On 17/04/2013, at 9:05 AM, Jiang Long wrote: > In this page（http://community.gluster.org/q/do-glusterfs-have-something-like-network-raid-like-in-hadoopdfs/）; > “There's already an academic group working on an erasure-coding translator, which would actually be a leap beyond the erasure coding implemented for HDFS[1] ”Mr Darcy says. > anyone knows the academic group，would you please give me some clues? Managed to grab Jeff and ask him for you. The details are: ********************************************************** On 17/04/2013, at 1:17 PM, Jeff Darcy wrote: > Actually it turns out it's not an academic group. The company is called > Datalab, they're in Spain, the translator is called "disperse" and > there's a presentation about it here. > > http://www.gluster.org/community/documentation/images/b/bb/Disperse_Xlator_Ramon_Datalab.pdf > > They've even posted code, but I haven't had a chance to test it yet. > > https://github.com/datalab-bcn/glusterfs-ida ********************************************************** Hopefully that's helpful. :) Regards and best wishes, Justin Clift -- Open Source and Standards @ Red Hat twitter.com/realjustinclift
