks; but if there is nothing to do on
 * that basis, we check for unwritten async commits in the current incomplete
 * block, and write through the latest one of those.  Thus, if async commits
 * are not being used, we will write complete blocks only.
 *
 * If, based on the above, there's anything to write we do so immediately. But
 * to avoid calling fsync, fdatasync et. al. at a rate that'd impact
 * concurrent IO, we only flush WAL every wal_writer_delay ms, or if there's
 * more than wal_writer_flush_after unflushed blocks.
 *
 * We can guarantee that async commits reach disk after at most three
 * wal_writer_delay cycles. (When flushing complete blocks, we allow XLogWrite
 * to write "flexibly", meaning it can stop at the end of the buffer ring;
 * this makes a difference only with very high load or long wal_writer_delay,
 * but imposes one extra cycle for the worst case for async commits.)
 *
 * This routine is invoked periodically by the background walwriter process.
 *
 * Returns true if there was any work to do, even if we skipped flushing due
 * to wal_writer_delay/wal_writer_flush_after.
 */
bool
XLogBackgroundFlush(void)
{
    XLogwrtRqst WriteRqst;
    bool        flexible = true;
    static TimestampTz lastflush;
    TimestampTz now;
    int         flushbytes;

    /* XLOG doesn't need flushing during recovery */
    if (RecoveryInProgress())
        return false;

    /* read LogwrtResult and update local state */
    SpinLockAcquire(&XLogCtl->info_lck);
    LogwrtResult = XLogCtl->LogwrtResult;
    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 */
    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.
     */
    now = GetCurrentTimestamp();
    flushbytes =
        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 (flushbytes >= 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);
    LogwrtResult = XLogCtl->LogwrtResult;
    if (WriteRqst.Write > LogwrtResult.Write ||
        WriteRqst.Flush > LogwrtResult.Flush)
    {
        XLogWrite(WriteRqst, flexible);
    }
    LWLockRelease(WALWriteLock);

    END_CRIT_SECTION();

    /* wake up walsenders now that we've released heavily contended locks */
    WalSndWakeupProcessRequests();

    /*
     * 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, 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;
}

/*
 * Test whether XLOG data has been flushed up to (at least) the given position.
 *
 * Returns true if a flush is still needed.  (It may be that someone else
 * is already in process of flushing that far, however.)
 */
bool
XLogNeedsFlush(XLogRecPtr record)
{
    /*
     * 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(minRecoveryPoint) && InRecovery)
            updateMinRecoveryPoint = false;

        /* Quick exit if already known to be updated or cannot be updated */
        if (record <= minRecoveryPoint || !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;
        minRecoveryPoint = ControlFile->minRecoveryPoint;
        minRecoveryPointTLI = 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(minRecoveryPoint))
            updateMinRecoveryPoint = false;

        /* check again */
        if (record <= minRecoveryPoint || !updateMinRecoveryPoint)
            return false;
        else
            return true;
    }

    /* Quick exit if already known flushed */
    if (record <= LogwrtResult.Flush)
        return false;

    /* read LogwrtResult and update local state */
    SpinLockAcquire(&XLogCtl->info_lck);
    LogwrtResult = XLogCtl->LogwrtResult;
    SpinLockRelease(&XLogCtl->info_lck);

    /* check again */
    if (record <= LogwrtResult.Flush)
        return false;

    return true;
}

/*
 * Try to make a given XLOG file segment exist.
 *
 * logsegno: identify segment.
 *
 * *added: on return, true if this call raised the number of extant segments.
 *
 * path: on return, this char[MAXPGPATH] has the path to the logsegno file.
 *
 * Returns -1 or FD of opened file.  A -1 here is not an error; a caller
 * wanting an open segment should attempt to open "path", which usually will
 * succeed.  (This is weird, but it's efficient for the callers.)
 */
static int
XLogFileInitInternal(XLogSegNo logsegno, bool *added, char *path)
{
    char        tmppath[MAXPGPATH];
    PGAlignedXLogBlock zbuffer;
    XLogSegNo   installed_segno;
    XLogSegNo   max_segno;
    int         fd;
    int         save_errno;

    XLogFilePath(path, ThisTimeLineID, logsegno, wal_segment_size);

    /*
     * Try to use existent file (checkpoint maker may have created it already)
     */
    *added = false;
    fd = BasicOpenFile(path, O_RDWR | PG_BINARY | get_sync_bit(sync_method));
    if (fd < 0)
    {
        if (errno != ENOENT)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not open file \"%s\": %m", path)));
    }
    else
        return fd;

    /*
     * Initialize an empty (all zeroes) segment.  NOTE: it is possible that
     * another process is doing the same thing.  If so, we will end up
     * pre-creating an extra log segment.  That seems OK, and better than
     * holding the lock throughout this lengthy process.
     */
    elog(DEBUG2, "creating and filling new WAL file");

    snprintf(tmppath, MAXPGPATH, XLOGDIR "/xlogtemp.%d", (int) getpid());

    unlink(tmppath);

    /* do not use get_sync_bit() here --- want to fsync only at end of fill */
    fd = BasicOpenFile(tmppath, O_RDWR | O_CREAT | O_EXCL | PG_BINARY);
    if (fd < 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not create file \"%s\": %m", tmppath)));

    memset(zbuffer.data, 0, XLOG_BLCKSZ);

    pgstat_report_wait_start(WAIT_EVENT_WAL_INIT_WRITE);
    save_errno = 0;
    if (wal_init_zero)
    {
        struct iovec iov[PG_IOV_MAX];
        int         blocks;

        /*
         * Zero-fill the file.  With this setting, we do this the hard way to
         * ensure that all the file space has really been allocated.  On
         * platforms that allow "holes" in files, just seeking to the end
         * doesn't allocate intermediate space.  This way, we know that we
         * have all the space and (after the fsync below) that all the
         * indirect blocks are down on disk.  Therefore, fdatasync(2) or
         * O_DSYNC will be sufficient to sync future writes to the log file.
         */

        /* Prepare to write out a lot of copies of our zero buffer at once. */
        for (int i = 0; i < lengthof(iov); ++i)
        {
            iov[i].iov_base = zbuffer.data;
            iov[i].iov_len = XLOG_BLCKSZ;
        }

        /* Loop, writing as many blocks as we can for each system call. */
        blocks = wal_segment_size / XLOG_BLCKSZ;
        for (int i = 0; i < blocks;)
        {
            int         iovcnt = Min(blocks - i, lengthof(iov));
            off_t       offset = i * XLOG_BLCKSZ;

            if (pg_pwritev_with_retry(fd, iov, iovcnt, offset) < 0)
            {
                save_errno = errno;
                break;
            }

            i += iovcnt;
        }
    }
    else
    {
        /*
         * Otherwise, seeking to the end and writing a solitary byte is
         * enough.
         */
        errno = 0;
        if (pg_pwrite(fd, zbuffer.data, 1, wal_segment_size - 1) != 1)
        {
            /* if write didn't set errno, assume no disk space */
            save_errno = errno ? errno : ENOSPC;
        }
    }
    pgstat_report_wait_end();

    if (save_errno)
    {
        /*
         * If we fail to make the file, delete it to release disk space
         */
        unlink(tmppath);

        close(fd);

        errno = save_errno;

        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not write to file \"%s\": %m", tmppath)));
    }

    pgstat_report_wait_start(WAIT_EVENT_WAL_INIT_SYNC);
    if (pg_fsync(fd) != 0)
    {
        int         save_errno = errno;

        close(fd);
        errno = save_errno;
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not fsync file \"%s\": %m", tmppath)));
    }
    pgstat_report_wait_end();

    if (close(fd) != 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m", tmppath)));

    /*
     * Now move the segment into place with its final name.  Cope with
     * possibility that someone else has created the file while we were
     * filling ours: if so, use ours to pre-create a future log segment.
     */
    installed_segno = logsegno;

    /*
     * XXX: What should we use as max_segno? We used to use XLOGfileslop when
     * that was a constant, but that was always a bit dubious: normally, at a
     * checkpoint, XLOGfileslop was the offset from the checkpoint record, but
     * here, it was the offset from the insert location. We can't do the
     * normal XLOGfileslop calculation here because we don't have access to
     * the prior checkpoint's redo location. So somewhat arbitrarily, just use
     * CheckPointSegments.
     */
    max_segno = logsegno + CheckPointSegments;
    if (InstallXLogFileSegment(&installed_segno, tmppath, true, max_segno))
    {
        *added = true;
        elog(DEBUG2, "done creating and filling new WAL file");
    }
    else
    {
        /*
         * No need for any more future segments, or InstallXLogFileSegment()
         * failed to rename the file into place. If the rename failed, a
         * caller opening the file may fail.
         */
        unlink(tmppath);
        elog(DEBUG2, "abandoned new WAL file");
    }

    return -1;
}

/*
 * Create a new XLOG file segment, or open a pre-existing one.
 *
 * logsegno: identify segment to be created/opened.
 *
 * Returns FD of opened file.
 *
 * Note: errors here are ERROR not PANIC because we might or might not be
 * inside a critical section (eg, during checkpoint there is no reason to
 * take down the system on failure).  They will promote to PANIC if we are
 * in a critical section.
 */
int
XLogFileInit(XLogSegNo logsegno)
{
    bool        ignore_added;
    char        path[MAXPGPATH];
    int         fd;

    fd = XLogFileInitInternal(logsegno, &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 | get_sync_bit(sync_method));
    if (fd < 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));
    return fd;
}

