From: Peter Zijlstra <peterz@infradead.org>
To: Jason Low <jason.low2@hp.com>
Cc: mingo@kernel.org, linux-kernel@vger.kernel.org,
daniel.lezcano@linaro.org, alex.shi@linaro.org,
preeti@linux.vnet.ibm.com, efault@gmx.de,
vincent.guittot@linaro.org, morten.rasmussen@arm.com,
aswin@hp.com, chegu_vinod@hp.com
Subject: Re: [PATCH 3/3] sched, fair: Stop searching for tasks in newidle balance if there are runnable tasks
Date: Thu, 24 Apr 2014 18:54:03 +0200 [thread overview]
Message-ID: <20140424165403.GY11096@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <1398357789.3509.6.camel@j-VirtualBox>
On Thu, Apr 24, 2014 at 09:43:09AM -0700, Jason Low wrote:
> I recall seeing somewhere around a +7% performance improvement
> in at least least 1 of the AIM7 workloads. I can do some more testing
> with this.
But yeah, please test more than 1 workload; its fairly typical for one
workload to win and another to completely tank :-/
next prev parent reply other threads:[~2014-04-24 16:54 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-24 1:30 [PATCH 0/3] sched: Idle balance patches Jason Low
2014-04-24 1:30 ` [PATCH 1/3] sched, balancing: Update rq->max_idle_balance_cost whenever newidle balance is attempted Jason Low
2014-04-24 10:14 ` Preeti U Murthy
2014-04-24 12:04 ` Peter Zijlstra
2014-04-24 12:44 ` Peter Zijlstra
2014-04-24 16:53 ` Jason Low
2014-04-24 17:14 ` Peter Zijlstra
2014-04-24 17:29 ` Peter Zijlstra
2014-04-24 22:18 ` Jason Low
2014-04-25 5:12 ` Preeti U Murthy
2014-04-25 7:13 ` Jason Low
2014-04-25 7:58 ` Mike Galbraith
2014-04-25 17:03 ` Jason Low
2014-04-25 5:08 ` Preeti U Murthy
2014-04-25 9:43 ` Peter Zijlstra
2014-04-25 19:54 ` Jason Low
2014-04-26 14:50 ` Peter Zijlstra
2014-04-28 16:42 ` Jason Low
2014-04-27 8:31 ` Preeti Murthy
2014-04-28 9:24 ` Peter Zijlstra
2014-04-29 3:10 ` Preeti U Murthy
2014-04-28 18:04 ` Jason Low
2014-04-29 3:52 ` Preeti U Murthy
2014-04-24 1:30 ` [PATCH 2/3] sched: Initialize newidle balance stats in sd_numa_init() Jason Low
2014-04-24 12:18 ` Peter Zijlstra
2014-04-25 5:57 ` Preeti U Murthy
2014-05-08 10:42 ` [tip:sched/core] sched/numa: " tip-bot for Jason Low
2014-04-24 1:30 ` [PATCH 3/3] sched, fair: Stop searching for tasks in newidle balance if there are runnable tasks Jason Low
2014-04-24 2:51 ` Mike Galbraith
2014-04-24 8:28 ` Mike Galbraith
2014-04-24 16:37 ` Jason Low
2014-04-24 19:07 ` Mike Galbraith
2014-04-24 7:15 ` Peter Zijlstra
2014-04-24 16:43 ` Jason Low
2014-04-24 16:52 ` Peter Zijlstra
2014-04-25 1:24 ` Jason Low
2014-04-25 2:45 ` Mike Galbraith
2014-04-25 3:33 ` Jason Low
2014-04-25 5:46 ` Mike Galbraith
2014-04-24 16:54 ` Peter Zijlstra [this message]
2014-04-24 10:30 ` Morten Rasmussen
2014-04-24 11:32 ` Peter Zijlstra
2014-04-24 14:08 ` Morten Rasmussen
2014-04-24 14:59 ` Peter Zijlstra
2014-05-08 10:44 ` [tip:sched/core] sched/fair: " tip-bot for Jason Low
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=20140424165403.GY11096@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=alex.shi@linaro.org \
--cc=aswin@hp.com \
--cc=chegu_vinod@hp.com \
--cc=daniel.lezcano@linaro.org \
--cc=efault@gmx.de \
--cc=jason.low2@hp.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=morten.rasmussen@arm.com \
--cc=preeti@linux.vnet.ibm.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