Exploiting Redundancies and Deferred Writes to Conserve Energy in Erasure-Coded Storage Clusters

摘要

We present a power-efficient scheme for erasure-coded storage clusters - ECS~2 - which aims to offer high energy efficiency with marginal reliability degradation. ECS~2 utilizes data redundancies and deferred writes to conserve energy. In ECS~2 parity blocks are buffered exclusively in active data nodes whereas parity nodes are placed into low-power mode. (k + r, k) RS-coded ECS~2 can achieve [(r + 1)/2]-fault tolerance for k active data nodes and r-fault tolerance for all k+r nodes. ECS~2 employs the following three optimizing approaches to improve the energy efficiency of storage clusters. (1) An adaptive threshold policy takes system configurations and I/O workloads into account to maximize standby time periods; (2) a selective activation policy minimizes the number of power-transitions in storage nodes; and (3) a region-based buffer policy speeds up the synchronization process by migrating parity blocks in a batch method. After implementing an ECS~2-based prototype in a Linux cluster, we evaluated its energy efficiency and performance using four different types of I/O workloads. The experimental results indicate that compared to energy-oblivious erasure-coded storage, ECS~2 can save the energy used by storage clusters up to 29.8% and 28.0% in read-intensive and write-dominated workloads when k = 6 and r = 3, respectively. The results also show that ECS~2 accomplishes high power efficiency in both normal and failed cases without noticeably affecting the I/O performance of storage clusters.