Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Brian Foster <bfoster@redhat.com>
To: Dave Chinner <david@fromorbit.com>
Cc: linux-xfs@vger.kernel.org, linux-mm@kvack.org,
	linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 02/26] xfs: Throttle commits on delayed background CIL push
Date: Fri, 11 Oct 2019 08:38:37 -0400
Message-ID: <20191011123837.GA61257@bfoster> (raw)
In-Reply-To: <20191009032124.10541-3-david@fromorbit.com>

On Wed, Oct 09, 2019 at 02:21:00PM +1100, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> In certain situations the background CIL push can be indefinitely
> delayed. While we have workarounds from the obvious cases now, it
> doesn't solve the underlying issue. This issue is that there is no
> upper limit on the CIL where we will either force or wait for
> a background push to start, hence allowing the CIL to grow without
> bound until it consumes all log space.
> 
> To fix this, add a new wait queue to the CIL which allows background
> pushes to wait for the CIL context to be switched out. This happens
> when the push starts, so it will allow us to block incoming
> transaction commit completion until the push has started. This will
> only affect processes that are running modifications, and only when
> the CIL threshold has been significantly overrun.
> 
> This has no apparent impact on performance, and doesn't even trigger
> until over 45 million inodes had been created in a 16-way fsmark
> test on a 2GB log. That was limiting at 64MB of log space used, so
> the active CIL size is only about 3% of the total log in that case.
> The concurrent removal of those files did not trigger the background
> sleep at all.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> ---

This looks the same as the previous version.

