From: Jamie Lokier <jamie@shareable.org>
To: Christoph Lameter <cl@linux-foundation.org>
Cc: Matthew Wilcox <matthew@wil.cx>,
Pekka Enberg <penberg@cs.helsinki.fi>,
akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-fsdevel@vger.kernel.org, Mel Gorman <mel@skynet.ie>,
andi@firstfloor.org, Rik van Riel <riel@redhat.com>
Subject: Re: No, really, stop trying to delete slab until you've finished making slub perform as well
Date: Mon, 4 Aug 2008 15:48:23 +0100 [thread overview]
Message-ID: <20080804144823.GE18868@shareable.org> (raw)
In-Reply-To: <48970779.80902@linux-foundation.org>
Christoph Lameter wrote:
> Matthew Wilcox wrote:
> > On Fri, May 09, 2008 at 07:21:01PM -0700, Christoph Lameter wrote:
> >> - Add a patch that obsoletes SLAB and explains why SLOB does not support
> >> defrag (Either of those could be theoretically equipped to support
> >> slab defrag in some way but it seems that Andrew/Linus want to reduce
> >> the number of slab allocators).
> >
> > Do we have to once again explain that slab still outperforms slub on at
> > least one important benchmark? I hope Nick Piggin finds time to finish
> > tuning slqb; it already outperforms slub.
> >
>
> Uhh. I forgot to delete that statement. I did not include the patch
> in the series.
>
> We have a fundamental issue design issue there. Queuing on free can result in
> better performance as in SLAB. However, it limits concurrency (per node lock
> taking) and causes latency spikes due to queue processing (f.e. one test load
> had 118.65 vs. 34 usecs just by switching to SLUB).
Vaguely on this topic, has anyone studied the effects of SLAB/SLUB
etc. on MMUless systems?
-- Jamie
next prev parent reply other threads:[~2008-08-04 14:48 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-10 2:21 [patch 00/19] Slab Fragmentation Reduction V13 Christoph Lameter
2008-05-10 2:21 ` [patch 01/19] slub: Add defrag_ratio field and sysfs support Christoph Lameter
2008-05-10 2:21 ` [patch 02/19] slub: Replace ctor field with ops field in /sys/slab/* Christoph Lameter
2008-05-10 2:21 ` [patch 03/19] slub: Add get() and kick() methods Christoph Lameter
2008-05-10 2:21 ` [patch 04/19] slub: Sort slab cache list and establish maximum objects for defrag slabs Christoph Lameter
2008-05-10 2:21 ` [patch 05/19] slub: Slab defrag core Christoph Lameter
2008-05-10 2:21 ` [patch 06/19] slub: Add KICKABLE to avoid repeated kick() attempts Christoph Lameter
2008-05-10 2:21 ` [patch 07/19] slub: Extend slabinfo to support -D and -F options Christoph Lameter
2008-05-10 2:21 ` [patch 08/19] slub/slabinfo: add defrag statistics Christoph Lameter
2008-05-10 2:21 ` [patch 09/19] slub: Trigger defragmentation from memory reclaim Christoph Lameter
2008-05-10 2:21 ` [patch 10/19] buffer heads: Support slab defrag Christoph Lameter
2008-05-10 2:21 ` [patch 11/19] inodes: Support generic defragmentation Christoph Lameter
2008-05-10 2:21 ` [patch 12/19] Filesystem: Ext2 filesystem defrag Christoph Lameter
2008-05-10 2:21 ` [patch 13/19] Filesystem: Ext3 " Christoph Lameter
2008-05-10 2:21 ` [patch 14/19] Filesystem: Ext4 " Christoph Lameter
2008-08-03 1:54 ` Theodore Tso
2008-08-13 7:26 ` Pekka Enberg
2008-05-10 2:21 ` [patch 15/19] Filesystem: XFS slab defragmentation Christoph Lameter
2008-08-03 1:42 ` Dave Chinner
2008-08-04 13:36 ` Christoph Lameter
2008-05-10 2:21 ` [patch 16/19] Filesystem: /proc filesystem support for slab defrag Christoph Lameter
2008-05-10 2:21 ` [patch 17/19] Filesystem: Slab defrag: Reiserfs support Christoph Lameter
2008-05-10 2:21 ` [patch 18/19] dentries: Add constructor Christoph Lameter
2008-05-10 2:21 ` [patch 19/19] dentries: dentry defragmentation Christoph Lameter
2008-08-03 1:58 ` No, really, stop trying to delete slab until you've finished making slub perform as well Matthew Wilcox
2008-08-03 21:25 ` Pekka Enberg
2008-08-04 2:37 ` Rene Herman
2008-08-04 21:22 ` Pekka Enberg
2008-08-04 21:41 ` Christoph Lameter
2008-08-04 23:09 ` Rene Herman
2008-08-04 13:43 ` Christoph Lameter
2008-08-04 14:48 ` Jamie Lokier [this message]
2008-08-04 15:21 ` Jamie Lokier
2008-08-04 16:35 ` Christoph Lameter
2008-08-04 15:11 ` Rik van Riel
2008-08-04 16:02 ` Christoph Lameter
2008-08-04 16:47 ` KOSAKI Motohiro
2008-08-04 17:13 ` Christoph Lameter
2008-08-04 17:20 ` Pekka Enberg
2008-08-05 12:06 ` KOSAKI Motohiro
2008-08-05 14:59 ` Christoph Lameter
2008-08-06 12:36 ` KOSAKI Motohiro
2008-08-06 14:24 ` Christoph Lameter
2008-08-13 10:46 ` KOSAKI Motohiro
2008-08-13 13:10 ` Christoph Lameter
2008-08-13 14:14 ` KOSAKI Motohiro
2008-08-13 14:16 ` Pekka Enberg
2008-08-13 14:31 ` Christoph Lameter
2008-08-13 15:05 ` KOSAKI Motohiro
2008-08-14 19:44 ` Christoph Lameter
2008-08-15 16:44 ` KOSAKI Motohiro
2008-08-15 18:24 ` Christoph Lameter
2008-08-15 19:42 ` Christoph Lameter
2008-08-18 10:08 ` KOSAKI Motohiro
2008-08-18 10:34 ` KOSAKI Motohiro
2008-08-18 14:08 ` Christoph Lameter
2008-08-19 10:34 ` KOSAKI Motohiro
2008-08-19 13:51 ` Christoph Lameter
2008-08-20 11:46 ` KOSAKI Motohiro
2008-08-14 7:15 ` Pekka Enberg
2008-08-14 14:45 ` Christoph Lameter
2008-08-14 15:06 ` Christoph Lameter
2008-08-04 17:19 ` Christoph Lameter
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=20080804144823.GE18868@shareable.org \
--to=jamie@shareable.org \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=cl@linux-foundation.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=matthew@wil.cx \
--cc=mel@skynet.ie \
--cc=penberg@cs.helsinki.fi \
--cc=riel@redhat.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;
as well as URLs for NNTP newsgroup(s).