Date: Wed, 26 Jun 2013 18:10:51 +0200
From: Ingo Molnar <mingo@kernel.org>
To: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
        Mike Galbraith <bitbucket@online.de>,
        Dave Chiluk <chiluk@canonical.com>, Ingo Molnar <mingo@redhat.com>,
        linux-kernel@vger.kernel.org
Subject: Re: Scheduler accounting inflated for io bound processes.
Message-ID: <20130626161051.GA8207@gmail.com>
References: <51C35C05.1070005@canonical.com>
 <1372176104.7497.86.camel@marge.simpson.net>
 <1372182534.7497.129.camel@marge.simpson.net>
 <20130626093713.GA27385@gmail.com>
 <20130626104243.GE28407@twins.programming.kicks-ass.net>
 <20130626155048.GA7399@gmail.com>
 <51CB110E.6010707@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <51CB110E.6010707@gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1644
Lines: 41


* David Ahern <dsahern@gmail.com> wrote:

> On 6/26/13 9:50 AM, Ingo Molnar wrote:
> >
> >* Peter Zijlstra <peterz@infradead.org> wrote:
> >
> >>On Wed, Jun 26, 2013 at 11:37:13AM +0200, Ingo Molnar wrote:
> >>>Would be very nice to randomize the sampling rate, by randomizing the
> >>>intervals within a 1% range or so - perf tooling will probably recognize
> >>>the different weights.
> >>
> >>You're suggesting adding noise to the regular kernel tick?
> >
> >No, to the perf interval (which I assumed Mike was using to profile this?)
> >- although slightly randomizing the kernel tick might make sense as well,
> >especially if it's hrtimer driven and reprogrammed anyway.
> >
> >I might have gotten it all wrong though ...
> 
> Sampled S/W events like cpu-clock have a fixed rate 
> (perf_swevent_init_hrtimer converts freq to sample_period).
> 
> Sampled H/W events have an adaptive period that converges to the desired 
> sampling rate. The first few samples come in 10 usecs are so apart and 
> the time period expands to the desired rate. As I recall that adaptive 
> algorithm starts over every time the event is scheduled in.

Yes, but last I checked it (2 years ago? :-) the auto-freq code was 
converging pretty well to the time clock, with little jitter - in essence 
turning it into a fixed-period, fixed-frequency sampling method. That 
would explain Mike's results.

Thanks,

	Ingo
--
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/