bufmgr.c

postgresql8.3.4源码,开源数据库

		{
			if (buf->usage_count == 0)
				buf->usage_count = 1;
		}
		result = (buf->flags & BM_VALID) != 0;
		UnlockBufHdr(buf);
	}
	else
	{
		/* If we previously pinned the buffer, it must surely be valid */
		result = true;
	}
	PrivateRefCount[b]++;
	Assert(PrivateRefCount[b] > 0);
	ResourceOwnerRememberBuffer(CurrentResourceOwner,
								BufferDescriptorGetBuffer(buf));
	return result;
}

/*
 * PinBuffer_Locked -- as above, but caller already locked the buffer header.
 * The spinlock is released before return.
 *
 * Currently, no callers of this function want to modify the buffer's
 * usage_count at all, so there's no need for a strategy parameter.
 * Also we don't bother with a BM_VALID test (the caller could check that for
 * itself).
 *
 * Note: use of this routine is frequently mandatory, not just an optimization
 * to save a spin lock/unlock cycle, because we need to pin a buffer before
 * its state can change under us.
 */
static void
PinBuffer_Locked(volatile BufferDesc *buf)
{
	int			b = buf->buf_id;

	if (PrivateRefCount[b] == 0)
		buf->refcount++;
	UnlockBufHdr(buf);
	PrivateRefCount[b]++;
	Assert(PrivateRefCount[b] > 0);
	ResourceOwnerRememberBuffer(CurrentResourceOwner,
								BufferDescriptorGetBuffer(buf));
}

/*
 * UnpinBuffer -- make buffer available for replacement.
 *
 * This should be applied only to shared buffers, never local ones.
 *
 * Most but not all callers want CurrentResourceOwner to be adjusted.
 * Those that don't should pass fixOwner = FALSE.
 */
static void
UnpinBuffer(volatile BufferDesc *buf, bool fixOwner)
{
	int			b = buf->buf_id;

	if (fixOwner)
		ResourceOwnerForgetBuffer(CurrentResourceOwner,
								  BufferDescriptorGetBuffer(buf));

	Assert(PrivateRefCount[b] > 0);
	PrivateRefCount[b]--;
	if (PrivateRefCount[b] == 0)
	{
		/* I'd better not still hold any locks on the buffer */
		Assert(!LWLockHeldByMe(buf->content_lock));
		Assert(!LWLockHeldByMe(buf->io_in_progress_lock));

		LockBufHdr(buf);

		/* Decrement the shared reference count */
		Assert(buf->refcount > 0);
		buf->refcount--;

		/* Support LockBufferForCleanup() */
		if ((buf->flags & BM_PIN_COUNT_WAITER) &&
			buf->refcount == 1)
		{
			/* we just released the last pin other than the waiter's */
			int			wait_backend_pid = buf->wait_backend_pid;

			buf->flags &= ~BM_PIN_COUNT_WAITER;
			UnlockBufHdr(buf);
			ProcSendSignal(wait_backend_pid);
		}
		else
			UnlockBufHdr(buf);
	}
}

/*
 * BufferSync -- Write out all dirty buffers in the pool.
 *
 * This is called at checkpoint time to write out all dirty shared buffers.
 * The checkpoint request flags should be passed in; currently the only one
 * examined is CHECKPOINT_IMMEDIATE, which disables delays between writes.
 */
static void
BufferSync(int flags)
{
	int			buf_id;
	int			num_to_scan;
	int			num_to_write;
	int			num_written;

