An Adaptive Tiering Scheme for an Autonomous Distributed Storage System
Atsushi Nunome, Hiroaki Hirata · 2021
Our previous works showed a distributed storage system capable to migrate data blocks autonomously across storage tiers. In this paper, we present an adaptive method for constructing storage tiers in the autonomous distributed storage system. This method can reduce task for tuning runtime parameters. The task normally depends on the configuration of storage devices and the behavior of process, so it should be done periodically by system administrators. The proposed method fine-tunes the configuration of the storage tiers during execution to match the execution environment, thus eliminating the need for manual parameter adjustments by the system administrator. The simulation results show that the proposed method can reduce the execution time by up to about 23% compared to the previous method.