Admon: I/O Workload Management by ViSaGe Administration and Monitoring Service

Abstract

Virtualization in grid environments is a recent way to improve platform usage. ViSaGe is a middleware designed to provide set of functionalities needed for storage virtualizaion: transparent reliable remote access to data and distributed data management. ViSaGe aggregates distributed physical storage resources. However, ensuring the performances of data access in grid environment is a major issue, as large amount of data are stored and constantly accessed, and directly involved into tasks execution time. Especially, the placement and selection of replicated data are made particularly difficult because of the dynamic nature of grid environments - grid nodes workload variations. The workload variations represent the state of the system resources (CPU, disks and networks). These variations are mainly perceived by a monitoring system. Several monitoring systems exist in the literature. They monitor system resources consumption and applications but none of these systems presents the whole of the pertinent characteristics for ViSaGe. ViSaGe needs a system that analyzes nodes workload during runtime execution for improving data storage management. Therefore, ViSaGe Administration and monitoring service, namely Admon, is proposed. In this paper, we present Admon and its workload prediction model. Admon allows to dynamically placing data according to resources usage, especially disk I/O workload, ensuring the best performances while limiting the monitoring overhead. Experiments show the relevance of Admon decisions.