Core Algorithms of the Maui Scheduler
The Maui scheduler has received wide acceptance in the HPC community as a highly configurable and effective batch scheduler. It is currently in use on hundreds of SP, O2K, and Linux cluster systems throughout the world including a high percentage of the largest and most cutting edge research sites. While the algorithms used within Maui have proven themselves effective, nothing has been published to date documenting these algorithms nor the configurable aspects they support. This paper focuses on three areas of Maui scheduling, specifically, backfill, job prioritization, and fairshare. It briefly discusses the goals of each component, the issues and corresponding design decisions, and the algorithms enabling the Maui policies. It also covers the configurable aspects of each algorithm and the impact of various parameter selections.
Unable to display preview. Download preview PDF.
- 1.D. Jackson. The Maui Scheduler. Technical report. http://supercluster.org/projects/maui.
- 3.R.L. Henderson. Job scheduling under the Portable Batch System. Job Scheduling Strategies for Parallel Processing, Lecture Notes in Computer Science, 949, 1995.Google Scholar
- 4.J.M. Barton and N. Bitar. A scalable multi-discipline multiple processor scheduling framework for IRIX. Job Scheduling Strategies for Parallel Processing, Lecture Notes in Computer Science, 949, 1995.Google Scholar
- 5.D. Jackson. HPC workload repository. Technical report. http://www.supercluster.org/research/traces.
- 6.D. Feitelson and A. Mu’alem Weil. Utilization and predicability in scheduling the IBM SP2 with backfilling. In Proceedings of IPPS/SPDP, April 1998.Google Scholar
- 8.John Jardine. Avoiding livelock using the Y Metascheduler and exponential backo off Master’s thesis, Brigham Young University, 2000.Google Scholar
- 9.D. Jackson, Q. Snell, and M. Clement. Simulation based HPC workload analysis. In International Parallel and Distributed Processing Symposium, 2001.Google Scholar