linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Tobin C. Harding" <tobin@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Tobin C. Harding" <tobin@kernel.org>,
	Christopher Lameter <cl@linux.com>,
	Pekka Enberg <penberg@cs.helsinki.fi>,
	Matthew Wilcox <willy@infradead.org>,
	Tycho Andersen <tycho@tycho.ws>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: [RFC 07/15] slub: Add defrag_used_ratio field and sysfs support
Date: Fri,  8 Mar 2019 15:14:18 +1100	[thread overview]
Message-ID: <20190308041426.16654-8-tobin@kernel.org> (raw)
In-Reply-To: <20190308041426.16654-1-tobin@kernel.org>

In preparation for enabling defragmentation of slab pages.

"defrag_used_ratio" is used to set the threshold at which
defragmentation should be attempted on a slab page.

"defrag_used_ratio" is a percentage in the range of 0 - 100 (inclusive).
If less than that percentage of slots in a slab page are in use then the
slab page will become subject to defragmentation.

Add a defrag ratio field and set it to 30% by default. A limit of 30%
specifies that more than 3 out of 10 available slots for objects need to
be in use otherwise slab defragmentation will be attempted on the
remaining objects.

Co-developed-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tobin C. Harding <tobin@kernel.org>
---
 Documentation/ABI/testing/sysfs-kernel-slab | 14 ++++++++++++
 include/linux/slub_def.h                    |  7 ++++++
 mm/slub.c                                   | 24 +++++++++++++++++++++
 3 files changed, 45 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
index 29601d93a1c2..7770c03be6b4 100644
--- a/Documentation/ABI/testing/sysfs-kernel-slab
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -180,6 +180,20 @@ Description:
 		list.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
+What:		/sys/kernel/slab/cache/defrag_used_ratio
+Date:		February 2019
+KernelVersion:	5.0
+Contact:	Christoph Lameter <cl@linux-foundation.org>
+		Pekka Enberg <penberg@cs.helsinki.fi>,
+Description:
+		The defrag_used_ratio file allows the control of how aggressive
+		slab fragmentation reduction works at reclaiming objects from
+		sparsely populated slabs. This is a percentage. If a slab has
+		less than this percentage of objects allocated then reclaim will
+		attempt to reclaim objects so that the whole slab page can be
+		freed. 0% specifies no reclaim attempt (defrag disabled), 100%
+		specifies attempt to reclaim all pages.  The default is 30%.
+
 What:		/sys/kernel/slab/cache/deactivate_to_tail
 Date:		February 2008
 KernelVersion:	2.6.25
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index a7340a1ed5dc..6da6197ca973 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -107,6 +107,13 @@ struct kmem_cache {
 	unsigned int red_left_pad;	/* Left redzone padding size */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
+	int defrag_used_ratio;	/*
+				 * Ratio used to check against the
+				 * percentage of objects allocated in a
+				 * slab page.  If less than this ratio
+				 * is allocated then reclaim attempts
+				 * are made.
+				 */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 	struct work_struct kobj_remove_work;
diff --git a/mm/slub.c b/mm/slub.c
index f37103e22d3f..515db0f36c55 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3642,6 +3642,7 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 
 	set_cpu_partial(s);
 
+	s->defrag_used_ratio = 30;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 1000;
 #endif
@@ -5261,6 +5262,28 @@ static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(destroy_by_rcu);
 
+static ssize_t defrag_used_ratio_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%d\n", s->defrag_used_ratio);
+}
+
+static ssize_t defrag_used_ratio_store(struct kmem_cache *s,
+				       const char *buf, size_t length)
+{
+	unsigned long ratio;
+	int err;
+
+	err = kstrtoul(buf, 10, &ratio);
+	if (err)
+		return err;
+
+	if (ratio <= 100)
+		s->defrag_used_ratio = ratio;
+
+	return length;
+}
+SLAB_ATTR(defrag_used_ratio);
+
 #ifdef CONFIG_SLUB_DEBUG
 static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
@@ -5585,6 +5608,7 @@ static struct attribute *slab_attrs[] = {
 	&validate_attr.attr,
 	&alloc_calls_attr.attr,
 	&free_calls_attr.attr,
+	&defrag_used_ratio_attr.attr,
 #endif
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
-- 
2.21.0


