public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Kirill Tkhai <tkhai@yandex.ru>
To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	Tkhai Kirill <ktkhai@parallels.com>
Subject: Re: [PATCH 1/2] sched: Rework migrate_tasks()
Date: Wed, 11 Jun 2014 16:20:54 +0400	[thread overview]
Message-ID: <3732251402489254@web2m.yandex.ru> (raw)
In-Reply-To: <20140611112411.GA21191@linux.vnet.ibm.com>

11.06.2014, 15:24, "Srikar Dronamraju" <srikar@linux.vnet.ibm.com>:
> * Kirill Tkhai <ktkhai@parallels.com> [2014-06-11 13:52:10]:
>>  Currently migrate_tasks() skips throttled tasks,
>>  because they are not pickable by pick_next_task().
>
> Before migrate_tasks() is called, we do call set_rq_offline(), in
> migration_call().
>
> Shouldnt this take care of unthrottling the tasks and making sure that
> they can be picked by pick_next_task().

If we do this separate for every class, we'll have to do this 3 times.
Furthermore, deadline class does not have a list of throttled tasks.
So we'll have to the same as I did: to lock tasklist_lock and to iterate
throw all of the tasks in the system just to found deadline tasks.

>>  These tasks stay on dead cpu even after they
>>  becomes unthrottled. They are not schedulable
>>  till user manually changes their affinity or till
>>  cpu becomes alive again.
>
> If we are still seeing tasks not being picked by pick_next_task(), then
> can it probably mean that rq->rd was NULL?

Unthrottle functions dl_task_timer() and unthrottle_cfs_rq() put tasks and
queues back. They do not look at rq->rd.

do_sched_rt_period_timer() does not unthrottle dead queue at all (they
are excluded from rd).

Thanks,
Kirill

  reply	other threads:[~2014-06-11 12:21 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20140611093417.27807.2288.stgit@tkhai>
2014-06-11  9:52 ` [PATCH 1/2] sched: Rework migrate_tasks() Kirill Tkhai
2014-06-11 10:57   ` Peter Zijlstra
2014-06-11 11:15     ` Kirill Tkhai
2014-06-11 11:24   ` Srikar Dronamraju
2014-06-11 12:20     ` Kirill Tkhai [this message]
2014-06-11 13:15       ` Srikar Dronamraju
2014-06-11 13:43         ` Kirill Tkhai
2014-06-11 19:33           ` Kirill Tkhai
2014-06-12  2:05             ` Mike Galbraith
2014-06-17 12:56               ` Kirill Tkhai
2014-06-11  9:52 ` [PATCH 2/2] sched: Rework check_for_tasks() Kirill Tkhai

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=3732251402489254@web2m.yandex.ru \
    --to=tkhai@yandex.ru \
    --cc=ktkhai@parallels.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=srikar@linux.vnet.ibm.com \
    /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