smgr.c

postgresql8.3.4源码,开源数据库

	/*
	 * It'd be nice to tell the stats collector to forget it immediately, too.
	 * But we can't because we don't know the OID (and in cases involving
	 * relfilenode swaps, it's not always clear which table OID to forget,
	 * anyway).
	 */

	/*
	 * And delete the physical files.
	 *
	 * Note: smgr_unlink must treat deletion failure as a WARNING, not an
	 * ERROR, because we've already decided to commit or abort the current
	 * xact.
	 */
	(*(smgrsw[which].smgr_unlink)) (rnode, isRedo);
}

/*
 *	smgrextend() -- Add a new block to a file.
 *
 *		The semantics are nearly the same as smgrwrite(): write at the
 *		specified position.  However, this is to be used for the case of
 *		extending a relation (i.e., blocknum is at or beyond the current
 *		EOF).  Note that we assume writing a block beyond current EOF
 *		causes intervening file space to become filled with zeroes.
 */
void
smgrextend(SMgrRelation reln, BlockNumber blocknum, char *buffer, bool isTemp)
{
	(*(smgrsw[reln->smgr_which].smgr_extend)) (reln, blocknum, buffer, isTemp);
}

/*
 *	smgrread() -- read a particular block from a relation into the supplied
 *				  buffer.
 *
 *		This routine is called from the buffer manager in order to
 *		instantiate pages in the shared buffer cache.  All storage managers
 *		return pages in the format that POSTGRES expects.
 */
void
smgrread(SMgrRelation reln, BlockNumber blocknum, char *buffer)
{
	(*(smgrsw[reln->smgr_which].smgr_read)) (reln, blocknum, buffer);
}

/*
 *	smgrwrite() -- Write the supplied buffer out.
 *
 *		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 smgrextend().
 *
 *		This is not a synchronous write -- the block is not necessarily
 *		on disk at return, only dumped out to the kernel.  However,
 *		provisions will be made to fsync the write before the next checkpoint.
 *
 *		isTemp indicates that the relation is a temp table (ie, is managed
 *		by the local-buffer manager).  In this case no provisions need be
 *		made to fsync the write before checkpointing.
 */
void
smgrwrite(SMgrRelation reln, BlockNumber blocknum, char *buffer, bool isTemp)
{
	(*(smgrsw[reln->smgr_which].smgr_write)) (reln, blocknum, buffer, isTemp);
}

/*
 *	smgrnblocks() -- Calculate the number of blocks in the
 *					 supplied relation.
 */
BlockNumber
smgrnblocks(SMgrRelation reln)
{
	return (*(smgrsw[reln->smgr_which].smgr_nblocks)) (reln);
}

/*
 *	smgrtruncate() -- Truncate supplied relation to the specified number
 *					  of blocks
 */
void
smgrtruncate(SMgrRelation reln, BlockNumber nblocks, bool isTemp)
{
	/*
	 * Get rid of any buffers for the about-to-be-deleted blocks. bufmgr will
	 * just drop them without bothering to write the contents.
	 */
	DropRelFileNodeBuffers(reln->smgr_rnode, isTemp, nblocks);

	/*
	 * Tell the free space map to forget anything it may have stored for the
	 * about-to-be-deleted blocks.	We want to be sure it won't return bogus
	 * block numbers later on.
	 */
	FreeSpaceMapTruncateRel(&reln->smgr_rnode, nblocks);

	/* Do the truncation */
	(*(smgrsw[reln->smgr_which].smgr_truncate)) (reln, nblocks, isTemp);

	if (!isTemp)
	{
		/*
		 * Make an XLOG entry showing the file truncation.
		 */
		XLogRecPtr	lsn;
		XLogRecData rdata;
		xl_smgr_truncate xlrec;

		xlrec.blkno = nblocks;
		xlrec.rnode = reln->smgr_rnode;

		rdata.data = (char *) &xlrec;
		rdata.len = sizeof(xlrec);
		rdata.buffer = InvalidBuffer;
		rdata.next = NULL;

