No. 35 (211), issue 6Pages 91 - 103

ON PROGRAM RESTORATION FROM CHECKPOINTS SET

A.Y. Polyakov
In paper two approaches to distributed programs restore problem from checkpoints set are described. Computation node wide algorithm of parent-child relationships and group/session assignement recreation at restore time is proposed. Also coordinated algorithm for process set restoration from several nodes/terminals is designed. Described algorightms are implemented in checkpointing package called extitDMTCP ( extitDistributed MultiThreaded CheckPointing).
Full text
Keywords
HPC, rollback-recovery, checkpointing, fault tolerance