Hybrid Workload Scheduling on HPC Systems

TL;DR

This paper proposes and evaluates new scheduling mechanisms for efficiently managing hybrid workloads, including on-demand, rigid, and malleable jobs, on a single HPC system to improve responsiveness and overall system performance.

Contribution

It introduces novel scheduling strategies for co-scheduling diverse HPC workloads on a single system, addressing responsiveness, malleability incentives, and performance tradeoffs.

Findings

Proposed mechanisms effectively reduce on-demand request delays.

Incentives for malleable job declarations are increased.

Overall system performance is improved under various workloads.

Abstract

Traditionally, on-demand, rigid, and malleable applications have been scheduled and executed on separate systems. The ever-growing workload demands and rapidly developing HPC infrastructure trigger the interest of converging these applications on a single HPC system. Although allocating the hybrid workloads within one system could potentially improve system efficiency, it is difficult to balance the tradeoff between the responsiveness of on-demand requests, the incentive for malleable jobs, and the performance of rigid applications. In this study, we present several scheduling mechanisms to address the issues involved in co-scheduling on-demand, rigid, and malleable jobs on a single HPC system. We extensively evaluate and compare their performance under various configurations and workloads. Our experimental results show that our proposed mechanisms are capable of serving on-demand workloads with minimal delay, offering incentives for declaring malleability, and improving system performance.