Home // ACCSE 2017, The Second International Conference on Advances in Computation, Communications and Services // View article

Workload Adaptive I/O Fairness Scheme for Modern Cloud Storage

Authors:
Kisung Jin
Sangmin Lee
Hongyeon Kim
Youngkyun Kim

Keywords: Cloud; Cloud Storage; I/O Fairness; QoS

Abstract:
Although many cloud services have introduced several algorithms for providing Quality of Service (QoS) satisfaction to users, the performance interference problem among services has not yet been solved. Because multiple heterogeneous services produce non-deterministic workloads in the real world, service providers often experience contradictory results in their quality prediction. To solve this phenomenon, we specifically focus on the storage layer among the entire cloud stack. In this paper, we propose a workload adaptive Input/Output (I/O) fairness scheme to guarantee balanced data access regardless of various service workloads. Furthermore, we validate our idea through performance evaluations and show that our algorithm can satisfy QoS requirements in the cloud service.

Pages: 26 to 32

Copyright: Copyright (c) IARIA, 2017

Publication date: June 25, 2017

Published in: conference

ISSN: 2519-8459

ISBN: 978-1-61208-570-8

Location: Venice, Italy

Dates: from June 25, 2017 to June 29, 2017