From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Eric Dumazet <dada1@cosmosbay.com>
Cc: Prarit Bhargava <prarit@redhat.com>,
Rick Lindsley <ricklind@us.ibm.com>,
john stultz <johnstul@us.ibm.com>, Ingo Molnar <mingo@elte.hu>,
Linux Kernel <linux-kernel@vger.kernel.org>,
virtualization@lists.osdl.org, Paul Mackerras <paulus@samba.org>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
Thomas Gleixner <tglx@linutronix.de>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [patch 1/2] Ignore stolen time in the softlockup watchdog
Date: Tue, 27 Mar 2007 00:12:53 -0700 [thread overview]
Message-ID: <4608C3F5.1030106@goop.org> (raw)
In-Reply-To: <4608C121.4050309@cosmosbay.com>
Eric Dumazet wrote:
> Jeremy Fitzhardinge a écrit :
>
>> +static DEFINE_PER_CPU(unsigned long long, touch_timestamp);
>
> ...
>
>> void touch_softlockup_watchdog(void)
>> {
>> - __raw_get_cpu_var(touch_timestamp) = jiffies;
>> + __raw_get_cpu_var(touch_timestamp) = sched_clock();
>> }
>
> Not very clear if this is safe on 32bit, since this is not anymore
> atomic.
Hm, good point. Don't think it matters very much. These values are
per-cpu, and if an interrupt happens between the word updates and the
intermediate values causes a timeout, then it was pretty marginal
anyway. I guess the worst case is if the low-word gets written first,
and it goes from a high value to low, then it could be sampled as if
time had gone back by up to ~4 seconds.
I'll give it another look.
J
WARNING: multiple messages have this Message-ID (diff)
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Eric Dumazet <dada1@cosmosbay.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Linux Kernel <linux-kernel@vger.kernel.org>,
virtualization@lists.osdl.org, Ingo Molnar <mingo@elte.hu>,
Thomas Gleixner <tglx@linutronix.de>,
john stultz <johnstul@us.ibm.com>,
Zachary Amsden <zach@vmware.com>,
James Morris <jmorris@namei.org>, Dan Hecht <dhecht@vmware.com>,
Paul Mackerras <paulus@samba.org>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
Prarit Bhargava <prarit@redhat.com>,
Chris Lalancette <clalance@redhat.com>,
Rick Lindsley <ricklind@us.ibm.com>
Subject: Re: [patch 1/2] Ignore stolen time in the softlockup watchdog
Date: Tue, 27 Mar 2007 00:12:53 -0700 [thread overview]
Message-ID: <4608C3F5.1030106@goop.org> (raw)
In-Reply-To: <4608C121.4050309@cosmosbay.com>
Eric Dumazet wrote:
> Jeremy Fitzhardinge a écrit :
>
>> +static DEFINE_PER_CPU(unsigned long long, touch_timestamp);
>
> ...
>
>> void touch_softlockup_watchdog(void)
>> {
>> - __raw_get_cpu_var(touch_timestamp) = jiffies;
>> + __raw_get_cpu_var(touch_timestamp) = sched_clock();
>> }
>
> Not very clear if this is safe on 32bit, since this is not anymore
> atomic.
Hm, good point. Don't think it matters very much. These values are
per-cpu, and if an interrupt happens between the word updates and the
intermediate values causes a timeout, then it was pretty marginal
anyway. I guess the worst case is if the low-word gets written first,
and it goes from a high value to low, then it could be sampled as if
time had gone back by up to ~4 seconds.
I'll give it another look.
J
next prev parent reply other threads:[~2007-03-27 7:12 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-27 5:38 [patch 0/2] softlockup watchdog improvements Jeremy Fitzhardinge
2007-03-27 5:38 ` Jeremy Fitzhardinge
2007-03-27 5:38 ` [patch 1/2] Ignore stolen time in the softlockup watchdog Jeremy Fitzhardinge
2007-03-27 7:00 ` Eric Dumazet
2007-03-27 7:12 ` Jeremy Fitzhardinge [this message]
2007-03-27 7:12 ` Jeremy Fitzhardinge
2007-03-27 7:50 ` Eric Dumazet
2007-03-27 7:50 ` Eric Dumazet
2007-03-27 14:39 ` Prarit Bhargava
2007-03-27 14:39 ` Prarit Bhargava
2007-03-27 16:37 ` Jeremy Fitzhardinge
2007-03-27 16:53 ` Prarit Bhargava
2007-03-27 16:53 ` Prarit Bhargava
2007-03-27 17:10 ` Jeremy Fitzhardinge
2007-03-27 17:10 ` Jeremy Fitzhardinge
2007-03-27 17:20 ` Prarit Bhargava
2007-03-27 17:20 ` Prarit Bhargava
2007-03-27 5:38 ` [patch 2/2] percpu enable flag for " Jeremy Fitzhardinge
2007-03-27 5:38 ` Jeremy Fitzhardinge
2007-03-27 14:42 ` Prarit Bhargava
2007-03-27 14:42 ` Prarit Bhargava
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=4608C3F5.1030106@goop.org \
--to=jeremy@goop.org \
--cc=akpm@linux-foundation.org \
--cc=dada1@cosmosbay.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=prarit@redhat.com \
--cc=ricklind@us.ibm.com \
--cc=schwidefsky@de.ibm.com \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.osdl.org \
/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.