  parent reply	other threads:[~2019-03-08  4:15 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-08  4:14 [RFC 00/15] mm: Implement Slab Movable Objects (SMO) Tobin C. Harding
2019-03-08  4:14 ` [RFC 01/15] slub: Create sysfs field /sys/slab/<cache>/ops Tobin C. Harding
2019-03-11 21:23   ` Roman Gushchin
2019-03-12  1:16     ` Tobin C. Harding
2019-03-08  4:14 ` [RFC 02/15] slub: Add isolate() and migrate() methods Tobin C. Harding
2019-03-08 15:28   ` Tycho Andersen
2019-03-08 16:15     ` Christopher Lameter
2019-03-08 16:22       ` Tycho Andersen
2019-03-08 19:53         ` Tobin C. Harding
2019-03-08 20:08           ` Tycho Andersen
2019-03-11 21:51   ` Roman Gushchin
2019-03-12  1:08     ` Tobin C. Harding
2019-03-12  4:35     ` Christopher Lameter
2019-03-12 18:47       ` Roman Gushchin
2019-03-08  4:14 ` [RFC 03/15] tools/vm/slabinfo: Add support for -C and -F options Tobin C. Harding
2019-03-11 21:54   ` Roman Gushchin
2019-03-12  1:20     ` Tobin C. Harding
2019-03-08  4:14 ` [RFC 04/15] slub: Enable Slab Movable Objects (SMO) Tobin C. Harding
2019-03-11 22:48   ` Roman Gushchin
2019-03-12  1:47     ` Tobin C. Harding
2019-03-12 18:00       ` Roman Gushchin
2019-03-12  4:39     ` Christopher Lameter
2019-03-08  4:14 ` [RFC 05/15] slub: Sort slab cache list Tobin C. Harding
2019-03-08  4:14 ` [RFC 06/15] tools/vm/slabinfo: Add remote node defrag ratio output Tobin C. Harding
2019-03-08  4:14 ` Tobin C. Harding [this message]
2019-03-08 16:01   ` [RFC 07/15] slub: Add defrag_used_ratio field and sysfs support Tycho Andersen
2019-03-11  6:04     ` Tobin C. Harding
2019-03-08  4:14 ` [RFC 08/15] tools/vm/slabinfo: Add defrag_used_ratio output Tobin C. Harding
2019-03-08  4:14 ` [RFC 09/15] slub: Enable slab defragmentation using SMO Tobin C. Harding
2019-03-11 23:35   ` Roman Gushchin
2019-03-12  1:49     ` Tobin C. Harding
2019-03-08  4:14 ` [RFC 10/15] tools/testing/slab: Add object migration test module Tobin C. Harding
2019-03-08  4:14 ` [RFC 11/15] tools/testing/slab: Add object migration test suite Tobin C. Harding
2019-03-08  4:14 ` [RFC 12/15] xarray: Implement migration function for objects Tobin C. Harding
2019-03-12  0:16   ` Roman Gushchin
2019-03-12  1:54     ` Tobin C. Harding
2019-03-08  4:14 ` [RFC 13/15] tools/testing/slab: Add XArray movable objects tests Tobin C. Harding
2019-03-08  4:14 ` [RFC 14/15] slub: Enable move _all_ objects to node Tobin C. Harding
2019-03-08  4:14 ` [RFC 15/15] slub: Enable balancing slab objects across nodes Tobin C. Harding
2019-03-12  0:09 ` [RFC 00/15] mm: Implement Slab Movable Objects (SMO) Roman Gushchin
2019-03-12  1:48   ` Tobin C. Harding

Reply instructions:

You may reply publicly 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=20190308041426.16654-8-tobin@kernel.org \
    --to=tobin@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=tycho@tycho.ws \
    --cc=willy@infradead.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).