From: Shaohua Li <shaohua.li@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Christoph Lameter <cl@linux.com>,
David Rientjes <rientjes@google.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
LKML <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>
Subject: Re: [PATCH 1/2] mm: page allocator: Adjust the per-cpu counter threshold when memory is low
Date: Tue, 02 Nov 2010 08:53:20 +0800 [thread overview]
Message-ID: <1288659200.8722.963.camel@sli10-conroe.sh.intel.com> (raw)
In-Reply-To: <20101029124002.356bd592.akpm@linux-foundation.org>
On Sat, 2010-10-30 at 03:40 +0800, Andrew Morton wrote:
> On Fri, 29 Oct 2010 11:12:11 +0100
> Mel Gorman <mel@csn.ul.ie> wrote:
>
> > On Thu, Oct 28, 2010 at 03:04:33PM -0700, Andrew Morton wrote:
> > > On Thu, 28 Oct 2010 16:13:35 +0100
> >
> > >
> > > I have a feeling this problem will bite us again perhaps due to those
> > > other callsites, but we haven't found the workload yet.
> > >
> > > I don't undestand why restore/reduce_pgdat_percpu_threshold() were
> > > called around that particular sleep in kswapd and nowhere else.
> > >
> > > > vanilla 11.6615%
> > > > disable-threshold 0.2584%
> > >
> > > Wow. That's 12% of all CPUs? How many CPUs and what workload?
> > >
> >
> > 112 threads CPUs 14 sockets. Workload initialisation creates NR_CPU sparse
> > files that are 10*TOTAL_MEMORY/NR_CPU in size. Workload itself is NR_CPU
> > processes just reading their own file.
> >
> > The critical thing is the number of sockets. For single-socket-8-thread
> > for example, vanilla was just 0.66% of time (although the patches did
> > bring it down to 0.11%).
>
> I'm surprised. I thought the inefficiency here was caused by CPUs
> tromping through percpu data, adding things up. But the above info
> would indicate that the problem was caused by lots of cross-socket
> traffic? If so, where did that come from?
>From my understanding, the problem is zone_nr_free_pages() will try to
read each cpu's ->vm_stat_diff, while other CPUs are changing their
vm_stat_diff. This will cause a lot of cache bounce.
--
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 policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2010-11-02 0:53 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-28 15:13 [PATCH 0/2] Reduce the amount of time spent in watermark-related functions V4 Mel Gorman
2010-10-28 15:13 ` [PATCH 1/2] mm: page allocator: Adjust the per-cpu counter threshold when memory is low Mel Gorman
2010-10-28 22:04 ` Andrew Morton
2010-10-29 10:12 ` Mel Gorman
2010-10-29 19:40 ` Andrew Morton
2010-11-02 0:53 ` Shaohua Li [this message]
2010-11-09 11:33 ` Mel Gorman
2010-11-09 16:48 ` Christoph Lameter
2010-10-29 14:58 ` Christoph Lameter
2010-10-29 18:25 ` Andrew Morton
2010-10-29 19:33 ` Christoph Lameter
2010-10-28 15:13 ` [PATCH 2/2] mm: vmstat: Use a single setter function and callback for adjusting percpu thresholds Mel Gorman
2010-10-28 22:09 ` Andrew Morton
2010-10-29 10:17 ` Mel Gorman
-- strict thread matches above, loose matches on Subject: below --
2010-10-27 8:47 [PATCH 0/2] Reduce the amount of time spent in watermark-related functions Mel Gorman
2010-10-27 8:47 ` [PATCH 1/2] mm: page allocator: Adjust the per-cpu counter threshold when memory is low Mel Gorman
2010-10-27 20:16 ` Christoph Lameter
2010-10-28 1:09 ` KAMEZAWA Hiroyuki
2010-10-28 9:49 ` Mel Gorman
2010-10-28 9:58 ` KAMEZAWA Hiroyuki
2010-11-01 7:06 ` KOSAKI Motohiro
2010-11-26 16:06 ` Kyle McMartin
2010-11-29 9:56 ` Mel Gorman
2010-11-29 13:16 ` Kyle McMartin
2010-11-29 15:08 ` Mel Gorman
2010-11-29 15:22 ` Kyle McMartin
2010-11-29 15:26 ` Kyle McMartin
2010-11-29 15:58 ` Mel Gorman
2010-12-23 22:18 ` David Rientjes
2010-12-23 22:35 ` Andrew Morton
2010-12-23 23:00 ` Kyle McMartin
2010-12-23 23:07 ` David Rientjes
2010-12-23 23:17 ` 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=1288659200.8722.963.camel@sli10-conroe.sh.intel.com \
--to=shaohua.li@intel.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--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;
as well as URLs for NNTP newsgroup(s).