RE: ext4: smp_processor_id() in preemptible

From: Leyendecker, Robert
Date: Sat Nov 28 2009 - 22:03:26 EST




> -----Original Message-----
> From: Tim Blechmann [mailto:tim@xxxxxxxxxx]
> Sent: Friday, November 27, 2009 4:33 AM
> To: Leyendecker, Robert
> Cc: linux-kernel@xxxxxxxxxxxxxxx; linux-ext4@xxxxxxxxxxxxxxx
> Subject: Re: ext4: smp_processor_id() in preemptible
>
> > I have similar crash, but probably different cause-vector, posted on
> this list, fedora bugzilla, rt-users but no response so far from
> anyone. Did you find any work around? I tried looking at smp code for
> hints on problem it looks like in my case it could be trying to
> reschedule work on different CPU at time of crash. However, I admit
> that I could be way, way off on that cause. In my case, if I hammer my
> network interface with packets while another app is reading packets, my
> host locks up and clients are reporting dest unreachables.
> >
> > I don't think I have the problem in non-rt kernel. Have you tried
> booting without smp support?
>
> i haven't tried to reproduce it since then ... it occurred, when i was
> doing some heavy io tasks ...
>
> tim
>
> --
> tim@xxxxxxxxxx
> http://tim.klingt.org
>
> Nothing exists until or unless it is observed. An artist is making
> something exist by observing it. And his hope for other people is that
> they will also make it exist by observing it. I call it 'creative
> observation.' Creative viewing.
> William S. Burroughs

OK - thanks. I'm arriving here via heavy network io, relatively easy to repro in my case.

-Bob
¢éì®&Þ~º&¶¬–+-±éÝ¥Šw®žË±Êâmébžìdz¹Þ)í…æèw*jg¬±¨¶‰šŽŠÝj/êäz¹ÞŠà2ŠÞ¨è­Ú&¢)ß«a¶Úþø®G«éh®æj:+v‰¨Šwè†Ù>Wš±êÞiÛaxPjØm¶Ÿÿà -»+ƒùdš_