/*
 * Create a new XLOG file segment by copying a pre-existing one.
 *
 * destsegno: identify segment to be created.
 *
 * srcTLI, srcsegno: identify segment to be copied (could be from
 *      a different timeline)
 *
 * upto: how much of the source file to copy (the rest is filled with
 *      zeros)
 *
 * Currently this is only used during recovery, and so there are no locking
 * considerations.  But we should be just as tense as XLogFileInit to avoid
 * emplacing a bogus file.
 */
static void
XLogFileCopy(XLogSegNo destsegno, TimeLineID srcTLI, XLogSegNo srcsegno,
             int upto)
{
    char        path[MAXPGPATH];
    char        tmppath[MAXPGPATH];
    PGAlignedXLogBlock buffer;
    int         srcfd;
    int         fd;
    int         nbytes;

    /*
     * Open the source file
     */
    XLogFilePath(path, srcTLI, srcsegno, wal_segment_size);
    srcfd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
    if (srcfd < 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));

    /*
     * Copy into a temp file name.
     */
    snprintf(tmppath, MAXPGPATH, XLOGDIR "/xlogtemp.%d", (int) getpid());

    unlink(tmppath);

    /* do not use get_sync_bit() here --- want to fsync only at end of fill */
    fd = OpenTransientFile(tmppath, O_RDWR | O_CREAT | O_EXCL | PG_BINARY);
    if (fd < 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not create file \"%s\": %m", tmppath)));

    /*
     * Do the data copying.
     */
    for (nbytes = 0; nbytes < wal_segment_size; nbytes += sizeof(buffer))
    {
        int         nread;

        nread = upto - nbytes;

        /*
         * The part that is not read from the source file is filled with
         * zeros.
         */
        if (nread < sizeof(buffer))
            memset(buffer.data, 0, sizeof(buffer));

        if (nread > 0)
        {
            int         r;

            if (nread > sizeof(buffer))
                nread = sizeof(buffer);
            pgstat_report_wait_start(WAIT_EVENT_WAL_COPY_READ);
            r = read(srcfd, buffer.data, nread);
            if (r != nread)
            {
                if (r < 0)
                    ereport(ERROR,
                            (errcode_for_file_access(),
                             errmsg("could not read file \"%s\": %m",
                                    path)));
                else
                    ereport(ERROR,
                            (errcode(ERRCODE_DATA_CORRUPTED),
                             errmsg("could not read file \"%s\": read %d of %zu",
                                    path, r, (Size) nread)));
            }
            pgstat_report_wait_end();
        }
        errno = 0;
        pgstat_report_wait_start(WAIT_EVENT_WAL_COPY_WRITE);
        if ((int) write(fd, buffer.data, sizeof(buffer)) != (int) sizeof(buffer))
        {
            int         save_errno = errno;

            /*
             * If we fail to make the file, delete it to release disk space
             */
            unlink(tmppath);
            /* if write didn't set errno, assume problem is no disk space */
            errno = save_errno ? save_errno : ENOSPC;

            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not write to file \"%s\": %m", tmppath)));
        }
        pgstat_report_wait_end();
    }

    pgstat_report_wait_start(WAIT_EVENT_WAL_COPY_SYNC);
    if (pg_fsync(fd) != 0)
        ereport(data_sync_elevel(ERROR),
                (errcode_for_file_access(),
                 errmsg("could not fsync file \"%s\": %m", tmppath)));
    pgstat_report_wait_end();

    if (CloseTransientFile(fd) != 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m", tmppath)));

    if (CloseTransientFile(srcfd) != 0)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m", path)));

    /*
     * Now move the segment into place with its final name.
     */
    if (!InstallXLogFileSegment(&destsegno, tmppath, false, 0))
        elog(ERROR, "InstallXLogFileSegment should not have failed");
}

/*
 * Install a new XLOG segment file as a current or future log segment.
 *
 * This is used both to install a newly-created segment (which has a temp
 * filename while it's being created) and to recycle an old segment.
 *
 * *segno: identify segment to install as (or first possible target).
 * When find_free is true, this is modified on return to indicate the
 * actual installation location or last segment searched.
 *
 * tmppath: initial name of file to install.  It will be renamed into place.
 *
 * find_free: if true, install the new segment at the first empty segno
 * number at or after the passed numbers.  If false, install the new segment
 * exactly where specified, deleting any existing segment file there.
 *
 * max_segno: maximum segment number to install the new file as.  Fail if no
 * free slot is found between *segno and max_segno. (Ignored when find_free
 * is false.)
 *
 * Returns true if the file was installed successfully.  false indicates that
 * max_segno limit was exceeded, the startup process has disabled this
 * function for now, or an error occurred while renaming the file into place.
 */
static bool
InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
                       bool find_free, XLogSegNo max_segno)
{
    char        path[MAXPGPATH];
    struct stat stat_buf;

    XLogFilePath(path, ThisTimeLineID, *segno, wal_segment_size);

    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    if (!XLogCtl->InstallXLogFileSegmentActive)
    {
        LWLockRelease(ControlFileLock);
        return false;
    }

    if (!find_free)
    {
        /* Force installation: get rid of any pre-existing segment file */
        durable_unlink(path, DEBUG1);
    }
    else
    {
        /* Find a free slot to put it in */
        while (stat(path, &stat_buf) == 0)
        {
            if ((*segno) >= max_segno)
            {
                /* Failed to find a free slot within specified range */
                LWLockRelease(ControlFileLock);
                return false;
            }
            (*segno)++;
            XLogFilePath(path, ThisTimeLineID, *segno, wal_segment_size);
        }
    }

    /*
     * Perform the rename using link if available, paranoidly trying to avoid
     * overwriting an existing file (there shouldn't be one).
     */
    if (durable_rename_excl(tmppath, path, LOG) != 0)
    {
        LWLockRelease(ControlFileLock);
        /* durable_rename_excl already emitted log message */
        return false;
    }

    LWLockRelease(ControlFileLock);

    return true;
}

/*
 * Open a pre-existing logfile segment for writing.
 */
int
XLogFileOpen(XLogSegNo segno)
{
    char        path[MAXPGPATH];
    int         fd;

    XLogFilePath(path, ThisTimeLineID, segno, wal_segment_size);

    fd = BasicOpenFile(path, O_RDWR | PG_BINARY | get_sync_bit(sync_method));
    if (fd < 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));

    return fd;
}

/*
 * Open a logfile segment for reading (during recovery).
 *
 * If source == XLOG_FROM_ARCHIVE, the segment is retrieved from archive.
 * Otherwise, it's assumed to be already available in pg_wal.
 */
static int
XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli,
             XLogSource source, bool notfoundOk)
{
    char        xlogfname[MAXFNAMELEN];
    char        activitymsg[MAXFNAMELEN + 16];
    char        path[MAXPGPATH];
    int         fd;

    XLogFileName(xlogfname, tli, segno, wal_segment_size);

    switch (source)
    {
        case XLOG_FROM_ARCHIVE:
            /* Report recovery progress in PS display */
            snprintf(activitymsg, sizeof(activitymsg), "waiting for %s",
                     xlogfname);
            set_ps_display(activitymsg);

            if (!RestoreArchivedFile(path, xlogfname,
                                     "RECOVERYXLOG",
                                     wal_segment_size,
                                     InRedo))
                return -1;
            break;

        case XLOG_FROM_PG_WAL:
        case XLOG_FROM_STREAM:
            XLogFilePath(path, tli, segno, wal_segment_size);
            break;

        default:
            elog(ERROR, "invalid XLogFileRead source %d", source);
    }

    /*
     * If the segment was fetched from archival storage, replace the existing
     * xlog segment (if any) with the archival version.
     */
    if (source == XLOG_FROM_ARCHIVE)
    {
        Assert(!XLogCtl->InstallXLogFileSegmentActive);
        KeepFileRestoredFromArchive(path, xlogfname);

        /*
         * Set path to point at the new file in pg_wal.
         */
        snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlogfname);
    }

    fd = BasicOpenFile(path, O_RDONLY | PG_BINARY);
    if (fd >= 0)
    {
        /* Success! */
        curFileTLI = tli;

        /* Report recovery progress in PS display */
        snprintf(activitymsg, sizeof(activitymsg), "recovering %s",
                 xlogfname);
        set_ps_display(activitymsg);

        /* Track source of data in assorted state variables */
        readSource = source;
        XLogReceiptSource = source;
        /* In FROM_STREAM case, caller tracks receipt time, not me */
        if (source != XLOG_FROM_STREAM)
            XLogReceiptTime = GetCurrentTimestamp();

        return fd;
    }
    if (errno != ENOENT || !notfoundOk) /* unexpected failure? */
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m", path)));
    return -1;
}

