bufmgr.c

postgresql8.3.4源码,开源数据库

		 * above, or even while we are writing it out (since our share-lock
		 * won't prevent hint-bit updates).  We will recheck the dirty bit
		 * after re-locking the buffer header.
		 */
		if (oldFlags & BM_DIRTY)
		{
			/*
			 * We need a share-lock on the buffer contents to write it out
			 * (else we might write invalid data, eg because someone else is
			 * compacting the page contents while we write).  We must use a
			 * conditional lock acquisition here to avoid deadlock.  Even
			 * though the buffer was not pinned (and therefore surely not
			 * locked) when StrategyGetBuffer returned it, someone else could
			 * have pinned and exclusive-locked it by the time we get here. If
			 * we try to get the lock unconditionally, we'd block waiting for
			 * them; if they later block waiting for us, deadlock ensues.
			 * (This has been observed to happen when two backends are both
			 * trying to split btree index pages, and the second one just
			 * happens to be trying to split the page the first one got from
			 * StrategyGetBuffer.)
			 */
			if (LWLockConditionalAcquire(buf->content_lock, LW_SHARED))
			{
				/*
				 * If using a nondefault strategy, and writing the buffer
				 * would require a WAL flush, let the strategy decide whether
				 * to go ahead and write/reuse the buffer or to choose another
				 * victim.	We need lock to inspect the page LSN, so this
				 * can't be done inside StrategyGetBuffer.
				 */
				if (strategy != NULL &&
					XLogNeedsFlush(BufferGetLSN(buf)) &&
					StrategyRejectBuffer(strategy, buf))
				{
					/* Drop lock/pin and loop around for another buffer */
					LWLockRelease(buf->content_lock);
					UnpinBuffer(buf, true);
					continue;
				}

				/* OK, do the I/O */
				FlushBuffer(buf, NULL);
				LWLockRelease(buf->content_lock);
			}
			else
			{
				/*
				 * Someone else has locked the buffer, so give it up and loop
				 * back to get another one.
				 */
				UnpinBuffer(buf, true);
				continue;
			}
		}

		/*
		 * To change the association of a valid buffer, we'll need to have
		 * exclusive lock on both the old and new mapping partitions.
		 */
		if (oldFlags & BM_TAG_VALID)
		{
			/*
			 * Need to compute the old tag's hashcode and partition lock ID.
			 * XXX is it worth storing the hashcode in BufferDesc so we need
			 * not recompute it here?  Probably not.
			 */
			oldTag = buf->tag;
			oldHash = BufTableHashCode(&oldTag);
			oldPartitionLock = BufMappingPartitionLock(oldHash);

			/*
			 * Must lock the lower-numbered partition first to avoid
			 * deadlocks.
			 */
			if (oldPartitionLock < newPartitionLock)
			{
				LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			}
			else if (oldPartitionLock > newPartitionLock)
			{
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
				LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
			}
			else
			{
				/* only one partition, only one lock */
				LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			}
		}
		else
		{
			/* if it wasn't valid, we need only the new partition */
			LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
			/* these just keep the compiler quiet about uninit variables */
			oldHash = 0;
			oldPartitionLock = 0;
		}

		/*
		 * Try to make a hashtable entry for the buffer under its new tag.
		 * This could fail because while we were writing someone else
		 * allocated another buffer for the same block we want to read in.
		 * Note that we have not yet removed the hashtable entry for the old
		 * tag.
		 */
		buf_id = BufTableInsert(&newTag, newHash, buf->buf_id);

		if (buf_id >= 0)
		{
			/*
			 * Got a collision. Someone has already done what we were about to
			 * do. We'll just handle this as if it were found in the buffer
			 * pool in the first place.  First, give up the buffer we were
			 * planning to use.
			 */
			UnpinBuffer(buf, true);

			/* Can give up that buffer's mapping partition lock now */
			if ((oldFlags & BM_TAG_VALID) &&
				oldPartitionLock != newPartitionLock)
				LWLockRelease(oldPartitionLock);

			/* remaining code should match code at top of routine */

			buf = &BufferDescriptors[buf_id];

			valid = PinBuffer(buf, strategy);

			/* Can release the mapping lock as soon as we've pinned it */
			LWLockRelease(newPartitionLock);

			*foundPtr = TRUE;

			if (!valid)
			{
				/*
				 * We can only get here if (a) someone else is still reading
				 * in the page, or (b) a previous read attempt failed.	We
				 * have to wait for any active read attempt to finish, and
				 * then set up our own read attempt if the page is still not
				 * BM_VALID.  StartBufferIO does it all.
				 */
				if (StartBufferIO(buf, true))
				{
					/*
					 * If we get here, previous attempts to read the buffer
					 * must have failed ... but we shall bravely try again.
					 */
					*foundPtr = FALSE;
				}
			}

			return buf;
		}

		/*
		 * Need to lock the buffer header too in order to change its tag.
		 */
		LockBufHdr(buf);

