From: Christoph Lameter <clameter@sgi.com>
To: akpm@linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Subject: [patch 6/6] SLUB: Optimize cacheline use for zeroing
Date: Wed, 22 Aug 2007 23:46:59 -0700 [thread overview]
Message-ID: <20070823064734.997050223@sgi.com> (raw)
In-Reply-To: 20070823064653.081843729@sgi.com
[-- Attachment #1: 0010-SLUB-Optimize-cacheline-use-for-zeroing.patch --]
[-- Type: text/plain, Size: 2592 bytes --]
We touch a cacheline in the kmem_cache structure for zeroing to get the
size. However, the hot paths in slab_alloc and slab_free do not reference
any other fields in kmem_cache, so we may have to just bring in the
cacheline for this one access.
Add a new field to kmem_cache_cpu that contains the object size. That
cacheline must already be used in the hotpaths. So we save one cacheline
on every slab_alloc if we zero.
We need to update the kmem_cache_cpu object size if an aliasing operation
changes the objsize of an non debug slab.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
---
include/linux/slub_def.h | 1 +
mm/slub.c | 14 ++++++++++++--
2 files changed, 13 insertions(+), 2 deletions(-)
Index: linux-2.6.23-rc3-mm1/include/linux/slub_def.h
===================================================================
--- linux-2.6.23-rc3-mm1.orig/include/linux/slub_def.h 2007-08-22 17:23:47.000000000 -0700
+++ linux-2.6.23-rc3-mm1/include/linux/slub_def.h 2007-08-22 17:23:50.000000000 -0700
@@ -16,6 +16,7 @@ struct kmem_cache_cpu {
struct page *page;
int node;
unsigned int offset;
+ unsigned int objsize;
};
struct kmem_cache_node {
Index: linux-2.6.23-rc3-mm1/mm/slub.c
===================================================================
--- linux-2.6.23-rc3-mm1.orig/mm/slub.c 2007-08-22 17:23:47.000000000 -0700
+++ linux-2.6.23-rc3-mm1/mm/slub.c 2007-08-22 17:23:50.000000000 -0700
@@ -1556,7 +1556,7 @@ static void __always_inline *slab_alloc(
local_irq_restore(flags);
if (unlikely((gfpflags & __GFP_ZERO) && object))
- memset(object, 0, s->objsize);
+ memset(object, 0, c->objsize);
return object;
}
@@ -1843,8 +1843,9 @@ static void init_kmem_cache_cpu(struct k
{
c->page = NULL;
c->freelist = NULL;
- c->offset = s->offset / sizeof(void *);
c->node = 0;
+ c->offset = s->offset / sizeof(void *);
+ c->objsize = s->objsize;
}
static void init_kmem_cache_node(struct kmem_cache_node *n)
@@ -2842,12 +2843,21 @@ struct kmem_cache *kmem_cache_create(con
down_write(&slub_lock);
s = find_mergeable(size, align, flags, ctor);
if (s) {
+ int cpu;
+
s->refcount++;
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
s->objsize = max(s->objsize, (int)size);
+
+ /*
+ * And then we need to update the object size in the
+ * per cpu structures
+ */
+ for_each_online_cpu(cpu)
+ get_cpu_slab(s, cpu)->objsize = s->objsize;
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
up_write(&slub_lock);
if (sysfs_slab_alias(s, name))
--
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Lameter <clameter@sgi.com>
To: akpm@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Pekka Enberg <penberg@cs.helsinki.fi>
Subject: [patch 6/6] SLUB: Optimize cacheline use for zeroing
Date: Wed, 22 Aug 2007 23:46:59 -0700 [thread overview]
Message-ID: <20070823064734.997050223@sgi.com> (raw)
In-Reply-To: 20070823064653.081843729@sgi.com
[-- Attachment #1: 0010-SLUB-Optimize-cacheline-use-for-zeroing.patch --]
[-- Type: text/plain, Size: 2592 bytes --]
We touch a cacheline in the kmem_cache structure for zeroing to get the
size. However, the hot paths in slab_alloc and slab_free do not reference
any other fields in kmem_cache, so we may have to just bring in the
cacheline for this one access.