/*
 * Open a logfile segment for reading (during recovery).
 *
 * This version searches for the segment with any TLI listed in expectedTLEs.
 */
static int
XLogFileReadAnyTLI(XLogSegNo segno, int emode, XLogSource source)
{
    char        path[MAXPGPATH];
    ListCell   *cell;
    int         fd;
    List       *tles;

    /*
     * Loop looking for a suitable timeline ID: we might need to read any of
     * the timelines listed in expectedTLEs.
     *
     * We expect curFileTLI on entry to be the TLI of the preceding file in
     * sequence, or 0 if there was no predecessor.  We do not allow curFileTLI
     * to go backwards; this prevents us from picking up the wrong file when a
     * parent timeline extends to higher segment numbers than the child we
     * want to read.
     *
     * If we haven't read the timeline history file yet, read it now, so that
     * we know which TLIs to scan.  We don't save the list in expectedTLEs,
     * however, unless we actually find a valid segment.  That way if there is
     * neither a timeline history file nor a WAL segment in the archive, and
     * streaming replication is set up, we'll read the timeline history file
     * streamed from the primary when we start streaming, instead of
     * recovering with a dummy history generated here.
     */
    if (expectedTLEs)
        tles = expectedTLEs;
    else
        tles = readTimeLineHistory(recoveryTargetTLI);

    foreach(cell, tles)
    {
        TimeLineHistoryEntry *hent = (TimeLineHistoryEntry *) lfirst(cell);
        TimeLineID  tli = hent->tli;

        if (tli < curFileTLI)
            break;              /* don't bother looking at too-old TLIs */

        /*
         * Skip scanning the timeline ID that the logfile segment to read
         * doesn't belong to
         */
        if (hent->begin != InvalidXLogRecPtr)
        {
            XLogSegNo   beginseg = 0;

            XLByteToSeg(hent->begin, beginseg, wal_segment_size);

            /*
             * The logfile segment that doesn't belong to the timeline is
             * older or newer than the segment that the timeline started or
             * ended at, respectively. It's sufficient to check only the
             * starting segment of the timeline here. Since the timelines are
             * scanned in descending order in this loop, any segments newer
             * than the ending segment should belong to newer timeline and
             * have already been read before. So it's not necessary to check
             * the ending segment of the timeline here.
             */
            if (segno < beginseg)
                continue;
        }

        if (source == XLOG_FROM_ANY || source == XLOG_FROM_ARCHIVE)
        {
            fd = XLogFileRead(segno, emode, tli,
                              XLOG_FROM_ARCHIVE, true);
            if (fd != -1)
            {
                elog(DEBUG1, "got WAL segment from archive");
                if (!expectedTLEs)
                    expectedTLEs = tles;
                return fd;
            }
        }

        if (source == XLOG_FROM_ANY || source == XLOG_FROM_PG_WAL)
        {
            fd = XLogFileRead(segno, emode, tli,
                              XLOG_FROM_PG_WAL, true);
            if (fd != -1)
            {
                if (!expectedTLEs)
                    expectedTLEs = tles;
                return fd;
            }
        }
    }

    /* Couldn't find it.  For simplicity, complain about front timeline */
    XLogFilePath(path, recoveryTargetTLI, segno, wal_segment_size);
    errno = ENOENT;
    ereport(emode,
            (errcode_for_file_access(),
             errmsg("could not open file \"%s\": %m", path)));
    return -1;
}

/*
 * Close the current logfile segment for writing.
 */
static void
XLogFileClose(void)
{
    Assert(openLogFile >= 0);

    /*
     * WAL segment files will not be re-read in normal operation, so we advise
     * the OS to release any cached pages.  But do not do so if WAL archiving
     * or streaming is active, because archiver and walsender process could
     * use the cache to read the WAL segment.
     */
#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED)
    if (!XLogIsNeeded())
        (void) posix_fadvise(openLogFile, 0, 0, POSIX_FADV_DONTNEED);
#endif

    if (close(openLogFile) != 0)
    {
        char        xlogfname[MAXFNAMELEN];
        int         save_errno = errno;

        XLogFileName(xlogfname, ThisTimeLineID, openLogSegNo, wal_segment_size);
        errno = save_errno;
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m", xlogfname)));
    }

    openLogFile = -1;
    ReleaseExternalFD();
}

/*
 * Preallocate log files beyond the specified log endpoint.
 *
 * XXX this is currently extremely conservative, since it forces only one
 * future log segment to exist, and even that only if we are 75% done with
 * the current one.  This is only appropriate for very low-WAL-volume systems.
 * High-volume systems will be OK once they've built up a sufficient set of
 * recycled log segments, but the startup transient is likely to include
 * a lot of segment creations by foreground processes, which is not so good.
 *
 * XLogFileInitInternal() can ereport(ERROR).  All known causes indicate big
 * trouble; for example, a full filesystem is one cause.  The checkpoint WAL
 * and/or ControlFile updates already completed.  If a RequestCheckpoint()
 * initiated the present checkpoint and an ERROR ends this function, the
 * command that called RequestCheckpoint() fails.  That's not ideal, but it's
 * not worth contorting more functions to use caller-specified elevel values.
 * (With or without RequestCheckpoint(), an ERROR forestalls some inessential
 * reporting and resource reclamation.)
 */
static void
PreallocXlogFiles(XLogRecPtr endptr)
{
    XLogSegNo   _logSegNo;
    int         lf;
    bool        added;
    char        path[MAXPGPATH];
    uint64      offset;

    if (!XLogCtl->InstallXLogFileSegmentActive)
        return;                 /* unlocked check says no */

    XLByteToPrevSeg(endptr, _logSegNo, wal_segment_size);
    offset = XLogSegmentOffset(endptr - 1, wal_segment_size);
    if (offset >= (uint32) (0.75 * wal_segment_size))
    {
        _logSegNo++;
        lf = XLogFileInitInternal(_logSegNo, &added, path);
        if (lf >= 0)
            close(lf);
        if (added)
            CheckpointStats.ckpt_segs_added++;
    }
}

/*
 * Throws an error if the given log segment has already been removed or
 * recycled. The caller should only pass a segment that it knows to have
 * existed while the server has been running, as this function always
 * succeeds if no WAL segments have been removed since startup.
 * 'tli' is only used in the error message.
 *
 * Note: this function guarantees to keep errno unchanged on return.
 * This supports callers that use this to possibly deliver a better
 * error message about a missing file, while still being able to throw
 * a normal file-access error afterwards, if this does return.
 */
void
CheckXLogRemoved(XLogSegNo segno, TimeLineID tli)
{
    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;
}

/*
 * Return the last WAL segment removed, or 0 if no segment has been removed
 * since startup.
 *
 * NB: the result can be out of date arbitrarily fast, the caller has to deal
 * with that.
 */
XLogSegNo
XLogGetLastRemovedSegno(void)
{
    XLogSegNo   lastRemovedSegNo;

    SpinLockAcquire(&XLogCtl->info_lck);
    lastRemovedSegNo = XLogCtl->lastRemovedSegNo;
    SpinLockRelease(&XLogCtl->info_lck);

    return lastRemovedSegNo;
}


/*
 * Update the last removed segno pointer in shared memory, to reflect that the
 * given XLOG file has been removed.
 */
static void
UpdateLastRemovedPtr(char *filename)
{
    uint32      tli;
    XLogSegNo   segno;

    XLogFromFileName(filename, &tli, &segno, wal_segment_size);

    SpinLockAcquire(&XLogCtl->info_lck);
    if (segno > XLogCtl->lastRemovedSegNo)
        XLogCtl->lastRemovedSegNo = segno;
    SpinLockRelease(&XLogCtl->info_lck);
}

/*
 * Remove all temporary log files in pg_wal
 *
 * This is called at the beginning of recovery after a previous crash,
 * at a point where no other processes write fresh WAL data.
 */
static void
RemoveTempXlogFiles(void)
{
    DIR        *xldir;
    struct dirent *xlde;

    elog(DEBUG2, "removing all temporary WAL segments");

    xldir = AllocateDir(XLOGDIR);
    while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
    {
        char        path[MAXPGPATH];

        if (strncmp(xlde->d_name, "xlogtemp.", 9) != 0)
            continue;

        snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlde->d_name);
        unlink(path);
        elog(DEBUG2, "removed temporary WAL segment \"%s\"", path);
    }
    FreeDir(xldir);
}

/*
 * Recycle or remove all log files older or equal to passed segno.
 *
 * endptr is current (or recent) end of xlog, and lastredoptr is the
 * redo pointer of the last checkpoint. These are used to determine
 * whether we want to recycle rather than delete no-longer-wanted log files.
 */
static void
RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr lastredoptr, XLogRecPtr endptr)
{
    DIR        *xldir;
    struct dirent *xlde;
    char        lastoff[MAXFNAMELEN];
    XLogSegNo   endlogSegNo;
    XLogSegNo   recycleSegNo;

    /* Initialize info about where to try to recycle to */
    XLByteToSeg(endptr, endlogSegNo, wal_segment_size);
    recycleSegNo = XLOGfileslop(lastredoptr);

