xlog.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*-------------------------------------------------------------------------
 *
 * xlog.c
 *		PostgreSQL transaction log manager
 *
 *
 * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.222.2.3 2006/03/28 22:01:25 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

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

#include "access/clog.h"
#include "access/multixact.h"
#include "access/subtrans.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "access/xlog_internal.h"
#include "access/xlogutils.h"
#include "catalog/catversion.h"
#include "catalog/pg_control.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/bgwriter.h"
#include "storage/bufpage.h"
#include "storage/fd.h"
#include "storage/lwlock.h"
#include "storage/pmsignal.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/spin.h"
#include "utils/builtins.h"
#include "utils/guc.h"
#include "utils/nabstime.h"
#include "utils/pg_locale.h"
#include "utils/relcache.h"


/*
 *	Because O_DIRECT bypasses the kernel buffers, and because we never
 *	read those buffers except during crash recovery, it is a win to use
 *	it in all cases where we sync on each write().	We could allow O_DIRECT
 *	with fsync(), but because skipping the kernel buffer forces writes out
 *	quickly, it seems best just to use it for O_SYNC.  It is hard to imagine
 *	how fsync() could be a win for O_DIRECT compared to O_SYNC and O_DIRECT.
 *	Also, O_DIRECT is never enough to force data to the drives, it merely
 *	tries to bypass the kernel cache, so we still need O_SYNC or fsync().
 */
#ifdef O_DIRECT
#define PG_O_DIRECT				O_DIRECT
#else
#define PG_O_DIRECT				0
#endif

/*
 * This chunk of hackery attempts to determine which file sync methods
 * are available on the current platform, and to choose an appropriate
 * default method.	We assume that fsync() is always available, and that
 * configure determined whether fdatasync() is.
 */
#if defined(O_SYNC)
#define BARE_OPEN_SYNC_FLAG		O_SYNC
#elif defined(O_FSYNC)
#define BARE_OPEN_SYNC_FLAG		O_FSYNC
#endif
#ifdef BARE_OPEN_SYNC_FLAG
#define OPEN_SYNC_FLAG			(BARE_OPEN_SYNC_FLAG | PG_O_DIRECT)
#endif

#if defined(O_DSYNC)
#if defined(OPEN_SYNC_FLAG)
/* O_DSYNC is distinct? */
#if O_DSYNC != BARE_OPEN_SYNC_FLAG
#define OPEN_DATASYNC_FLAG		(O_DSYNC | PG_O_DIRECT)
#endif
#else							/* !defined(OPEN_SYNC_FLAG) */
/* Win32 only has O_DSYNC */
#define OPEN_DATASYNC_FLAG		(O_DSYNC | PG_O_DIRECT)
#endif
#endif

#if defined(OPEN_DATASYNC_FLAG)
#define DEFAULT_SYNC_METHOD_STR "open_datasync"
#define DEFAULT_SYNC_METHOD		SYNC_METHOD_OPEN
#define DEFAULT_SYNC_FLAGBIT	OPEN_DATASYNC_FLAG
#elif defined(HAVE_FDATASYNC)
#define DEFAULT_SYNC_METHOD_STR "fdatasync"
#define DEFAULT_SYNC_METHOD		SYNC_METHOD_FDATASYNC
#define DEFAULT_SYNC_FLAGBIT	0
#elif defined(HAVE_FSYNC_WRITETHROUGH_ONLY)
#define DEFAULT_SYNC_METHOD_STR "fsync_writethrough"
#define DEFAULT_SYNC_METHOD		SYNC_METHOD_FSYNC_WRITETHROUGH
#define DEFAULT_SYNC_FLAGBIT	0
#else
#define DEFAULT_SYNC_METHOD_STR "fsync"
#define DEFAULT_SYNC_METHOD		SYNC_METHOD_FSYNC
#define DEFAULT_SYNC_FLAGBIT	0
#endif


/*
 * Limitation of buffer-alignment for direct IO depends on OS and filesystem,
 * but BLCKSZ is assumed to be enough for it.
 */
#ifdef O_DIRECT
#define ALIGNOF_XLOG_BUFFER		BLCKSZ
#else
#define ALIGNOF_XLOG_BUFFER		ALIGNOF_BUFFER
#endif


/* File path names (all relative to $PGDATA) */
#define BACKUP_LABEL_FILE		"backup_label"
#define RECOVERY_COMMAND_FILE	"recovery.conf"
#define RECOVERY_COMMAND_DONE	"recovery.done"


