Time-sharing parallel applications with performance isolation and control

Bin Lin*, Ananth I. Sundararaj, Peter A Dinda

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Most parallel machines, such as clusters, are spaceshared in order to isolate batch parallel applications from each other and optimize their performance. However, this leads to low utilization or potentially long waiting times. We propose a self-adaptive approach to time-sharing such machines that provides isolation and allows the execution rate of an application to be tightly controlled by the administrator. Our approach combines a periodic real-time scheduler on each node with a global feedback-based control system that governs the local schedulers. We have developed an online system that implements our approach. The system takes as input a target execution rate for each application, and automatically and continuously adjusts the applications' realtime schedules to achieve those rates with proportional CPU utilization. Target rates can be dynamically adjusted. Applications are performance-isolated from each other and from other work that is not using our system. We present an extensive evaluation that shows that the system remains stable with low response times, and that our focus on CPU isolation and control does not come at the significant expense of network I/O, disk I/O, or memory isolation.

Original languageEnglish (US)
Title of host publicationFourth International Conference on Autonomic Computing, ICAC'07
DOIs
StatePublished - Nov 15 2007
Event4th International Conference on Autonomic Computing, ICAC'07 - Jacksonville, FL, United States
Duration: Jun 11 2007Jun 15 2007

Publication series

NameFourth International Conference on Autonomic Computing, ICAC'07

Other

Other4th International Conference on Autonomic Computing, ICAC'07
Country/TerritoryUnited States
CityJacksonville, FL
Period6/11/076/15/07

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Mathematics(all)

Fingerprint

Dive into the research topics of 'Time-sharing parallel applications with performance isolation and control'. Together they form a unique fingerprint.

Cite this