md.c

postgresql8.3.4源码,开源数据库

			/*
			 * This segment is no longer active (and has already been unlinked
			 * from the mdfd_chain). We truncate the file, but do not delete
			 * it, for reasons explained in the header comments.
			 */
			if (FileTruncate(v->mdfd_vfd, 0) < 0)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not truncate relation %u/%u/%u to %u blocks: %m",
								reln->smgr_rnode.spcNode,
								reln->smgr_rnode.dbNode,
								reln->smgr_rnode.relNode,
								nblocks)));
			if (!isTemp)
				register_dirty_segment(reln, v);
			v = v->mdfd_chain;
			Assert(ov != reln->md_fd);	/* we never drop the 1st segment */
			pfree(ov);
		}
		else if (priorblocks + ((BlockNumber) RELSEG_SIZE) > nblocks)
		{
			/*
			 * This is the last segment we want to keep. Truncate the file to
			 * the right length, and clear chain link that points to any
			 * remaining segments (which we shall zap). NOTE: if nblocks is
			 * exactly a multiple K of RELSEG_SIZE, we will truncate the K+1st
			 * segment to 0 length but keep it. This adheres to the invariant
			 * given in the header comments.
			 */
			BlockNumber lastsegblocks = nblocks - priorblocks;

			if (FileTruncate(v->mdfd_vfd, lastsegblocks * BLCKSZ) < 0)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not truncate relation %u/%u/%u to %u blocks: %m",
								reln->smgr_rnode.spcNode,
								reln->smgr_rnode.dbNode,
								reln->smgr_rnode.relNode,
								nblocks)));
			if (!isTemp)
				register_dirty_segment(reln, v);
			v = v->mdfd_chain;
			ov->mdfd_chain = NULL;
		}
		else
		{
			/*
			 * We still need this segment and 0 or more blocks beyond it, so
			 * nothing to do here.
			 */
			v = v->mdfd_chain;
		}
		priorblocks += RELSEG_SIZE;
	}
#else
	if (FileTruncate(v->mdfd_vfd, nblocks * BLCKSZ) < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
			  errmsg("could not truncate relation %u/%u/%u to %u blocks: %m",
					 reln->smgr_rnode.spcNode,
					 reln->smgr_rnode.dbNode,
					 reln->smgr_rnode.relNode,
					 nblocks)));
	if (!isTemp)
		register_dirty_segment(reln, v);
#endif
}

/*
 *	mdimmedsync() -- Immediately sync a relation to stable storage.
 *
 * Note that only writes already issued are synced; this routine knows
 * nothing of dirty buffers that may exist inside the buffer manager.
 */
void
mdimmedsync(SMgrRelation reln)
{
	MdfdVec    *v;
	BlockNumber curnblk;

	/*
	 * NOTE: mdnblocks makes sure we have opened all active segments, so that
	 * fsync loop will get them all!
	 */
	curnblk = mdnblocks(reln);

	v = mdopen(reln, EXTENSION_FAIL);

#ifndef LET_OS_MANAGE_FILESIZE
	while (v != NULL)
	{
		if (FileSync(v->mdfd_vfd) < 0)
			ereport(ERROR,
					(errcode_for_file_access(),
				errmsg("could not fsync segment %u of relation %u/%u/%u: %m",
					   v->mdfd_segno,
					   reln->smgr_rnode.spcNode,
					   reln->smgr_rnode.dbNode,
					   reln->smgr_rnode.relNode)));
		v = v->mdfd_chain;
	}
#else
	if (FileSync(v->mdfd_vfd) < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not fsync segment %u of relation %u/%u/%u: %m",
						v->mdfd_segno,
						reln->smgr_rnode.spcNode,
						reln->smgr_rnode.dbNode,
						reln->smgr_rnode.relNode)));
#endif
}

/*
 *	mdsync() -- Sync previous writes to stable storage.
 */
void
mdsync(void)
{
	static bool mdsync_in_progress = false;

	HASH_SEQ_STATUS hstat;
	PendingOperationEntry *entry;
	int			absorb_counter;

	/*
	 * This is only called during checkpoints, and checkpoints should only
	 * occur in processes that have created a pendingOpsTable.
	 */
	if (!pendingOpsTable)
		elog(ERROR, "cannot sync without a pendingOpsTable");

	/*
	 * If we are in the bgwriter, the sync had better include all fsync
	 * requests that were queued by backends up to this point.	The tightest
	 * race condition that could occur is that a buffer that must be written
	 * and fsync'd for the checkpoint could have been dumped by a backend just
	 * before it was visited by BufferSync().  We know the backend will have
	 * queued an fsync request before clearing the buffer's dirtybit, so we
	 * are safe as long as we do an Absorb after completing BufferSync().
	 */
	AbsorbFsyncRequests();