    /*
     * Construct a filename of the last segment to be kept. The timeline ID
     * doesn't matter, we ignore that in the comparison. (During recovery,
     * ThisTimeLineID isn't set, so we can't use that.)
     */
    XLogFileName(lastoff, 0, segno, wal_segment_size);

    elog(DEBUG2, "attempting to remove WAL segments older than log file %s",
         lastoff);

    xldir = AllocateDir(XLOGDIR);

    while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
    {
        /* Ignore files that are not XLOG segments */
        if (!IsXLogFileName(xlde->d_name) &&
            !IsPartialXLogFileName(xlde->d_name))
            continue;

        /*
         * We ignore the timeline part of the XLOG segment identifiers in
         * deciding whether a segment is still needed.  This ensures that we
         * won't prematurely remove a segment from a parent timeline. We could
         * probably be a little more proactive about removing segments of
         * non-parent timelines, but that would be a whole lot more
         * complicated.
         *
         * We use the alphanumeric sorting property of the filenames to decide
         * which ones are earlier than the lastoff segment.
         */
        if (strcmp(xlde->d_name + 8, lastoff + 8) <= 0)
        {
            if (XLogArchiveCheckDone(xlde->d_name))
            {
                /* Update the last removed location in shared memory first */
                UpdateLastRemovedPtr(xlde->d_name);

                RemoveXlogFile(xlde->d_name, recycleSegNo, &endlogSegNo);
            }
        }
    }

    FreeDir(xldir);
}

/*
 * Remove WAL files that are not part of the given timeline's history.
 *
 * This is called during recovery, whenever we switch to follow a new
 * timeline, and at the end of recovery when we create a new timeline. We
 * wouldn't otherwise care about extra WAL files lying in pg_wal, but they
 * might be leftover pre-allocated or recycled WAL segments on the old timeline
 * that we haven't used yet, and contain garbage. If we just leave them in
 * pg_wal, they will eventually be archived, and we can't let that happen.
 * Files that belong to our timeline history are valid, because we have
 * successfully replayed them, but from others we can't be sure.
 *
 * 'switchpoint' is the current point in WAL where we switch to new timeline,
 * and 'newTLI' is the new timeline we switch to.
 */
static void
RemoveNonParentXlogFiles(XLogRecPtr switchpoint, TimeLineID newTLI)
{
    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->d_name, recycleSegNo, &endLogSegNo);
        }
    }

    FreeDir(xldir);
}

/*
 * Recycle or remove a log file that's no longer needed.
 *
 * segname is the name of the segment to recycle or remove.  recycleSegNo
 * is the segment number to recycle up to.  endlogSegNo is the segment
 * number of the current (or recent) end of WAL.
 *
 * endlogSegNo gets incremented if the segment is recycled so as it is not
 * checked again with future callers of this function.
 */
static void
RemoveXlogFile(const char *segname, XLogSegNo recycleSegNo,
               XLogSegNo *endlogSegNo)
{
    char        path[MAXPGPATH];
#ifdef WIN32
    char        newpath[MAXPGPATH];
#endif
    struct stat statbuf;

    snprintf(path, MAXPGPATH, XLOGDIR "/%s", segname);

    /*
     * Before deleting the file, see if it can be recycled as a future log
     * segment. Only recycle normal files, because we don't want to recycle
     * symbolic links pointing to a separate archive directory.
     */
    if (wal_recycle &&
        *endlogSegNo <= recycleSegNo &&
        XLogCtl->InstallXLogFileSegmentActive &&    /* callee rechecks this */
        lstat(path, &statbuf) == 0 && S_ISREG(statbuf.st_mode) &&
        InstallXLogFileSegment(endlogSegNo, path,
                               true, recycleSegNo))
    {
        ereport(DEBUG2,
                (errmsg_internal("recycled write-ahead log file \"%s\"",
                                 segname)));
        CheckpointStats.ckpt_segs_recycled++;
        /* Needn't recheck that slot on future iterations */
        (*endlogSegNo)++;
    }
    else
    {
        /* No need for any more future segments, or recycling failed ... */
        int         rc;

        ereport(DEBUG2,
                (errmsg_internal("removing write-ahead log file \"%s\"",
                                 segname)));

#ifdef WIN32

        /*
         * On Windows, if another process (e.g another backend) holds the file
         * open in FILE_SHARE_DELETE mode, unlink will succeed, but the file
         * will still show up in directory listing until the last handle is
         * closed. To avoid confusing the lingering deleted file for a live
         * WAL file that needs to be archived, rename it before deleting it.
         *
         * If another process holds the file open without FILE_SHARE_DELETE
         * flag, rename will fail. We'll try again at the next checkpoint.
         */
        snprintf(newpath, MAXPGPATH, "%s.deleted", path);
        if (rename(path, newpath) != 0)
        {
            ereport(LOG,
                    (errcode_for_file_access(),
                     errmsg("could not rename file \"%s\": %m",
                            path)));
            return;
        }
        rc = durable_unlink(newpath, LOG);
#else
        rc = durable_unlink(path, LOG);
#endif
        if (rc != 0)
        {
            /* Message already logged by durable_unlink() */
            return;
        }
        CheckpointStats.ckpt_segs_removed++;
    }

    XLogArchiveCleanup(segname);
}

/*
 * Verify whether pg_wal and pg_wal/archive_status exist.
 * If the latter does not exist, recreate it.
 *
 * It is not the goal of this function to verify the contents of these
 * directories, but to help in cases where someone has performed a cluster
 * copy for PITR purposes but omitted pg_wal from the copy.
 *
 * We could also recreate pg_wal if it doesn't exist, but a deliberate
 * policy decision was made not to.  It is fairly common for pg_wal to be
 * a symlink, and if that was the DBA's intent then automatically making a
 * plain directory would result in degraded performance with no notice.
 */
static void
ValidateXLOGDirectoryStructure(void)
{
    char        path[MAXPGPATH];
    struct stat stat_buf;

    /* Check for pg_wal; if it doesn't exist, error out */
    if (stat(XLOGDIR, &stat_buf) != 0 ||
        !S_ISDIR(stat_buf.st_mode))
        ereport(FATAL,
                (errmsg("required WAL directory \"%s\" does not exist",
                        XLOGDIR)));

    /* Check for archive_status */
    snprintf(path, MAXPGPATH, XLOGDIR "/archive_status");
    if (stat(path, &stat_buf) == 0)
    {
        /* Check for weird cases where it exists but isn't a directory */
        if (!S_ISDIR(stat_buf.st_mode))
            ereport(FATAL,
                    (errmsg("required WAL directory \"%s\" does not exist",
                            path)));
    }
    else
    {
        ereport(LOG,
                (errmsg("creating missing WAL directory \"%s\"", path)));
        if (MakePGDirectory(path) < 0)
            ereport(FATAL,
                    (errmsg("could not create missing directory \"%s\": %m",
                            path)));
    }
}

/*
 * Remove previous backup history files.  This also retries creation of
 * .ready files for any backup history files for which XLogArchiveNotify
 * failed earlier.
 */
static void
CleanupBackupHistory(void)
{
    DIR        *xldir;
    struct dirent *xlde;
    char        path[MAXPGPATH + sizeof(XLOGDIR)];

    xldir = AllocateDir(XLOGDIR);

    while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
    {
        if (IsBackupHistoryFileName(xlde->d_name))
        {
            if (XLogArchiveCheckDone(xlde->d_name))
            {
                elog(DEBUG2, "removing WAL backup history file \"%s\"",
                     xlde->d_name);
                snprintf(path, sizeof(path), XLOGDIR "/%s", xlde->d_name);
                unlink(path);
                XLogArchiveCleanup(xlde->d_name);
            }
        }
    }

    FreeDir(xldir);
}

/*
 * Attempt to read the next XLOG record.
 *
 * Before first call, the reader needs to be positioned to the first record
 * by calling XLogBeginRead().
 *
 * If no valid record is available, returns NULL, or fails if emode is PANIC.
 * (emode must be either PANIC, LOG). In standby mode, retries until a valid
 * record is available.
 */
static XLogRecord *
ReadRecord(XLogReaderState *xlogreader, int emode,
           bool fetching_ckpt)
{
    XLogRecord *record;
    XLogPageReadPrivate *private = (XLogPageReadPrivate *) xlogreader->private_data;

    /* Pass through parameters to XLogPageRead */
    private->fetching_ckpt = fetching_ckpt;
    private->emode = emode;
    private->randAccess = (xlogreader->ReadRecPtr == InvalidXLogRecPtr);

    /* This is the first attempt to read this page. */
    lastSourceFailed = false;

    for (;;)
    {
        char       *errormsg;

        record = XLogReadRecord(xlogreader, &errormsg);
        ReadRecPtr = xlogreader->ReadRecPtr;
        EndRecPtr = xlogreader->EndRecPtr;
        if (record == NULL)
        {
            if (readFile >= 0)
            {
                close(readFile);
                readFile = -1;
            }

            /*
             * We only end up here without a message when XLogPageRead()
             * failed - in that case we already logged something. In
             * StandbyMode that only happens if we have been triggered, so we
             * shouldn't loop anymore in that case.
             */
            if (errormsg)
                ereport(emode_for_corrupt_record(emode, EndRecPtr),
                        (errmsg_internal("%s", errormsg) /* already translated */ ));
        }

