md.c

postgresql8.3.4源码,开源数据库

	 * If a relation manages to grow to 2^32-1 blocks, refuse to extend it any
	 * more --- we mustn't create a block whose number actually is
	 * InvalidBlockNumber.
	 */
	if (blocknum == InvalidBlockNumber)
		ereport(ERROR,
				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
				 errmsg("cannot extend relation %u/%u/%u beyond %u blocks",
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode,
						InvalidBlockNumber)));

	v = _mdfd_getseg(reln, blocknum, isTemp, EXTENSION_CREATE);

#ifndef LET_OS_MANAGE_FILESIZE
	seekpos = (long) (BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE)));
	Assert(seekpos < BLCKSZ * RELSEG_SIZE);
#else
	seekpos = (long) (BLCKSZ * (blocknum));
#endif

	/*
	 * Note: because caller usually obtained blocknum by calling mdnblocks,
	 * which did a seek(SEEK_END), this seek is often redundant and will be
	 * optimized away by fd.c.	It's not redundant, however, if there is a
	 * partial page at the end of the file. In that case we want to try to
	 * overwrite the partial page with a full page.  It's also not redundant
	 * if bufmgr.c had to dump another buffer of the same file to make room
	 * for the new page's buffer.
	 */
	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not seek to block %u of relation %u/%u/%u: %m",
						blocknum,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode)));

	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ)) != BLCKSZ)
	{
		if (nbytes < 0)
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not extend relation %u/%u/%u: %m",
							reln->smgr_rnode.spcNode,
							reln->smgr_rnode.dbNode,
							reln->smgr_rnode.relNode),
					 errhint("Check free disk space.")));
		/* short write: complain appropriately */
		ereport(ERROR,
				(errcode(ERRCODE_DISK_FULL),
				 errmsg("could not extend relation %u/%u/%u: wrote only %d of %d bytes at block %u",
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode,
						nbytes, BLCKSZ, blocknum),
				 errhint("Check free disk space.")));
	}

	if (!isTemp)
		register_dirty_segment(reln, v);

#ifndef LET_OS_MANAGE_FILESIZE
	Assert(_mdnblocks(reln, v) <= ((BlockNumber) RELSEG_SIZE));
#endif
}

/*
 *	mdopen() -- Open the specified relation.
 *
 * Note we only open the first segment, when there are multiple segments.
 *
 * If first segment is not present, either ereport or return NULL according
 * to "behavior".  We treat EXTENSION_CREATE the same as EXTENSION_FAIL;
 * EXTENSION_CREATE means it's OK to extend an existing relation, not to
 * invent one out of whole cloth.
 */
static MdfdVec *
mdopen(SMgrRelation reln, ExtensionBehavior behavior)
{
	MdfdVec    *mdfd;
	char	   *path;
	File		fd;

	/* No work if already open */
	if (reln->md_fd)
		return reln->md_fd;

	path = relpath(reln->smgr_rnode);

	fd = PathNameOpenFile(path, O_RDWR | PG_BINARY, 0600);

	if (fd < 0)
	{
		/*
		 * During bootstrap, there are cases where a system relation will be
		 * accessed (by internal backend processes) before the bootstrap
		 * script nominally creates it.  Therefore, accept mdopen() as a
		 * substitute for mdcreate() in bootstrap mode only. (See mdcreate)
		 */
		if (IsBootstrapProcessingMode())
			fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY, 0600);
		if (fd < 0)
		{
			pfree(path);
			if (behavior == EXTENSION_RETURN_NULL &&
				FILE_POSSIBLY_DELETED(errno))
				return NULL;
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not open relation %u/%u/%u: %m",
							reln->smgr_rnode.spcNode,
							reln->smgr_rnode.dbNode,
							reln->smgr_rnode.relNode)));
		}
	}

	pfree(path);

	reln->md_fd = mdfd = _fdvec_alloc();

	mdfd->mdfd_vfd = fd;
	mdfd->mdfd_segno = 0;
#ifndef LET_OS_MANAGE_FILESIZE
	mdfd->mdfd_chain = NULL;
	Assert(_mdnblocks(reln, mdfd) <= ((BlockNumber) RELSEG_SIZE));
#endif

	return mdfd;
}

/*
 *	mdclose() -- Close the specified relation, if it isn't closed already.
 */
void
mdclose(SMgrRelation reln)
{
	MdfdVec    *v = reln->md_fd;

