LKML Archive on
help / color / mirror / Atom feed
From: Ingo Molnar <>
To: Andrew Morton <>
Cc: Lukasz Trabinski <>,,
	Bartlomiej Solarz-Niesluchowski <>,
	Thomas Gleixner <>
Subject: Re: 2.6.20 BUG: soft lockup detected on CPU#0!
Date: Thu, 8 Feb 2007 09:06:44 +0100	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

* Andrew Morton <> wrote:

> The softlock detector has a long history of false positives and 
> precious few true positives, in my experience.

hm, not so the latest & lamest in my experience. The commit that made it 
quite robust was 6687a97d4041f996f725902d2990e5de6ef5cbe5, as of March 
2006, and first showed up in 2.6.17. (OTOH, since the merge of lockdep 
the main source of soft lockups in the field has been quite severely 
reduced. Nevertheless it's still good to have it around, occasionally 
there happen other types of soft lockups too, in open-coded loops, etc.)


  reply	other threads:[~2007-02-08  8:07 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-07 23:02 Lukasz Trabinski
2007-02-08  4:47 ` Andrew Morton
2007-02-08  8:06   ` Ingo Molnar [this message]
2007-02-08  8:15     ` Andrew Morton
2007-02-08  9:16     ` Eric Dumazet
2007-02-08  9:56       ` Ingo Molnar
2007-02-08 10:12         ` Andrew Morton
2007-02-08 15:51   ` Lukasz Trabinski

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:

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

  git send-email \ \ \ \ \ \ \ \
    --subject='Re: 2.6.20 BUG: soft lockup detected on CPU#0'\!'' \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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).