xlog.c

PostgreSQL7.4.6 for Linux

	 * bad LSN on a data page.
	 */
	if (XLByteLT(LogwrtResult.Flush, record))
		elog(InRecovery ? WARNING : ERROR,
			 "xlog flush request %X/%X is not satisfied --- flushed only to %X/%X",
			 record.xlogid, record.xrecoff,
			 LogwrtResult.Flush.xlogid, LogwrtResult.Flush.xrecoff);
}

/*
 * Create a new XLOG file segment, or open a pre-existing one.
 *
 * log, seg: identify segment to be created/opened.
 *
 * *use_existent: if TRUE, OK to use a pre-existing file (else, any
 * pre-existing file will be deleted).	On return, TRUE if a pre-existing
 * file was used.
 *
 * use_lock: if TRUE, acquire ControlFileLock while moving file into
 * place.  This should be TRUE except during bootstrap log creation.  The
 * caller must *not* hold the lock at call.
 *
 * Returns FD of opened file.
 */
static int
XLogFileInit(uint32 log, uint32 seg,
			 bool *use_existent, bool use_lock)
{
	char		path[MAXPGPATH];
	char		tmppath[MAXPGPATH];
	char		zbuffer[BLCKSZ];
	int			fd;
	int			nbytes;

	XLogFileName(path, log, seg);

	/*
	 * Try to use existent file (checkpoint maker may have created it
	 * already)
	 */
	if (*use_existent)
	{
		fd = BasicOpenFile(path, O_RDWR | PG_BINARY | XLOG_SYNC_BIT,
						   S_IRUSR | S_IWUSR);
		if (fd < 0)
		{
			if (errno != ENOENT)
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not open file \"%s\" (log file %u, segment %u): %m",
								path, log, seg)));
		}
		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.
	 */
	snprintf(tmppath, MAXPGPATH, "%s/xlogtemp.%d",
			 XLogDir, (int) getpid());

	unlink(tmppath);

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

	/*
	 * Zero-fill the file.	We have to 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.
	 */
	MemSet(zbuffer, 0, sizeof(zbuffer));
	for (nbytes = 0; nbytes < XLogSegSize; nbytes += sizeof(zbuffer))
	{
		errno = 0;
		if ((int) write(fd, zbuffer, sizeof(zbuffer)) != (int) sizeof(zbuffer))
		{
			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(PANIC,
					(errcode_for_file_access(),
					 errmsg("could not write to file \"%s\": %m", tmppath)));
		}
	}

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

	close(fd);

	/*
	 * Now move the segment into place with its final name.
	 *
	 * If caller didn't want to use a pre-existing file, get rid of any
	 * pre-existing file.  Otherwise, 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.
	 */
	if (!InstallXLogFileSegment(log, seg, tmppath,
								*use_existent, XLOGfileslop,
								use_lock))
	{
		/* No need for any more future segments... */
		unlink(tmppath);
	}

	/* Set flag to tell caller there was no existent file */
	*use_existent = false;

	/* Now open original target segment (might not be file I just made) */
	fd = BasicOpenFile(path, O_RDWR | PG_BINARY | XLOG_SYNC_BIT,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
			errmsg("could not open file \"%s\" (log file %u, segment %u): %m",
				   path, log, seg)));

	return (fd);
}

/*
 * 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.
 *
 * log, seg: identify segment to install as (or first possible target).
 *
 * 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 log/seg
 * number at or after the passed numbers.  If FALSE, install the new segment
 * exactly where specified, deleting any existing segment file there.
 *
 * max_advance: maximum number of log/seg slots to advance past the starting
 * point.  Fail if no free slot is found in this range.  (Irrelevant if
 * find_free is FALSE.)
 *
 * use_lock: if TRUE, acquire ControlFileLock while moving file into
 * place.  This should be TRUE except during bootstrap log creation.  The
 * caller must *not* hold the lock at call.
 *
 * Returns TRUE if file installed, FALSE if not installed because of
 * exceeding max_advance limit.  (Any other kind of failure causes ereport().)
 */
static bool
InstallXLogFileSegment(uint32 log, uint32 seg, char *tmppath,
					   bool find_free, int max_advance,
					   bool use_lock)
{
	char		path[MAXPGPATH];
	struct stat stat_buf;

