Client Based Data Isolation of Blue Whale File System in Non-linear Edit Field

We have designed and implemented the Blue Whale File System (BWFS), a scalable distributed file system for large distributed data-intensive applications. With many of the features as previous distributed file systems, BWFS has successfully met our storage needs and is widely deployed within many fields. In BWFS, like in mainly traditional File Systems, one client can only access data within one file system where the data access interferes with each other which will lead to performance degradations. In this paper we propose a client based data isolation mechanism of Blue Whale File System in Non-linear Edit (NLE) field to separate different data into different file systems. Test result has verified the effectiveness of data isolation. By separating different data into different file system, the application I/O bandwidth is promoted by 111% in average, and the peak performance is improved by 4 times.