	/* Make sure we can handle the pin inside SyncOneBuffer */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	/*
	 * Loop over all buffers, and mark the ones that need to be written with
	 * BM_CHECKPOINT_NEEDED.  Count them as we go (num_to_write), so that we
	 * can estimate how much work needs to be done.
	 *
	 * This allows us to write only those pages that were dirty when the
	 * checkpoint began, and not those that get dirtied while it proceeds.
	 * Whenever a page with BM_CHECKPOINT_NEEDED is written out, either by us
	 * later in this function, or by normal backends or the bgwriter cleaning
	 * scan, the flag is cleared.  Any buffer dirtied after this point won't
	 * have the flag set.
	 *
	 * Note that if we fail to write some buffer, we may leave buffers with
	 * BM_CHECKPOINT_NEEDED still set.	This is OK since any such buffer would
	 * certainly need to be written for the next checkpoint attempt, too.
	 */
	num_to_write = 0;
	for (buf_id = 0; buf_id < NBuffers; buf_id++)
	{
		volatile BufferDesc *bufHdr = &BufferDescriptors[buf_id];

		/*
		 * Header spinlock is enough to examine BM_DIRTY, see comment in
		 * SyncOneBuffer.
		 */
		LockBufHdr(bufHdr);

		if (bufHdr->flags & BM_DIRTY)
		{
			bufHdr->flags |= BM_CHECKPOINT_NEEDED;
			num_to_write++;
		}

		UnlockBufHdr(bufHdr);
	}

	if (num_to_write == 0)
		return;					/* nothing to do */

	/*
	 * Loop over all buffers again, and write the ones (still) marked with
	 * BM_CHECKPOINT_NEEDED.  In this loop, we start at the clock sweep point
	 * since we might as well dump soon-to-be-recycled buffers first.
	 *
	 * Note that we don't read the buffer alloc count here --- that should be
	 * left untouched till the next BgBufferSync() call.
	 */
	buf_id = StrategySyncStart(NULL, NULL);
	num_to_scan = NBuffers;
	num_written = 0;
	while (num_to_scan-- > 0)
	{
		volatile BufferDesc *bufHdr = &BufferDescriptors[buf_id];

		/*
		 * We don't need to acquire the lock here, because we're only looking
		 * at a single bit. It's possible that someone else writes the buffer
		 * and clears the flag right after we check, but that doesn't matter
		 * since SyncOneBuffer will then do nothing.  However, there is a
		 * further race condition: it's conceivable that between the time we
		 * examine the bit here and the time SyncOneBuffer acquires lock,
		 * someone else not only wrote the buffer but replaced it with another
		 * page and dirtied it.  In that improbable case, SyncOneBuffer will
		 * write the buffer though we didn't need to.  It doesn't seem worth
		 * guarding against this, though.
		 */
		if (bufHdr->flags & BM_CHECKPOINT_NEEDED)
		{
			if (SyncOneBuffer(buf_id, false) & BUF_WRITTEN)
			{
				BgWriterStats.m_buf_written_checkpoints++;
				num_written++;

				/*
				 * We know there are at most num_to_write buffers with
				 * BM_CHECKPOINT_NEEDED set; so we can stop scanning if
				 * num_written reaches num_to_write.
				 *
				 * Note that num_written doesn't include buffers written by
				 * other backends, or by the bgwriter cleaning scan. That
				 * means that the estimate of how much progress we've made is
				 * conservative, and also that this test will often fail to
				 * trigger.  But it seems worth making anyway.
				 */
				if (num_written >= num_to_write)
					break;

				/*
				 * Perform normal bgwriter duties and sleep to throttle our
				 * I/O rate.
				 */
				CheckpointWriteDelay(flags,
									 (double) num_written / num_to_write);
			}
		}

		if (++buf_id >= NBuffers)
			buf_id = 0;
	}

	/*
	 * Update checkpoint statistics. As noted above, this doesn't include
	 * buffers written by other backends or bgwriter scan.
	 */
	CheckpointStats.ckpt_bufs_written += num_written;
}

/*
 * BgBufferSync -- Write out some dirty buffers in the pool.
 *
 * This is called periodically by the background writer process.
 */
void
BgBufferSync(void)
{
	/* info obtained from freelist.c */
	int			strategy_buf_id;
	uint32		strategy_passes;
	uint32		recent_alloc;

