HIOBS: A Block Storage Scheduling Approach to Reduce Performance Fragmentation in Heterogeneous Cloud Environments

摘要

Cloud computing is a highly successful paradigm of service-oriented computing and has revolutionized the usage of computing infrastructure. In the cloud storage, the service user has requirements regarding availability and performance. Once the cloud resources are shared among multi-tenants, a service level agreement (SLA) is defined by the service provider and the user. The multi-tenant characteristic of the cloud implies a heterogeneity of SLA requirements from users. At the same time, cloud providers should upgrade their infrastructure with modern storage nodes to attend data-driven applications, resulting in a heterogeneous cloud environment. The heterogeneity of both SLA requirements and storage resources makes the volume scheduling problem complex to guarantee SLAs. This paper presents HIOBS, an SLA-aware approach for block storage scheduling in heterogeneous cloud environments to reduce the performance fragmentation of the available storage resources, thus increasing the chances of new SLA requirements to be met. We demonstrate through experiments that our method improves more than 40% the rate of SLA violations while using fewer storage nodes.