Brian

>  fs/xfs/xfs_log_cil.c  | 37 +++++++++++++++++++++++++++++++++----
>  fs/xfs/xfs_log_priv.h | 24 ++++++++++++++++++++++++
>  fs/xfs/xfs_trace.h    |  1 +
>  3 files changed, 58 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
> index ef652abd112c..4a09d50e1368 100644
> --- a/fs/xfs/xfs_log_cil.c
> +++ b/fs/xfs/xfs_log_cil.c
> @@ -670,6 +670,11 @@ xlog_cil_push(
>  	push_seq = cil->xc_push_seq;
>  	ASSERT(push_seq <= ctx->sequence);
>  
> +	/*
> +	 * Wake up any background push waiters now this context is being pushed.
> +	 */
> +	wake_up_all(&ctx->push_wait);
> +
>  	/*
>  	 * Check if we've anything to push. If there is nothing, then we don't
>  	 * move on to a new sequence number and so we have to be able to push
> @@ -746,6 +751,7 @@ xlog_cil_push(
>  	 */
>  	INIT_LIST_HEAD(&new_ctx->committing);
>  	INIT_LIST_HEAD(&new_ctx->busy_extents);
> +	init_waitqueue_head(&new_ctx->push_wait);
>  	new_ctx->sequence = ctx->sequence + 1;
>  	new_ctx->cil = cil;
>  	cil->xc_ctx = new_ctx;
> @@ -900,7 +906,7 @@ xlog_cil_push_work(
>   */
>  static void
>  xlog_cil_push_background(
> -	struct xlog	*log)
> +	struct xlog	*log) __releases(cil->xc_ctx_lock)
>  {
>  	struct xfs_cil	*cil = log->l_cilp;
>  
> @@ -914,14 +920,36 @@ xlog_cil_push_background(
>  	 * don't do a background push if we haven't used up all the
>  	 * space available yet.
>  	 */
> -	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log))
> +	if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) {
> +		up_read(&cil->xc_ctx_lock);
>  		return;
> +	}
>  
>  	spin_lock(&cil->xc_push_lock);
>  	if (cil->xc_push_seq < cil->xc_current_sequence) {
>  		cil->xc_push_seq = cil->xc_current_sequence;
>  		queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work);
>  	}
> +
> +	/*
> +	 * Drop the context lock now, we can't hold that if we need to sleep
> +	 * because we are over the blocking threshold. The push_lock is still
> +	 * held, so blocking threshold sleep/wakeup is still correctly
> +	 * serialised here.
> +	 */
> +	up_read(&cil->xc_ctx_lock);
> +
> +	/*
> +	 * If we are well over the space limit, throttle the work that is being
> +	 * done until the push work on this context has begun.
> +	 */
> +	if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
> +		trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
> +		ASSERT(cil->xc_ctx->space_used < log->l_logsize);
> +		xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock);
> +		return;
> +	}
> +
>  	spin_unlock(&cil->xc_push_lock);
>  
>  }
> @@ -1038,9 +1066,9 @@ xfs_log_commit_cil(
>  		if (lip->li_ops->iop_committing)
>  			lip->li_ops->iop_committing(lip, xc_commit_lsn);
>  	}
> -	xlog_cil_push_background(log);
>  
> -	up_read(&cil->xc_ctx_lock);
> +	/* xlog_cil_push_background() releases cil->xc_ctx_lock */
> +	xlog_cil_push_background(log);
>  }
>  
>  /*
> @@ -1199,6 +1227,7 @@ xlog_cil_init(
>  
>  	INIT_LIST_HEAD(&ctx->committing);
>  	INIT_LIST_HEAD(&ctx->busy_extents);
> +	init_waitqueue_head(&ctx->push_wait);
>  	ctx->sequence = 1;
>  	ctx->cil = cil;
>  	cil->xc_ctx = ctx;
> diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
> index a3cc8a9a16d9..f231b7dfaeab 100644
> --- a/fs/xfs/xfs_log_priv.h
> +++ b/fs/xfs/xfs_log_priv.h
> @@ -247,6 +247,7 @@ struct xfs_cil_ctx {
>  	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
>  	struct list_head	iclog_entry;
>  	struct list_head	committing;	/* ctx committing list */
> +	wait_queue_head_t	push_wait;	/* background push throttle */
>  	struct work_struct	discard_endio_work;
>  };
>  
> @@ -344,10 +345,33 @@ struct xfs_cil {
>   *   buffer window (32MB) as measurements have shown this to be roughly the
>   *   point of diminishing performance increases under highly concurrent
>   *   modification workloads.
> + *
> + * To prevent the CIL from overflowing upper commit size bounds, we introduce a
> + * new threshold at which we block committing transactions until the background
> + * CIL commit commences and switches to a new context. While this is not a hard
> + * limit, it forces the process committing a transaction to the CIL to block and
> + * yeild the CPU, giving the CIL push work a chance to be scheduled and start
> + * work. This prevents a process running lots of transactions from overfilling
> + * the CIL because it is not yielding the CPU. We set the blocking limit at
> + * twice the background push space threshold so we keep in line with the AIL
> + * push thresholds.
> + *
> + * Note: this is not a -hard- limit as blocking is applied after the transaction
> + * is inserted into the CIL and the push has been triggered. It is largely a
> + * throttling mechanism that allows the CIL push to be scheduled and run. A hard
> + * limit will be difficult to implement without introducing global serialisation
> + * in the CIL commit fast path, and it's not at all clear that we actually need
> + * such hard limits given the ~7 years we've run without a hard limit before
> + * finding the first situation where a checkpoint size overflow actually
> + * occurred. Hence the simple throttle, and an ASSERT check to tell us that
> + * we've overrun the max size.
>   */
>  #define XLOG_CIL_SPACE_LIMIT(log)	\
>  	min_t(int, (log)->l_logsize >> 3, BBTOB(XLOG_TOTAL_REC_SHIFT(log)) << 4)
>  
> +#define XLOG_CIL_BLOCKING_SPACE_LIMIT(log)	\
> +	(XLOG_CIL_SPACE_LIMIT(log) * 2)
> +
>  /*
>   * ticket grant locks, queues and accounting have their own cachlines
>   * as these are quite hot and can be operated on concurrently.
> diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
> index eaae275ed430..e7087ede2662 100644
> --- a/fs/xfs/xfs_trace.h
> +++ b/fs/xfs/xfs_trace.h
> @@ -1011,6 +1011,7 @@ DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_sub);
>  DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_enter);
>  DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_exit);
>  DEFINE_LOGGRANT_EVENT(xfs_log_ungrant_sub);
> +DEFINE_LOGGRANT_EVENT(xfs_log_cil_wait);
>  
>  DECLARE_EVENT_CLASS(xfs_log_item_class,
>  	TP_PROTO(struct xfs_log_item *lip),
> -- 
> 2.23.0.rc1
> 

