On the Latency and Energy Efficiency of Erasure-Coded Cloud Storage Systems

摘要

The increase in data storage and power consumption at data-centers has madeit imperative to design energy efficient Distributed Storage Systems (DSS). Theenergy efficiency of DSS is strongly influenced not only by the volume of data,frequency of data access and redundancy in data storage, but also by theheterogeneity exhibited by the DSS in these dimensions. To this end, we proposeand analyze the energy efficiency of a heterogeneous distributed storage systemin which $n$ storage servers (disks) store the data of $R$ distinct classes.Data of class $i$ is encoded using a $(n,k_{i})$ erasure code and the (random)data retrieval requests can also vary across classes. We show that the energyefficiency of such systems is closely related to the average latency and hencemotivates us to study the energy efficiency via the lens of average latency.Through this connection, we show that erasure coding serves the dual purpose ofreducing latency and increasing energy efficiency. We present a queuingtheoretic analysis of the proposed model and establish upper and lower boundson the average latency for each data class under various scheduling policies.Through extensive simulations, we present qualitative insights which reveal theimpact of coding rate, number of servers, service distribution and number ofredundant requests on the average latency and energy efficiency of the DSS.