From: Oleg Nesterov <oleg@redhat.com>
To: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Shailabh Nagar <nagar1234@in.ibm.com>,
Andrew Morton <akpm@linux-foundation.org>,
Venkatesh Pallipadi <venki@google.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Suresh Siddha <suresh.b.siddha@intel.com>,
John stultz <johnstul@us.ibm.com>,
Thomas Gleixner <tglx@linutronix.de>,
Balbir Singh <balbir@linux.vnet.ibm.com>,
Ingo Molnar <mingo@elte.hu>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 09/10] taskstats: Fix exit CPU time accounting
Date: Sun, 26 Sep 2010 20:11:27 +0200 [thread overview]
Message-ID: <20100926181127.GA26985@redhat.com> (raw)
In-Reply-To: <1285330688.2179.305.camel@holzheu-laptop>
Hi,
On 09/24, Michael Holzheu wrote:
>
> On Thu, 2010-09-23 at 19:10 +0200, Oleg Nesterov wrote:
> >
> > On 09/23, Michael Holzheu wrote:
> > >
> > > Currently there are code pathes (e.g. for kthreads) where the consumed
> > > CPU time is not accounted to the parents cumulative counters.
> >
> > Could you explain more?
>
> I think one place was "khelper" (kmod.c). It is created with
> kernel_thread() and it exits without having accounted the times with
> sys_wait() to the parent's ctimes
No. Well yes, it is not accounted, but this is not because it is
kthread.
To simplify the discussion, lets talk about utime/cutime only,
and lets forget about the multithreading.
It is very simple, currently linux accounts the exiting task's
utime and adds its to ->cutime _only_ if parent does do_wait().
If parent ignores SIGCHLD, the child reaps itself and it is not
accounted.
I do not know why it was done this way, but I'm afraid we can't
change this historical behaviour.
> Ok, the problem is that I did not consider exiting threads that are no
> thread group leaders. When they exit the ctime of the parent is not
> updated. Instead the time is accumulated in the signal struct.
I think I am a bit confused, but see above. With or without threads
the whole process can exit without accounting.
Oleg.
next prev parent reply other threads:[~2010-09-26 18:15 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-23 13:48 [RFC][PATCH 00/10] taskstats: Enhancements for precise accounting Michael Holzheu
2010-09-23 14:00 ` [RFC][PATCH 01/10] taskstats: Use real microsecond granularity for CPU times Michael Holzheu
2010-10-07 5:08 ` Balbir Singh
2010-10-08 15:08 ` Michael Holzheu
2010-10-08 16:39 ` Balbir Singh
2010-09-23 14:01 ` [RFC][PATCH 02/10] taskstats: Separate taskstats commands Michael Holzheu
2010-09-27 9:32 ` Balbir Singh
2010-10-11 7:40 ` Balbir Singh
2010-09-23 14:01 ` [RFC][PATCH 03/10] taskstats: Split fill_pid function Michael Holzheu
2010-09-23 17:33 ` Oleg Nesterov
2010-09-27 9:33 ` Balbir Singh
2010-10-11 8:31 ` Balbir Singh
2010-09-23 14:01 ` [RFC][PATCH 04/10] taskstats: Add new taskstats command TASKSTATS_CMD_ATTR_PIDS Michael Holzheu
2010-09-23 14:01 ` [RFC][PATCH 05/10] taskstats: Add "/proc/taskstats" Michael Holzheu
2010-09-23 14:01 ` [RFC][PATCH 06/10] taskstats: Add thread group ID to taskstats structure Michael Holzheu
2010-09-23 14:01 ` [RFC][PATCH 07/10] taskstats: Add per task steal time accounting Michael Holzheu
2010-09-23 14:02 ` [RFC][PATCH 08/10] taskstats: Add cumulative CPU time (user, system and steal) Michael Holzheu
2010-09-23 14:02 ` [RFC][PATCH 09/10] taskstats: Fix exit CPU time accounting Michael Holzheu
2010-09-23 17:10 ` Oleg Nesterov
2010-09-24 12:18 ` Michael Holzheu
2010-09-26 18:11 ` Oleg Nesterov [this message]
2010-09-27 13:23 ` Michael Holzheu
2010-09-27 13:42 ` Martin Schwidefsky
2010-09-27 16:51 ` Oleg Nesterov
2010-09-28 7:09 ` Martin Schwidefsky
2010-09-29 19:19 ` Roland McGrath
2010-09-30 13:47 ` Michael Holzheu
2010-10-05 8:57 ` Roland McGrath
2010-10-06 9:29 ` Michael Holzheu
2010-10-06 15:26 ` Oleg Nesterov
2010-10-07 15:06 ` Michael Holzheu
2010-10-11 12:37 ` Oleg Nesterov
2010-10-12 13:10 ` Michael Holzheu
2010-10-14 13:47 ` Oleg Nesterov
2010-10-15 14:34 ` Michael Holzheu
2010-10-19 14:17 ` Oleg Nesterov
2010-10-22 16:53 ` Michael Holzheu
2010-09-28 8:36 ` Balbir Singh
2010-09-28 9:08 ` Martin Schwidefsky
2010-09-28 9:23 ` Balbir Singh
2010-09-28 10:36 ` Martin Schwidefsky
2010-09-28 10:39 ` Balbir Singh
2010-09-28 8:21 ` Balbir Singh
2010-09-28 16:50 ` Michael Holzheu
2010-09-23 14:04 ` [RFC][PATCH 10/10] taststats: User space with ptop tool Michael Holzheu
2010-09-23 20:11 ` [RFC][PATCH 00/10] taskstats: Enhancements for precise accounting Andrew Morton
2010-09-23 22:11 ` Matt Helsley
2010-09-24 12:39 ` Michael Holzheu
2010-09-25 18:19 ` Serge E. Hallyn
2010-09-24 9:10 ` Michael Holzheu
2010-09-24 18:50 ` Andrew Morton
2010-09-27 9:18 ` Michael Holzheu
2010-09-27 20:02 ` Andrew Morton
2010-09-28 8:17 ` Balbir Singh
2010-09-27 10:49 ` Balbir Singh
2010-09-24 9:16 ` Balbir Singh
2010-09-30 8:38 ` Andi Kleen
2010-09-30 13:56 ` Michael Holzheu
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=20100926181127.GA26985@redhat.com \
--to=oleg@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=heiko.carstens@de.ibm.com \
--cc=holzheu@linux.vnet.ibm.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=nagar1234@in.ibm.com \
--cc=schwidefsky@de.ibm.com \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
--cc=venki@google.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).