[Gluster-devel] solutions for split brain situation

[Mark Mielke]

On 09/17/2009 11:52 PM, Michael Cassaniti wrote:
>
>
>     This could mean that GlusterFS is too lax with regard to
>     consistency guarantees. If files can appear in the background, and
>     magically be shown - this indicates that GlusterFS is not
>     enforcing use through the mount point, which introduces the
>     potential for inconsistent or faulty results. You are asking for
>     it to guess what you want, without seeing that what you are asking
>     for is incompatible with provisions for any guarantee of a
>     consistent view. That "it works" is actually more concerning to me
>     that justifying over your position. To me it says it's one more
>     potential problem that I might hit in the future. A file that
>     should be removed magically re-appears - how is this a good thing?
>
>
> I guess the last question is a good one for the developers. If the 
> required extended attributes do not exist on the backend, should the 
> files/directories (excluding the root directory) show in a stat() 
> call? That may be a blessing or curse for new users, especially when 
> this post has been going on about automatic creation of extended 
> attributes for pre-existing files in the backend.

Yep - exactly. Personally, I prefer correct behaviour over some one-time 
benefit of being able to mount on top of existing file store and have it 
do its best to automatically create extended attributes or treat files 
without extended attributes as files that exist.

When reading the GlusterFS replication description - it seemed like they 
discussed what happens if a node goes down *during* the unlink(), but 
they didn't specifically cover what happens if the node is down before 
and after the unlink(), but then brought back up some time later. One 
interpretation suggested to me that the journal would not hang around, 
and the file would be treated as gone from all "up" nodes, and then when 
the later node is brought back up, the file shows up as existing on only 
one node, and the self-heal would kick in and replicate the file as if 
it still exists. I didn't find the time to test this exact scenario yet, 
though...

Cheers,
mark

-- 
Mark Mielke<mark at mielke.cc>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-devel/attachments/20090918/231428b8/attachment-0003.html>