[Gluster-devel] AFR problem with 2.0rc4

[Vikas Gorur]

2009/3/19 Gordan Bobic <gordan at bobich.net>:
> That's unavoidable to some extent, since the first server is the one that
> is authoritative for locking. That means that all reads have to make a hit
> on the 1st server, even if the data then gets retrieved from another server
> in the cluster. Whether that explains all of the disparity you are seing, I
> don't know.

Not really. There is no need for locking while doing reads. Currently
replicate will use the read-subvolume if specified, and the first
available node if the option is not specified. Read load-balancing is
in the pipeline, but it needs some other code changes to be
implemented first.

Vikas
-- 
Engineer - Z Research
http://gluster.com/