        /*
         * Check page TLI is one of the expected values.
         */
        else if (!tliInHistory(xlogreader->latestPageTLI, expectedTLEs))
        {
            char        fname[MAXFNAMELEN];
            XLogSegNo   segno;
            int32       offset;

            XLByteToSeg(xlogreader->latestPagePtr, segno, wal_segment_size);
            offset = XLogSegmentOffset(xlogreader->latestPagePtr,
                                       wal_segment_size);
            XLogFileName(fname, xlogreader->seg.ws_tli, segno,
                         wal_segment_size);
            ereport(emode_for_corrupt_record(emode, EndRecPtr),
                    (errmsg("unexpected timeline ID %u in log segment %s, offset %u",
                            xlogreader->latestPageTLI,
                            fname,
                            offset)));
            record = NULL;
        }

        if (record)
        {
            /* Great, got a record */
            return record;
        }
        else
        {
            /* No valid record available from this source */
            lastSourceFailed = true;

            /*
             * If archive recovery was requested, but we were still doing
             * crash recovery, switch to archive recovery and retry using the
             * offline archive. We have now replayed all the valid WAL in
             * pg_wal, so we are presumably now consistent.
             *
             * We require that there's at least some valid WAL present in
             * pg_wal, however (!fetching_ckpt).  We could recover using the
             * WAL from the archive, even if pg_wal is completely empty, but
             * we'd have no idea how far we'd have to replay to reach
             * consistency.  So err on the safe side and give up.
             */
            if (!InArchiveRecovery && ArchiveRecoveryRequested &&
                !fetching_ckpt)
            {
                ereport(DEBUG1,
                        (errmsg_internal("reached end of WAL in pg_wal, entering archive recovery")));
                InArchiveRecovery = true;
                if (StandbyModeRequested)
                    StandbyMode = true;

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

                /*
                 * The startup process can update its local copy of
                 * minRecoveryPoint from this point.
                 */
                updateMinRecoveryPoint = true;

                UpdateControlFile();

                /*
                 * We update SharedRecoveryState while holding the lock on
                 * ControlFileLock so both states are consistent in shared
                 * memory.
                 */
                SpinLockAcquire(&XLogCtl->info_lck);
                XLogCtl->SharedRecoveryState = RECOVERY_STATE_ARCHIVE;
                SpinLockRelease(&XLogCtl->info_lck);

                LWLockRelease(ControlFileLock);

                CheckRecoveryConsistency();

                /*
                 * Before we retry, reset lastSourceFailed and currentSource
                 * so that we will check the archive next.
                 */
                lastSourceFailed = false;
                currentSource = XLOG_FROM_ANY;

                continue;
            }

            /* In standby mode, loop back to retry. Otherwise, give up. */
            if (StandbyMode && !CheckForStandbyTrigger())
                continue;
            else
                return NULL;
        }
    }
}

/*
 * Scan for new timelines that might have appeared in the archive since we
 * started recovery.
 *
 * If there are any, the function changes recovery target TLI to the latest
 * one and returns 'true'.
 */
static bool
rescanLatestTimeLine(void)
{
    List       *newExpectedTLEs;
    bool        found;
    ListCell   *cell;
    TimeLineID  newtarget;
    TimeLineID  oldtarget = recoveryTargetTLI;
    TimeLineHistoryEntry *currentTle = NULL;

    newtarget = findNewestTimeLine(recoveryTargetTLI);
    if (newtarget == recoveryTargetTLI)
    {
        /* No new timelines found */
        return false;
    }

    /*
     * Determine the list of expected TLIs for the new TLI
     */

    newExpectedTLEs = readTimeLineHistory(newtarget);

    /*
     * If the current timeline is not part of the history of the new timeline,
     * we cannot proceed to it.
     */
    found = false;
    foreach(cell, newExpectedTLEs)
    {
        currentTle = (TimeLineHistoryEntry *) lfirst(cell);

        if (currentTle->tli == recoveryTargetTLI)
        {
            found = true;
            break;
        }
    }
    if (!found)
    {
        ereport(LOG,
                (errmsg("new timeline %u is not a child of database system timeline %u",
                        newtarget,
                        ThisTimeLineID)));
        return false;
    }

    /*
     * The current timeline was found in the history file, but check that the
     * next timeline was forked off from it *after* the current recovery
     * location.
     */
    if (currentTle->end < EndRecPtr)
    {
        ereport(LOG,
                (errmsg("new timeline %u forked off current database system timeline %u before current recovery point %X/%X",
                        newtarget,
                        ThisTimeLineID,
                        LSN_FORMAT_ARGS(EndRecPtr))));
        return false;
    }

    /* The new timeline history seems valid. Switch target */
    recoveryTargetTLI = newtarget;
    list_free_deep(expectedTLEs);
    expectedTLEs = newExpectedTLEs;

    /*
     * As in StartupXLOG(), try to ensure we have all the history files
     * between the old target and new target in pg_wal.
     */
    restoreTimeLineHistoryFiles(oldtarget + 1, newtarget);

    ereport(LOG,
            (errmsg("new target timeline is %u",
                    recoveryTargetTLI)));

    return true;
}

/*
 * I/O routines for pg_control
 *
 * *ControlFile is a buffer in shared memory that holds an image of the
 * contents of pg_control.  WriteControlFile() initializes pg_control
 * given a preloaded buffer, ReadControlFile() loads the buffer from
 * the pg_control file (during postmaster or standalone-backend startup),
 * and UpdateControlFile() rewrites pg_control after we modify xlog state.
 * InitControlFile() fills the buffer with initial values.
 *
 * For simplicity, WriteControlFile() initializes the fields of pg_control
 * that are related to checking backend/database compatibility, and
 * ReadControlFile() verifies they are correct.  We could split out the
 * I/O and compatibility-check functions, but there seems no need currently.
 */

static void
InitControlFile(uint64 sysidentifier)
{
    char        mock_auth_nonce[MOCK_AUTH_NONCE_LEN];

    /*
     * Generate a random nonce. This is used for authentication requests that
     * will fail because the user does not exist. The nonce is used to create
     * a genuine-looking password challenge for the non-existent user, in lieu
     * of an actual stored password.
     */
    if (!pg_strong_random(mock_auth_nonce, MOCK_AUTH_NONCE_LEN))
        ereport(PANIC,
                (errcode(ERRCODE_INTERNAL_ERROR),
                 errmsg("could not generate secret authorization token")));

    memset(ControlFile, 0, sizeof(ControlFileData));
    /* Initialize pg_control status fields */
    ControlFile->system_identifier = sysidentifier;
    memcpy(ControlFile->mock_authentication_nonce, mock_auth_nonce, MOCK_AUTH_NONCE_LEN);
    ControlFile->state = DB_SHUTDOWNED;
    ControlFile->unloggedLSN = FirstNormalUnloggedLSN;

    /* Set important parameter values for use when replaying WAL */
    ControlFile->MaxConnections = MaxConnections;
    ControlFile->max_worker_processes = max_worker_processes;
    ControlFile->max_wal_senders = max_wal_senders;
    ControlFile->max_prepared_xacts = max_prepared_xacts;
    ControlFile->max_locks_per_xact = max_locks_per_xact;
    ControlFile->wal_level = wal_level;
    ControlFile->wal_log_hints = wal_log_hints;
    ControlFile->track_commit_timestamp = track_commit_timestamp;
    ControlFile->data_checksum_version = bootstrap_data_checksum_version;
}

static void
WriteControlFile(void)
{
    int         fd;
    char        buffer[PG_CONTROL_FILE_SIZE];   /* need not be aligned */

    /*
     * Ensure that the size of the pg_control data structure is sane.  See the
     * comments for these symbols in pg_control.h.
     */
    StaticAssertStmt(sizeof(ControlFileData) <= PG_CONTROL_MAX_SAFE_SIZE,
                     "pg_control is too large for atomic disk writes");
    StaticAssertStmt(sizeof(ControlFileData) <= PG_CONTROL_FILE_SIZE,
                     "sizeof(ControlFileData) exceeds PG_CONTROL_FILE_SIZE");

    /*
     * Initialize version and compatibility-check fields
     */
    ControlFile->pg_control_version = PG_CONTROL_VERSION;
    ControlFile->catalog_version_no = CATALOG_VERSION_NO;

    ControlFile->maxAlign = MAXIMUM_ALIGNOF;
    ControlFile->floatFormat = FLOATFORMAT_VALUE;

    ControlFile->blcksz = BLCKSZ;
    ControlFile->relseg_size = RELSEG_SIZE;
    ControlFile->xlog_blcksz = XLOG_BLCKSZ;
    ControlFile->xlog_seg_size = wal_segment_size;

    ControlFile->nameDataLen = NAMEDATALEN;
    ControlFile->indexMaxKeys = INDEX_MAX_KEYS;

    ControlFile->toast_max_chunk_size = TOAST_MAX_CHUNK_SIZE;
    ControlFile->loblksize = LOBLKSIZE;

    ControlFile->float8ByVal = FLOAT8PASSBYVAL;