/* User-settable parameters */
int			CheckPointSegments = 3;
int			XLOGbuffers = 8;
char	   *XLogArchiveCommand = NULL;
char	   *XLOG_sync_method = NULL;
const char	XLOG_sync_method_default[] = DEFAULT_SYNC_METHOD_STR;
bool		fullPageWrites = true;

#ifdef WAL_DEBUG
bool		XLOG_DEBUG = false;
#endif

/*
 * XLOGfileslop is used in the code as the allowed "fuzz" in the number of
 * preallocated XLOG segments --- we try to have at least XLOGfiles advance
 * segments but no more than XLOGfileslop segments.  This could
 * be made a separate GUC variable, but at present I think it's sufficient
 * to hardwire it as 2*CheckPointSegments+1.  Under normal conditions, a
 * checkpoint will free no more than 2*CheckPointSegments log segments, and
 * we want to recycle all of them; the +1 allows boundary cases to happen
 * without wasting a delete/create-segment cycle.
 */

#define XLOGfileslop	(2*CheckPointSegments + 1)


/* these are derived from XLOG_sync_method by assign_xlog_sync_method */
int			sync_method = DEFAULT_SYNC_METHOD;
static int	open_sync_bit = DEFAULT_SYNC_FLAGBIT;

#define XLOG_SYNC_BIT  (enableFsync ? open_sync_bit : 0)


/*
 * 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? */
bool		InRecovery = false;

/* Are we recovering using offline XLOG archives? */
static bool InArchiveRecovery = false;

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

/* options taken from recovery.conf */
static char *recoveryRestoreCommand = NULL;
static bool recoveryTarget = false;
static bool recoveryTargetExact = false;
static bool recoveryTargetInclusive = true;
static TransactionId recoveryTargetXid;
static time_t recoveryTargetTime;

/* if recoveryStopsHere returns true, it saves actual stop xid/time here */
static TransactionId recoveryStopXid;
static time_t recoveryStopTime;
static bool recoveryStopAfter;

/* constraint set by read_backup_label */
static XLogRecPtr recoveryMinXlogOffset = {0, 0};

/*
 * 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:
 *
 * recoveryTargetTLI: the desired timeline that we want to end in.
 *
 * expectedTLIs: an integer list of recoveryTargetTLI and the TLIs 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.
 */
static TimeLineID recoveryTargetTLI;
static List *expectedTLIs;
static TimeLineID curFileTLI;

/*
 * MyLastRecPtr points to the start of the last XLOG record inserted by the
 * current transaction.  If MyLastRecPtr.xrecoff == 0, then the current
 * xact hasn't yet inserted any transaction-controlled XLOG records.
 *
 * Note that XLOG records inserted outside transaction control are not
 * reflected into MyLastRecPtr.  They do, however, cause MyXactMadeXLogEntry
 * to be set true.	The latter can be used to test whether the current xact
 * made any loggable changes (including out-of-xact changes, such as
 * sequence updates).
 *
 * When we insert/update/delete a tuple in a temporary relation, we do not
 * make any XLOG record, since we don't care about recovering the state of
 * the temp rel after a crash.	However, we will still need to remember
 * whether our transaction committed or aborted in that case.  So, we must
 * set MyXactMadeTempRelUpdate true to indicate that the XID will be of
 * interest later.
 */
XLogRecPtr	MyLastRecPtr = {0, 0};

bool		MyXactMadeXLogEntry = false;

bool		MyXactMadeTempRelUpdate = false;

/*
 * ProcLastRecPtr points to the start of the last XLOG record inserted by the
 * current backend.  It is updated for all inserts, transaction-controlled
 * or not.	ProcLastRecEnd is similar but points to end+1 of last record.
 */
static XLogRecPtr ProcLastRecPtr = {0, 0};

XLogRecPtr	ProcLastRecEnd = {0, 0};

/*
 * 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 the Insert lock).  See XLogInsert for details.	We are also allowed
 * to update from XLogCtl->Insert.RedoRecPtr if we hold the info_lck;
 * see GetRedoRecPtr.  A freshly spawned backend obtains the value during
 * InitXLOGAccess.
 */
static XLogRecPtr RedoRecPtr;

