Subject: Re: [RFC][PATCH] sched: Optimize cgroup pick_next_task_fair
From: Peter Zijlstra <peterz@infradead.org>
To: Mike Galbraith <efault@gmx.de>
Cc: Paul Turner <pjt@google.com>, Venkatesh Pallipadi <venki@google.com>,
        Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>
In-Reply-To: <1328943389.7340.29.camel@marge.simpson.net>
References: <1328936700.2476.17.camel@laptop>
	 <1328943389.7340.29.camel@marge.simpson.net>
Content-Type: text/plain; charset="UTF-8"
Date: Sat, 11 Feb 2012 16:02:17 +0100
Message-ID: <1328972537.11320.11.camel@laptop>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1027
Lines: 24

On Sat, 2012-02-11 at 07:56 +0100, Mike Galbraith wrote:
> On Sat, 2012-02-11 at 06:05 +0100, Peter Zijlstra wrote: 
> > Since commit 2f36825b1 ("sched: Next buddy hint on sleep and preempt
> > path") it is likely we pick a new task from the same cgroup, doing a put
> > and then set on all intermediate entities is a waste of time, so try to
> > avoid this.
> 
> Good idea, we need to lose some weight. 

I actually set out to do something else, but then ended up here.. weird
how that works ;-)

My initial idea was to try and get rid of the pick_next_entity()
downward walk by keeping that data up-to-date when we dequeue/enqueue.

That all got a tad convoluted, I'll have to try it again. Anyway, that
ended up needing to rework the put/set stuff, and that part wasn't as
bad.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/