Presentation 2005/6/10
On the Evaluation of Distributed Checkpointing
Mamoru OHARA, Masayuki ARAI, Satoshi FUKUMOTO, Kazuhiko IWASAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Coordinated checkpointing has been gaining its effectiveness with decreasing communication overhead. However, in checkpointing, it must wait for all processes completing state saving. Thus large distributed systems may be suffered from bottleneck effects of a few slow processes. This paper presents a coordinated checkpointing technique, which reduces its checkpointing overhead while keeping its recovery cost low, by using both relatively infrequent coordination and individual incremental state saving. We also analyze complexity of checkpointing and recovery algorithms of the proposed technique, respectively. Comparing with a traditional technique, it can achieve better trade-off between these complexities with low message frequency.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) distributed systems / coordinated checkpointing / incremental snapshots / reliability / probability models
Paper # DC2005-11
Date of Issue

Conference Information
Committee DC
Conference Date 2005/6/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the Evaluation of Distributed Checkpointing
Sub Title (in English)
Keyword(1) distributed systems
Keyword(2) coordinated checkpointing
Keyword(3) incremental snapshots
Keyword(4) reliability
Keyword(5) probability models
1st Author's Name Mamoru OHARA
1st Author's Affiliation Graduate School of Engineering, Tokyo Metropolitan University()
2nd Author's Name Masayuki ARAI
2nd Author's Affiliation Graduate School of Engineering, Tokyo Metropolitan University
3rd Author's Name Satoshi FUKUMOTO
3rd Author's Affiliation Graduate School of Engineering, Tokyo Metropolitan University
4th Author's Name Kazuhiko IWASAKI
4th Author's Affiliation Graduate School of Engineering, Tokyo Metropolitan University
Date 2005/6/10
Paper # DC2005-11
Volume (vol) vol.105
Number (no) 123
Page pp.pp.-
#Pages 6
Date of Issue