		/*
		 * Somebody could have pinned or re-dirtied the buffer while we were
		 * doing the I/O and making the new hashtable entry.  If so, we can't
		 * recycle this buffer; we must undo everything we've done and start
		 * over with a new victim buffer.
		 */
		oldFlags = buf->flags;
		if (buf->refcount == 1 && !(oldFlags & BM_DIRTY))
			break;

		UnlockBufHdr(buf);
		BufTableDelete(&newTag, newHash);
		if ((oldFlags & BM_TAG_VALID) &&
			oldPartitionLock != newPartitionLock)
			LWLockRelease(oldPartitionLock);
		LWLockRelease(newPartitionLock);
		UnpinBuffer(buf, true);
	}

	/*
	 * Okay, it's finally safe to rename the buffer.
	 *
	 * Clearing BM_VALID here is necessary, clearing the dirtybits is just
	 * paranoia.  We also reset the usage_count since any recency of use of
	 * the old content is no longer relevant.  (The usage_count starts out at
	 * 1 so that the buffer can survive one clock-sweep pass.)
	 */
	buf->tag = newTag;
	buf->flags &= ~(BM_VALID | BM_DIRTY | BM_JUST_DIRTIED | BM_CHECKPOINT_NEEDED | BM_IO_ERROR);
	buf->flags |= BM_TAG_VALID;
	buf->usage_count = 1;

	UnlockBufHdr(buf);

	if (oldFlags & BM_TAG_VALID)
	{
		BufTableDelete(&oldTag, oldHash);
		if (oldPartitionLock != newPartitionLock)
			LWLockRelease(oldPartitionLock);
	}

	LWLockRelease(newPartitionLock);

	/*
	 * Buffer contents are currently invalid.  Try to get the io_in_progress
	 * lock.  If StartBufferIO returns false, then someone else managed to
	 * read it before we did, so there's nothing left for BufferAlloc() to do.
	 */
	if (StartBufferIO(buf, true))
		*foundPtr = FALSE;
	else
		*foundPtr = TRUE;

	return buf;
}

/*
 * InvalidateBuffer -- mark a shared buffer invalid and return it to the
 * freelist.
 *
 * The buffer header spinlock must be held at entry.  We drop it before
 * returning.  (This is sane because the caller must have locked the
 * buffer in order to be sure it should be dropped.)
 *
 * This is used only in contexts such as dropping a relation.  We assume
 * that no other backend could possibly be interested in using the page,
 * so the only reason the buffer might be pinned is if someone else is
 * trying to write it out.	We have to let them finish before we can
 * reclaim the buffer.
 *
 * The buffer could get reclaimed by someone else while we are waiting
 * to acquire the necessary locks; if so, don't mess it up.
 */
static void
InvalidateBuffer(volatile BufferDesc *buf)
{
	BufferTag	oldTag;
	uint32		oldHash;		/* hash value for oldTag */
	LWLockId	oldPartitionLock;		/* buffer partition lock for it */
	BufFlags	oldFlags;

	/* Save the original buffer tag before dropping the spinlock */
	oldTag = buf->tag;

	UnlockBufHdr(buf);

	/*
	 * Need to compute the old tag's hashcode and partition lock ID. XXX is it
	 * worth storing the hashcode in BufferDesc so we need not recompute it
	 * here?  Probably not.
	 */
	oldHash = BufTableHashCode(&oldTag);
	oldPartitionLock = BufMappingPartitionLock(oldHash);

retry:

	/*
	 * Acquire exclusive mapping lock in preparation for changing the buffer's
	 * association.
	 */
	LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);

	/* Re-lock the buffer header */
	LockBufHdr(buf);

	/* If it's changed while we were waiting for lock, do nothing */
	if (!BUFFERTAGS_EQUAL(buf->tag, oldTag))
	{
		UnlockBufHdr(buf);
		LWLockRelease(oldPartitionLock);
		return;
	}

	/*
	 * We assume the only reason for it to be pinned is that someone else is
	 * flushing the page out.  Wait for them to finish.  (This could be an
	 * infinite loop if the refcount is messed up... it would be nice to time
	 * out after awhile, but there seems no way to be sure how many loops may
	 * be needed.  Note that if the other guy has pinned the buffer but not
	 * yet done StartBufferIO, WaitIO will fall through and we'll effectively
	 * be busy-looping here.)
	 */
	if (buf->refcount != 0)
	{
		UnlockBufHdr(buf);
		LWLockRelease(oldPartitionLock);
		/* safety check: should definitely not be our *own* pin */
		if (PrivateRefCount[buf->buf_id] != 0)
			elog(ERROR, "buffer is pinned in InvalidateBuffer");
		WaitIO(buf);
		goto retry;
	}

	/*
	 * Clear out the buffer's tag and flags.  We must do this to ensure that
	 * linear scans of the buffer array don't think the buffer is valid.
	 */
	oldFlags = buf->flags;
	CLEAR_BUFFERTAG(buf->tag);
	buf->flags = 0;
	buf->usage_count = 0;

