[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1316704637.31429.25.camel@twins>
Date: Thu, 22 Sep 2011 17:17:17 +0200
From: Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: Balbir Singh <bsingharora@...il.com>
Cc: Srivatsa Vaddagiri <vatsa@...ux.vnet.ibm.com>,
Glauber Costa <glommer@...allels.com>,
linux-kernel@...r.kernel.org, xemul@...allels.com,
paul@...lmenage.org, lizf@...fujitsu.com, daniel.lezcano@...e.fr,
mingo@...e.hu, jbottomley@...allels.com
Subject: Re: [PATCH 1/9] Remove parent field in cpuacct cgroup
On Thu, 2011-09-22 at 20:41 +0530, Balbir Singh wrote:
> On Tue, Sep 20, 2011 at 10:59 PM, Srivatsa Vaddagiri
> <vatsa@...ux.vnet.ibm.com> wrote:
> > * Peter Zijlstra <a.p.zijlstra@...llo.nl> [2011-09-19 20:40:53]:
> >
> >> > Note I was talking about cpuusage. Well, in this case, I myself fail
> >> > to see the value of the whole cpuusage thing...
> >
> > If I recall, cpuacct was prototyped by Paul Menage (and later modified
> > by Balbir) as a way to demonstrate cgroup controller ..It was one
> > of those "first" cgroups controllers written to demonstrate how cgroups worked.
> >
> > With regard to its value, it does provide a handy interface to measure
> > cpu utilization of cgroups (vs having to manually sum up task's
> > utilization) and afaik libvirt makes use of it (although I
> > don't think anyone reads it at "high" frequency).
> >
>
> Android makes heavy use of cpuacct as well. We invented it to do cpu
> accounting independent of control
But its a massive waste of time to have to iterate a double hierarchy,
cache-miss heaven.
Or so people really have independent cgroups as well? I thought people
just co-mount all this crap.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists