From: Mel Gorman <mgorman@techsingularity.net>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
Valentin Schneider <valentin.schneider@arm.com>,
Aubrey Li <aubrey.li@linux.intel.com>,
Barry Song <song.bao.hua@hisilicon.com>,
Mike Galbraith <efault@gmx.de>,
Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
LKML <linux-kernel@vger.kernel.org>,
Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH v4 0/2] Reduce stacking and overscheduling
Date: Thu, 28 Oct 2021 10:48:32 +0100 [thread overview]
Message-ID: <20211028094834.1312-1-mgorman@techsingularity.net> (raw)
Also available at
git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git sched-scalewakegran-v4r1
Changelog since v3
o No code changes, added some additional results to patch 1
These series tackles two problems. The first is that heavy wakers
can stack an excessive number of tasks on the same CPU. The
second is that tasks can overschedule when the task has not
reached its minimum preemption granularity.
The patches are independent but were discussed together in the thread
https://lore.kernel.org/r/20210920142614.4891-1-mgorman@techsingularity.net
so are presented together.
With both patches on a zen3 machine
hackbench-process-pipes
5.15.0-rc3 5.15.0-rc3
vanilla sched-scalewakegran-v3r2
Amean 1 0.3667 ( 0.00%) 0.3823 ( -4.27%)
Amean 4 0.5343 ( 0.00%) 0.4867 ( 8.92%)
Amean 7 0.5300 ( 0.00%) 0.5053 ( 4.65%)
Amean 12 0.5737 ( 0.00%) 0.5450 ( 5.00%)
Amean 21 0.6727 ( 0.00%) 0.6807 ( -1.19%)
Amean 30 0.8583 ( 0.00%) 0.7107 * 17.20%*
Amean 48 1.3977 ( 0.00%) 1.0447 * 25.26%*
Amean 79 1.9790 ( 0.00%) 1.6033 * 18.98%*
Amean 110 2.8020 ( 0.00%) 2.0763 * 25.90%*
Amean 141 3.6683 ( 0.00%) 2.5313 * 31.00%*
Amean 172 4.6687 ( 0.00%) 3.1163 * 33.25%*
Amean 203 5.2183 ( 0.00%) 3.5560 * 31.86%*
Amean 234 6.1077 ( 0.00%) 3.8913 * 36.29%*
Amean 265 7.1313 ( 0.00%) 4.2293 * 40.69%*
Amean 296 7.7557 ( 0.00%) 4.5357 * 41.52%*
5.15.0-rc3 5.15.0-rc3
vanilla sched-scalewakegran-v3r2
Duration User 2933.05 2034.17
Duration System 25652.83 17137.08
Duration Elapsed 162.50 120.25
kernel/sched/fair.c | 27 ++++++++++++++++++++++++---
kernel/sched/features.h | 2 ++
2 files changed, 26 insertions(+), 3 deletions(-)
--
2.31.1
next reply other threads:[~2021-10-28 9:49 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-28 9:48 Mel Gorman [this message]
2021-10-28 9:48 ` [PATCH 1/2] sched/fair: Couple wakee flips with heavy wakers Mel Gorman
2021-10-28 16:19 ` Tao Zhou
2021-10-29 8:42 ` Mel Gorman
2021-11-10 9:53 ` Tao Zhou
2021-11-10 15:40 ` Mike Galbraith
2021-10-29 15:17 ` Vincent Guittot
2021-10-30 3:11 ` Mike Galbraith
2021-10-30 4:12 ` Mike Galbraith
2021-11-01 8:56 ` Mel Gorman
2021-10-28 9:48 ` [PATCH 2/2] sched/fair: Increase wakeup_gran if current task has not executed the minimum granularity Mel Gorman
2021-10-29 16:07 ` Vincent Guittot
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=20211028094834.1312-1-mgorman@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=aubrey.li@linux.intel.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=song.bao.hua@hisilicon.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=valentin.schneider@arm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox