public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Dima Zavin <dima@android.com>
Cc: linux-kernel@vger.kernel.org, "Ingo Molnar" <mingo@elte.hu>,
	"Mike Galbraith" <efault@gmx.de>,
	"Arve Hjønnevåg" <arve@android.com>
Subject: Re: [PATCH 1/2] sched: normalize sleeper's vruntime during group change
Date: Fri, 01 Oct 2010 13:59:28 +0200	[thread overview]
Message-ID: <1285934368.2144.60.camel@laptop> (raw)
In-Reply-To: <AANLkTikVQist_VnCcpZzU78t0TVuocwOcDPG4POVzSdv@mail.gmail.com>

On Thu, 2010-09-30 at 12:14 -0700, Dima Zavin wrote:
> 
> > Please explain this stuff..
> 
> The situation today is quite bad for sleeping tasks. Currently, when
> you move a sleeping thread between cgroups, the thread can retain its
> old vruntime value if the old group was far ahead of the new group
> since it essentially does a max(se->vruntime, new_vruntime) in
> place_entity. This can prevent the task from running for a very long
> time. That is what this patch was trying to address. It normalizes the
> sleeper thread's vruntime before moving it to the new group.
> 
> 

Hrm,.. ok, I tend to not use this cgroup gunk more that I absolutely
have to, so I'll take your word for it.

But doesn't normal cross-cpu task migration already solve this problem?
Therefore wouldn't it be possible to adapt/extend that code to also deal
with this particular issue?

It would avoid growing more cgroup fudge..

  reply	other threads:[~2010-10-01 11:59 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-29  6:46 [PATCH 1/2] sched: normalize sleeper's vruntime during group change Dima Zavin
2010-09-29  6:46 ` [PATCH 2/2] sched: use the old min_vruntime when normalizing on dequeue Dima Zavin
2010-10-07 21:00   ` Dima Zavin
2010-10-08  6:57     ` Mike Galbraith
2010-09-29  6:54 ` [PATCH 1/2] sched: normalize sleeper's vruntime during group change Pekka Enberg
2010-09-29  7:17   ` Dima Zavin
2010-09-29  8:13 ` Mike Galbraith
2010-09-29 19:02   ` Dima Zavin
2010-09-29 21:44   ` Dima Zavin
2010-09-30 10:47 ` Peter Zijlstra
2010-09-30 19:14   ` Dima Zavin
2010-10-01 11:59     ` Peter Zijlstra [this message]
2010-10-04 19:18       ` Dima Zavin
2010-10-06 22:56         ` Dima Zavin
2010-10-07  2:24           ` Mike Galbraith
2010-10-15 13:50         ` Peter Zijlstra
2010-10-22 13:02           ` [tip:sched/urgent] sched, cgroup: Fixup broken cgroup movement tip-bot for Peter Zijlstra

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=1285934368.2144.60.camel@laptop \
    --to=peterz@infradead.org \
    --cc=arve@android.com \
    --cc=dima@android.com \
    --cc=efault@gmx.de \
    --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