SYEL: Simple Yet Efficient Locally Repairable Code for Cloud Storage Systems
Talk by Roberta Barbi
Date: 26.10.16 Time: 16.00 - 17.00 Room:
Distributed storage systems often use erasure coding techniques to provide reliability while decreasing the storage overhead required by replication. Due to the drawbacks of standard MDS erasure-correcting codes, numerous coding schemes recently proposed for distributed storage systems target other metrics such as repair locality and repair bandwidth. Unfortunately, these schemes are not always practical. In this work, we propose SYEL, a very Simple Yet Efficient optimal Locally repairable code directly built from its generator matrix. We provide comparisons against a well-known Reed-Solomon code and a recently proposed pyramid code using a Python implementation. We show that SYEL provides enhanced repair bandwidth, competitive fault tolerance and faster erasure repair process than the other two solutions while requiring less than 50 lines of code.