An Application-Assisted Checkpoint-Restart Mechanism for Java Applications

Abstract

This paper was published in the proceedings of the IEEE 12th International Symposium on Parallel and Distributed Computing. The final, published version of the paper can be found in the IEEE Xplore database: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6663581&queryText%3D.QT.An+Application-Assisted+Checkpoint-Restart+Mechanism+for+Java+Applications.QT. The contributions of the 3rd author are mostly of a software engineering and algorithmic nature (some of them based on his experience as a participant and as a member of the scientific committee of multiple algorithmic contests - some examples of algorithmic contest tasks and solutions, both official ones and written by the 3rd author, can be found in the attached ZIP archive).International audienceIn this paper we present a novel application-assisted checkpoint-restart mechanism for Java applications. The checkpoint-restart API provides the application developers with full control over what data needs to be check-pointed. The novelty of our system is that it allows different checkpoint periods for different data items. Our implementation makes full use of the Java Reflection API