Evaluation of simple causal message logging for large-scale fault tolerant HPC systems

Esteban Meneses, Greg Bronevetsky, Laxmikant V. Kalé

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

Abstract

The era of petascale computing brought machines with hundreds of thousands of processors. The next generation of exascale supercomputers will make available clusters with millions of processors. In those machines, mean time between failures will range from a few minutes to few tens of minutes, making the crash of a processor the common case, instead of a rarity. Parallel applications running on those large machines will need to simultaneously survive crashes and maintain high productivity. To achieve that, fault tolerance techniques will have to go beyond checkpoint/restart, which requires all processors to roll back in case of a failure. Incorporating some form of message logging will provide a framework where only a subset of processors are rolled back after a crash. In this paper, we discuss why a simple causal message logging protocol seems a promising alternative to provide fault tolerance in large supercomputers. As opposed to pessimistic message logging, it has low latency overhead, especially in collective communication operations. Besides, it saves messages when more than one thread is running per processor. Finally, we demonstrate that a simple causal message logging protocol has a faster recovery and a low performance penalty when compared to checkpoint/restart. Running NAS Parallel Benchmarks (CG, MG, BT and DT) on 1024 processors, simple causal message logging has a latency overhead below 5%.

Original languageEnglish (US)
Title of host publication2011 IEEE International Symposium on Parallel and Distributed Processing, Workshops and Phd Forum, IPDPSW 2011
Pages1533-1540
Number of pages8
DOIs
StatePublished - 2011
Event25th IEEE International Parallel and Distributed Processing Symposium, Workshops and Phd Forum, IPDPSW 2011 - Anchorage, AK, United States
Duration: May 16 2011May 20 2011

Publication series

NameIEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum

Other

Other25th IEEE International Parallel and Distributed Processing Symposium, Workshops and Phd Forum, IPDPSW 2011
CountryUnited States
CityAnchorage, AK
Period5/16/115/20/11

Keywords

  • Causal message logging
  • Migratable objects
  • Parallel applications
  • Pessimistic message logging

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Evaluation of simple causal message logging for large-scale fault tolerant HPC systems'. Together they form a unique fingerprint.

Cite this