>> Note that this approach wouldn't solve the problem of load balancing,
>> because a write would be available after successful return only on the
>> producer and on the consumer that processed the request; the other
>> consumers would be updated according to replication schedule, so if the
>> read successive to a write is delegated to another shadow by the load
>> balancer, the write would not be in place yet.
>
> Yes, but in real life most load balancers implement persistence. So the
> read successive to a write will be on the same directory.

True.  Perhaps then the cost to re-master the entry to the requesting node would
be lower than performing the update and subsequent read on the master?

John




-- 
John Madden
UNIX Systems Engineer
Ivy Tech Community College of Indiana
[EMAIL PROTECTED]

Reply via email to