    /* Contents are protected with a CRC */
    INIT_CRC32C(ControlFile->crc);
    COMP_CRC32C(ControlFile->crc,
                (char *) ControlFile,
                offsetof(ControlFileData, crc));
    FIN_CRC32C(ControlFile->crc);

    /*
     * We write out PG_CONTROL_FILE_SIZE bytes into pg_control, zero-padding
     * the excess over sizeof(ControlFileData).  This reduces the odds of
     * premature-EOF errors when reading pg_control.  We'll still fail when we
     * check the contents of the file, but hopefully with a more specific
     * error than "couldn't read pg_control".
     */
    memset(buffer, 0, PG_CONTROL_FILE_SIZE);
    memcpy(buffer, ControlFile, sizeof(ControlFileData));

    fd = BasicOpenFile(XLOG_CONTROL_FILE,
                       O_RDWR | O_CREAT | O_EXCL | PG_BINARY);
    if (fd < 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not create file \"%s\": %m",
                        XLOG_CONTROL_FILE)));

    errno = 0;
    pgstat_report_wait_start(WAIT_EVENT_CONTROL_FILE_WRITE);
    if (write(fd, buffer, PG_CONTROL_FILE_SIZE) != PG_CONTROL_FILE_SIZE)
    {
        /* 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 to file \"%s\": %m",
                        XLOG_CONTROL_FILE)));
    }
    pgstat_report_wait_end();

    pgstat_report_wait_start(WAIT_EVENT_CONTROL_FILE_SYNC);
    if (pg_fsync(fd) != 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not fsync file \"%s\": %m",
                        XLOG_CONTROL_FILE)));
    pgstat_report_wait_end();

    if (close(fd) != 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not close file \"%s\": %m",
                        XLOG_CONTROL_FILE)));
}

static void
ReadControlFile(void)
{
    pg_crc32c   crc;
    int         fd;
    static char wal_segsz_str[20];
    int         r;

    /*
     * Read data...
     */
    fd = BasicOpenFile(XLOG_CONTROL_FILE,
                       O_RDWR | PG_BINARY);
    if (fd < 0)
        ereport(PANIC,
                (errcode_for_file_access(),
                 errmsg("could not open file \"%s\": %m",
                        XLOG_CONTROL_FILE)));

    pgstat_report_wait_start(WAIT_EVENT_CONTROL_FILE_READ);
    r = read(fd, ControlFile, sizeof(ControlFileData));
    if (r != sizeof(ControlFileData))
    {
        if (r < 0)
            ereport(PANIC,
                    (errcode_for_file_access(),
                     errmsg("could not read file \"%s\": %m",
                            XLOG_CONTROL_FILE)));
        else
            ereport(PANIC,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg("could not read file \"%s\": read %d of %zu",
                            XLOG_CONTROL_FILE, r, sizeof(ControlFileData))));
    }
    pgstat_report_wait_end();

    close(fd);

    /*
     * Check for expected pg_control format version.  If this is wrong, the
     * CRC check will likely fail because we'll be checking the wrong number
     * of bytes.  Complaining about wrong version will probably be more
     * enlightening than complaining about wrong CRC.
     */

    if (ControlFile->pg_control_version != PG_CONTROL_VERSION && ControlFile->pg_control_version % 65536 == 0 && ControlFile->pg_control_version / 65536 != 0)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with PG_CONTROL_VERSION %d (0x%08x),"
                           " but the server was compiled with PG_CONTROL_VERSION %d (0x%08x).",
                           ControlFile->pg_control_version, ControlFile->pg_control_version,
                           PG_CONTROL_VERSION, PG_CONTROL_VERSION),
                 errhint("This could be a problem of mismatched byte ordering.  It looks like you need to initdb.")));

    if (ControlFile->pg_control_version != PG_CONTROL_VERSION)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with PG_CONTROL_VERSION %d,"
                           " but the server was compiled with PG_CONTROL_VERSION %d.",
                           ControlFile->pg_control_version, PG_CONTROL_VERSION),
                 errhint("It looks like you need to initdb.")));

    /* Now check the CRC. */
    INIT_CRC32C(crc);
    COMP_CRC32C(crc,
                (char *) ControlFile,
                offsetof(ControlFileData, crc));
    FIN_CRC32C(crc);

    if (!EQ_CRC32C(crc, ControlFile->crc))
        ereport(FATAL,
                (errmsg("incorrect checksum in control file")));

    /*
     * Do compatibility checking immediately.  If the database isn't
     * compatible with the backend executable, we want to abort before we can
     * possibly do any damage.
     */
    if (ControlFile->catalog_version_no != CATALOG_VERSION_NO)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with CATALOG_VERSION_NO %d,"
                           " but the server was compiled with CATALOG_VERSION_NO %d.",
                           ControlFile->catalog_version_no, CATALOG_VERSION_NO),
                 errhint("It looks like you need to initdb.")));
    if (ControlFile->maxAlign != MAXIMUM_ALIGNOF)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with MAXALIGN %d,"
                           " but the server was compiled with MAXALIGN %d.",
                           ControlFile->maxAlign, MAXIMUM_ALIGNOF),
                 errhint("It looks like you need to initdb.")));
    if (ControlFile->floatFormat != FLOATFORMAT_VALUE)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster appears to use a different floating-point number format than the server executable."),
                 errhint("It looks like you need to initdb.")));
    if (ControlFile->blcksz != BLCKSZ)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with BLCKSZ %d,"
                           " but the server was compiled with BLCKSZ %d.",
                           ControlFile->blcksz, BLCKSZ),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->relseg_size != RELSEG_SIZE)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with RELSEG_SIZE %d,"
                           " but the server was compiled with RELSEG_SIZE %d.",
                           ControlFile->relseg_size, RELSEG_SIZE),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->xlog_blcksz != XLOG_BLCKSZ)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with XLOG_BLCKSZ %d,"
                           " but the server was compiled with XLOG_BLCKSZ %d.",
                           ControlFile->xlog_blcksz, XLOG_BLCKSZ),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->nameDataLen != NAMEDATALEN)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with NAMEDATALEN %d,"
                           " but the server was compiled with NAMEDATALEN %d.",
                           ControlFile->nameDataLen, NAMEDATALEN),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->indexMaxKeys != INDEX_MAX_KEYS)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with INDEX_MAX_KEYS %d,"
                           " but the server was compiled with INDEX_MAX_KEYS %d.",
                           ControlFile->indexMaxKeys, INDEX_MAX_KEYS),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->toast_max_chunk_size != TOAST_MAX_CHUNK_SIZE)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with TOAST_MAX_CHUNK_SIZE %d,"
                           " but the server was compiled with TOAST_MAX_CHUNK_SIZE %d.",
                           ControlFile->toast_max_chunk_size, (int) TOAST_MAX_CHUNK_SIZE),
                 errhint("It looks like you need to recompile or initdb.")));
    if (ControlFile->loblksize != LOBLKSIZE)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with LOBLKSIZE %d,"
                           " but the server was compiled with LOBLKSIZE %d.",
                           ControlFile->loblksize, (int) LOBLKSIZE),
                 errhint("It looks like you need to recompile or initdb.")));

#ifdef USE_FLOAT8_BYVAL
    if (ControlFile->float8ByVal != true)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized without USE_FLOAT8_BYVAL"
                           " but the server was compiled with USE_FLOAT8_BYVAL."),
                 errhint("It looks like you need to recompile or initdb.")));
#else
    if (ControlFile->float8ByVal != false)
        ereport(FATAL,
                (errmsg("database files are incompatible with server"),
                 errdetail("The database cluster was initialized with USE_FLOAT8_BYVAL"
                           " but the server was compiled without USE_FLOAT8_BYVAL."),
                 errhint("It looks like you need to recompile or initdb.")));
#endif

    wal_segment_size = ControlFile->xlog_seg_size;

    if (!IsValidWalSegSize(wal_segment_size))
        ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                        errmsg_plural("WAL segment size must be a power of two between 1 MB and 1 GB, but the control file specifies %d byte",
                                      "WAL segment size must be a power of two between 1 MB and 1 GB, but the control file specifies %d bytes",
                                      wal_segment_size,
                                      wal_segment_size)));

    snprintf(wal_segsz_str, sizeof(wal_segsz_str), "%d", wal_segment_size);
    SetConfigOption("wal_segment_size", wal_segsz_str, PGC_INTERNAL,
                    PGC_S_OVERRIDE);

    /* check and update variables dependent on wal_segment_size */
    if (ConvertToXSegs(min_wal_size_mb, wal_segment_size) < 2)
        ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                        errmsg("\"min_wal_size\" must be at least twice \"wal_segment_size\"")));

    if (ConvertToXSegs(max_wal_size_mb, wal_segment_size) < 2)
        ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                        errmsg("\"max_wal_size\" must be at least twice \"wal_segment_size\"")));

    UsableBytesInSegment =
        (wal_segment_size / XLOG_BLCKSZ * UsableBytesInPage) -
        (SizeOfXLogLongPHD - SizeOfXLogShortPHD);

    CalculateCheckpointSegments();

