Hi, A feature page for improved rebalance performance is put up here, http://www.gluster.org/community/documentation/index.php/Features/improve_rebalance_performance
This mail is a request for comments and further ideas in this regard. In short this aims at improving the existing rebalance performance in a few ways, so as to help the cluster grow or shrink faster than the current mechanism. This takes off from the existing rebalance logic, and adds better resource utilization possibilities for rebalance, by driving more IO and network throughput and reducing the crawl width of rebalance as it stands today. It also touches upon a rebalance on access like mechanism where we could potentially, move data out of existing bricks to a newer brick faster, in the case of brick addition, and vice versa for brick removal, and heal the rest of the data on access. This mail is a request for comments and further ideas in this regard. Current state of development is at the prototyping stage, so nothing is certain to provide the improvements unless tested :) Regards, Shyam _______________________________________________ Gluster-devel mailing list Gluster-devel@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel
