[Gluster-devel] regression burn-in summary over the last 7 days

[Milind Changire]

On 08/04/2016 05:40 PM, Kaleb KEITHLEY wrote:
> On 08/04/2016 08:07 AM, Niels de Vos wrote:
>> On Thu, Aug 04, 2016 at 12:00:53AM +0200, Niels de Vos wrote:
>>> On Wed, Aug 03, 2016 at 10:30:28AM -0400, Vijay Bellur wrote:
>>> ....
>> ...
>>>> ./tests/bugs/gfapi/bug-1093594.t ; Failed 1 times
>>>>     Regression Links:
>>>> https://build.gluster.org/job/regression-test-burn-in/1423/consoleFull
>>>
>>> I have not seen this fail yet... All gfapi tests are running in a loop
>>> on a test-system now, we'll see if it reproducible in a few days or so.
>>
>> It seems that glfs_fini() returns -1 every now and then (once after 1027
>> iterations, once after 287). Some of the gfapi test cases actually
>> succeed their intended test, but still return an error when glfs_fini()
>> fails. I am tempted to just skip this error in most tests and have only
>> tests/basic/gfapi/libgfapi-fini-hang error out on it. (Obviously also
>> intend to fix the failure.)
>
> If you fix the bug in glfs_fini() then it should not be necessary to
> ignore the failure in the tests, right?
>
> Just fix the bug, don't hack the test.
>
> --
>
> Kaleb
>


I've faced similar issues with glfs_fini() while working on the bareos
integration. When using a libgfapi built with --enable-debug, an assert
causes the process to dump core.

https://bugzilla.redhat.com/show_bug.cgi?id=1233136 may be worth addressing.

Milind