Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published December 1997 | public
Journal Article Open

Performance optimization of checkpointing schemes with task duplication

Abstract

In checkpointing schemes with task duplication, checkpointing serves two purposes: detecting faults by comparing the processors' states at checkpoints, and reducing fault recovery time by supplying a safe point to rollback to. In this paper, we show that, by tuning the checkpointing schemes to a given architecture, a significant reduction in the execution time can be achieved. The main idea is to use two types of checkpoints: compare-checkpoints (comparing the states of the redundant processes to detect faults) and store-checkpoints (storing the states to reduce recovery time). With two types of checkpoints, we can use both the comparison and storage operations in an efficient way and improve the performance of checkpointing schemes. Results we obtained show that, in some cases, using compare and store checkpoints can reduce the overhead of DMR checkpointing schemes by as much as 30 percent.

Additional Information

© Copyright 1997 IEEE. Reprinted with permission. Manuscript revised 13 Aug. 1997. The research reported in this paper was supported in part by U.S. National Science Foundation Young Investigator Award CCR-9457811, by the Sloan Research Fellowship, by a grant from the IBM Almaden Research Center, San Jose, California, and by a grant from the AT&T Foundation. This research was performed, in part, using the CSCC parallel computer system operated by Caltech on behalf of the Concurrent Supercomputing Consortium. Access to this facility was provided by Caltech.

Files

ZIVieeetc97a.pdf
Files (86.4 kB)
Name Size Download all
md5:d9f00865d394704e92f83cd02b6503ff
86.4 kB Preview Download

Additional details

Created:
September 13, 2023
Modified:
October 23, 2023