All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yuyang Du <yuyang.du@intel.com>
To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: bsegall@google.com, pjt@google.com, morten.rasmussen@arm.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	matt@codeblueprint.co.uk, umgwanakikbuti@gmail.com
Subject: Re: [PATCH v1 00/10] Optimize sched avgs computation and implement flat util hierarchy
Date: Wed, 10 Aug 2016 08:23:52 +0800	[thread overview]
Message-ID: <20160810002352.GB3273@intel.com> (raw)
In-Reply-To: <1470788095-2125-1-git-send-email-yuyang.du@intel.com>

[-- Attachment #1: Type: text/plain, Size: 1143 bytes --]

On Wed, Aug 10, 2016 at 08:14:45AM +0800, Yuyang Du wrote:
> Hi Peter,
> 
> I should have sent out my flat util hierarchy implementation long time ago,
> actually code was there but not rebased. I finally have time to do this,
> so here it is. There are also other proposals to solve migrated tasks' util
> mobility problem, such as the ones from Dietmar and Vincent.
> 
> The sched avgs computation optimization was initiated for the flat util thing,
> so I send them out together.
> 
> According to Morten and Ben's feedback, I removed 32-bit as a period's upper
> bound limit. So, thanks a lot to them.
> 

To compare the effectiveness of the flat util hierarchy, a simple experiment
was done: rt-app to generate a 50% duty-cycling workload (100us/200us), and
in the meantime a script to set the CPU affinity of the task, alternating
to taskset the task to run on CPU x and CPU y every 0.3 sec, so forcing the
task to ping-pong migrate. By auto-group and ssh itself, the task under test
is at the third level task group.

So compare the top cfs_rq's util_avg (group_hierarchy.jpg) vs. the rq's util_avg
(flat_hierarchy.jpg)

Thanks,
Yuyang

[-- Attachment #2: group_hierarchy.jpg --]
[-- Type: image/jpeg, Size: 48406 bytes --]

[-- Attachment #3: flat_hierarchy.jpg --]
[-- Type: image/jpeg, Size: 32646 bytes --]

  parent reply	other threads:[~2016-08-10 18:46 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-08-10  0:14 [PATCH v1 00/10] Optimize sched avgs computation and implement flat util hierarchy Yuyang Du
2016-08-10  0:14 ` [PATCH v1 01/10] sched/fair: Chance LOAD_AVG_MAX_N from 345 to 347 Yuyang Du
2016-08-24 16:01   ` Vincent Guittot
2016-08-29  0:07     ` Yuyang Du
2016-08-10  0:14 ` [PATCH v1 02/10] documentation: Add scheduler/sched-avg.txt Yuyang Du
2016-08-22 16:48   ` Randy Dunlap
2016-08-10  0:14 ` [PATCH v1 03/10] sched/fair: Add static to remove_entity_load_avg() Yuyang Du
2016-08-10  0:14 ` [PATCH v1 04/10] sched/fair: Rename variable names for sched averages Yuyang Du
2016-08-10  0:14 ` [PATCH v1 05/10] sched/fair: Add __always_inline compiler attribute to __accumulate_sum() Yuyang Du
2016-08-10  0:14 ` [PATCH v1 06/10] sched/fair: Optimize __update_sched_avg() Yuyang Du
2016-08-10  0:14 ` [PATCH v1 07/10] sched/fair: Remove useless 64-bit to 32-bit variable conversion Yuyang Du
2016-08-25  7:11   ` Vincent Guittot
2016-08-29  1:00     ` Yuyang Du
2016-08-10  0:14 ` [PATCH v1 08/10] sched/fair: Remove scale_load_down() for load_avg Yuyang Du
2016-08-10  0:14 ` [PATCH v1 09/10] sched/fair: Rename scale_load() and scale_load_down() Yuyang Du
2016-08-10  0:14 ` [PATCH v1 10/10] sched/fair: Implement flat hierarchical structure for util_avg Yuyang Du
2016-08-10  0:23 ` Yuyang Du [this message]
2016-08-22 23:26   ` [PATCH v1 00/10] Optimize sched avgs computation and implement flat util hierarchy Yuyang Du
2016-08-23 13:28     ` Vincent Guittot
2016-08-23 14:13       ` Peter Zijlstra
2016-08-23 14:45         ` Vincent Guittot
2016-08-23 15:39           ` Dietmar Eggemann
2016-08-29  1:37             ` Yuyang Du
2016-09-01 18:32               ` Dietmar Eggemann
2016-08-24  8:54           ` Morten Rasmussen
2016-08-24  9:48             ` Vincent Guittot
2016-08-29 19:00             ` Yuyang Du
2016-09-01 14:22               ` Morten Rasmussen
2016-08-23 19:09         ` Yuyang Du
2016-08-23 19:01       ` Yuyang Du

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=20160810002352.GB3273@intel.com \
    --to=yuyang.du@intel.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matt@codeblueprint.co.uk \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=umgwanakikbuti@gmail.com \
    --cc=vincent.guittot@linaro.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.