proliant server lockups with freebsd-amd64-stable (2010-03-10)

[Alexander Motin]

Kai Gallasch wrote:
> Am Fri, 12 Mar 2010 20:38:31 +0200
> schrieb Alexander Motin <mav at FreeBSD.org>:
>> Pawel Jakub Dawidek wrote:
>>> I was analizing similar problem as potential ZFS bug. It turned out
>>> to be bug in ciss(4) and I believe mav@ (CCed) has fix for that.
>> That my patch is already at 8-STABLE since r204873 of 2010-03-08. Make
>> sure you have it.
> 
> Updating collection src-all/cvs
> ..
> ..
>  Edit src/sys/dev/ciss/ciss.c
>  Edit src/sys/dev/ciss/cissvar.h
> 
> Didn't have it! Must have been just a few hours I missed it,
> when I built the last kernel. So I will rebuild my kernel and
> give it a spin later on.
> 
>> In this case trap stopped process at ciss_get_request(), which indeed
>> called holding cissmtx lock. But there is no place to sleep or loop
>> there, so may be it was just spontaneous. With bugs I was fixing there
>> was a chance to loop indefinitely between ciss and CAM on resource
>> constraint. That increases chance for such situation to be caught.
>>
>> You may try also look what's going on with `top -HS` and `systat -vm
>> 1`.
> 
> FYI. Without your patch of ciss.c and cissvar.h a lockup with top -HS
> and systat -vm running gives following information below. Is there a
> pattern visible relating to your patch of the ciss driver?

May be. You should try,

-- 
Alexander Motin