/*----------
 * 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.
 *
 * We do a lot of pushups to minimize the amount of access to lockable
 * shared memory values.  There are actually three shared-memory copies of
 * LogwrtResult, plus one unshared copy in each backend.  Here's how it works:
 *		XLogCtl->LogwrtResult is protected by info_lck
 *		XLogCtl->Write.LogwrtResult is protected by WALWriteLock
 *		XLogCtl->Insert.LogwrtResult is protected by WALInsertLock
 * One must hold the associated lock to read or write any of these, but
 * of course no lock is needed to read/write the unshared LogwrtResult.
 *
 * XLogCtl->LogwrtResult and XLogCtl->Write.LogwrtResult are both "always
 * right", since both are updated by a write or flush operation before
 * it releases WALWriteLock.  The point of keeping XLogCtl->Write.LogwrtResult
 * is that it can be examined/modified by code that already holds WALWriteLock
 * without needing to grab info_lck as well.
 *
 * XLogCtl->Insert.LogwrtResult may lag behind the reality of the other two,
 * but is updated when convenient.	Again, it exists for the convenience of
 * code that is already holding WALInsertLock but not the other locks.
 *
 * The unshared LogwrtResult may lag behind any or all of these, and again
 * 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.
 *
 * Note that this all works because the request and result positions can only
 * advance forward, never back up, and so we can easily determine which of two
 * values is "more up to date".
 *
 * 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:
 *
 * WALInsertLock: must be held to insert a record into the WAL buffers.
 *
 * 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 (ensures only one
 * checkpointer at a time; even though the postmaster won't launch
 * parallel checkpoint processes, we need this because manual checkpoints
 * could be launched simultaneously).
 *
 *----------
 */

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;

/*
 * Shared state data for XLogInsert.
 */
typedef struct XLogCtlInsert
{
	XLogwrtResult LogwrtResult; /* a recent value of LogwrtResult */
	XLogRecPtr	PrevRecord;		/* start of previously-inserted record */
	int			curridx;		/* current block index in cache */
	XLogPageHeader currpage;	/* points to header of block in cache */
	char	   *currpos;		/* current insertion point in cache */
	XLogRecPtr	RedoRecPtr;		/* current redo point for insertions */
} XLogCtlInsert;

/*
 * Shared state data for XLogWrite/XLogFlush.
 */
typedef struct XLogCtlWrite
{
	XLogwrtResult LogwrtResult; /* current value of LogwrtResult */
	int			curridx;		/* cache index of next block to write */
} XLogCtlWrite;

/*
 * Total shared-memory state for XLOG.
 */
typedef struct XLogCtlData
{
	/* Protected by WALInsertLock: */
	XLogCtlInsert Insert;
	/* Protected by info_lck: */
	XLogwrtRqst LogwrtRqst;
	XLogwrtResult LogwrtResult;
	/* Protected by WALWriteLock: */
	XLogCtlWrite Write;

	/*
	 * These values do not change after startup, although the pointed-to pages
	 * and xlblocks values certainly do.  Permission to read/write the pages
	 * and xlblocks values depends on WALInsertLock and WALWriteLock.
	 */
	char	   *pages;			/* buffers for unwritten XLOG pages */
	XLogRecPtr *xlblocks;		/* 1st byte ptr-s + BLCKSZ */
	Size		XLogCacheByte;	/* # bytes in xlog buffers */
	int			XLogCacheBlck;	/* highest allocated xlog buffer index */
	TimeLineID	ThisTimeLineID;

	slock_t		info_lck;		/* locks shared LogwrtRqst/LogwrtResult */
} XLogCtlData;

static XLogCtlData *XLogCtl = NULL;

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

/*
 * Macros for managing XLogInsert state.  In most cases, the calling routine
 * has local copies of XLogCtl->Insert and/or XLogCtl->Insert->curridx,
 * so these are passed as parameters instead of being fetched via XLogCtl.
 */

/* Free space remaining in the current xlog page buffer */
#define INSERT_FREESPACE(Insert)  \
	(BLCKSZ - ((Insert)->currpos - (char *) (Insert)->currpage))

/* Construct XLogRecPtr value for current insertion point */
#define INSERT_RECPTR(recptr,Insert,curridx)  \
	( \
	  (recptr).xlogid = XLogCtl->xlblocks[curridx].xlogid, \
	  (recptr).xrecoff = \
		XLogCtl->xlblocks[curridx].xrecoff - INSERT_FREESPACE(Insert) \
	)

#define PrevBufIdx(idx)		\
		(((idx) == 0) ? XLogCtl->XLogCacheBlck : ((idx) - 1))

#define NextBufIdx(idx)		\
		(((idx) == XLogCtl->XLogCacheBlck) ? 0 : ((idx) + 1))

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

/*
 * openLogFile is -1 or a kernel FD for an open log file segment.
 * When it's open, openLogOff is the current seek offset in the file.
 * openLogId/openLogSeg identify the segment.  These variables are only