Abstract | ||
---|---|---|
Abstract Coscheduling has been shown to be a critical factor in achieving efficient parallel execution in timeshared environments [11, 18, 4]. However, the most common approach, gang scheduling, has limitations in scaling, can compromise good interactive response, and requires that communicating processes be identified in advance. We explore a technique called dynamic,coscheduling(DCS) which produces emergent,coscheduling,of the processes constituting a parallel job. Experiments are performed,in a workstation environment,with high performance,networks and autonomous,timesharing schedulers for each CPU. The results demonstrate that DCS can achieve effective, robust coscheduling for a range of workloads and background,loads. Empirical comparisons to implicit scheduling and uncoordinated scheduling are presented. Under spin-block synchronization, DCS reduces job response times by up to 20% over implicit scheduling while maintaining fairness; and under spinning synchronization, DCS reduces job response times by up to two decimal orders of magnitude over uncoordinated scheduling. The results suggest that DCS is a promising avenue for achieving coordinated parallel scheduling in an environment,that |
Year | Venue | Keywords |
---|---|---|
1998 | IPPS/SPDP '98 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing | workstation clusters,dynamic coscheduling,time sharing,gang scheduling |
Field | DocType | ISBN |
Resource management,Coscheduling,Computer science,Parallel computing,Gang scheduling,Real-time computing,Message Passing Interface,Workstation clusters,Processor scheduling,Distributed computing,Context switch | Conference | 3-540-64825-9 |
Citations | PageRank | References |
74 | 3.26 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Patrick Sobalvarro | 1 | 928 | 68.85 |
Scott Pakin | 2 | 1098 | 134.55 |
William E. Weihl | 3 | 2614 | 903.11 |
Andrew A. Chien | 4 | 3696 | 405.97 |