	UnlockBufHdr(buf);

	/*
	 * Remove the buffer from the lookup hashtable, if it was in there.
	 */
	if (oldFlags & BM_TAG_VALID)
		BufTableDelete(&oldTag, oldHash);

	/*
	 * Done with mapping lock.
	 */
	LWLockRelease(oldPartitionLock);

	/*
	 * Insert the buffer at the head of the list of free buffers.
	 */
	StrategyFreeBuffer(buf);
}

/*
 * MarkBufferDirty
 *
 *		Marks buffer contents as dirty (actual write happens later).
 *
 * Buffer must be pinned and exclusive-locked.	(If caller does not hold
 * exclusive lock, then somebody could be in process of writing the buffer,
 * leading to risk of bad data written to disk.)
 */
void
MarkBufferDirty(Buffer buffer)
{
	volatile BufferDesc *bufHdr;

	if (!BufferIsValid(buffer))
		elog(ERROR, "bad buffer id: %d", buffer);

	if (BufferIsLocal(buffer))
	{
		MarkLocalBufferDirty(buffer);
		return;
	}

	bufHdr = &BufferDescriptors[buffer - 1];

	Assert(PrivateRefCount[buffer - 1] > 0);
	/* unfortunately we can't check if the lock is held exclusively */
	Assert(LWLockHeldByMe(bufHdr->content_lock));

	LockBufHdr(bufHdr);

	Assert(bufHdr->refcount > 0);

	/*
	 * If the buffer was not dirty already, do vacuum cost accounting.
	 */
	if (!(bufHdr->flags & BM_DIRTY) && VacuumCostActive)
		VacuumCostBalance += VacuumCostPageDirty;

	bufHdr->flags |= (BM_DIRTY | BM_JUST_DIRTIED);

	UnlockBufHdr(bufHdr);
}

/*
 * ReleaseAndReadBuffer -- combine ReleaseBuffer() and ReadBuffer()
 *
 * Formerly, this saved one cycle of acquiring/releasing the BufMgrLock
 * compared to calling the two routines separately.  Now it's mainly just
 * a convenience function.	However, if the passed buffer is valid and
 * already contains the desired block, we just return it as-is; and that
 * does save considerable work compared to a full release and reacquire.
 *
 * Note: it is OK to pass buffer == InvalidBuffer, indicating that no old
 * buffer actually needs to be released.  This case is the same as ReadBuffer,
 * but can save some tests in the caller.
 */
Buffer
ReleaseAndReadBuffer(Buffer buffer,
					 Relation relation,
					 BlockNumber blockNum)
{
	volatile BufferDesc *bufHdr;

	if (BufferIsValid(buffer))
	{
		if (BufferIsLocal(buffer))
		{
			Assert(LocalRefCount[-buffer - 1] > 0);
			bufHdr = &LocalBufferDescriptors[-buffer - 1];
			if (bufHdr->tag.blockNum == blockNum &&
				RelFileNodeEquals(bufHdr->tag.rnode, relation->rd_node))
				return buffer;
			ResourceOwnerForgetBuffer(CurrentResourceOwner, buffer);
			LocalRefCount[-buffer - 1]--;
		}
		else
		{
			Assert(PrivateRefCount[buffer - 1] > 0);
			bufHdr = &BufferDescriptors[buffer - 1];
			/* we have pin, so it's ok to examine tag without spinlock */
			if (bufHdr->tag.blockNum == blockNum &&
				RelFileNodeEquals(bufHdr->tag.rnode, relation->rd_node))
				return buffer;
			UnpinBuffer(bufHdr, true);
		}
	}

	return ReadBuffer(relation, blockNum);
}

/*
 * PinBuffer -- make buffer unavailable for replacement.
 *
 * For the default access strategy, the buffer's usage_count is incremented
 * when we first pin it; for other strategies we just make sure the usage_count
 * isn't zero.  (The idea of the latter is that we don't want synchronized
 * heap scans to inflate the count, but we need it to not be zero to discourage
 * other backends from stealing buffers from our ring.	As long as we cycle
 * through the ring faster than the global clock-sweep cycles, buffers in
 * our ring won't be chosen as victims for replacement by other backends.)
 *
 * This should be applied only to shared buffers, never local ones.
 *
 * Note that ResourceOwnerEnlargeBuffers must have been done already.
 *
 * Returns TRUE if buffer is BM_VALID, else FALSE.	This provision allows
 * some callers to avoid an extra spinlock cycle.
 */
static bool
PinBuffer(volatile BufferDesc *buf, BufferAccessStrategy strategy)
{
	int			b = buf->buf_id;
	bool		result;

	if (PrivateRefCount[b] == 0)
	{
		LockBufHdr(buf);
		buf->refcount++;
		if (strategy == NULL)
		{
			if (buf->usage_count < BM_MAX_USAGE_COUNT)
				buf->usage_count++;
		}
		else