xlog.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * xlog.c
 *		PostgreSQL transaction log manager
 *
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/backend/access/transam/xlog.c,v 1.292.2.4 2008/05/13 20:54:02 mha Exp $
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

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

#include "access/clog.h"
#include "access/heapam.h"
#include "access/multixact.h"
#include "access/subtrans.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog_internal.h"
#include "access/xlogdefs.h"
#include "access/xlogutils.h"
#include "catalog/catversion.h"
#include "catalog/pg_control.h"
#include "catalog/pg_type.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/bgwriter.h"
#include "storage/bufpage.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/pmsignal.h"
#include "storage/procarray.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "utils/builtins.h"
#include "utils/pg_locale.h"
#include "utils/ps_status.h"


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


/* User-settable parameters */
int			CheckPointSegments = 3;
int			XLOGbuffers = 8;
int			XLogArchiveTimeout = 0;
bool		XLogArchiveMode = false;
char	   *XLogArchiveCommand = NULL;
char	   *XLOG_sync_method = NULL;
const char	XLOG_sync_method_default[] = DEFAULT_SYNC_METHOD_STR;
bool		fullPageWrites = true;
bool		log_checkpoints = false;

#ifdef WAL_DEBUG
bool		XLOG_DEBUG = false;
#endif

/*
 * XLOGfileslop is the maximum number of preallocated future XLOG segments.
 * When we are done with an old XLOG segment file, we will recycle it as a
 * future XLOG segment as long as there aren't already XLOGfileslop future
 * segments; else we'll delete it.  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)


/*
 * Statistics for current checkpoint are collected in this global struct.
 * Because only the background writer 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? */
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 bool recoveryLogRestartpoints = false;
static TransactionId recoveryTargetXid;
static TimestampTz recoveryTargetTime;
static TimestampTz recoveryLastXTime = 0;

/* if recoveryStopsHere returns true, it saves actual stop xid/time here */
static TransactionId recoveryStopXid;
static TimestampTz recoveryStopTime;
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:
 *
 * 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;

/*
 * 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.
 */
static XLogRecPtr ProcLastRecPtr = {0, 0};

XLogRecPtr	XactLastRecEnd = {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; currently, with all checkpoints done by the
 * bgwriter, 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;

/*
 * 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 */
	bool		forcePageWrites;	/* forcing full-page writes for PITR? */
} 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 */
	time_t		lastSegSwitchTime;		/* time of last xlog segment switch */
} XLogCtlWrite;

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

	/* Protected by info_lck: */
	XLogwrtRqst LogwrtRqst;
	XLogwrtResult LogwrtResult;
	uint32		ckptXidEpoch;	/* nextXID & epoch of latest checkpoint */
	TransactionId ckptXid;
	XLogRecPtr	asyncCommitLSN; /* LSN of newest async commit */

	/* 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 + XLOG_BLCKSZ */
	Size		XLogCacheByte;	/* # bytes in xlog buffers */
	int			XLogCacheBlck;	/* highest allocated xlog buffer index */
	TimeLineID	ThisTimeLineID;

	slock_t		info_lck;		/* locks shared variables shown above */
} 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)  \
	(XLOG_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
 * used to write the XLOG, and so will normally refer to the active segment.
 */
static int	openLogFile = -1;
static uint32 openLogId = 0;
static uint32 openLogSeg = 0;
static uint32 openLogOff = 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.
 */
static int	readFile = -1;
static uint32 readId = 0;
static uint32 readSeg = 0;
static uint32 readOff = 0;

/* Buffer for currently read page (XLOG_BLCKSZ bytes) */
static char *readBuf = NULL;

/* Buffer for current ReadRecord result (expandable) */
static char *readRecordBuf = NULL;
static uint32 readRecordBufSize = 0;

/* State information for XLOG reading */
static XLogRecPtr ReadRecPtr;	/* start of last record read */
static XLogRecPtr EndRecPtr;	/* end+1 of last record read */
static XLogRecord *nextRecord = NULL;
static TimeLineID lastPageTLI = 0;

static bool InRedo = false;


static void XLogArchiveNotify(const char *xlog);
static void XLogArchiveNotifySeg(uint32 log, uint32 seg);
static bool XLogArchiveCheckDone(const char *xlog);
static void XLogArchiveCleanup(const char *xlog);
static void readRecoveryCommandFile(void);
static void exitArchiveRecovery(TimeLineID endTLI,
					uint32 endLogId, uint32 endLogSeg);
static bool recoveryStopsHere(XLogRecord *record, bool *includeThis);
static void CheckPointGuts(XLogRecPtr checkPointRedo, int flags);

static bool XLogCheckBuffer(XLogRecData *rdata, bool doPageWrites,
				XLogRecPtr *lsn, BkpBlock *bkpb);
static bool AdvanceXLInsertBuffer(bool new_segment);
static void XLogWrite(XLogwrtRqst WriteRqst, bool flexible, bool xlog_switch);
static int XLogFileInit(uint32 log, uint32 seg,
			 bool *use_existent, bool use_lock);
static bool InstallXLogFileSegment(uint32 *log, uint32 *seg, char *tmppath,
					   bool find_free, int *max_advance,
					   bool use_lock);
static int	XLogFileOpen(uint32 log, uint32 seg);
static int	XLogFileRead(uint32 log, uint32 seg, int emode);
static void XLogFileClose(void);
static bool RestoreArchivedFile(char *path, const char *xlogfname,
					const char *recovername, off_t expectedSize);
static void PreallocXlogFiles(XLogRecPtr endptr);
static void RemoveOldXlogFiles(uint32 log, uint32 seg, XLogRecPtr endptr);
static void CleanupBackupHistory(void);
static XLogRecord *ReadRecord(XLogRecPtr *RecPtr, int emode);
static bool ValidXLOGHeader(XLogPageHeader hdr, int emode);
static XLogRecord *ReadCheckpointRecord(XLogRecPtr RecPtr, int whichChkpt);
static List *readTimeLineHistory(TimeLineID targetTLI);
static bool existsTimeLineHistory(TimeLineID probeTLI);
static TimeLineID findNewestTimeLine(TimeLineID startTLI);
static void writeTimeLineHistory(TimeLineID newTLI, TimeLineID parentTLI,
					 TimeLineID endTLI,
					 uint32 endLogId, uint32 endLogSeg);
static void WriteControlFile(void);
static void ReadControlFile(void);