	/*
	 * To avoid excess fsync'ing (in the worst case, maybe a never-terminating
	 * checkpoint), we want to ignore fsync requests that are entered into the
	 * hashtable after this point --- they should be processed next time,
	 * instead.  We use mdsync_cycle_ctr to tell old entries apart from new
	 * ones: new ones will have cycle_ctr equal to the incremented value of
	 * mdsync_cycle_ctr.
	 *
	 * In normal circumstances, all entries present in the table at this point
	 * will have cycle_ctr exactly equal to the current (about to be old)
	 * value of mdsync_cycle_ctr.  However, if we fail partway through the
	 * fsync'ing loop, then older values of cycle_ctr might remain when we
	 * come back here to try again.  Repeated checkpoint failures would
	 * eventually wrap the counter around to the point where an old entry
	 * might appear new, causing us to skip it, possibly allowing a checkpoint
	 * to succeed that should not have.  To forestall wraparound, any time the
	 * previous mdsync() failed to complete, run through the table and
	 * forcibly set cycle_ctr = mdsync_cycle_ctr.
	 *
	 * Think not to merge this loop with the main loop, as the problem is
	 * exactly that that loop may fail before having visited all the entries.
	 * From a performance point of view it doesn't matter anyway, as this path
	 * will never be taken in a system that's functioning normally.
	 */
	if (mdsync_in_progress)
	{
		/* prior try failed, so update any stale cycle_ctr values */
		hash_seq_init(&hstat, pendingOpsTable);
		while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
		{
			entry->cycle_ctr = mdsync_cycle_ctr;
		}
	}

	/* Advance counter so that new hashtable entries are distinguishable */
	mdsync_cycle_ctr++;

	/* Set flag to detect failure if we don't reach the end of the loop */
	mdsync_in_progress = true;

	/* Now scan the hashtable for fsync requests to process */
	absorb_counter = FSYNCS_PER_ABSORB;
	hash_seq_init(&hstat, pendingOpsTable);
	while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
	{
		/*
		 * If the entry is new then don't process it this time.  Note that
		 * "continue" bypasses the hash-remove call at the bottom of the loop.
		 */
		if (entry->cycle_ctr == mdsync_cycle_ctr)
			continue;

		/* Else assert we haven't missed it */
		Assert((CycleCtr) (entry->cycle_ctr + 1) == mdsync_cycle_ctr);

		/*
		 * If fsync is off then we don't have to bother opening the file at
		 * all.  (We delay checking until this point so that changing fsync on
		 * the fly behaves sensibly.)  Also, if the entry is marked canceled,
		 * fall through to delete it.
		 */
		if (enableFsync && !entry->canceled)
		{
			int			failures;

			/*
			 * If in bgwriter, we want to absorb pending requests every so
			 * often to prevent overflow of the fsync request queue.  It is
			 * unspecified whether newly-added entries will be visited by
			 * hash_seq_search, but we don't care since we don't need to
			 * process them anyway.
			 */
			if (--absorb_counter <= 0)
			{
				AbsorbFsyncRequests();
				absorb_counter = FSYNCS_PER_ABSORB;
			}

			/*
			 * The fsync table could contain requests to fsync segments that
			 * have been deleted (unlinked) by the time we get to them. Rather
			 * than just hoping an ENOENT (or EACCES on Windows) error can be
			 * ignored, what we do on error is absorb pending requests and
			 * then retry.	Since mdunlink() queues a "revoke" message before
			 * actually unlinking, the fsync request is guaranteed to be
			 * marked canceled after the absorb if it really was this case.
			 * DROP DATABASE likewise has to tell us to forget fsync requests
			 * before it starts deletions.
			 */
			for (failures = 0;; failures++)		/* loop exits at "break" */
			{
				SMgrRelation reln;
				MdfdVec    *seg;

				/*
				 * Find or create an smgr hash entry for this relation. This
				 * may seem a bit unclean -- md calling smgr?  But it's really
				 * the best solution.  It ensures that the open file reference
				 * isn't permanently leaked if we get an error here. (You may
				 * say "but an unreferenced SMgrRelation is still a leak!" Not
				 * really, because the only case in which a checkpoint is done
				 * by a process that isn't about to shut down is in the
				 * bgwriter, and it will periodically do smgrcloseall(). This
				 * fact justifies our not closing the reln in the success path
				 * either, which is a good thing since in non-bgwriter cases
				 * we couldn't safely do that.)  Furthermore, in many cases
				 * the relation will have been dirtied through this same smgr
				 * relation, and so we can save a file open/close cycle.
				 */
				reln = smgropen(entry->tag.rnode);