	/* No work if already closed */
	if (v == NULL)
		return;

	reln->md_fd = NULL;			/* prevent dangling pointer after error */

#ifndef LET_OS_MANAGE_FILESIZE
	while (v != NULL)
	{
		MdfdVec    *ov = v;

		/* if not closed already */
		if (v->mdfd_vfd >= 0)
			FileClose(v->mdfd_vfd);
		/* Now free vector */
		v = v->mdfd_chain;
		pfree(ov);
	}
#else
	if (v->mdfd_vfd >= 0)
		FileClose(v->mdfd_vfd);
	pfree(v);
#endif
}

/*
 *	mdread() -- Read the specified block from a relation.
 */
void
mdread(SMgrRelation reln, BlockNumber blocknum, char *buffer)
{
	long		seekpos;
	int			nbytes;
	MdfdVec    *v;

	v = _mdfd_getseg(reln, blocknum, false, EXTENSION_FAIL);

#ifndef LET_OS_MANAGE_FILESIZE
	seekpos = (long) (BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE)));
	Assert(seekpos < BLCKSZ * RELSEG_SIZE);
#else
	seekpos = (long) (BLCKSZ * (blocknum));
#endif

	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not seek to block %u of relation %u/%u/%u: %m",
						blocknum,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode)));

	if ((nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ)) != BLCKSZ)
	{
		if (nbytes < 0)
			ereport(ERROR,
					(errcode_for_file_access(),
				   errmsg("could not read block %u of relation %u/%u/%u: %m",
						  blocknum,
						  reln->smgr_rnode.spcNode,
						  reln->smgr_rnode.dbNode,
						  reln->smgr_rnode.relNode)));

		/*
		 * Short read: we are at or past EOF, or we read a partial block at
		 * EOF.  Normally this is an error; upper levels should never try to
		 * read a nonexistent block.  However, if zero_damaged_pages is ON or
		 * we are InRecovery, we should instead return zeroes without
		 * complaining.  This allows, for example, the case of trying to
		 * update a block that was later truncated away.
		 */
		if (zero_damaged_pages || InRecovery)
			MemSet(buffer, 0, BLCKSZ);
		else
			ereport(ERROR,
					(errcode(ERRCODE_DATA_CORRUPTED),
					 errmsg("could not read block %u of relation %u/%u/%u: read only %d of %d bytes",
							blocknum,
							reln->smgr_rnode.spcNode,
							reln->smgr_rnode.dbNode,
							reln->smgr_rnode.relNode,
							nbytes, BLCKSZ)));
	}
}

/*
 *	mdwrite() -- Write the supplied block at the appropriate location.
 *
 *		This is to be used only for updating already-existing blocks of a
 *		relation (ie, those before the current EOF).  To extend a relation,
 *		use mdextend().
 */
void
mdwrite(SMgrRelation reln, BlockNumber blocknum, char *buffer, bool isTemp)
{
	long		seekpos;
	int			nbytes;
	MdfdVec    *v;

	/* This assert is too expensive to have on normally ... */
#ifdef CHECK_WRITE_VS_EXTEND
	Assert(blocknum < mdnblocks(reln));
#endif

	v = _mdfd_getseg(reln, blocknum, isTemp, EXTENSION_FAIL);

#ifndef LET_OS_MANAGE_FILESIZE
	seekpos = (long) (BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE)));
	Assert(seekpos < BLCKSZ * RELSEG_SIZE);
#else
	seekpos = (long) (BLCKSZ * (blocknum));
#endif

	if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not seek to block %u of relation %u/%u/%u: %m",
						blocknum,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode)));