		lsn = XLogInsert(RM_SMGR_ID, XLOG_SMGR_TRUNCATE, &rdata);
	}
}

/*
 *	smgrimmedsync() -- Force the specified relation to stable storage.
 *
 *		Synchronously force all previous writes to the specified relation
 *		down to disk.
 *
 *		This is useful for building completely new relations (eg, new
 *		indexes).  Instead of incrementally WAL-logging the index build
 *		steps, we can just write completed index pages to disk with smgrwrite
 *		or smgrextend, and then fsync the completed index file before
 *		committing the transaction.  (This is sufficient for purposes of
 *		crash recovery, since it effectively duplicates forcing a checkpoint
 *		for the completed index.  But it is *not* sufficient if one wishes
 *		to use the WAL log for PITR or replication purposes: in that case
 *		we have to make WAL entries as well.)
 *
 *		The preceding writes should specify isTemp = true to avoid
 *		duplicative fsyncs.
 *
 *		Note that you need to do FlushRelationBuffers() first if there is
 *		any possibility that there are dirty buffers for the relation;
 *		otherwise the sync is not very meaningful.
 */
void
smgrimmedsync(SMgrRelation reln)
{
	(*(smgrsw[reln->smgr_which].smgr_immedsync)) (reln);
}


/*
 *	PostPrepare_smgr -- Clean up after a successful PREPARE
 *
 * What we have to do here is throw away the in-memory state about pending
 * relation deletes.  It's all been recorded in the 2PC state file and
 * it's no longer smgr's job to worry about it.
 */
void
PostPrepare_smgr(void)
{
	PendingRelDelete *pending;
	PendingRelDelete *next;

	for (pending = pendingDeletes; pending != NULL; pending = next)
	{
		next = pending->next;
		pendingDeletes = next;
		/* must explicitly free the list entry */
		pfree(pending);
	}
}


/*
 *	smgrDoPendingDeletes() -- Take care of relation deletes at end of xact.
 *
 * This also runs when aborting a subxact; we want to clean up a failed
 * subxact immediately.
 */
void
smgrDoPendingDeletes(bool isCommit)
{
	int			nestLevel = GetCurrentTransactionNestLevel();
	PendingRelDelete *pending;
	PendingRelDelete *prev;
	PendingRelDelete *next;

	prev = NULL;
	for (pending = pendingDeletes; pending != NULL; pending = next)
	{
		next = pending->next;
		if (pending->nestLevel < nestLevel)
		{
			/* outer-level entries should not be processed yet */
			prev = pending;
		}
		else
		{
			/* unlink list entry first, so we don't retry on failure */
			if (prev)
				prev->next = next;
			else
				pendingDeletes = next;
			/* do deletion if called for */
			if (pending->atCommit == isCommit)
				smgr_internal_unlink(pending->relnode,
									 pending->which,
									 pending->isTemp,
									 false);
			/* must explicitly free the list entry */
			pfree(pending);
			/* prev does not change */
		}
	}
}

/*
 * smgrGetPendingDeletes() -- Get a list of relations to be deleted.
 *
 * The return value is the number of relations scheduled for termination.
 * *ptr is set to point to a freshly-palloc'd array of RelFileNodes.
 * If there are no relations to be deleted, *ptr is set to NULL.
 *
 * If haveNonTemp isn't NULL, the bool it points to gets set to true if
 * there is any non-temp table pending to be deleted; false if not.
 *
 * Note that the list does not include anything scheduled for termination
 * by upper-level transactions.
 */
int
smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr, bool *haveNonTemp)
{
	int			nestLevel = GetCurrentTransactionNestLevel();
	int			nrels;
	RelFileNode *rptr;
	PendingRelDelete *pending;

	nrels = 0;
	if (haveNonTemp)
		*haveNonTemp = false;
	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
	{
		if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit)
			nrels++;
	}
	if (nrels == 0)
	{
		*ptr = NULL;
		return 0;
	}
	rptr = (RelFileNode *) palloc(nrels * sizeof(RelFileNode));
	*ptr = rptr;
	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
	{
		if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit)
			*rptr++ = pending->relnode;
		if (haveNonTemp && !pending->isTemp)
			*haveNonTemp = true;
	}
	return nrels;
}

/*
 * AtSubCommit_smgr() --- Take care of subtransaction commit.
 *
 * Reassign all items in the pending-deletes list to the parent transaction.
 */
void
AtSubCommit_smgr(void)
{
	int			nestLevel = GetCurrentTransactionNestLevel();
	PendingRelDelete *pending;

	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
	{
		if (pending->nestLevel >= nestLevel)
			pending->nestLevel = nestLevel - 1;
	}
}