				/*
				 * It is possible that the relation has been dropped or
				 * truncated since the fsync request was entered.  Therefore,
				 * allow ENOENT, but only if we didn't fail already on this
				 * file.  This applies both during _mdfd_getseg() and during
				 * FileSync, since fd.c might have closed the file behind our
				 * back.
				 */
				seg = _mdfd_getseg(reln,
							  entry->tag.segno * ((BlockNumber) RELSEG_SIZE),
								   false, EXTENSION_RETURN_NULL);
				if (seg != NULL &&
					FileSync(seg->mdfd_vfd) >= 0)
					break;		/* success; break out of retry loop */

				/*
				 * XXX is there any point in allowing more than one retry?
				 * Don't see one at the moment, but easy to change the test
				 * here if so.
				 */
				if (!FILE_POSSIBLY_DELETED(errno) ||
					failures > 0)
					ereport(ERROR,
							(errcode_for_file_access(),
							 errmsg("could not fsync segment %u of relation %u/%u/%u: %m",
									entry->tag.segno,
									entry->tag.rnode.spcNode,
									entry->tag.rnode.dbNode,
									entry->tag.rnode.relNode)));
				else
					ereport(DEBUG1,
							(errcode_for_file_access(),
							 errmsg("could not fsync segment %u of relation %u/%u/%u, but retrying: %m",
									entry->tag.segno,
									entry->tag.rnode.spcNode,
									entry->tag.rnode.dbNode,
									entry->tag.rnode.relNode)));

				/*
				 * Absorb incoming requests and check to see if canceled.
				 */
				AbsorbFsyncRequests();
				absorb_counter = FSYNCS_PER_ABSORB;		/* might as well... */

				if (entry->canceled)
					break;
			}					/* end retry loop */
		}

		/*
		 * If we get here, either we fsync'd successfully, or we don't have to
		 * because enableFsync is off, or the entry is (now) marked canceled.
		 * Okay to delete it.
		 */
		if (hash_search(pendingOpsTable, &entry->tag,
						HASH_REMOVE, NULL) == NULL)
			elog(ERROR, "pendingOpsTable corrupted");
	}							/* end loop over hashtable entries */

	/* Flag successful completion of mdsync */
	mdsync_in_progress = false;
}

/*
 * mdpreckpt() -- Do pre-checkpoint work
 *
 * To distinguish unlink requests that arrived before this checkpoint
 * started from those that arrived during the checkpoint, we use a cycle
 * counter similar to the one we use for fsync requests. That cycle
 * counter is incremented here.
 *
 * This must be called *before* the checkpoint REDO point is determined.
 * That ensures that we won't delete files too soon.
 *
 * Note that we can't do anything here that depends on the assumption
 * that the checkpoint will be completed.
 */
void
mdpreckpt(void)
{
	ListCell   *cell;

	/*
	 * In case the prior checkpoint wasn't completed, stamp all entries in the
	 * list with the current cycle counter.  Anything that's in the list at
	 * the start of checkpoint can surely be deleted after the checkpoint is
	 * finished, regardless of when the request was made.
	 */
	foreach(cell, pendingUnlinks)
	{
		PendingUnlinkEntry *entry = (PendingUnlinkEntry *) lfirst(cell);

		entry->cycle_ctr = mdckpt_cycle_ctr;
	}

	/*
	 * Any unlink requests arriving after this point will be assigned the next
	 * cycle counter, and won't be unlinked until next checkpoint.
	 */
	mdckpt_cycle_ctr++;
}

/*
 * mdpostckpt() -- Do post-checkpoint work
 *
 * Remove any lingering files that can now be safely removed.
 */
void
mdpostckpt(void)
{
	while (pendingUnlinks != NIL)
	{
		PendingUnlinkEntry *entry = (PendingUnlinkEntry *) linitial(pendingUnlinks);
		char	   *path;

		/*
		 * New entries are appended to the end, so if the entry is new we've
		 * reached the end of old entries.
		 */
		if (entry->cycle_ctr == mdckpt_cycle_ctr)
			break;

		/* Else assert we haven't missed it */
		Assert((CycleCtr) (entry->cycle_ctr + 1) == mdckpt_cycle_ctr);

		/* Unlink the file */
		path = relpath(entry->rnode);
		if (unlink(path) < 0)
		{
			/*
			 * There's a race condition, when the database is dropped at the
			 * same time that we process the pending unlink requests. If the
			 * DROP DATABASE deletes the file before we do, we will get ENOENT
			 * here. rmtree() also has to ignore ENOENT errors, to deal with
			 * the possibility that we delete the file first.
			 */
			if (errno != ENOENT)
				ereport(WARNING,
						(errcode_for_file_access(),
						 errmsg("could not remove relation %u/%u/%u: %m",
								entry->rnode.spcNode,
								entry->rnode.dbNode,
								entry->rnode.relNode)));
		}
		pfree(path);

		pendingUnlinks = list_delete_first(pendingUnlinks);
		pfree(entry);
	}
}

/*
 * register_dirty_segment() -- Mark a relation segment as needing fsync