    /* Make the initdb settings visible as GUC variables, too */
    SetConfigOption("data_checksums", DataChecksumsEnabled() ? "yes" : "no",
                    PGC_INTERNAL, PGC_S_OVERRIDE);
}

/*
 * Utility wrapper to update the control file.  Note that the control
 * file gets flushed.
 */
void
UpdateControlFile(void)
{
    update_controlfile(DataDir, ControlFile, true);
}

/*
 * Returns the unique system identifier from control file.
 */
uint64
GetSystemIdentifier(void)
{
    Assert(ControlFile != NULL);
    return ControlFile->system_identifier;
}

/*
 * Returns the random nonce from control file.
 */
char *
GetMockAuthenticationNonce(void)
{
    Assert(ControlFile != NULL);
    return ControlFile->mock_authentication_nonce;
}

/*
 * Are checksums enabled for data pages?
 */
bool
DataChecksumsEnabled(void)
{
    Assert(ControlFile != NULL);
    return (ControlFile->data_checksum_version > 0);
}

/*
 * Returns a fake LSN for unlogged relations.
 *
 * Each call generates an LSN that is greater than any previous value
 * returned. The current counter value is saved and restored across clean
 * shutdowns, but like unlogged relations, does not survive a crash. This can
 * be used in lieu of real LSN values returned by XLogInsert, if you need an
 * LSN-like increasing sequence of numbers without writing any WAL.
 */
XLogRecPtr
GetFakeLSNForUnloggedRel(void)
{
    XLogRecPtr  nextUnloggedLSN;

    /* increment the unloggedLSN counter, need SpinLock */
    SpinLockAcquire(&XLogCtl->ulsn_lck);
    nextUnloggedLSN = XLogCtl->unloggedLSN++;
    SpinLockRelease(&XLogCtl->ulsn_lck);

    return nextUnloggedLSN;
}

/*
 * Auto-tune the number of XLOG buffers.
 *
 * The preferred setting for wal_buffers is about 3% of shared_buffers, with
 * a maximum of one XLOG segment (there is little reason to think that more
 * is helpful, at least so long as we force an fsync when switching log files)
 * and a minimum of 8 blocks (which was the default value prior to PostgreSQL
 * 9.1, when auto-tuning was added).
 *
 * This should not be called until NBuffers has received its final value.
 */
static int
XLOGChooseNumBuffers(void)
{
    int         xbuffers;

    xbuffers = NBuffers / 32;
    if (xbuffers > (wal_segment_size / XLOG_BLCKSZ))
        xbuffers = (wal_segment_size / XLOG_BLCKSZ);
    if (xbuffers < 8)
        xbuffers = 8;
    return xbuffers;
}

/*
 * GUC check_hook for wal_buffers
 */
bool
check_wal_buffers(int *newval, void **extra, GucSource source)
{
    /*
     * -1 indicates a request for auto-tune.
     */
    if (*newval == -1)
    {
        /*
         * If we haven't yet changed the boot_val default of -1, just let it
         * be.  We'll fix it when XLOGShmemSize is called.
         */
        if (XLOGbuffers == -1)
            return true;

        /* Otherwise, substitute the auto-tune value */
        *newval = XLOGChooseNumBuffers();
    }

    /*
     * We clamp manually-set values to at least 4 blocks.  Prior to PostgreSQL
     * 9.1, a minimum of 4 was enforced by guc.c, but since that is no longer
     * the case, we just silently treat such values as a request for the
     * minimum.  (We could throw an error instead, but that doesn't seem very
     * helpful.)
     */
    if (*newval < 4)
        *newval = 4;

    return true;
}

/*
 * Read the control file, set respective GUCs.
 *
 * This is to be called during startup, including a crash recovery cycle,
 * unless in bootstrap mode, where no control file yet exists.  As there's no
 * usable shared memory yet (its sizing can depend on the contents of the
 * control file!), first store the contents in local memory. XLOGShmemInit()
 * will then copy it to shared memory later.
 *
 * reset just controls whether previous contents are to be expected (in the
 * reset case, there's a dangling pointer into old shared memory), or not.
 */
void
LocalProcessControlFile(bool reset)
{
    Assert(reset || ControlFile == NULL);
    ControlFile = palloc(sizeof(ControlFileData));
    ReadControlFile();
}

/*
 * Initialization of shared memory for XLOG
 */
Size
XLOGShmemSize(void)
{
    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.
     */
    if (XLOGbuffers == -1)
    {
        char        buf[32];

        snprintf(buf, sizeof(buf), "%d", XLOGChooseNumBuffers());
        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(XLogRecPtr), XLOGbuffers));
    /* extra alignment padding for XLOG I/O buffers */
    size = add_size(size, XLOG_BLCKSZ);
    /* 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;
}

void
XLOGShmemInit(void)
{
    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 = (XLogRecPtr *) allocptr;
    memset(XLogCtl->xlblocks, 0, sizeof(XLogRecPtr) * XLOGbuffers);
    allocptr += sizeof(XLogRecPtr) * XLOGbuffers;


    /* 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);
        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->SharedHotStandbyActive = false;
    XLogCtl->InstallXLogFileSegmentActive = false;
    XLogCtl->SharedPromoteIsTriggered = false;
    XLogCtl->WalWriterSleeping = false;

    SpinLockInit(&XLogCtl->Insert.insertpos_lck);
    SpinLockInit(&XLogCtl->info_lck);
    SpinLockInit(&XLogCtl->ulsn_lck);
    InitSharedLatch(&XLogCtl->recoveryWakeupLatch);
    ConditionVariableInit(&XLogCtl->recoveryNotPausedCV);
}

/*
 * This func must be called ONCE on system install.  It creates pg_control
 * and the initial XLOG segment.
 */
void
BootStrapXLOG(void)
{
    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 */
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    XLogCtl->InstallXLogFileSegmentActive = true;
    LWLockRelease(ControlFileLock);

    /*
     * 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;

    /* First timeline ID is always 1 */
    ThisTimeLineID = 1;

    /* 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 = ThisTimeLineID;
    checkPoint.PrevTimeLineID = ThisTimeLineID;
    checkPoint.fullPageWrites = fullPageWrites;
    checkPoint.nextXid =
        FullTransactionIdFromEpochAndXid(0, FirstNormalTransactionId);
    checkPoint.nextOid = FirstGenbkiObjectId;
    checkPoint.nextMulti = FirstMultiXactId;
    checkPoint.nextMultiOffset = 0;
    checkPoint.oldestXid = FirstNormalTransactionId;
    checkPoint.oldestXidDB = TemplateDbOid;
    checkPoint.oldestMulti = FirstMultiXactId;
    checkPoint.oldestMultiDB = TemplateDbOid;
    checkPoint.oldestCommitTsXid = InvalidTransactionId;
    checkPoint.newestCommitTsXid = InvalidTransactionId;
    checkPoint.time = (pg_time_t) time(NULL);
    checkPoint.oldestActiveXid = InvalidTransactionId;

    ShmemVariableCache->nextXid = checkPoint.nextXid;
    ShmemVariableCache->nextOid = checkPoint.nextOid;
    ShmemVariableCache->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 = ThisTimeLineID;
    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 */
    openLogFile = XLogFileInit(1);

    /*
     * 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);
    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();
}

static char *
str_time(pg_time_t tnow)
{
    static char buf[128];

    pg_strftime(buf, sizeof(buf),
                "%Y-%m-%d %H:%M:%S %Z",
                pg_localtime(&tnow, log_timezone));

    return buf;
}

/*
 * See if there are any recovery signal files and if so, set state for
 * recovery.
 *
 * See if there is a recovery command file (recovery.conf), and if so
 * throw an ERROR since as of PG12 we no longer recognize that.
 */
static void
readRecoverySignalFile(void)
{
    struct stat stat_buf;

    if (IsBootstrapProcessingMode())
        return;

    /*
     * Check for old recovery API file: recovery.conf
     */
    if (stat(RECOVERY_COMMAND_FILE, &stat_buf) == 0)
        ereport(FATAL,
                (errcode_for_file_access(),
                 errmsg("using recovery command file \"%s\" is not supported",
                        RECOVERY_COMMAND_FILE)));

    /*
     * Remove unused .done file, if present. Ignore if absent.
     */
    unlink(RECOVERY_COMMAND_DONE);

    /*
     * Check for recovery signal files and if found, fsync them since they
     * represent server state information.  We don't sweat too much about the
     * possibility of fsync failure, however.
     *
     * If present, standby signal file takes precedence. If neither is present
     * then we won't enter archive recovery.
     */
    if (stat(STANDBY_SIGNAL_FILE, &stat_buf) == 0)
    {
        int         fd;

        fd = BasicOpenFilePerm(STANDBY_SIGNAL_FILE, O_RDWR | PG_BINARY,
                               S_IRUSR | S_IWUSR);
        if (fd >= 0)
        {
            (void) pg_fsync(fd);
            close(fd);
        }
        standby_signal_file_found = true;
    }
    else if (stat(RECOVERY_SIGNAL_FILE, &stat_buf) == 0)
    {
        int         fd;

        fd = BasicOpenFilePerm(RECOVERY_SIGNAL_FILE, O_RDWR | PG_BINARY,
                               S_IRUSR | S_IWUSR);
        if (fd >= 0)
        {
            (void) pg_fsync(fd);
            close(fd);
        }
        recovery_signal_file_found = true;
    }

