On Tue, Mar 25, 2014 at 11:20 AM, Olivier Bonvalet <ceph.list@xxxxxxxxx> wrote:
>
> Le mardi 25 mars 2014 à 11:04 +0200, Ilya Dryomov a écrit :
>> On Tue, Mar 25, 2014 at 10:39 AM, Olivier Bonvalet <ceph.list@xxxxxxxxx> wrote:
>> > Hi,
>> >
>> > what can/should I do to help fix that problem ?
>> >
>> > for now, RBD kernel client hang on :
>> > Assertion failure in rbd_img_obj_callback() at line 2131:
>> > rbd_assert(which >= img_request->next_completion);
>> >
>> > or on :
>> > Assertion failure in rbd_img_obj_callback() at line 2127:
>> > rbd_assert(img_request != NULL);
>> >
>> >
>> > I have both case at least once per week, on latest 3.13.5 kernels.
>> >
>> > It seems that the problem occurs only on more loaded servers (I have 4
>> > near same servers, and crash occurs on two of them. If I move the VM,
>> > crash follows...).
>>
>> Hi,
>>
>> I'm looking into this, but it doesn't reproduce on my boxes. This must
>> be some sort of race and the fact that there is nothing else in the
>> dmesg right before the splats doesn't help.
>>
>> Can you send me your 3.13.5 rbd.ko and libceph.ko? Also, just so
>> I know, can you build your own kernel?
>>
>> Thanks,
>>
>> Ilya
>>
>
> Thanks for your help. Yes, logs are not very usefull here :( Maybe can I
> enable some debugging informations ?
>
> I add libceph.ko and rbd.ko in attachment. And yes, I can patch and
> build my own kernel. I also add the config file used to compile my
> current kernel, if it can help.
That's great, I'll keep that in mind. Our debug mode is probably waay
too verbose for running it under load on the order of days so for now
I'll try to make as much sense as I can from the .ko and dumps and keep
digging.
Thanks,
Ilya
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
