Sign up or log in to see what your friends are attending and create your own schedule!

View analytic


Tech: Analyzing .. Trestles
    Tuesday July 17, 2012 11:00am - 11:30am @ Camelot 3rd Floor

    Tech: Analyzing Throughput and Utilization on Trestles

    Abstract: The Trestles system is targeted to modest-scale and gateway users, and is operated to enhance users’ productivity by maintaining good turnaround time as well as other user-friendly features such as long run times and user reservations. However the goal of maintaining good throughput competes with the goal of high system utilization. This paper analyzes one year of Trestles operations to characterize the empirical relationship between utilization and throughput, with the objectives of understanding their trade-off, and informing allocations and scheduling policies to optimize this trade-off. There is considerable scatter in the correlation between utilization and throughput, as measured by expansion factor. There are periods of good throughput at both low and high utilizations, while there are other periods when throughput degrades significantly not only at high utilization but even at low utilization. However, throughput consistently degrades above ~90% utilization. User behavior clearly impacts the expansion factor metrics; the great majority of jobs with extreme expansion factors are associated with a very small fraction of users who either flood the queue with many jobs or request run times far in excess of actual run times. While the former is a user workflow choice, the latter clearly demonstrates the benefit for users to request run times that are well-matched to actual run times. Utilization and throughput metrics derived from XDMoD are compared for Trestles with two other XSEDE systems, Ranger and Kraken, with different sizes and allocation/scheduling policies. Both Ranger and Kraken have generally higher utilization and, not surprisingly, higher expansion factors than Trestles over the analysis period. As a result of this analysis, we intend to increase the target allocation fraction from the current 70% to ~75-80%, and strongly advise users to reasonably match requested run times to actual run times.



    Type Technology Track
    Session Titles XSEDE Service Provider Systems

Get Adobe Flash player