• Home
  • Search
  • Adaptive Metric-Aware Job Scheduling for Production Supercomputers
  • Cite Icon19
  • https://doi.org/10.1109/icppw.2012.17Copy DOI Icon

Adaptive Metric-Aware Job Scheduling for Production Supercomputers

  • Sep 1, 2012
  • Wei Tang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Job scheduling is a critical and complex task on large-scale supercomputers where a scheduling policy is expected to fulfill amorphous and sometimes conflicting goals from both users and system owners. Moreover, the effectiveness of a scheduling policy is dependent on workload characteristics which vary from time to time. Thus it is challenging to design a versatile scheduling policy that is effective in all circumstances. To address this issue, we propose an adaptive metric-aware job scheduling strategy. First, we propose metric-aware scheduling which enables the scheduler to balance competing scheduling goals represented by different metrics such as job waiting time, fairness, and system utilization. Second, we enhance the scheduler to adaptively adjust scheduling policies based on feedback information of monitored metrics at runtime. We evaluate our design using real workloads from supercomputer centers and demonstrate that our scheduling mechanism can significantly improve system performance in a balanced, sustainable fashion.

Similar Papers
  • Conference Article
  • Citations25

Dynamic Resource Provisioning and Scheduling with Deadline Constraint in Elastic Cloud

  • Apr 01, 2013
  • Guan Le +2
  • Conference Article
  • Citations40

Job fairness in non-preemptive job scheduling

  • Aug 15, 2004
  • Gerald Sabin +2
  • Book Chapter

Two-Dimensional Priority Scheduling Scheme for Open Real-Time Systems

  • Jan 01, 2006
  • Pengliu Tan +2
  • Conference Article
  • Citations24

Kernel-level scheduling for the nano-threads programming model

  • Jul 13, 1998
  • Eleftherios D Polychronopoulos +5
  • Conference Article
  • Citations18

A Comparative Study of Job Scheduling Strategies in Large-Scale Parallel Computational Systems

  • Jul 01, 2013
  • Aftab Ahmed Chandio +4
  • Research Article
  • Citations27

Processor saving scheduling policies for multiprocessor systems

  • Jan 01, 1998
  • IEEE Transactions on Computers
  • E Rosti +4
  • Conference Article
  • Citations1

An Adaptive Scheduler Framework for Complex Workflow Jobs on Grid Systems

  • Sep 01, 2011
  • G M Siddesh +1
  • Conference Article
  • Citations3

Parallelization and scheduling of data intensive particle physics analysis jobs on clusters of PCs

  • Apr 26, 2004
  • S Ponce +1
  • Conference Article
  • Citations30

Power efficient job scheduling by predicting the impact of processor manufacturing variability

  • Jun 26, 2019
  • Dimitrios Chasapis +5
  • Book Chapter
  • Citations4

Using On-the-Fly Simulation for Estimating the Turnaround Time on Non-dedicated Clusters

  • Jan 01, 2006
  • Mauricio Hanzich +5
  • Research Article
  • Citations77

Scheduling shared scans of large data files

  • Aug 01, 2008
  • Proceedings of the VLDB Endowment
  • Parag Agrawal +2
  • Conference Article
  • Citations7

RJSSIM: A reconfigurable job scheduling smulator for parallel processing learning

  • Nov 05, 2003
  • L.Fw Goes +1
  • Research Article
  • Citations29

Combining performance and priority for scheduling resizable parallel applications

  • Sep 30, 2015
  • Journal of Parallel and Distributed Computing
  • Rajesh Sudarsan +1
  • Conference Article
  • Citations5

On the comparison of CPLEX-computed job schedules with the self-tuning dynP job scheduler

  • Apr 26, 2004
  • S Grothklags +1
  • Book Chapter
  • Citations11

The Resource Usage Aware Backfilling

  • Jan 01, 2009
  • Francesc Guim +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.