	XLogFileName(path, log, seg);

	/*
	 * We want to be sure that only one process does this at a time.
	 */
	if (use_lock)
		LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

	if (!find_free)
	{
		/* Force installation: get rid of any pre-existing segment file */
		unlink(path);
	}
	else
	{
		/* Find a free slot to put it in */
		while (stat(path, &stat_buf) == 0)
		{
			if (--max_advance < 0)
			{
				/* Failed to find a free slot within specified range */
				if (use_lock)
					LWLockRelease(ControlFileLock);
				return false;
			}
			NextLogSeg(log, seg);
			XLogFileName(path, log, seg);
		}
	}

	/*
	 * Prefer link() to rename() here just to be really sure that we don't
	 * overwrite an existing logfile.  However, there shouldn't be one, so
	 * rename() is an acceptable substitute except for the truly paranoid.
	 */
#if HAVE_WORKING_LINK
	if (link(tmppath, path) < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not link file \"%s\" to \"%s\" (initialization of log file %u, segment %u): %m",
						tmppath, path, log, seg)));
	unlink(tmppath);
#else
	if (rename(tmppath, path) < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not rename file \"%s\" to \"%s\" (initialization of log file %u, segment %u): %m",
						tmppath, path, log, seg)));
#endif

	if (use_lock)
		LWLockRelease(ControlFileLock);

	return true;
}

/*
 * Open a pre-existing logfile segment.
 */
static int
XLogFileOpen(uint32 log, uint32 seg, bool econt)
{
	char		path[MAXPGPATH];
	int			fd;

	XLogFileName(path, log, seg);

	fd = BasicOpenFile(path, O_RDWR | PG_BINARY | XLOG_SYNC_BIT,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
	{
		if (econt && errno == ENOENT)
		{
			ereport(LOG,
					(errcode_for_file_access(),
			errmsg("could not open file \"%s\" (log file %u, segment %u): %m",
				   path, log, seg)));
			return (fd);
		}
		ereport(PANIC,
				(errcode_for_file_access(),
			errmsg("could not open file \"%s\" (log file %u, segment %u): %m",
				   path, log, seg)));
	}

	return (fd);
}

/*
 * Preallocate log files beyond the specified log endpoint, according to
 * the XLOGfile user parameter.
 */
static void
PreallocXlogFiles(XLogRecPtr endptr)
{
	uint32		_logId;
	uint32		_logSeg;
	int			lf;
	bool		use_existent;

	XLByteToPrevSeg(endptr, _logId, _logSeg);
	if ((endptr.xrecoff - 1) % XLogSegSize >=
		(uint32) (0.75 * XLogSegSize))
	{
		NextLogSeg(_logId, _logSeg);
		use_existent = true;
		lf = XLogFileInit(_logId, _logSeg, &use_existent, true);
		close(lf);
	}
}

/*
 * Remove or move offline all log files older or equal to passed log/seg#
 *
 * endptr is current (or recent) end of xlog; this is used to determine
 * whether we want to recycle rather than delete no-longer-wanted log files.
 */
static void
MoveOfflineLogs(uint32 log, uint32 seg, XLogRecPtr endptr)
{
	uint32		endlogId;
	uint32		endlogSeg;
	DIR		   *xldir;
	struct dirent *xlde;
	char		lastoff[32];
	char		path[MAXPGPATH];

