Hi, Currently, the readdirp at the dht layer is issued to all the bricks in a sequential manner. This greatly reduces the performance of directory enumeration in large clusters. Hence proposing to make readdirp parallel.
Here is the BZ: https://bugzilla.redhat.com/show_bug.cgi?id=1401812 Design doc: http://review.gluster.org/#/c/16090/ Regards, Poornima
_______________________________________________ Gluster-devel mailing list Gluster-devel@gluster.org http://www.gluster.org/mailman/listinfo/gluster-devel