Reliability Analysis of Deduplicated and Erasure-Coded Storage
In this paper, the author present initial results on the reliability analysis of HP-KVS, a deduplicated key-value store that allows each object to specify its own reliability level and that uses software erasure coding for data reliability. The combination of deduplication and erasure coding gives rise to several interesting research problems. The author shows how to compare the reliability of erasure codes with different parameters and how to analyze the reliability of a big data object given its constituent parts' reliabilities. The author also present a method for system designers to determine under what conditions deduplication will save space for erasure-coded data.