public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jason Low <jason.low2@hp.com>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>,
	Preeti U Murthy <preeti@linux.vnet.ibm.com>,
	"peterz@infradead.org" <peterz@infradead.org>,
	"mingo@kernel.org" <mingo@kernel.org>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	"riel@redhat.com" <riel@redhat.com>,
	"vincent.guittot@linaro.org" <vincent.guittot@linaro.org>,
	"srikar@linux.vnet.ibm.com" <srikar@linux.vnet.ibm.com>,
	"pjt@google.com" <pjt@google.com>,
	"benh@kernel.crashing.org" <benh@kernel.crashing.org>,
	"efault@gmx.de" <efault@gmx.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"iamjoonsoo.kim@lge.com" <iamjoonsoo.kim@lge.com>,
	"svaidy@linux.vnet.ibm.com" <svaidy@linux.vnet.ibm.com>,
	jason.low2@hp.com
Subject: Re: sched: Improve load balancing in the presence of idle CPUs
Date: Tue, 07 Apr 2015 10:42:41 -0700	[thread overview]
Message-ID: <1428428561.2556.63.camel@j-VirtualBox> (raw)
In-Reply-To: <1428100518.660.34.camel@schen9-desk2.jf.intel.com>

On Fri, 2015-04-03 at 15:35 -0700, Tim Chen wrote:
> I think we can get rid of the done_balancing boolean 
> and make it a bit easier to read if we change the above code to
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index bcfe320..08317dc 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7557,8 +7557,13 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
>                  * work being done for other cpus. Next load
>                  * balancing owner will pick it up.
>                  */
> -               if (need_resched())
> -                       break;
> +               if (need_resched()) {
> +                       /* preparing to bail, kicking other cpu to continue */
> +                       clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
> +                       if (nohz_kick_needed(this_rq))
> +                               nohz_balance_kick();
> +                       return;
> +               }

Hi Tim,

We would also need the nohz_kick_needed/nohz_balance_kick if we
initially find that the current CPU is not idle (at the beginning of
nohz_idle_balance). In the above case, we would need to add the code to
2 locations.

Would it be better to still keep the done_balancing to avoid having
duplicate code?


  reply	other threads:[~2015-04-07 17:42 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-30 18:55 sched: Improve load balancing in the presence of idle CPUs Jason Low
2015-03-31  8:37 ` Preeti U Murthy
2015-03-31 18:54   ` Jason Low
2015-04-01  6:49     ` Preeti U Murthy
2015-04-01 17:04       ` Morten Rasmussen
2015-04-02  3:30         ` Jason Low
2015-04-02  8:49           ` Morten Rasmussen
2015-04-02  5:59         ` Jason Low
2015-04-02  8:42           ` Preeti U Murthy
2015-04-02  9:17           ` Morten Rasmussen
2015-04-02 17:22             ` Jason Low
2015-04-03 22:35           ` Tim Chen
2015-04-07 17:42             ` Jason Low [this message]
2015-04-07 19:39               ` Tim Chen
2015-04-07 20:24                 ` Jason Low
2015-04-04  9:59           ` Preeti U Murthy
2015-04-07 23:28             ` Jason Low
2015-04-08  0:07               ` Jason Low
2015-04-08 11:12                 ` Srikar Dronamraju
2015-04-08 21:22                   ` Jason Low
2015-04-10  8:37                     ` Srikar Dronamraju
2015-04-13 18:55                       ` Jason Low
2015-04-13 20:54                       ` Jason Low
2015-04-09  2:39                   ` Jason Low
2015-04-09  7:02                     ` Srikar Dronamraju
2015-04-09 22:49                       ` Jason Low
2015-04-13  6:16                 ` Preeti U Murthy
2015-04-13 22:49                   ` Jason Low
2015-04-14  2:59                     ` Jason Low
2015-04-02  2:11   ` 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=1428428561.2556.63.camel@j-VirtualBox \
    --to=jason.low2@hp.com \
    --cc=benh@kernel.crashing.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=efault@gmx.de \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=preeti@linux.vnet.ibm.com \
    --cc=riel@redhat.com \
    --cc=srikar@linux.vnet.ibm.com \
    --cc=svaidy@linux.vnet.ibm.com \
    --cc=tim.c.chen@linux.intel.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