Harnessing Correlations in Distributed Erasure-Coded Key-Value Stores

TL;DR

This paper investigates how to efficiently store correlated data versions in distributed key-value stores, reducing storage costs by exploiting correlations, and provides nearly optimal coding schemes for this purpose.

Contribution

It introduces new multi-version coding schemes that leverage data correlation to lower storage costs in distributed systems, with theoretical guarantees of near-optimality.

Findings

Storage cost decreases with higher data correlation.

Proposed codes are based on Reed-Solomon and random binning.

Achieves near-optimality within a factor of 2 in certain regimes.

Abstract

Motivated by applications of distributed storage systems to key-value stores, the multi-version coding problem was formulated to efficiently store frequently updated data in asynchronous decentralized storage systems. Inspired by consistency requirements in distributed systems, the main goal in the multi-version coding problem is to ensure that the latest possible version of the data is decodable, even if the data updates have not reached some servers in the system. In this paper, we study the storage cost of ensuring consistency for the case where the data versions are correlated, in contrast to previous work where data versions were treated as being independent. We provide multi-version code constructions that show that the storage cost can be significantly smaller than the previous constructions depending on the degree of correlation, despite the asynchrony and the decentralized nature. Our achievability results are based on Reed-Solomon codes and random binning. Through an information-theoretic converse, we show that our multi-version codes are nearly-optimal, within a factor of $2$, in certain interesting regimes.