	XLByteToPrevSeg(endptr, endlogId, endlogSeg);

	xldir = AllocateDir(XLogDir);
	if (xldir == NULL)
		ereport(ERROR,
				(errcode_for_file_access(),
			errmsg("could not open transaction log directory \"%s\": %m",
				   XLogDir)));

	sprintf(lastoff, "%08X%08X", log, seg);

	errno = 0;
	while ((xlde = readdir(xldir)) != NULL)
	{
		if (strlen(xlde->d_name) == 16 &&
			strspn(xlde->d_name, "0123456789ABCDEF") == 16 &&
			strcmp(xlde->d_name, lastoff) <= 0)
		{
			snprintf(path, MAXPGPATH, "%s/%s", XLogDir, xlde->d_name);
			if (XLOG_archive_dir[0])
			{
				ereport(LOG,
						(errmsg("archiving transaction log file \"%s\"",
								xlde->d_name)));
				elog(WARNING, "archiving log files is not implemented");
			}
			else
			{
				/*
				 * Before deleting the file, see if it can be recycled as
				 * a future log segment.  We allow recycling segments up
				 * to XLOGfileslop segments beyond the current XLOG
				 * location.
				 */
				if (InstallXLogFileSegment(endlogId, endlogSeg, path,
										   true, XLOGfileslop,
										   true))
				{
					ereport(LOG,
						  (errmsg("recycled transaction log file \"%s\"",
								  xlde->d_name)));
				}
				else
				{
					/* No need for any more future segments... */
					ereport(LOG,
						  (errmsg("removing transaction log file \"%s\"",
								  xlde->d_name)));
					unlink(path);
				}
			}
		}
		errno = 0;
	}
	if (errno)
		ereport(ERROR,
				(errcode_for_file_access(),
			errmsg("could not read transaction log directory \"%s\": %m",
				   XLogDir)));
	FreeDir(xldir);
}

/*
 * Restore the backup blocks present in an XLOG record, if any.
 *
 * We assume all of the record has been read into memory at *record.
 */
static void
RestoreBkpBlocks(XLogRecord *record, XLogRecPtr lsn)
{
	Relation	reln;
	Buffer		buffer;
	Page		page;
	BkpBlock	bkpb;
	char	   *blk;
	int			i;

	blk = (char *) XLogRecGetData(record) + record->xl_len;
	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		if (!(record->xl_info & XLR_SET_BKP_BLOCK(i)))
			continue;

		memcpy((char *) &bkpb, blk, sizeof(BkpBlock));
		blk += sizeof(BkpBlock);

		reln = XLogOpenRelation(true, record->xl_rmid, bkpb.node);

		if (reln)
		{
			buffer = XLogReadBuffer(true, reln, bkpb.block);
			if (BufferIsValid(buffer))
			{
				page = (Page) BufferGetPage(buffer);
				memcpy((char *) page, blk, BLCKSZ);
				PageSetLSN(page, lsn);
				PageSetSUI(page, ThisStartUpID);
				UnlockAndWriteBuffer(buffer);
			}
		}

		blk += BLCKSZ;
	}
}

/*
 * CRC-check an XLOG record.  We do not believe the contents of an XLOG
 * record (other than to the minimal extent of computing the amount of
 * data to read in) until we've checked the CRCs.
 *
 * We assume all of the record has been read into memory at *record.
 */
static bool
RecordIsValid(XLogRecord *record, XLogRecPtr recptr, int emode)
{
	crc64		crc;
	crc64		cbuf;
	int			i;
	uint32		len = record->xl_len;
	char	   *blk;

	/* Check CRC of rmgr data and record header */
	INIT_CRC64(crc);
	COMP_CRC64(crc, XLogRecGetData(record), len);
	COMP_CRC64(crc, (char *) record + sizeof(crc64),
			   SizeOfXLogRecord - sizeof(crc64));
	FIN_CRC64(crc);

	if (!EQ_CRC64(record->xl_crc, crc))
	{
		ereport(emode,
		 (errmsg("incorrect resource manager data checksum in record at %X/%X",
				 recptr.xlogid, recptr.xrecoff)));