[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20120208092331.GA24625@quack.suse.cz>
Date: Wed, 8 Feb 2012 10:23:31 +0100
From: Jan Kara <jack@...e.cz>
To: Wolfram Gloger <wmglo@...t.med.uni-muenchen.de>
Cc: jack@...e.cz, linux-kernel@...r.kernel.org
Subject: Re: Soft lockup problem
On Wed 08-02-12 00:16:15, Wolfram Gloger wrote:
> Thanks for your response.
>
> > From: Jan Kara <jack@...e.cz>
>
> > Hmm, then this isn't really a deadlock (at least in your case) but only a
> > rather unresponsive system.
>
> Well, like the subject says this is a "soft lockup"..
We differ in terminology a bit but that's not really important when I
know what you mean :)
> When it happened the first time the system actually recovered
> after some hours.
> But like Gerard said, there is no apparent ground for this
> unresponsiveness, there are tons of memory free and no swapping.
Yeah, interesting. There are no processes waiting for IO either so I'm
puzzled what causes you problems.
> > Looking at the backtraces you provided I don't
> > see anything really suspicious. Only maybe fsnotify_mark process - do you
> > use fsnotify?
>
> I have configured CONFIG_FSNOTIFY=y indeed but don't think I'm using it
> from userspace..
Well, apparently something uses it because fsnotify_mark thread is just
in the process of destroying some mark. Maybe you could run with
CONFIG_FSNOTIFY=n just to rule out some problems there...
Honza
--
Jan Kara <jack@...e.cz>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists