Checkpointing in hybrid distributed systems

To provide fault tolerance to computer systems suffering from transient faults, checkpointing and rollback recovery is one of the widely-used techniques. Among others, two primary checkpointing schemes have been proposed: independent and coordinated schemes. However, most existing works address only the need of employing a single checkpointing and rollback recovery scheme to a target system. In this paper, issues are discussed and a new algorithm is developed to address the need of integrating independent and coordinated checkpointing schemes for applications running in a hybrid distributed environment containing multiple heterogeneous subsystems. The required changes to the original checkpointing schemes for each subsystem and the overall prevented unnecessary rollbacks for the integrated system are presented. Also described is an algorithm for collecting garbage checkpoints in the combined hybrid system.