From: Mike Galbraith <efault@gmx.de>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>
Subject: [patch 0/12] sched: fastpath cycle recovery
Date: Thu, 11 Mar 2010 10:49:10 +0100 [thread overview]
Message-ID: <1268300950.6785.27.camel@marge.simson.net> (raw)
Hi Peter,
The following patchlets take a pinned pipe-test context switch frequency
in tip from 663KHZ to 694KHZ, and an unpinned instance from 450KHz to
540KHz. With these applied to tip.today, I have zero 31-12->today
regressions, and even some modest progressions.
The biggest difference is made by the first patch. We have a problem
with nohz when waking cross-cpu, which given select_idle_sibling(), we
do quite a bit. In testing netperf TCP_RR, hitting nohz code on every
micro-idle was eating ~10% of throughput, making cross-cpu wakeup a
loser. These patchlets combined turned netperf TCP_RR cross-cpu vs
affine from big loser into a winner.
All of these are trivial, mostly axe murder, but cycles add up.
-Mike
next reply other threads:[~2010-03-11 9:49 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-11 9:49 Mike Galbraith [this message]
2010-03-11 9:50 ` [patch 1/12] sched: ratelimit nohz Mike Galbraith
2010-03-11 18:30 ` [tip:sched/core] sched: Rate-limit nohz tip-bot for Mike Galbraith
2010-03-11 9:51 ` [patch 2/12] sched: remove avg_wakeup Mike Galbraith
2010-03-11 18:30 ` [tip:sched/core] sched: Remove avg_wakeup tip-bot for Mike Galbraith
2010-03-11 9:52 ` [patch 3/12] sched: remove avg_overlap Mike Galbraith
2010-03-11 18:31 ` [tip:sched/core] sched: Remove avg_overlap tip-bot for Mike Galbraith
2010-03-11 9:53 ` [patch 4/12] sched: cleanup/optimize clock updates Mike Galbraith
2010-03-11 18:31 ` [tip:sched/core] sched: Cleanup/optimize " tip-bot for Mike Galbraith
2010-03-11 9:54 ` [patch 5/12] sched: tweak sched_latency and min_granularity Mike Galbraith
2010-03-11 18:31 ` [tip:sched/core] sched: Tweak " tip-bot for Mike Galbraith
2010-03-11 9:56 ` [patch 6/12] sched: fix select_idle_sibling() Mike Galbraith
2010-03-11 18:32 ` [tip:sched/core] sched: Fix select_idle_sibling() tip-bot for Mike Galbraith
2010-03-11 9:57 ` [patch 7/12] sched: remove NORMALIZED_SLEEPER Mike Galbraith
2010-03-11 18:32 ` [tip:sched/core] sched: Remove NORMALIZED_SLEEPER tip-bot for Mike Galbraith
2010-03-11 9:58 ` [patch 8/12] sched: remove FAIR_SLEEPERS feature Mike Galbraith
2010-03-11 18:32 ` [tip:sched/core] sched: Remove " tip-bot for Mike Galbraith
2010-03-11 9:59 ` [patch 9/12] sched: remove WAKEUP_SYNC feature Mike Galbraith
2010-03-11 18:32 ` [tip:sched/core] sched: Remove " tip-bot for Mike Galbraith
2010-03-11 10:01 ` [patch 11/12] sched: remove ASYM_GRAN feature Mike Galbraith
2010-03-11 18:33 ` [tip:sched/core] sched: Remove " tip-bot for Mike Galbraith
2010-03-11 10:03 ` [patch 10/12] sched: remove SYNC_WAKEUPS feature Mike Galbraith
2010-03-11 18:33 ` [tip:sched/core] sched: Remove " tip-bot for Mike Galbraith
2010-03-11 10:04 ` [patch 12/12] sched: remove AFFINE_WAKEUPS feature Mike Galbraith
2010-03-11 18:33 ` [tip:sched/core] sched: Remove " tip-bot for Mike Galbraith
2010-03-12 3:23 ` Yong Zhang
2010-03-12 4:37 ` Mike Galbraith
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=1268300950.6785.27.camel@marge.simson.net \
--to=efault@gmx.de \
--cc=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
/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