[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAE4VaGBwFvduqOyn8pQnN3U4ozuB=4DVx6i1vheAg-2PegvE9Q@mail.gmail.com>
Date: Thu, 14 May 2020 12:22:05 +0200
From: Jirka Hladky <jhladky@...hat.com>
To: Mel Gorman <mgorman@...hsingularity.net>
Cc: Phil Auld <pauld@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Juri Lelli <juri.lelli@...hat.com>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>,
Valentin Schneider <valentin.schneider@....com>,
Hillf Danton <hdanton@...a.com>,
LKML <linux-kernel@...r.kernel.org>,
Douglas Shakshober <dshaks@...hat.com>,
Waiman Long <longman@...hat.com>,
Joe Mario <jmario@...hat.com>, Bill Gray <bgray@...hat.com>
Subject: Re: [PATCH 00/13] Reconcile NUMA balancing decisions with the load
balancer v6
Thanks!
Do you have a link? I cannot find it on github
(https://github.com/gormanm/mmtests, searched for
config-network-netperf-cstate-small-cross-socket)
On Thu, May 14, 2020 at 12:08 PM Mel Gorman <mgorman@...hsingularity.net> wrote:
>
> On Thu, May 14, 2020 at 11:58:36AM +0200, Jirka Hladky wrote:
> > Thank you, Mel!
> >
> > We are using netperf as well, but AFAIK it's running on two different
> > hosts. I will check with colleagues, if they can
> > add network-netperf-unbound run on the localhost.
> >
> > Is this the right config?
> > https://github.com/gormanm/mmtests/blob/345f82bee77cbf09ba57f470a1cfc1ae413c97df/bin/generate-generic-configs
> > sed -e 's/NETPERF_BUFFER_SIZES=.*/NETPERF_BUFFER_SIZES=64/'
> > config-network-netperf-unbound > config-network-netperf-unbound-small
> >
>
> That's one I was using at the moment to have a quick test after
> the reconciliation series was completed. It has since changed to
> config-network-netperf-cstate-small-cross-socket to limit cstates, bind
> the client and server to two local CPUs and using one buffer size. It
> was necessary to get an ftrace function graph of the wakeup path that
> was readable and not too noisy due to migrations, cpuidle exit costs etc.
>
> --
> Mel Gorman
> SUSE Labs
>
--
-Jirka
Powered by blists - more mailing lists