	/*
	 * Information saved between calls so we can determine the strategy
	 * point's advance rate and avoid scanning already-cleaned buffers.
	 */
	static bool saved_info_valid = false;
	static int	prev_strategy_buf_id;
	static uint32 prev_strategy_passes;
	static int	next_to_clean;
	static uint32 next_passes;

	/* Moving averages of allocation rate and clean-buffer density */
	static float smoothed_alloc = 0;
	static float smoothed_density = 10.0;

	/* Potentially these could be tunables, but for now, not */
	float		smoothing_samples = 16;
	float		scan_whole_pool_milliseconds = 120000.0;

	/* Used to compute how far we scan ahead */
	long		strategy_delta;
	int			bufs_to_lap;
	int			bufs_ahead;
	float		scans_per_alloc;
	int			reusable_buffers_est;
	int			upcoming_alloc_est;
	int			min_scan_buffers;

	/* Variables for the scanning loop proper */
	int			num_to_scan;
	int			num_written;
	int			reusable_buffers;

	/*
	 * Find out where the freelist clock sweep currently is, and how many
	 * buffer allocations have happened since our last call.
	 */
	strategy_buf_id = StrategySyncStart(&strategy_passes, &recent_alloc);

	/* Report buffer alloc counts to pgstat */
	BgWriterStats.m_buf_alloc += recent_alloc;

	/*
	 * If we're not running the LRU scan, just stop after doing the stats
	 * stuff.  We mark the saved state invalid so that we can recover sanely
	 * if LRU scan is turned back on later.
	 */
	if (bgwriter_lru_maxpages <= 0)
	{
		saved_info_valid = false;
		return;
	}

	/*
	 * Compute strategy_delta = how many buffers have been scanned by the
	 * clock sweep since last time.  If first time through, assume none. Then
	 * see if we are still ahead of the clock sweep, and if so, how many
	 * buffers we could scan before we'd catch up with it and "lap" it. Note:
	 * weird-looking coding of xxx_passes comparisons are to avoid bogus
	 * behavior when the passes counts wrap around.
	 */
	if (saved_info_valid)
	{
		int32		passes_delta = strategy_passes - prev_strategy_passes;

		strategy_delta = strategy_buf_id - prev_strategy_buf_id;
		strategy_delta += (long) passes_delta *NBuffers;

		Assert(strategy_delta >= 0);

		if ((int32) (next_passes - strategy_passes) > 0)
		{
			/* we're one pass ahead of the strategy point */
			bufs_to_lap = strategy_buf_id - next_to_clean;
#ifdef BGW_DEBUG
			elog(DEBUG2, "bgwriter ahead: bgw %u-%u strategy %u-%u delta=%ld lap=%d",
				 next_passes, next_to_clean,
				 strategy_passes, strategy_buf_id,
				 strategy_delta, bufs_to_lap);
#endif
		}
		else if (next_passes == strategy_passes &&
				 next_to_clean >= strategy_buf_id)
		{
			/* on same pass, but ahead or at least not behind */
			bufs_to_lap = NBuffers - (next_to_clean - strategy_buf_id);
#ifdef BGW_DEBUG
			elog(DEBUG2, "bgwriter ahead: bgw %u-%u strategy %u-%u delta=%ld lap=%d",
				 next_passes, next_to_clean,
				 strategy_passes, strategy_buf_id,
				 strategy_delta, bufs_to_lap);
#endif
		}
		else
		{
			/*
			 * We're behind, so skip forward to the strategy point and start
			 * cleaning from there.
			 */
#ifdef BGW_DEBUG
			elog(DEBUG2, "bgwriter behind: bgw %u-%u strategy %u-%u delta=%ld",
				 next_passes, next_to_clean,
				 strategy_passes, strategy_buf_id,
				 strategy_delta);
#endif
			next_to_clean = strategy_buf_id;
			next_passes = strategy_passes;
			bufs_to_lap = NBuffers;
		}
	}
	else
	{
		/*
		 * Initializing at startup or after LRU scanning had been off. Always
		 * start at the strategy point.
		 */
#ifdef BGW_DEBUG
		elog(DEBUG2, "bgwriter initializing: strategy %u-%u",
			 strategy_passes, strategy_buf_id);
#endif
		strategy_delta = 0;
		next_to_clean = strategy_buf_id;
		next_passes = strategy_passes;
		bufs_to_lap = NBuffers;
	}

