[stgt] tgtd segfault during heavy I/O

[Andy Grover]

On 09/20/2011 06:58 PM, Kiefer Chang wrote:
> Dear Andy,
> 
> Yes, It's the way I used for each LUN.
> 
> Unfortunately the issue still exists, but ``harder`` to reproduce.
> 
> Symptoms are:
> (1) segfault
> (2) tgtd CPU 100% , block when iterating a list.

I think we need some locking, maybe a mutex around each element in the
itn->cmd_hash_list. The list is being modified by multiple threads,
unless I'm missing something.

I'll work on a patch and hopefully test & post it tomorrow.

Regards -- Andy

> 
> --
> Best Regards,
> Kiefer
> 
> 2011/9/21 Andy Grover <agrover at redhat.com>:
>> On 07/16/2011 05:05 AM, Kiefer Chang wrote:
>>> Dear Tomonori,
>>>
>>> I will try it. Thanks!
>>>
>>> By the way, using single thread for each LUN seems avoid the symptom
>>> (at least before weekend...)
>>> I will report if there are any progresses.
>>
>> Hello Kiefer,
>>
>> You're saying setting NR_WORKER_THREADS to 1 fixed the issue for you? Is
>> that how you used a single thread for each LUN?
>>
>> Thanks -- Regards -- Andy
>>

--
To unsubscribe from this list: send the line "unsubscribe stgt" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html