multi-replication in distributed system

["Wang Yu" <wangyuict@xxxxxxxxx>]

Hi, all

Recent distributed systems usually adopt object-based storage, and 
every object has several replications to avoid data loss. When several
clients access the same file concurrently, are there some algorithms to
improve read performace using replications? Some references are
prefered!

Best regards!

-- 
National Research Center for Intelligent Computing Systems
Institute of Computing Technology, Chinese Academy of Sciences