Performance evaluation of gang scheduling in a two-cluster system with migrations
Authors:
- 1 May 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Gang scheduling is considered to be a highly effective task scheduling policy for distributed systems. In this paper we present a migration scheme which reduces the fragmentation in the schedule caused by gang scheduled jobs which cannot start. Furthermore, the existence of high priority jobs in the workload is addressed by the proposed strategy. High priority jobs need to be started immediately, which can in turn lead to the interruption of a parallel job's execution. A distributed system consisting of two homogeneous clusters is simulated to evaluate the performance. Our simulation results indicate that the proposed strategy can result in a performance boost.Keywords
This publication has 11 references indexed in Scilit:
- Multi-cluster Load Balancing Based on Process Migration2007
- On Grid Performance Evaluation Using Synthetic Workloads2005
- Enhancements to the Decision Process of the Self-Tuning dynP SchedulerLecture Notes in Computer Science, 2005
- Gang scheduling in a distributed system under processor failures and time-varying gang size2004
- An integrated approach to parallel scheduling using gang-scheduling, backfilling, and migrationIEEE Transactions on Parallel and Distributed Systems, 2003
- A simulation-based performance analysis of gang scheduling in a distributed system2003
- Condor-a hunter of idle workstations2003
- Improved utilization and responsiveness with gang scheduling1997
- Load balancing and fault tolerance in workstation clusters migrating groups of communicating processesACM SIGOPS Operating Systems Review, 1995
- The limited performance benefits of migrating active processes for load sharing1988