[Gluster-devel] solutions for split brain situation

[Anand Avati]

>> Now, if your system is going down - no removal of the volume - and it
>> comes back up with the behaviour you describe, then I am very concerned
>> as well.
>
> I can tell you for sure that this is the case, we fell into this hole already
> twice, shot down around 14 days of logs (half of course because of the
> distributing file access).
> This is really a hotspot that should be dealt with as soon as possible. The
> only current solution is to delete everything before re-adding volumes.

Can you please describe the exact steps you followed to reproduce this
situation? If just one server goes down and comes back, it should not
be resulting in a split brain situation. And if it indeed resulted in
a split brain situation, it would not heal unless you specified the
favorite child option (which comes with an elaborate warning). Is it
that in your situation you indeed specified a favorite child and it
got used in a wrongly diagnosed split brain?

A bug report with the debug logs and steps to reproduce will be
greatly appreciated.

Avati