Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Cc: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 10/26] mm: factor shrinker work calculations
Date: Wed,  9 Oct 2019 14:21:08 +1100
Message-ID: <20191009032124.10541-11-david@fromorbit.com> (raw)
In-Reply-To: <20191009032124.10541-1-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

Start to clean up the shrinker code by factoring out the calculation
that determines how much work to do. This separates the calculation
from clamping and other adjustments that are done before the
shrinker work is run. Document the scan batch size calculation
better while we are there.

Also convert the calculation for the amount of work to be done to
use 64 bit logic so we don't have to keep jumping through hoops to
keep calculations within 32 bits on 32 bit systems.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 mm/vmscan.c | 97 ++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 70 insertions(+), 27 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1445bc7578c0..de6b09ad97ed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -458,13 +458,68 @@ EXPORT_SYMBOL(unregister_shrinker);
 
 #define SHRINK_BATCH 128
 
+/*
+ * Calculate the number of new objects to scan this time around. Return
+ * the work to be done. If there are freeable objects, return that number in
+ * @freeable_objects.
+ */
+static int64_t shrink_scan_count(struct shrink_control *shrinkctl,
+			    struct shrinker *shrinker, int priority,
+			    int64_t *freeable_objects)
+{
+	int64_t delta;
+	int64_t freeable;
+
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0 || freeable == SHRINK_EMPTY)
+		return freeable;
+
+	if (shrinker->seeks) {
+		/*
+		 * shrinker->seeks is a measure of how much IO is required to
+		 * reinstantiate the object in memory. The default value is 2
+		 * which is typical for a cold inode requiring a directory read
+		 * and an inode read to re-instantiate.
+		 *
+		 * The scan batch size is defined by the shrinker priority, but
+		 * to be able to bias the reclaim we increase the default batch
+		 * size by 4. Hence we end up with a scan batch multipler that
+		 * scales like so:
+		 *
+		 * ->seeks	scan batch multiplier
+		 *    1		      4.00x
+		 *    2               2.00x
+		 *    3               1.33x
+		 *    4               1.00x
+		 *    8               0.50x
+		 *
+		 * IOWs, the more seeks it takes to pull the item into cache,
+		 * the smaller the reclaim scan batch. Hence we put more reclaim
+		 * pressure on caches that are fast to repopulate and to keep a
+		 * rough balance between caches that have different costs.
+		 */
+		delta = freeable >> (priority - 2);
+		do_div(delta, shrinker->seeks);
+	} else {
+		/*
+		 * These objects don't require any IO to create. Trim them
+		 * aggressively under memory pressure to keep them from causing
+		 * refetches in the IO caches.
+		 */
+		delta = freeable / 2;
+	}
+
+	*freeable_objects = freeable;
+	return delta > 0 ? delta : 0;
+}
+
 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 				    struct shrinker *shrinker, int priority)
 {
 	unsigned long freed = 0;
-	unsigned long long delta;
 	long total_scan;
-	long freeable;
+	int64_t freeable_objects = 0;
+	int64_t scan_count;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
@@ -475,9 +530,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
 		nid = 0;
 
-	freeable = shrinker->count_objects(shrinker, shrinkctl);
-	if (freeable == 0 || freeable == SHRINK_EMPTY)
-		return freeable;
+	scan_count = shrink_scan_count(shrinkctl, shrinker, priority,
+					&freeable_objects);
+	if (scan_count == 0 || scan_count == SHRINK_EMPTY)
+		return scan_count;
 
 	/*
 	 * copy the current shrinker scan count into a local variable
@@ -486,25 +542,11 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 */
 	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
 
-	total_scan = nr;
-	if (shrinker->seeks) {
-		delta = freeable >> priority;
-		delta *= 4;
-		do_div(delta, shrinker->seeks);
-	} else {
-		/*
-		 * These objects don't require any IO to create. Trim
-		 * them aggressively under memory pressure to keep
-		 * them from causing refetches in the IO caches.
-		 */
-		delta = freeable / 2;
-	}
-
-	total_scan += delta;
+	total_scan = nr + scan_count;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = freeable;
+		total_scan = scan_count;
 		next_deferred = nr;
 	} else
 		next_deferred = total_scan;
@@ -521,19 +563,20 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < freeable / 4)
-		total_scan = min(total_scan, freeable / 2);
+	if (scan_count < freeable_objects / 4)
+		total_scan = min_t(long, total_scan, freeable_objects / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > freeable * 2)
-		total_scan = freeable * 2;
+	if (total_scan > freeable_objects * 2)
+		total_scan = freeable_objects * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
-				   freeable, delta, total_scan, priority);
+				   freeable_objects, scan_count,
+				   total_scan, priority);
 
 	/*
 	 * If the shrinker can't run (e.g. due to gfp_mask constraints), then
@@ -558,7 +601,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 * possible.
 	 */
 	while (total_scan >= batch_size ||
-	       total_scan >= freeable) {
+	       total_scan >= freeable_objects) {
 		unsigned long ret;
 		unsigned long nr_to_scan = min(batch_size, total_scan);
 
-- 
2.23.0.rc1



  parent 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
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 ` Dave Chinner [this message]
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=20191009032124.10541-11-david@fromorbit.com \
    --to=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-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/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-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


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