A Checkpoint and Recovery Facility for the Fault-Tolerant Process on Linux Environment


The KIPS Transactions:PartA, Vol. 11, No. 5, pp. 313-318, Oct. 2004
10.3745/KIPSTA.2004.11.5.313,   PDF Download:

Abstract

In this paper, we suggest a checkpoint and recovery facility for the fault-tolerable process which is expected to be executed for a long time. The basic concept of the suggested facility is to allow the process to be executed continuously, when the process was stopped due to a system fault, by storing the execution status of the process periodically and recovering the execution status prior to the fault was occurred. In the suggested facility, it does not need to modify the source code for the fault-tolerable process. It was designed for the user to specify directly the file name and the checkpoint frequency, and two system calls(save, recover) were added. Finally, it was implemented on the Linux environment(kernel 2.4.18) for checking the feasibility.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. R. Rim and S. H. Kim, "A Checkpoint and Recovery Facility for the Fault-Tolerant Process on Linux Environment," The KIPS Transactions:PartA, vol. 11, no. 5, pp. 313-318, 2004. DOI: 10.3745/KIPSTA.2004.11.5.313.

[ACM Style]
Seong Rak Rim and Sin Ho Kim. 2004. A Checkpoint and Recovery Facility for the Fault-Tolerant Process on Linux Environment. The KIPS Transactions:PartA, 11, 5, (2004), 313-318. DOI: 10.3745/KIPSTA.2004.11.5.313.