From: Shaohua Li <shaohua.li@intel.com>
To: "Shi, Alex" <alex.shi@intel.com>
Cc: Christoph Lameter <cl@linux.com>,
"penberg@kernel.org" <penberg@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"Huang, Ying" <ying.huang@intel.com>,
"Chen, Tim C" <tim.c.chen@intel.com>,
"linux-mm@kvack.org" <linux-mm@kvack.org>
Subject: RE: [PATCH] slub Discard slab page only when node partials > minimum setting
Date: Thu, 08 Sep 2011 09:34:34 +0800 [thread overview]
Message-ID: <1315445674.29510.74.camel@sli10-conroe> (raw)
In-Reply-To: <1315442639.31737.224.camel@debian>
On Thu, 2011-09-08 at 08:43 +0800, Shi, Alex wrote:
> On Wed, 2011-09-07 at 23:05 +0800, Christoph Lameter wrote:
> > On Wed, 7 Sep 2011, Shi, Alex wrote:
> >
> > > Oh, seems the deactivate_slab() corrected at linus' tree already, but
> > > the unfreeze_partials() just copied from the old version
> > > deactivate_slab().
> >
> > Ok then the patch is ok.
> >
> > Do you also have performance measurements? I am a bit hesitant to merge
> > the per cpu partials patchset if there are regressions in the low
> > concurrency tests as seem to be indicated by intels latest tests.
> >
>
> My LKP testing system most focus on server platforms. I tested your per
> cpu partial set on hackbench and netperf loopback benchmark. hackbench
> improve much.
>
> Maybe some IO testing is low concurrency for SLUB, maybe a few jobs
> kbuild? or low swap press testing. I may try them for your patchset in
> the near days.
>
> BTW, some testing results for your PCP SLUB:
>
> for hackbench process testing:
> on WSM-EP, inc ~60%, NHM-EP inc ~25%
> on NHM-EX, inc ~200%, core2-EP, inc ~250%.
> on Tigerton-EX, inc 1900%, :)
>
> for hackbench thread testing:
> on WSM-EP, no clear inc, NHM-EP no clear inc
> on NHM-EX, inc 10%, core2-EP, inc ~20%.
> on Tigertion-EX, inc 100%,
>
> for netperf loopback testing, no clear performance change.
did you add my patch to add page to partial list tail in the test?
Without it the per-cpu partial list can have more significant impact to
reduce lock contention, so the result isn't precise.
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-09-08 1:31 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1315188460.31737.5.camel@debian>
[not found] ` <alpine.DEB.2.00.1109061914440.18646@router.home>
2011-09-07 1:03 ` [PATCH] slub Discard slab page only when node partials > minimum setting Alex,Shi
2011-09-07 2:26 ` [PATCH] slub: code optimze in get_partial_node() Alex,Shi
2011-09-07 2:45 ` [PATCH 2/2] slub: continue to seek slab in node partial if met a null page Alex,Shi
2011-09-07 15:01 ` Christoph Lameter
2011-09-08 8:38 ` Alex,Shi
2011-09-08 18:41 ` Christoph Lameter
2011-09-07 2:56 ` [rfc ] slub: unfreeze full page if it's in node partial Alex,Shi
2011-09-07 3:06 ` Alex,Shi
2011-09-07 14:56 ` [PATCH] slub: code optimze in get_partial_node() Christoph Lameter
[not found] ` <alpine.DEB.2.00.1109062022100.20474@router.home>
[not found] ` <4E671E5C.7010405@cs.helsinki.fi>
[not found] ` <6E3BC7F7C9A4BF4286DD4C043110F30B5D00DA333C@shsmsx502.ccr.corp.intel.com>
[not found] ` <alpine.DEB.2.00.1109071003240.9406@router.home>
2011-09-08 0:43 ` [PATCH] slub Discard slab page only when node partials > minimum setting Alex,Shi
2011-09-08 1:34 ` Shaohua Li [this message]
2011-09-08 2:24 ` Alex,Shi
2011-09-15 5:40 ` Pekka Enberg
2011-09-15 6:03 ` Alex,Shi
2011-09-08 18:37 ` Christoph Lameter
2011-09-09 8:45 ` Alex,Shi
2011-09-11 11:41 ` Christoph Lameter
2011-09-13 8:29 ` Alex,Shi
2011-09-13 15:04 ` Christoph Lameter
2011-09-15 1:32 ` Alex,Shi
2011-09-15 1:51 ` Christoph Lameter
2011-09-15 2:00 ` Alex,Shi
[not found] ` <1316765880.4188.34.camel@debian>
[not found] ` <alpine.DEB.2.00.1109231500580.15559@router.home>
2011-09-29 9:53 ` Alex,Shi
2011-09-29 14:32 ` Christoph Lameter
2011-10-02 12:47 ` Shi, Alex
2011-10-03 15:21 ` Christoph Lameter
2011-10-09 6:28 ` Alex,Shi
2011-10-10 17:12 ` Christoph Lameter
2011-09-14 15:38 ` Christoph Lameter
2011-09-15 5:48 ` Pekka Enberg
2011-09-15 6:16 ` Alex,Shi
2011-09-07 3:14 ` [PATCH] slub: correct comments error for per cpu partial Alex,Shi
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=1315445674.29510.74.camel@sli10-conroe \
--to=shaohua.li@intel.com \
--cc=alex.shi@intel.com \
--cc=cl@linux.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=penberg@kernel.org \
--cc=tim.c.chen@intel.com \
--cc=ying.huang@intel.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).