From: Mike Galbraith <efault@gmx.de>
To: Michael Wang <wangyun@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
LKML <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>, Alex Shi <alex.shi@intel.com>,
Namhyung Kim <namhyung@kernel.org>, Paul Turner <pjt@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
"Nikunj A. Dadhania" <nikunj@linux.vnet.ibm.com>,
Ram Pai <linuxram@us.ibm.com>
Subject: Re: [PATCH] sched: smart wake-affine
Date: Thu, 04 Jul 2013 12:33:33 +0200 [thread overview]
Message-ID: <1372934013.9046.16.camel@marge.simpson.net> (raw)
In-Reply-To: <51D5428D.7080805@linux.vnet.ibm.com>
On Thu, 2013-07-04 at 17:38 +0800, Michael Wang wrote:
> On 07/04/2013 05:13 PM, Peter Zijlstra wrote:
> [snip]
> >
> > Right, but something like the below is limited in cost to at most 32/64 (I
> > forgot the type) shifts. Now its probably not worth doing, but it shows
> > things like that can be done in 'constant' time.
> >
> > now = jiffies;
> > if (now - p->last_switch_decay > 8*sizeof(p->nr_wakee_switch)*HZ) {
> > p->nr_wakee_switch = 0;
> > p->last_switch_decay = now;
> > } else while (now > p->last_switch_decay + HZ) {
> > p->nr_wakee_switch >>= 1;
> > p->last_switch_decay += HZ;
> > }
>
> Hmm...interesting, some kind of cataclysm decay, not sure how it works
> but yes, the cost was capped.
>
> Well, seems like we still have many follow-up research works after fix
> the issue ;-)
Yeah. Like how to how to exterminate the plus sign, they munch cache
lines, and have a general tendency to negatively impact benchmarks.
Q6600 box, hackbench -l 1000
avg
3.10.0-regress 2.293 2.297 2.313 2.291 2.295 2.297 1.000
3.10.0-regressx 2.560 2.524 2.427 2.599 2.602 2.542 1.106
pahole said...
marge:/usr/local/src/kernel/linux-3.x.git # tail virgin
long unsigned int timer_slack_ns; /* 1512 8 */
long unsigned int default_timer_slack_ns; /* 1520 8 */
atomic_t ptrace_bp_refcnt; /* 1528 4 */
/* size: 1536, cachelines: 24, members: 125 */
/* sum members: 1509, holes: 6, sum holes: 23 */
/* bit holes: 1, sum bit holes: 26 bits */
/* padding: 4 */
/* paddings: 1, sum paddings: 4 */
};
marge:/usr/local/src/kernel/linux-3.x.git # tail michael
long unsigned int default_timer_slack_ns; /* 1552 8 */
atomic_t ptrace_bp_refcnt; /* 1560 4 */
/* size: 1568, cachelines: 25, members: 128 */
/* sum members: 1533, holes: 8, sum holes: 31 */
/* bit holes: 1, sum bit holes: 26 bits */
/* padding: 4 */
/* paddings: 1, sum paddings: 4 */
/* last cacheline: 32 bytes */
};
..but plugging holes, didn't help, moving this/that around neither, nor
did letting pahole go wild to get the line back. It's plus signs I tell
ya, the evil things must die ;-)
-Mike
next prev parent reply other threads:[~2013-07-04 10:33 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-28 5:05 [RFC PATCH] " Michael Wang
2013-06-03 2:28 ` Michael Wang
2013-06-03 3:09 ` Mike Galbraith
2013-06-03 3:26 ` Michael Wang
2013-06-03 3:53 ` Mike Galbraith
2013-06-03 4:52 ` Michael Wang
2013-06-03 5:22 ` Mike Galbraith
2013-06-03 5:50 ` Michael Wang
2013-06-03 6:05 ` Mike Galbraith
2013-06-03 6:31 ` Michael Wang
2013-06-13 3:09 ` Michael Wang
2013-07-02 4:43 ` [PATCH] " Michael Wang
2013-07-02 5:38 ` Mike Galbraith
2013-07-02 5:50 ` Michael Wang
2013-07-02 5:54 ` Mike Galbraith
2013-07-02 6:17 ` Michael Wang
2013-07-02 6:29 ` Mike Galbraith
2013-07-02 6:45 ` Michael Wang
2013-07-02 8:52 ` Peter Zijlstra
2013-07-02 9:35 ` Michael Wang
2013-07-02 9:44 ` Michael Wang
2013-07-04 9:13 ` Peter Zijlstra
2013-07-04 9:38 ` Michael Wang
2013-07-04 10:33 ` Mike Galbraith [this message]
2013-07-05 2:47 ` Michael Wang
2013-07-05 4:08 ` Mike Galbraith
2013-07-05 4:33 ` Michael Wang
2013-07-05 5:41 ` Mike Galbraith
2013-07-05 6:16 ` Michael Wang
2013-07-07 6:43 ` Mike Galbraith
2013-07-08 2:49 ` Michael Wang
2013-07-08 3:12 ` Mike Galbraith
2013-07-08 8:21 ` Peter Zijlstra
2013-07-08 8:49 ` Mike Galbraith
2013-07-08 9:08 ` Michael Wang
2013-07-08 8:58 ` Michael Wang
2013-07-08 18:59 ` Davidlohr Bueso
2013-07-09 2:30 ` Michael Wang
2013-07-09 2:36 ` Davidlohr Bueso
2013-07-09 2:52 ` Michael Wang
2013-07-15 5:13 ` Michael Wang
2013-07-15 5:57 ` Davidlohr Bueso
2013-07-15 6:01 ` Michael Wang
2013-07-18 2:15 ` Michael Wang
2013-07-03 6:10 ` [PATCH v2] " Michael Wang
2013-07-03 8:50 ` Peter Zijlstra
2013-07-03 9:11 ` Michael Wang
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=1372934013.9046.16.camel@marge.simpson.net \
--to=efault@gmx.de \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxram@us.ibm.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=nikunj@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=wangyun@linux.vnet.ibm.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
all inboxes | Powered by JetHome®