On Thu, Jan 1, 2009 at 1:59 AM, Martin Fick <[email protected]> wrote:
> I am a bit curious about the new HA translator and how it it supposed to 
> work?  I have looked through the code a bit and this is my naive 
> interpretation of the way it is designed:
>
> It appears that the HA translator keeps track of its subvolumes and whether 
> they are active or not.  When attempting to dispatch a request, it picks a 
> currently active subvolume or fails if none are currently active.  It appears 
> that once it has chosen an active subvolume for a request, it can no longer 
> fail over to another subvolume for that particular request, is this true?  If 
> so, then it is possible (perhaps likely) that during failovers some requests 
> will fail before failover happens even if certain subvolumes never go down?  
> :(   Is this correct or am I missing something?

No. Requests are retried on the next subvolume if the current one goes
down during the operation, so it should work fine.

Krishna


_______________________________________________
Gluster-devel mailing list
[email protected]
http://lists.nongnu.org/mailman/listinfo/gluster-devel

Reply via email to