    StandbyModeRequested = false;
    ArchiveRecoveryRequested = false;
    if (standby_signal_file_found)
    {
        StandbyModeRequested = true;
        ArchiveRecoveryRequested = true;
    }
    else if (recovery_signal_file_found)
    {
        StandbyModeRequested = false;
        ArchiveRecoveryRequested = true;
    }
    else
        return;

    /*
     * We don't support standby mode in standalone backends; that requires
     * other processes such as the WAL receiver to be alive.
     */
    if (StandbyModeRequested && !IsUnderPostmaster)
        ereport(FATAL,
                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                 errmsg("standby mode is not supported by single-user servers")));
}

static void
validateRecoveryParameters(void)
{
    if (!ArchiveRecoveryRequested)
        return;

    /*
     * Check for compulsory parameters
     */
    if (StandbyModeRequested)
    {
        if ((PrimaryConnInfo == NULL || strcmp(PrimaryConnInfo, "") == 0) &&
            (recoveryRestoreCommand == NULL || strcmp(recoveryRestoreCommand, "") == 0))
            ereport(WARNING,
                    (errmsg("specified neither primary_conninfo nor restore_command"),
                     errhint("The database server will regularly poll the pg_wal subdirectory to check for files placed there.")));
    }
    else
    {
        if (recoveryRestoreCommand == NULL ||
            strcmp(recoveryRestoreCommand, "") == 0)
            ereport(FATAL,
                    (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                     errmsg("must specify restore_command when standby mode is not enabled")));
    }

    /*
     * Override any inconsistent requests. Note that this is a change of
     * behaviour in 9.5; prior to this we simply ignored a request to pause if
     * hot_standby = off, which was surprising behaviour.
     */
    if (recoveryTargetAction == RECOVERY_TARGET_ACTION_PAUSE &&
        !EnableHotStandby)
        recoveryTargetAction = RECOVERY_TARGET_ACTION_SHUTDOWN;

    /*
     * Final parsing of recovery_target_time string; see also
     * check_recovery_target_time().
     */
    if (recoveryTarget == RECOVERY_TARGET_TIME)
    {
        recoveryTargetTime = DatumGetTimestampTz(DirectFunctionCall3(timestamptz_in,
                                                                     CStringGetDatum(recovery_target_time_string),
                                                                     ObjectIdGetDatum(InvalidOid),
                                                                     Int32GetDatum(-1)));
    }

    /*
     * If user specified recovery_target_timeline, validate it or compute the
     * "latest" value.  We can't do this until after we've gotten the restore
     * command and set InArchiveRecovery, because we need to fetch timeline
     * history files from the archive.
     */
    if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_NUMERIC)
    {
        TimeLineID  rtli = recoveryTargetTLIRequested;

        /* Timeline 1 does not have a history file, all else should */
        if (rtli != 1 && !existsTimeLineHistory(rtli))
            ereport(FATAL,
                    (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                     errmsg("recovery target timeline %u does not exist",
                            rtli)));
        recoveryTargetTLI = rtli;
    }
    else if (recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_LATEST)
    {
        /* We start the "latest" search from pg_control's timeline */
        recoveryTargetTLI = findNewestTimeLine(recoveryTargetTLI);
    }
    else
    {
        /*
         * else we just use the recoveryTargetTLI as already read from
         * ControlFile
         */
        Assert(recoveryTargetTimeLineGoal == RECOVERY_TARGET_TIMELINE_CONTROLFILE);
    }
}

/*
 * Exit archive-recovery state
 */
static void
exitArchiveRecovery(TimeLineID endTLI, XLogRecPtr endOfLog)
{
    char        xlogfname[MAXFNAMELEN];
    XLogSegNo   endLogSegNo;
    XLogSegNo   startLogSegNo;

    /* we always switch to a new timeline after archive recovery */
    Assert(endTLI != ThisTimeLineID);

    /*
     * We are no longer in archive recovery state.
     */
    InArchiveRecovery = false;

    /*
     * Update min recovery point one last time.
     */
    UpdateMinRecoveryPoint(InvalidXLogRecPtr, true);

    /*
     * If the ending log segment is still open, close it (to avoid problems on
     * Windows with trying to rename or delete an open file).
     */
    if (readFile >= 0)
    {
        close(readFile);
        readFile = -1;
    }

    /*
     * Calculate the last segment on the old timeline, and the first segment
     * on the new timeline. If the switch happens in the middle of a segment,
     * they are the same, but if the switch happens exactly at a segment
     * boundary, startLogSegNo will be endLogSegNo + 1.
     */
    XLByteToPrevSeg(endOfLog, endLogSegNo, wal_segment_size);
    XLByteToSeg(endOfLog, startLogSegNo, wal_segment_size);

    /*
     * Initialize the starting WAL segment for the new timeline. If the switch
     * happens in the middle of a segment, copy data from the last WAL segment
     * of the old timeline up to the switch point, to the starting WAL segment
     * on the new timeline.
     */
    if (endLogSegNo == startLogSegNo)
    {
        /*
         * Make a copy of the file on the new timeline.
         *
         * Writing WAL isn't allowed yet, so there are no locking
         * considerations. But we should be just as tense as XLogFileInit to
         * avoid emplacing a bogus file.
         */
        XLogFileCopy(endLogSegNo, endTLI, endLogSegNo,
                     XLogSegmentOffset(endOfLog, wal_segment_size));
    }
    else
    {
        /*
         * The switch happened at a segment boundary, so just create the next
         * segment on the new timeline.
         */
        int         fd;

        fd = XLogFileInit(startLogSegNo);

        if (close(fd) != 0)
        {
            char        xlogfname[MAXFNAMELEN];
            int         save_errno = errno;

            XLogFileName(xlogfname, ThisTimeLineID, startLogSegNo,
                         wal_segment_size);
            errno = save_errno;
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not close file \"%s\": %m", xlogfname)));
        }
    }

    /*
     * Let's just make real sure there are not .ready or .done flags posted
     * for the new segment.
     */
    XLogFileName(xlogfname, ThisTimeLineID, startLogSegNo, wal_segment_size);
    XLogArchiveCleanup(xlogfname);

    /*
     * Remove the signal files out of the way, so that we don't accidentally
     * re-enter archive recovery mode in a subsequent crash.
     */
    if (standby_signal_file_found)
        durable_unlink(STANDBY_SIGNAL_FILE, FATAL);

    if (recovery_signal_file_found)
        durable_unlink(RECOVERY_SIGNAL_FILE, FATAL);

    ereport(LOG,
            (errmsg("archive recovery complete")));
}

/*
 * Extract timestamp from WAL record.
 *
 * If the record contains a timestamp, returns true, and saves the timestamp
 * in *recordXtime. If the record type has no timestamp, returns false.
 * Currently, only transaction commit/abort records and restore points contain
 * timestamps.
 */
static bool
getRecordTimestamp(XLogReaderState *record, TimestampTz *recordXtime)
{
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
    uint8       xact_info = info & XLOG_XACT_OPMASK;
    uint8       rmid = XLogRecGetRmid(record);

    if (rmid == RM_XLOG_ID && info == XLOG_RESTORE_POINT)
    {
        *recordXtime = ((xl_restore_point *) XLogRecGetData(record))->rp_time;
        return true;
    }
    if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_COMMIT ||
                               xact_info == XLOG_XACT_COMMIT_PREPARED))
    {
        *recordXtime = ((xl_xact_commit *) XLogRecGetData(record))->xact_time;
        return true;
    }
    if (rmid == RM_XACT_ID && (xact_info == XLOG_XACT_ABORT ||
                               xact_info == XLOG_XACT_ABORT_PREPARED))
    {
        *recordXtime = ((xl_xact_abort *) XLogRecGetData(record))->xact_time;
        return true;
    }
    return false;
}

/*
 * For point-in-time recovery, this function decides whether we want to
 * stop applying the XLOG before the current record.
 *
 * Returns true if we are stopping, false otherwise. If stopping, some
 * information is saved in recoveryStopXid et al for use in annotating the
 * new timeline's history file.
 */
static bool
recoveryStopsBefore(XLogReaderState *record)
{
    bool        stopsHere = false;
    uint8       xact_info;
    bool        isCommit;
    TimestampTz recordXtime = 0;
    TransactionId recordXid;

    /*
     * Ignore recovery target settings when not in archive recovery (meaning
     * we are in crash recovery).
     */
    if (!ArchiveRecoveryRequested)
        return false;

    /* Check if we should stop as soon as reaching consistency */
    if (recoveryTarget == RECOVERY_TARGET_IMMEDIATE && reachedConsistency)
    {
        ereport(LOG,
                (errmsg("recovery stopping after reaching consistency")));

        recoveryStopAfter = false;
        recoveryStopXid = InvalidTransactionId;
        recoveryStopLSN = InvalidXLogRecPtr;
        recoveryStopTime = 0;
        recoveryStopName[0] = '\0';