Draft as Accepted to Sigmetrics Please Do Not Distribute -symbiotic Jobscheduling with Priorities for a Simultaneous Multithreading Processor

Simultaneous Multithreading machines beneet from jobscheduling software that monitors how well coscheduled jobs share CPU resources, and coschedules jobs that interact well to make more eecient use of those resources. As a result, informed coscheduling can yield signiicant performance gains over naive schedulers. However, prior work has only focused only the situation where jobs have equal priority, which is an unrealistic assumption for schedulers for modern operating systems. This paper demonstrates that a scheduler for an SMT machine can both satisfy process priorities and symbiotically schedule low and high priority threads to increase system throughput. Naive priority schedulers dedicate the machine to high priority jobs to meet priority goals, and as a result decrease opportunities for increased performance from multithreading and coscheduling. More informed sched-ulers, however, can dynamically monitor the progress and resource utilization of jobs on the machine, and dynamically adjust the degree of multithreading to improve performance while still meeting priority goals. Using detailed simulation of an SMT architecture, we introduce and evaluate a series of ve software and hardware-assisted priority schedulers. Overall, our results indicate that coscheduling priority jobs can signiicantly increase system throughput by as much as 40%, and that (1) the beneet depends upon the relative priority of the coscheduled jobs, and (2) more complex schedulers are more eeective the greater the diierences in priorities. We also show that, although our priority schedulers focus on increasing system throughput, as a result they can also decrease average turnaround times for a random jobmix by as much as 33%.