[Gluster-users] Small File and "ls" performance ..

[mki-glusterfs at mozone.net]

On Wed, May 05, 2010 at 01:00:40AM -0500, Tejas N. Bhise wrote:
> selective readdirp - http://patches.gluster.com/patch/3203/
> dht lookup revalidation optimization - http://patches.gluster.com/patch/3204/
> updated write-behind default values - http://patches.gluster.com/patch/3223/
 
While digging through the 3.0.5 source tree, I noticed that patch 3204
didn't make it in there.. Was there a reason for this or is there a plan
to have this patch in a future release?

Also, does the selecting readdirp require that the backend bricks also
be running a version of glusterfs that has the feature?  For instance if
the backends are running 3.0.4, but the clients are running 3.0.5, will
the readdirp feature work as advertised?

Thanks.