Probabilistic QoS Guarantees for Supercomputing Systems

Supercomputing systems must be able to reliably and efficiently complete their assigned workloads, even in the presence of failures. This paper proposes a system that allows the system and users to negotiate a mutually desirable risk strategy; in order to accomplish this, the system makes probabilistic guarantees on quality of service (QoS), of the form, “Job j can be completed by deadline d with probability p.” In order to make such guarantees, the system uses event prediction (forecasting) in conjunction with fault-aware job scheduling and cooperative checkpointing strategies. Using job logs and failure traces from actual high performance computing systems, we employ trace-based simulations to assess the effects of the prediction accuracy (a) and user risk strategy (U) on a variety of performance metrics. Compared to a system that does not use event prediction, a high forecasting accuracy resulted in QoS and utilization improvements of as much as 6%, along with an 89% reduction...

• Type: Conference
• Year: 2005
• Where: DSN
• Authors: Adam J. Oliner, Larry Rudolph, Ramendra K. Sahoo, José E. Moreira, Manish Gupta
• Keywords: Computer Networks, DSN 2005, Event Prediction, Probabilistic Qos Guarantees, Risk Strategy