Performance Analysis of Gang Scheduling in a Distributed System under Processor Failures

In this paper we study the performance of a distributed system that is subject to hardware failures and subsequent repairs. A special type of scheduling called gang scheduling is considered, under which jobs consist of a number of interacting tasks which are scheduled to run simultaneously on distinct processors. Two different gang scheduling policies used to schedule parallel jobs are examined in two cases: In the blocking case, a job that is blocked due to processor failure keeps all of its assigned processors until the failed processor is repaired. In the nonblocking case, the remaining operable processors can serve other jobs. Furthermore, this paper combines two different I/O scheduling methods with the two gang scheduling policies, so that three policy combinations are used. The impact of the variability in processor service time is also studied. Various degrees of multiprogramming, coefficients of variation of processor service time and failure to repair ratios are examined using simulation techniques.