path: root/src/backend/access/transam/xlog.c

/*-------------------------------------------------------------------------
 *
 * xlog.c
 *		PostgreSQL write-ahead log manager
 *
 *
 * Portions Copyright (c) 1996-2019, 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/multixact.h"
#include "access/rewriteheap.h"
#include "access/subtrans.h"
#include "access/timeline.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog_internal.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/tablespace.h"
#include "common/controldata_utils.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "port/atomics.h"
#include "postmaster/bgwriter.h"
#include "postmaster/walwriter.h"
#include "postmaster/startup.h"
#include "replication/basebackup.h"
#include "replication/logical.h"
#include "replication/slot.h"
#include "replication/origin.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/snapmgr.h"
#include "utils/timestamp.h"
#include "pg_trace.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_segments = 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;
bool		wal_compression = false;
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;

#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;

/*
 * Are we doing recovery from XLOG?
 *
 * This is only ever true in the startup process; it should be read as meaning
 * "this process is replaying WAL records", rather than "the system is in
 * recovery mode".  It should be examined primarily by functions that need
 * to act differently when called from a WAL redo function (e.g., to skip WAL
 * logging).  To check whether the system is in recovery regardless of which
 * process you're running in, use RecoveryInProgress() but only after shared
 * memory startup and lock initialization.
 */
bool		InRecovery = false;

/* Are we in Hot Standby mode? Only valid in startup process, see xlog.h */
HotStandbyState standbyState = STANDBY_DISABLED;

static XLogRecPtr LastRec;

/* Local copy of WalRcv->receivedUpto */
static XLogRecPtr receivedUpto = 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 SharedRecoveryInProgress variable. 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 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;

/* Was the last xlog file restored from archive, or local? */
static bool restoredFromArchive = false;

/* Buffers dedicated to consistency checks of size BLCKSZ */
static char *replay_image_masked = NULL;
static char *master_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;
TimestampTz recoveryTargetTime;
const char *recoveryTargetName;
XLogRecPtr	recoveryTargetLSN;
int			recovery_min_apply_delay = 0;
TimestampTz recoveryDelayUntilTime;

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

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

/* whether request for fast promotion has been made yet */
static bool fast_promote = 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
 *
 * recoveryTargetIsLatest: was the requested target timeline 'latest'?
 *
 * 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.
 *
 * CheckpointLock: must be held to do a checkpoint or restartpoint (ensures
 * only one checkpointer at a time; currently, with all checkpoints done by
 * the checkpointer, this is just pro forma).
 *
 *----------
 */

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 master copy used by all backends to determine
	 * whether to write full-page to WAL, instead of using process-local one.
	 * This 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;	/* nextFullXid 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.  xlblock 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;

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

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

	/*
	 * 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.
	 */
	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;
	/* Are we requested to pause recovery? */
	bool		recoveryPause;

	/*
	 * 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 min_wal_size_mb and max wal_size_mb to equivalent segment count */
#define ConvertToXSegs(x, segsize)	\
	(x / ((segsize) / (1024 * 1024)))

/* 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 master */
} XLogSource;

/* human-readable names for XLogSources, for debugging output */
static const char *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.
 */
static int	openLogFile = -1;
static XLogSegNo openLogSegNo = 0;

/*
 * These variables are used similarly to the ones above, but for reading
 * the XLOG.  Note, however, that readOff generally represents the offset
 * of the page just read, not the seek position of the FD itself, which
 * will be just past that page. readLen indicates how much of the current
 * page has been read into readBuf, and readSource indicates where we got
 * the currently open file from.
 */
static int	readFile = -1;
static XLogSegNo readSegNo = 0;
static uint32 readOff = 0;
static uint32 readLen = 0;
static XLogSource readSource = 0;	/* XLOG_FROM_* code */

/*
 * 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.
 */
static XLogSource currentSource = 0;	/* XLOG_FROM_* code */
static bool lastSourceFailed = 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 = 0;	/* XLOG_FROM_* code */

/* State information for XLOG reading */
static XLogRecPtr