Add a new field to kmem_cache_cpu that contains the object size. That
cacheline must already be used in the hotpaths. So we save one cacheline
on every slab_alloc if we zero.
We need to update the kmem_cache_cpu object size if an aliasing operation
changes the objsize of an non debug slab.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
---
include/linux/slub_def.h | 1 +
mm/slub.c | 14 ++++++++++++--
2 files changed, 13 insertions(+), 2 deletions(-)
Index: linux-2.6.23-rc3-mm1/include/linux/slub_def.h
===================================================================
--- linux-2.6.23-rc3-mm1.orig/include/linux/slub_def.h 2007-08-22 17:23:47.000000000 -0700
+++ linux-2.6.23-rc3-mm1/include/linux/slub_def.h 2007-08-22 17:23:50.000000000 -0700
@@ -16,6 +16,7 @@ struct kmem_cache_cpu {
struct page *page;
int node;
unsigned int offset;
+ unsigned int objsize;
};
struct kmem_cache_node {
Index: linux-2.6.23-rc3-mm1/mm/slub.c
===================================================================
--- linux-2.6.23-rc3-mm1.orig/mm/slub.c 2007-08-22 17:23:47.000000000 -0700
+++ linux-2.6.23-rc3-mm1/mm/slub.c 2007-08-22 17:23:50.000000000 -0700
@@ -1556,7 +1556,7 @@ static void __always_inline *slab_alloc(
local_irq_restore(flags);
if (unlikely((gfpflags & __GFP_ZERO) && object))
- memset(object, 0, s->objsize);
+ memset(object, 0, c->objsize);
return object;
}
@@ -1843,8 +1843,9 @@ static void init_kmem_cache_cpu(struct k
{
c->page = NULL;
c->freelist = NULL;
- c->offset = s->offset / sizeof(void *);
c->node = 0;
+ c->offset = s->offset / sizeof(void *);
+ c->objsize = s->objsize;
}
static void init_kmem_cache_node(struct kmem_cache_node *n)
@@ -2842,12 +2843,21 @@ struct kmem_cache *kmem_cache_create(con
down_write(&slub_lock);
s = find_mergeable(size, align, flags, ctor);
if (s) {
+ int cpu;
+
s->refcount++;
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
s->objsize = max(s->objsize, (int)size);
+
+ /*
+ * And then we need to update the object size in the
+ * per cpu structures
+ */
+ for_each_online_cpu(cpu)
+ get_cpu_slab(s, cpu)->objsize = s->objsize;
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
up_write(&slub_lock);
if (sysfs_slab_alias(s, name))
--
next prev parent reply other threads:[~2007-08-23 6:49 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-23 6:46 [patch 0/6] Per cpu structures for SLUB Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 6:46 ` [patch 1/6] SLUB: Avoid page struct cacheline bouncing due to remote frees to cpu slab Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 6:46 ` [patch 2/6] SLUB: Do not use page->mapping Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 6:46 ` [patch 3/6] SLUB: Move page->offset to kmem_cache_cpu->offset Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 6:46 ` [patch 4/6] SLUB: Avoid touching page struct when freeing to per cpu slab Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 15:05 ` Peter Zijlstra
2007-08-23 19:30 ` Christoph Lameter
2007-08-24 16:46 ` Christoph Lameter
2007-08-23 6:46 ` [patch 5/6] SLUB: Place kmem_cache_cpu structures in a NUMA aware way Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter
2007-08-23 6:46 ` Christoph Lameter [this message]
2007-08-23 6:46 ` [patch 6/6] SLUB: Optimize cacheline use for zeroing Christoph Lameter
2007-08-23 9:52 ` [patch 0/6] Per cpu structures for SLUB Peter Zijlstra
2007-08-23 19:25 ` Christoph Lameter
2007-08-24 21:38 ` Andrew Morton
2007-08-24 21:38 ` Andrew Morton
2007-08-27 18:50 ` Christoph Lameter
2007-08-27 18:50 ` Christoph Lameter
2007-08-27 23:51 ` Andrew Morton
2007-08-27 23:51 ` Andrew Morton
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=20070823064734.997050223@sgi.com \
--to=clameter@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.