From: Michal Hocko <mhocko@kernel.org>
To: Christoph Lameter <cl@linux.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>,
Peter Zijlstra <peterz@infradead.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: fast path cycle muncher (vmstat: make vmstat_updater deferrable again and shut down on idle)
Date: Mon, 25 Jan 2016 18:42:24 +0100 [thread overview]
Message-ID: <20160125174224.GH23934@dhcp22.suse.cz> (raw)
In-Reply-To: <1453566115.3529.8.camel@gmail.com>
On Sat 23-01-16 17:21:55, Mike Galbraith wrote:
> Hi Christoph,
>
> While you're fixing that commit up, can you perhaps find a better home
> for quiet_vmstat()? It not only munches cycles when switching cross
> -core mightily, for -rt it injects a sleeping lock into the idle task.
>
> 12.89% [kernel] [k] refresh_cpu_vm_stats.isra.12
> 4.75% [kernel] [k] __schedule
> 4.70% [kernel] [k] mutex_unlock
> 3.14% [kernel] [k] __switch_to
Hmm, I wouldn't have expected that refresh_cpu_vm_stats could have
such a large footprint. I guess this would be just an expensive noop
because we have to check all the zones*counters and do an expensive
this_cpu_xchg. Is the whole deferred thing worth this overhead?
0eb77e988032 ("vmstat: make vmstat_updater deferrable again and
shut down on idle") doesn't talk about any numbers and neither does
39bf6270f524 ("VM statistics: Make timer deferrable").
But even when refresh_cpu_vm_stats is made more effective there would
still be the problem for RT and the work canceling, though. We would
need much more changes to make this RT ready (both timer and WQ code
would need some changes AFAIU).
Unless there is a clear and huge win from doing the vmstat update
deferrable then I think a revert is more appropriate IMHO.
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2016-01-25 17:42 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-19 0:33 mm, vmstat: kernel BUG at mm/vmstat.c:1408! Sasha Levin
2015-12-21 13:08 ` Christoph Lameter
2015-12-21 20:28 ` Sasha Levin
2015-12-21 21:07 ` Sasha Levin
2015-12-21 21:14 ` Christoph Lameter
2015-12-22 17:21 ` Christoph Lameter
2015-12-24 20:14 ` Sasha Levin
2015-12-29 17:01 ` Christoph Lameter
2015-12-29 17:18 ` Christoph Lameter
2016-01-04 18:05 ` Christoph Lameter
2016-01-04 18:46 ` Sasha Levin
2016-01-12 11:31 ` Shiraz Hashim
2016-01-12 12:23 ` Christoph Lameter
2016-01-12 12:27 ` Shiraz Hashim
2016-01-13 11:36 ` Shiraz Hashim
2016-01-13 12:32 ` Shiraz Hashim
2016-01-14 21:06 ` Sasha Levin
2016-01-20 14:37 ` Michal Hocko
2016-01-20 14:56 ` Sasha Levin
2016-01-20 15:10 ` Michal Hocko
2016-01-20 15:20 ` Christoph Lameter
2016-01-20 15:49 ` Sasha Levin
2016-01-20 15:55 ` Christoph Lameter
2016-01-20 21:28 ` Michal Hocko
2016-01-20 21:57 ` Christoph Lameter
2016-01-21 8:24 ` Michal Hocko
2016-01-21 15:45 ` Christoph Lameter
2016-01-21 16:51 ` Michal Hocko
2016-01-21 17:38 ` Christoph Lameter
2016-01-22 11:00 ` Shiraz Hashim
2016-01-22 14:04 ` Michal Hocko
2016-01-22 16:07 ` Christoph Lameter
2016-01-22 16:12 ` Michal Hocko
2016-01-22 16:46 ` Christoph Lameter
2016-01-22 17:12 ` Michal Hocko
2016-01-23 16:21 ` fast path cycle muncher (vmstat: make vmstat_updater deferrable again and shut down on idle) Mike Galbraith
2016-01-24 0:33 ` Christoph Lameter
2016-01-24 2:46 ` Mike Galbraith
2016-01-24 3:46 ` Christoph Lameter
2016-01-24 5:36 ` Mike Galbraith
2016-01-25 17:42 ` Michal Hocko [this message]
2016-01-25 18:02 ` Christoph Lameter
2016-01-25 20:13 ` Michal Hocko
2016-01-26 16:25 ` Christoph Lameter
2016-01-26 18:31 ` Mike Galbraith
2016-01-26 18:34 ` Christoph Lameter
2016-01-26 18:45 ` Mike Galbraith
2016-01-26 19:20 ` Christoph Lameter
2016-01-27 3:12 ` Mike Galbraith
2016-01-27 4:15 ` Mike Galbraith
2016-01-27 16:28 ` Christoph Lameter
2016-01-28 15:36 ` Frederic Weisbecker
2016-01-28 16:42 ` Christoph Lameter
2016-01-26 2:14 ` Mike Galbraith
2016-01-26 2:25 ` Mike Galbraith
2016-01-26 16:26 ` Christoph Lameter
2016-01-26 17:39 ` Mike Galbraith
2016-01-26 18:19 ` Christoph Lameter
2016-01-26 16:26 ` Christoph Lameter
2016-01-26 17:08 ` Mike Galbraith
2016-01-26 18:22 ` Christoph Lameter
2016-01-26 19:09 ` Mike Galbraith
2016-01-26 19:22 ` Christoph Lameter
2016-01-27 16:48 ` [PATCH] mm, vmstat: make quiet_vmstat lighter (was: Re: fast path cycle muncher (vmstat: make vmstat_updater deferrable) " Michal Hocko
2016-01-27 17:03 ` Mike Galbraith
2016-01-27 18:26 ` Christoph Lameter
2016-01-28 15:21 ` Michal Hocko
2016-01-28 16:40 ` Christoph Lameter
2016-01-28 16:53 ` Michal Hocko
2016-01-28 17:05 ` Christoph Lameter
2016-01-28 15:31 ` Michal Hocko
2016-01-28 15:37 ` [PATCH] vmstat: make vmstat_update deferrable (was: Re: [PATCH] mm, vmstat: make quiet_vmstat lighter) " Michal Hocko
2016-01-28 16:48 ` Christoph Lameter
2016-01-28 16:42 ` [PATCH] mm, vmstat: make quiet_vmstat lighter (was: Re: fast " Christoph Lameter
2016-01-24 16:57 ` mm, vmstat: kernel BUG at mm/vmstat.c:1408! Linus Torvalds
2016-01-20 15:14 ` Christoph Lameter
2016-01-20 15:20 ` Michal Hocko
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=20160125174224.GH23934@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=cl@linux.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=umgwanakikbuti@gmail.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).