  reply index

Thread overview: 87+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-09  3:20 [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Dave Chinner
2019-10-09  3:20 ` [PATCH 01/26] xfs: Lower CIL flush limit for large logs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:08   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 02/26] xfs: Throttle commits on delayed background CIL push Dave Chinner
2019-10-11 12:38   ` Brian Foster [this message]
2019-10-09  3:21 ` [PATCH 03/26] xfs: don't allow log IO to be throttled Dave Chinner
2019-10-11  9:35   ` Christoph Hellwig
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:14   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 04/26] xfs: Improve metadata buffer reclaim accountability Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-11 12:57     ` Christoph Hellwig
2019-10-11 23:14       ` Dave Chinner
2019-10-11 23:13     ` Dave Chinner
2019-10-12 12:05       ` Brian Foster
2019-10-13  3:14         ` Dave Chinner
2019-10-14 13:05           ` Brian Foster
2019-10-30 17:25   ` Darrick J. Wong
2019-10-30 21:43     ` Dave Chinner
2019-10-31  3:06       ` Darrick J. Wong
2019-10-31 20:50         ` Dave Chinner
2019-10-31 21:05           ` Darrick J. Wong
2019-10-31 21:22             ` Christoph Hellwig
2019-11-03 21:26             ` Dave Chinner
2019-11-04 23:08               ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 05/26] xfs: correctly acount for reclaimable slabs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:16   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 06/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11  9:42   ` Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-11 23:15     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 07/26] xfs: tail updates only need to occur when LSN changes Dave Chinner
2019-10-11  9:50   ` Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-09  3:21 ` [PATCH 08/26] mm: directed shrinker work deferral Dave Chinner
2019-10-14  8:46   ` Christoph Hellwig
2019-10-14 13:06     ` Brian Foster
2019-10-18  7:59     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 09/26] shrinkers: use defer_work for GFP_NOFS sensitive shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 10/26] mm: factor shrinker work calculations Dave Chinner
2019-10-09  3:21 ` [PATCH 11/26] shrinker: defer work only to kswapd Dave Chinner
2019-10-09  3:21 ` [PATCH 12/26] shrinker: clean up variable types and tracepoints Dave Chinner
2019-10-09  3:21 ` [PATCH 13/26] mm: reclaim_state records pages reclaimed, not slabs Dave Chinner
2019-10-09  3:21 ` [PATCH 14/26] mm: back off direct reclaim on excessive shrinker deferral Dave Chinner
2019-10-11 16:21   ` Matthew Wilcox
2019-10-11 23:20     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 15/26] mm: kswapd backoff for shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 16/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11 10:18   ` Christoph Hellwig
2019-10-11 15:29     ` Brian Foster
2019-10-11 23:27       ` Dave Chinner
2019-10-12 12:08         ` Brian Foster
2019-10-09  3:21 ` [PATCH 17/26] xfs: don't block kswapd in inode reclaim Dave Chinner
2019-10-11 15:29   ` Brian Foster
2019-10-09  3:21 ` [PATCH 18/26] xfs: reduce kswapd blocking on inode locking Dave Chinner
2019-10-11 10:29   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 19/26] xfs: kill background reclaim work Dave Chinner
2019-10-11 10:31   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 20/26] xfs: use AIL pushing for inode reclaim IO Dave Chinner
2019-10-11 17:38   ` Brian Foster
2019-10-09  3:21 ` [PATCH 21/26] xfs: remove mode from xfs_reclaim_inodes() Dave Chinner
2019-10-11 10:39   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 22/26] xfs: track reclaimable inodes using a LRU list Dave Chinner
2019-10-11 10:42   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 23/26] xfs: reclaim inodes from the LRU Dave Chinner
2019-10-11 10:56   ` Christoph Hellwig
2019-10-30 23:25     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 24/26] xfs: remove unusued old inode reclaim code Dave Chinner
2019-10-09  3:21 ` [PATCH 25/26] xfs: rework unreferenced inode lookups Dave Chinner
2019-10-11 12:55   ` Christoph Hellwig
2019-10-11 13:39     ` Peter Zijlstra
2019-10-11 23:38     ` Dave Chinner
2019-10-14 13:07   ` Brian Foster
2019-10-17  1:24     ` Dave Chinner
2019-10-17  7:57       ` Brian Foster
2019-10-18 20:29         ` Dave Chinner
2019-10-09  3:21 ` [PATCH 26/26] xfs: use xfs_ail_push_all_sync in xfs_reclaim_inodes Dave Chinner
2019-10-11  9:55   ` Christoph Hellwig
2019-10-09  7:06 ` [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Christoph Hellwig
2019-10-11 19:03 ` Josef Bacik
2019-10-11 23:48   ` Dave Chinner
2019-10-12  0:19     ` Josef Bacik
2019-10-12  0:48       ` Dave Chinner

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191011123837.GA61257@bfoster \
    --to=bfoster@redhat.com \
    --cc=david@fromorbit.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git