/*
 * AtSubAbort_smgr() --- Take care of subtransaction abort.
 *
 * Delete created relations and forget about deleted relations.
 * We can execute these operations immediately because we know this
 * subtransaction will not commit.
 */
void
AtSubAbort_smgr(void)
{
	smgrDoPendingDeletes(false);
}

/*
 *	smgrcommit() -- Prepare to commit changes made during the current
 *					transaction.
 *
 *		This is called before we actually commit.
 */
void
smgrcommit(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_commit)
			(*(smgrsw[i].smgr_commit)) ();
	}
}

/*
 *	smgrabort() -- Clean up after transaction abort.
 */
void
smgrabort(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_abort)
			(*(smgrsw[i].smgr_abort)) ();
	}
}

/*
 *	smgrpreckpt() -- Prepare for checkpoint.
 */
void
smgrpreckpt(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_pre_ckpt)
			(*(smgrsw[i].smgr_pre_ckpt)) ();
	}
}

/*
 *	smgrsync() -- Sync files to disk during checkpoint.
 */
void
smgrsync(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_sync)
			(*(smgrsw[i].smgr_sync)) ();
	}
}

/*
 *	smgrpostckpt() -- Post-checkpoint cleanup.
 */
void
smgrpostckpt(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_post_ckpt)
			(*(smgrsw[i].smgr_post_ckpt)) ();
	}
}


void
smgr_redo(XLogRecPtr lsn, XLogRecord *record)
{
	uint8		info = record->xl_info & ~XLR_INFO_MASK;

	if (info == XLOG_SMGR_CREATE)
	{
		xl_smgr_create *xlrec = (xl_smgr_create *) XLogRecGetData(record);
		SMgrRelation reln;

		reln = smgropen(xlrec->rnode);
		smgrcreate(reln, false, true);
	}
	else if (info == XLOG_SMGR_TRUNCATE)
	{
		xl_smgr_truncate *xlrec = (xl_smgr_truncate *) XLogRecGetData(record);
		SMgrRelation reln;

		reln = smgropen(xlrec->rnode);

		/*
		 * Forcibly create relation if it doesn't exist (which suggests that
		 * it was dropped somewhere later in the WAL sequence).  As in
		 * XLogOpenRelation, we prefer to recreate the rel and replay the log
		 * as best we can until the drop is seen.
		 */
		smgrcreate(reln, false, true);

		/* Can't use smgrtruncate because it would try to xlog */

		/*
		 * First, force bufmgr to drop any buffers it has for the to-be-
		 * truncated blocks.  We must do this, else subsequent XLogReadBuffer
		 * operations will not re-extend the file properly.
		 */
		DropRelFileNodeBuffers(xlrec->rnode, false, xlrec->blkno);

		/*
		 * Tell the free space map to forget anything it may have stored for
		 * the about-to-be-deleted blocks.	We want to be sure it won't return
		 * bogus block numbers later on.
		 */
		FreeSpaceMapTruncateRel(&reln->smgr_rnode, xlrec->blkno);

		/* Do the truncation */
		(*(smgrsw[reln->smgr_which].smgr_truncate)) (reln,
													 xlrec->blkno,
													 false);

		/* Also tell xlogutils.c about it */
		XLogTruncateRelation(xlrec->rnode, xlrec->blkno);
	}
	else
		elog(PANIC, "smgr_redo: unknown op code %u", info);
}

void
smgr_desc(StringInfo buf, uint8 xl_info, char *rec)
{
	uint8		info = xl_info & ~XLR_INFO_MASK;

	if (info == XLOG_SMGR_CREATE)
	{
		xl_smgr_create *xlrec = (xl_smgr_create *) rec;

		appendStringInfo(buf, "file create: %u/%u/%u",
						 xlrec->rnode.spcNode, xlrec->rnode.dbNode,
						 xlrec->rnode.relNode);
	}
	else if (info == XLOG_SMGR_TRUNCATE)
	{
		xl_smgr_truncate *xlrec = (xl_smgr_truncate *) rec;

		appendStringInfo(buf, "file truncate: %u/%u/%u to %u blocks",
						 xlrec->rnode.spcNode, xlrec->rnode.dbNode,
						 xlrec->rnode.relNode, xlrec->blkno);
	}
	else
		appendStringInfo(buf, "UNKNOWN");
}