	/* Update saved info for next time */
	prev_strategy_buf_id = strategy_buf_id;
	prev_strategy_passes = strategy_passes;
	saved_info_valid = true;

	/*
	 * Compute how many buffers had to be scanned for each new allocation, ie,
	 * 1/density of reusable buffers, and track a moving average of that.
	 *
	 * If the strategy point didn't move, we don't update the density estimate
	 */
	if (strategy_delta > 0 && recent_alloc > 0)
	{
		scans_per_alloc = (float) strategy_delta / (float) recent_alloc;
		smoothed_density += (scans_per_alloc - smoothed_density) /
			smoothing_samples;
	}

	/*
	 * Estimate how many reusable buffers there are between the current
	 * strategy point and where we've scanned ahead to, based on the smoothed
	 * density estimate.
	 */
	bufs_ahead = NBuffers - bufs_to_lap;
	reusable_buffers_est = (float) bufs_ahead / smoothed_density;

	/*
	 * Track a moving average of recent buffer allocations.  Here, rather than
	 * a true average we want a fast-attack, slow-decline behavior: we
	 * immediately follow any increase.
	 */
	if (smoothed_alloc <= (float) recent_alloc)
		smoothed_alloc = recent_alloc;
	else
		smoothed_alloc += ((float) recent_alloc - smoothed_alloc) /
			smoothing_samples;

	/* Scale the estimate by a GUC to allow more aggressive tuning. */
	upcoming_alloc_est = smoothed_alloc * bgwriter_lru_multiplier;

	/*
	 * Even in cases where there's been little or no buffer allocation
	 * activity, we want to make a small amount of progress through the buffer
	 * cache so that as many reusable buffers as possible are clean after an
	 * idle period.
	 *
	 * (scan_whole_pool_milliseconds / BgWriterDelay) computes how many times
	 * the BGW will be called during the scan_whole_pool time; slice the
	 * buffer pool into that many sections.
	 */
	min_scan_buffers = (int) (NBuffers / (scan_whole_pool_milliseconds / BgWriterDelay));

	if (upcoming_alloc_est < (min_scan_buffers + reusable_buffers_est))
	{
#ifdef BGW_DEBUG
		elog(DEBUG2, "bgwriter: alloc_est=%d too small, using min=%d + reusable_est=%d",
			 upcoming_alloc_est, min_scan_buffers, reusable_buffers_est);
#endif
		upcoming_alloc_est = min_scan_buffers + reusable_buffers_est;
	}

	/*
	 * Now write out dirty reusable buffers, working forward from the
	 * next_to_clean point, until we have lapped the strategy scan, or cleaned
	 * enough buffers to match our estimate of the next cycle's allocation
	 * requirements, or hit the bgwriter_lru_maxpages limit.
	 */

	/* Make sure we can handle the pin inside SyncOneBuffer */
	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

	num_to_scan = bufs_to_lap;
	num_written = 0;
	reusable_buffers = reusable_buffers_est;

	/* Execute the LRU scan */
	while (num_to_scan > 0 && reusable_buffers < upcoming_alloc_est)
	{
		int			buffer_state = SyncOneBuffer(next_to_clean, true);

		if (++next_to_clean >= NBuffers)
		{
			next_to_clean = 0;
			next_passes++;
		}
		num_to_scan--;

		if (buffer_state & BUF_WRITTEN)
		{
			reusable_buffers++;
			if (++num_written >= bgwriter_lru_maxpages)