From: Ingo Molnar <mingo@elte.hu>
To: Andi Kleen <andi@firstfloor.org>
Cc: Arjan van de Ven <arjan@infradead.org>,
linux-kernel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [feature] automatically detect hung TASK_UNINTERRUPTIBLE tasks
Date: Sun, 2 Dec 2007 23:20:40 +0100 [thread overview]
Message-ID: <20071202222040.GA31707@elte.hu> (raw)
In-Reply-To: <20071202211925.GA26414@one.firstfloor.org>
* Andi Kleen <andi@firstfloor.org> wrote:
> > Until now users had little direct recourse to get such problems
> > fixed. (we had sysrq-t, but that included no real metric of how long
> > a task was
>
> Actually task delay accounting can measure this now. iirc someone had
> a latencytop based on it already.
Delay accounting (or the /proc/<PID>/sched fields that i added recently)
only get updated once a task has finished its unreasonably long delay
and has scheduled. So lockups or extremely long delays _wont be
detected_ this way. This is a debugging facility that clearly belongs
into the kernel. Your arguments just make no objective sense.
Ingo
next prev parent reply other threads:[~2007-12-02 22:21 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-01 9:20 [feature] automatically detect hung TASK_UNINTERRUPTIBLE tasks Ingo Molnar
2007-12-01 18:31 ` David Rientjes
2007-12-01 18:33 ` Ingo Molnar
2007-12-01 18:42 ` David Rientjes
2007-12-01 19:36 ` Ingo Molnar
2007-12-02 0:54 ` Ingo Oeser
2007-12-02 8:58 ` Ingo Molnar
2007-12-02 15:52 ` David Rientjes
2007-12-02 18:57 ` Andi Kleen
2007-12-02 18:59 ` Ingo Molnar
2007-12-02 19:41 ` Arjan van de Ven
2007-12-02 20:08 ` Ingo Molnar
2007-12-02 20:09 ` Andi Kleen
2007-12-02 20:26 ` Ingo Molnar
2007-12-02 20:47 ` Andi Kleen
2007-12-02 21:10 ` Ingo Molnar
2007-12-02 21:19 ` Andi Kleen
2007-12-02 21:24 ` Ingo Molnar
2007-12-02 21:34 ` Andi Kleen
2007-12-02 22:25 ` Ingo Molnar
2007-12-02 22:18 ` Arjan van de Ven
2007-12-02 22:20 ` Ingo Molnar [this message]
2007-12-03 0:00 ` Andi Kleen
2007-12-02 22:43 ` Arjan van de Ven
2007-12-03 0:07 ` Andi Kleen
2007-12-03 0:59 ` Arjan van de Ven
2007-12-03 9:55 ` Andi Kleen
2007-12-03 10:15 ` Radoslaw Szkodzinski
2007-12-03 10:23 ` Ingo Molnar
2007-12-03 10:27 ` Andi Kleen
2007-12-03 10:38 ` Ingo Molnar
2007-12-03 11:04 ` Andi Kleen
2007-12-03 11:59 ` Ingo Molnar
2007-12-03 12:13 ` Andi Kleen
2007-12-03 12:28 ` Ingo Molnar
2007-12-03 12:41 ` Andi Kleen
2007-12-03 13:00 ` Ingo Molnar
2007-12-03 13:14 ` Andi Kleen
[not found] ` <20071203132955.GA31354@elte.hu>
2007-12-03 13:41 ` Radoslaw Szkodzinski
2007-12-03 13:59 ` Ingo Molnar
2007-12-03 14:15 ` Andi Kleen
2007-12-03 13:48 ` Andi Kleen
2007-12-03 13:55 ` Ingo Molnar
2007-12-03 14:17 ` Andi Kleen
2007-12-03 14:33 ` Ingo Molnar
2007-12-03 17:02 ` Ray Lee
2007-12-03 13:50 ` Pekka Enberg
2007-12-03 13:57 ` Ingo Molnar
2007-12-03 14:14 ` Andi Kleen
2007-12-03 14:19 ` Ingo Molnar
2007-12-03 17:57 ` Andrew Morton
2007-12-03 18:28 ` Rafael J. Wysocki
2007-12-03 19:24 ` Ingo Molnar
2007-12-03 22:47 ` Rafael J. Wysocki
2007-12-04 0:05 ` Ingo Molnar
2007-12-03 15:23 ` Arjan van de Ven
2007-12-03 16:36 ` Andi Kleen
2007-12-05 22:31 ` Mark Lord
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=20071202222040.GA31707@elte.hu \
--to=mingo@elte.hu \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=arjan@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
/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.