[Gluster-devel] AFR Replication

[gordan at bobich.net]

On Fri, 18 Apr 2008, Christopher Hawkins wrote:

>> I can see that it's less of an issue than block-level
>> split-brain, because this would at most lead to the odd file
>> getting corrupted, whereas block-level split-brain would
>> destroy the entire FS very quickly.
>
> Good distinction. You are certainly right that there are
> more possibilities for split brain than I am thinking of, but wouldn't
> the worst case scenario be that two versions of the same file(s) are
> getting written, and then when you sync only one of them will remain?

Yes, that's right.

> In that case you have no corruption, just lost changes on the file that got
> tossed.

The line dividing data loss and data corruption is a hazy one, and both 
are certainly something to be avoided at all cost.

> I'm not sure that corruption is out of the question, just thinking out loud.

Since it's all file based, the FS, in theory, cannot get corrupted any 
more than it can with, say, NFS. GlusterFS, from what I have seen so far 
in my extremely limited experience of it (2 days so far) seems to have 
much more in common with network file systems than it has with cluster 
file systems.

Gordan