Messages in this thread |  | | | Date | Mon, 17 Mar 2008 08:23:25 +0100 | | From | Jens Axboe <> | | Subject | Re: Linux 2.6.25-rc4 | |
On Sun, Mar 16 2008, Bartlomiej Zolnierkiewicz wrote:
> On Sunday 16 March 2008, Bartlomiej Zolnierkiewicz wrote:
>
> [...]
>
> > I think that we are looking into completely wrong direction...
>
> Alt-SysRq-T traces that Anders posted shows that the system hangs inside
> block layer, if not clearing DRQ would be the case we should see system
> getting stuck inside IDE (or at least IDE commands timing out)...
The bisect ends up pointing at IDE bits everytime, plus it's io
scheduler independent. So I don't think a generic issue is very likely.
> I really do think that it is the same hang-in-block-layer issue that
> Ingo managed to hit once (his system was using libata)...
There's no data to back any such conclusion up, that would be extremely
hand wavy (at best).
Ingo hit a hang in one boot out of hundreds to thousands. Anders can
reproduce easily, should be easy enough to narrow down.
--
Jens Axboe
|  |