Message-ID: <1329434900.2293.261.camel@twins>
Subject: Re: [RFC][PATCH] sched: Optimize cgroup pick_next_task_fair
From: Peter Zijlstra <peterz@infradead.org>
To: Paul Turner <pjt@google.com>
Cc: Venkatesh Pallipadi <venki@google.com>, Ingo Molnar <mingo@elte.hu>,
        Mike Galbraith <efault@gmx.de>, LKML <linux-kernel@vger.kernel.org>
Date: Fri, 17 Feb 2012 00:28:20 +0100
In-Reply-To: <1329434437.2293.259.camel@twins>
References: <1328936700.2476.17.camel@laptop>
	 <1329434437.2293.259.camel@twins>
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7BIT
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 679
Lines: 15

On Fri, 2012-02-17 at 00:20 +0100, Peter Zijlstra wrote:
> +       if (prev && (prev->sched_class != &fair_sched_class ||
> +                               cfs_rq->nr_running == 1)) { 

this ==1 check is way ugly and a problem that needs addressing. Not
putting cfs_rq->curr back in the tree perturbs pick_next_entity()'s view
of things.

Probably easiest to pick leftmost and ->curr and go from there, but
that's for tomorrow or so.
--
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/