Message-ID: <1418551001.14250.25.camel@marge.simpson.net>
Subject: Re: [PATCH] sched/fair: change where we report sched stats
From: Mike Galbraith <umgwanakikbuti@gmail.com>
To: Josef Bacik <jbacik@fb.com>
Cc: bmaurer@fb.com, rkroll@fb.com, kernel-team@fb.com, mingo@redhat.com,
        peterz@infradead.org, linux-kernel@vger.kernel.org
Date: Sun, 14 Dec 2014 10:56:41 +0100
In-Reply-To: <5489B07E.9000200@fb.com>
References: <1418149315-30173-1-git-send-email-jbacik@fb.com>
	 <1418192604.5312.28.camel@marge.simpson.net> <5488BFC5.3080001@fb.com>
	 <1418268856.5263.46.camel@marge.simpson.net> <5489B07E.9000200@fb.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org

On Thu, 2014-12-11 at 09:55 -0500, Josef Bacik wrote:

> How did you do it?  I had one latency spike in a 90 minute test that 
> runs across 30 boxes that could have been caused by anything, so if 
> there is a way I could have easily found that without moving these 
> tracepoints around I'd love to hear it.  Thanks,

If I have a target, I tend to set tracing_off() traps.

Seems you want an ftrace tracer that tracks sched_switch sleeping to
sched_switch running in addition to the wakeup latency tracer.

-Mike

--
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/