Dynamic load balance for optimized message logging in fault tolerant HPC applications

Esteban Meneses, Laxmikant V. Kalé, Greg Bronevetsky

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

Abstract

Computing systems will grow significantly larger in the near future to satisfy the needs of computational scientists in areas like climate modeling, biophysics and cosmology. Supercomputers being installed in the next few years will comprise millions of cores, hundreds of thousands of processor chips and millions of physical components. However, it is expected that failures become more prevalent in those machines to the point where 10% of an Exascale system will be wasted just recovering from failures. Further, with such large numbers of cores, fine-grained and dynamic load balance will become increasingly critical for maintaining good system utilization. This paper addresses both fault tolerance and load balancing by presenting a novel extension of traditional message logging protocols based on team check pointing. Message logging makes it possible to recover from localized failures by rolling back just the failed processing elements. Since this comes at a high memory overhead from logging all communication, we reduce this cost by organizing processing elements into teams and only logging messages between teams. Further, we show how to dynamically partition the application into teams to simultaneously minimize the cost of fault tolerance and to balance application load. We experimentally show that this scheme has low overhead and can dramatically reduce the memory cost of message logging.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE International Conference on Cluster Computing, CLUSTER 2011
Pages281-289
Number of pages9
DOIs
StatePublished - Nov 16 2011
Event2011 IEEE International Conference on Cluster Computing, CLUSTER 2011 - Austin, TX, United States
Duration: Sep 26 2011Sep 30 2011

Publication series

NameProceedings - IEEE International Conference on Cluster Computing, ICCC
ISSN (Print)1552-5244

Other

Other2011 IEEE International Conference on Cluster Computing, CLUSTER 2011
CountryUnited States
CityAustin, TX
Period9/26/119/30/11

Keywords

  • causal message logging
  • fault tolerance
  • load balancing

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Signal Processing

Fingerprint Dive into the research topics of 'Dynamic load balance for optimized message logging in fault tolerant HPC applications'. Together they form a unique fingerprint.

Cite this