	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ)) != BLCKSZ)
	{
		if (nbytes < 0)
			ereport(ERROR,
					(errcode_for_file_access(),
				  errmsg("could not write block %u of relation %u/%u/%u: %m",
						 blocknum,
						 reln->smgr_rnode.spcNode,
						 reln->smgr_rnode.dbNode,
						 reln->smgr_rnode.relNode)));
		/* short write: complain appropriately */
		ereport(ERROR,
				(errcode(ERRCODE_DISK_FULL),
				 errmsg("could not write block %u of relation %u/%u/%u: wrote only %d of %d bytes",
						blocknum,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode,
						nbytes, BLCKSZ),
				 errhint("Check free disk space.")));
	}

	if (!isTemp)
		register_dirty_segment(reln, v);
}

/*
 *	mdnblocks() -- Get the number of blocks stored in a relation.
 *
 *		Important side effect: all active segments of the relation are opened
 *		and added to the mdfd_chain list.  If this routine has not been
 *		called, then only segments up to the last one actually touched
 *		are present in the chain.
 */
BlockNumber
mdnblocks(SMgrRelation reln)
{
	MdfdVec    *v = mdopen(reln, EXTENSION_FAIL);

#ifndef LET_OS_MANAGE_FILESIZE
	BlockNumber nblocks;
	BlockNumber segno = 0;

	/*
	 * Skip through any segments that aren't the last one, to avoid redundant
	 * seeks on them.  We have previously verified that these segments are
	 * exactly RELSEG_SIZE long, and it's useless to recheck that each time.
	 *
	 * NOTE: this assumption could only be wrong if another backend has
	 * truncated the relation.	We rely on higher code levels to handle that
	 * scenario by closing and re-opening the md fd, which is handled via
	 * relcache flush.	(Since the bgwriter doesn't participate in relcache
	 * flush, it could have segment chain entries for inactive segments;
	 * that's OK because the bgwriter never needs to compute relation size.)
	 */
	while (v->mdfd_chain != NULL)
	{
		segno++;
		v = v->mdfd_chain;
	}

	for (;;)
	{
		nblocks = _mdnblocks(reln, v);
		if (nblocks > ((BlockNumber) RELSEG_SIZE))
			elog(FATAL, "segment too big");
		if (nblocks < ((BlockNumber) RELSEG_SIZE))
			return (segno * ((BlockNumber) RELSEG_SIZE)) + nblocks;

		/*
		 * If segment is exactly RELSEG_SIZE, advance to next one.
		 */
		segno++;

		if (v->mdfd_chain == NULL)
		{
			/*
			 * Because we pass O_CREAT, we will create the next segment (with
			 * zero length) immediately, if the last segment is of length
			 * RELSEG_SIZE.  While perhaps not strictly necessary, this keeps
			 * the logic simple.
			 */
			v->mdfd_chain = _mdfd_openseg(reln, segno, O_CREAT);
			if (v->mdfd_chain == NULL)
				ereport(ERROR,
						(errcode_for_file_access(),
				 errmsg("could not open segment %u of relation %u/%u/%u: %m",
						segno,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode)));
		}

		v = v->mdfd_chain;
	}
#else
	return _mdnblocks(reln, v);
#endif
}

/*
 *	mdtruncate() -- Truncate relation to specified number of blocks.
 */
void
mdtruncate(SMgrRelation reln, BlockNumber nblocks, bool isTemp)
{
	MdfdVec    *v;
	BlockNumber curnblk;

#ifndef LET_OS_MANAGE_FILESIZE
	BlockNumber priorblocks;
#endif

	/*
	 * NOTE: mdnblocks makes sure we have opened all active segments, so that
	 * truncation loop will get them all!
	 */
	curnblk = mdnblocks(reln);
	if (nblocks > curnblk)
	{
		/* Bogus request ... but no complaint if InRecovery */
		if (InRecovery)
			return;
		ereport(ERROR,
				(errmsg("could not truncate relation %u/%u/%u to %u blocks: it's only %u blocks now",
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode,
						nblocks, curnblk)));
	}
	if (nblocks == curnblk)
		return;					/* no work */

	v = mdopen(reln, EXTENSION_FAIL);

#ifndef LET_OS_MANAGE_FILESIZE
	priorblocks = 0;
	while (v != NULL)
	{
		MdfdVec    *ov = v;

		if (priorblocks > nblocks)
		{