All of lore.kernel.org
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@parallels.com>
To: Paul Turner <pjt@google.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	cgroups@vger.kernel.org,
	linux-kernel <linux-kernel@vger.kernel.org>,
	devel@openvz.org, Linux Containers <containers@lists.osdl.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Balbir Singh <bsingharora@gmail.com>,
	Serge Hallyn <serge.hallyn@canonical.com>,
	Frederic Weisbecker <fweisbec@gmail.com>
Subject: How to draw values for /proc/stat
Date: Mon, 5 Dec 2011 07:32:33 -0200	[thread overview]
Message-ID: <4EDC8FB1.60407@parallels.com> (raw)

Hi,

Specially Peter and Paul, but all the others:

As you can see in https://lkml.org/lkml/2011/12/4/178, and in my answer 
to that, there is a question - one I've asked before but without that 
much of an audience - of whether /proc files read from process living on 
cgroups should display global or per-cgroup resources.

In the past, I was arguing for a knob to control that, but I recently 
started to believe that a knob here will only overcomplicate matters:
if you live in a cgroup, you should display only the resources you can 
possibly use. Global is for whoever is in the main cgroup.

Now, it comes two questions:
1) Do you agree with that, for files like /proc/stat ? I think the most 
important part is to be consistent inside the system, regardless of what 
is done

2) Will cpuacct stay? I think if it does, that becomes almost mandatory 
(at least the bind mount idea is pretty much over here), because drawing 
value for /proc/stat becomes quite complex.
The cpuacct cgroup can provide user, sys, etc values. But we also have:

* nr_context_switches,
* jiffies since boot,
* total_forks,
* nr_running,
* nr_iowait,

Now I doubt any of us want to see /proc/stat extended to accommodate 
things like nr_context_switches, or even worse, nr_running. The way I 
see it, there are two options here:

  a) moving everything to cpu cgroup so we keep all values being drawn
     from the same place
  b) Collect that info from multiple places in a transparent way. ctx,
     nr_running and nr_iowait will probably come from cpu. jiffies can
     come from wherever, and maybe we can even draw total_forks
     from Frederic's and avoid counting it twice.

WARNING: multiple messages have this Message-ID (diff)
From: Glauber Costa <glommer@parallels.com>
To: Paul Turner <pjt@google.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	<cgroups@vger.kernel.org>,
	linux-kernel <linux-kernel@vger.kernel.org>, <devel@openvz.org>,
	Linux Containers <containers@lists.osdl.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Balbir Singh <bsingharora@gmail.com>,
	Serge Hallyn <serge.hallyn@canonical.com>,
	Frederic Weisbecker <fweisbec@gmail.com>
Subject: How to draw values for /proc/stat
Date: Mon, 5 Dec 2011 07:32:33 -0200	[thread overview]
Message-ID: <4EDC8FB1.60407@parallels.com> (raw)

Hi,

Specially Peter and Paul, but all the others:

As you can see in https://lkml.org/lkml/2011/12/4/178, and in my answer 
to that, there is a question - one I've asked before but without that 
much of an audience - of whether /proc files read from process living on 
cgroups should display global or per-cgroup resources.

In the past, I was arguing for a knob to control that, but I recently 
started to believe that a knob here will only overcomplicate matters:
if you live in a cgroup, you should display only the resources you can 
possibly use. Global is for whoever is in the main cgroup.

Now, it comes two questions:
1) Do you agree with that, for files like /proc/stat ? I think the most 
important part is to be consistent inside the system, regardless of what 
is done

2) Will cpuacct stay? I think if it does, that becomes almost mandatory 
(at least the bind mount idea is pretty much over here), because drawing 
value for /proc/stat becomes quite complex.
The cpuacct cgroup can provide user, sys, etc values. But we also have:

* nr_context_switches,
* jiffies since boot,
* total_forks,
* nr_running,
* nr_iowait,

Now I doubt any of us want to see /proc/stat extended to accommodate 
things like nr_context_switches, or even worse, nr_running. The way I 
see it, there are two options here:

  a) moving everything to cpu cgroup so we keep all values being drawn
     from the same place
  b) Collect that info from multiple places in a transparent way. ctx,
     nr_running and nr_iowait will probably come from cpu. jiffies can
     come from wherever, and maybe we can even draw total_forks
     from Frederic's and avoid counting it twice.

             reply	other threads:[~2011-12-05  9:32 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-05  9:32 Glauber Costa [this message]
2011-12-05  9:32 ` How to draw values for /proc/stat Glauber Costa
     [not found] ` <4EDC8FB1.60407-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2011-12-06  0:05   ` KAMEZAWA Hiroyuki
2011-12-06  0:05     ` KAMEZAWA Hiroyuki
     [not found]     ` <20111206090543.e72128b6.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2011-12-06  0:17       ` Glauber Costa
2011-12-06  0:17         ` Glauber Costa
2011-12-07 14:17   ` Zhu Yanhai
2011-12-07 14:17     ` Zhu Yanhai
2011-12-09 14:07     ` Peter Zijlstra
2011-12-09 14:03   ` Peter Zijlstra
2011-12-09 14:03     ` Peter Zijlstra
2011-12-09 14:55     ` Glauber Costa
2011-12-09 14:55       ` Glauber Costa
     [not found]       ` <4EE22179.5090106-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2011-12-11 14:50         ` Glauber Costa
2011-12-11 14:50           ` Glauber Costa
     [not found]           ` <4EE4C350.90509-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2011-12-11 19:11             ` KOSAKI Motohiro
2011-12-11 19:11               ` KOSAKI Motohiro
     [not found]               ` <4EE5006F.6070604-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2011-12-11 20:48                 ` Glauber Costa
2011-12-11 20:48                   ` Glauber Costa
2011-12-12  0:31             ` KAMEZAWA Hiroyuki
2011-12-12  0:31               ` KAMEZAWA Hiroyuki
     [not found]               ` <20111212093116.96537551.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2011-12-12  7:06                 ` Glauber Costa
2011-12-12  7:06                   ` Glauber Costa
     [not found]                   ` <4EE5A7FA.8050707-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2011-12-12  8:22                     ` Glauber Costa
2011-12-12  8:22                       ` Glauber Costa
2011-12-12  9:33         ` Peter Zijlstra
2011-12-12  9:33           ` Peter Zijlstra
2011-12-12  9:35           ` Glauber Costa
2011-12-12  9:35             ` Glauber Costa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4EDC8FB1.60407@parallels.com \
    --to=glommer@parallels.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=bsingharora@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=containers@lists.osdl.org \
    --cc=devel@openvz.org \
    --cc=fweisbec@gmail.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pjt@google.com \
    --cc=serge.hallyn@canonical.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.