linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Lameter <cl@linux.com>
To: JoonSoo Kim <js1304@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Pekka Enberg <penberg@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Rientjes <rientjes@google.com>,
	Linux Memory Management List <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 05/16] slab: remove cachep in struct slab_rcu
Date: Fri, 23 Aug 2013 15:41:31 +0000	[thread overview]
Message-ID: <00000140abd66e64-21601d31-3ba2-42bd-8153-9f1d41fcc0d9-000000@email.amazonses.com> (raw)
In-Reply-To: <CAAmzW4NZHXXX08tdQitwapfi8raQ-BTRry92A0jdFQkm0vaqxw@mail.gmail.com>

On Fri, 23 Aug 2013, JoonSoo Kim wrote:

> I don't get it. This patch only affect to the rcu case, because it
> change the code
> which is in kmem_rcu_free(). It doesn't touch anything in standard case.

In general this patchset moves struct slab to overlay struct page. The
design of SLAB was (at least at some point in the past) to avoid struct
page references. The freelist was kept close to struct slab so that the
contents are in the same cache line. Moving fields to struct page will add
another cacheline to be referenced.

The freelist (bufctl_t) was dimensioned in such a way as to be small
and close cache wise to struct slab. Somewhow bufctl_t grew to
unsigned int and therefore the table became a bit large. Fundamentally
these are indexes into the objects in page. They really could be sized
again to just be single bytes as also explained in the comments in slab.c:

/*
 * kmem_bufctl_t:
 *
 * Bufctl's are used for linking objs within a slab
 * linked offsets.
 *
 * This implementation relies on "struct page" for locating the cache &
 * slab an object belongs to.
 * This allows the bufctl structure to be small (one int), but limits
 * the number of objects a slab (not a cache) can contain when off-slab
 * bufctls are used. The limit is the size of the largest general cache
 * that does not use off-slab slabs.
 * For 32bit archs with 4 kB pages, is this 56.
 * This is not serious, as it is only for large objects, when it is unwise
 * to have too many per slab.
 * Note: This limit can be raised by introducing a general cache whose size
 * is less than 512 (PAGE_SIZE<<3), but greater than 256.
 */

For 56 objects the bufctl_t could really be reduced to an 8 bit integer
which would shrink the size of the table significantly and improve speed
by reducing cache footprint.


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2013-08-23 15:41 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-22  8:44 [PATCH 00/16] slab: overload struct slab over struct page to reduce memory usage Joonsoo Kim
2013-08-22  8:44 ` [PATCH 01/16] slab: correct pfmemalloc check Joonsoo Kim
2013-09-11 14:30   ` Christoph Lameter
2013-09-12  6:51     ` Joonsoo Kim
2013-08-22  8:44 ` [PATCH 02/16] slab: change return type of kmem_getpages() to struct page Joonsoo Kim
2013-08-22 17:49   ` Christoph Lameter
2013-08-23  6:40     ` Joonsoo Kim
2013-09-11 14:31   ` Christoph Lameter
2013-08-22  8:44 ` [PATCH 03/16] slab: remove colouroff in struct slab Joonsoo Kim
2013-09-11 14:32   ` Christoph Lameter
2013-08-22  8:44 ` [PATCH 04/16] slab: remove nodeid " Joonsoo Kim
2013-08-22 17:51   ` Christoph Lameter
2013-08-23  6:49     ` Joonsoo Kim
2013-08-22  8:44 ` [PATCH 05/16] slab: remove cachep in struct slab_rcu Joonsoo Kim
2013-08-22 17:53   ` Christoph Lameter
2013-08-23  6:53     ` Joonsoo Kim
2013-08-23 13:42       ` Christoph Lameter
2013-08-23 14:24         ` JoonSoo Kim
2013-08-23 15:41           ` Christoph Lameter [this message]
2013-08-23 16:12             ` JoonSoo Kim
2013-09-02  8:38               ` [PATCH 0/4] slab: implement byte sized indexes for the freelist of a slab Joonsoo Kim
2013-09-02  8:38                 ` [PATCH 1/4] slab: factor out calculate nr objects in cache_estimate Joonsoo Kim
2013-09-02  8:38                 ` [PATCH 2/4] slab: introduce helper functions to get/set free object Joonsoo Kim
2013-09-02  8:38                 ` [PATCH 3/4] slab: introduce byte sized index for the freelist of a slab Joonsoo Kim
2013-09-02  8:38                 ` [PATCH 4/4] slab: make more slab management structure off the slab Joonsoo Kim
2013-09-03 14:15                 ` [PATCH 0/4] slab: implement byte sized indexes for the freelist of a slab Christoph Lameter
2013-09-04  8:33                   ` Joonsoo Kim
2013-09-05  6:55                     ` Joonsoo Kim
2013-09-05 14:33                       ` Christoph Lameter
2013-09-06  5:58                         ` Joonsoo Kim
2013-09-04  2:17                 ` Wanpeng Li
2013-09-04  2:17                 ` Wanpeng Li
     [not found]                 ` <5226985f.4475320a.1c61.2623SMTPIN_ADDED_BROKEN@mx.google.com>
2013-09-04  8:28                   ` Joonsoo Kim
2013-09-11 14:33   ` [PATCH 05/16] slab: remove cachep in struct slab_rcu Christoph Lameter
2013-08-22  8:44 ` [PATCH 06/16] slab: put forward freeing slab management object Joonsoo Kim
2013-09-11 14:35   ` Christoph Lameter
2013-08-22  8:44 ` [PATCH 07/16] slab: overloading the RCU head over the LRU for RCU free Joonsoo Kim
2013-08-27 22:06   ` Jonathan Corbet
2013-08-28  6:36     ` Joonsoo Kim
2013-09-11 14:39   ` Christoph Lameter
2013-09-12  6:55     ` Joonsoo Kim
2013-09-12 14:21       ` Christoph Lameter
2013-08-22  8:44 ` [PATCH 08/16] slab: use well-defined macro, virt_to_slab() Joonsoo Kim
2013-09-11 14:40   ` Christoph Lameter
2013-08-22  8:44 ` [PATCH 09/16] slab: use __GFP_COMP flag for allocating slab pages Joonsoo Kim
2013-08-22 18:00   ` Christoph Lameter
2013-08-23  6:55     ` Joonsoo Kim
2013-08-22  8:44 ` [PATCH 10/16] slab: change the management method of free objects of the slab Joonsoo Kim
2013-08-22  8:44 ` [PATCH 11/16] slab: remove kmem_bufctl_t Joonsoo Kim
2013-08-22  8:44 ` [PATCH 12/16] slab: remove SLAB_LIMIT Joonsoo Kim
2013-08-22  8:44 ` [PATCH 13/16] slab: replace free and inuse in struct slab with newly introduced active Joonsoo Kim
2013-08-22  8:44 ` [PATCH 14/16] slab: use struct page for slab management Joonsoo Kim
2013-08-22  8:44 ` [PATCH 15/16] slab: remove useless statement for checking pfmemalloc Joonsoo Kim
2013-08-22  8:44 ` [PATCH 16/16] slab: rename slab_bufctl to slab_freelist Joonsoo Kim
2013-08-22 16:47 ` [PATCH 00/16] slab: overload struct slab over struct page to reduce memory usage Christoph Lameter
2013-08-23  6:35   ` Joonsoo Kim
2013-09-04  3:38     ` Wanpeng Li
2013-09-04  3:38     ` Wanpeng Li
     [not found]     ` <5226ab2c.02092b0a.5eed.ffffd7e4SMTPIN_ADDED_BROKEN@mx.google.com>
2013-09-04  8:25       ` Joonsoo Kim

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=00000140abd66e64-21601d31-3ba2-42bd-8153-9f1d41fcc0d9-000000@email.amazonses.com \
    --to=cl@linux.com \
    --cc=akpm@linux-foundation.org \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=js1304@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    /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