Lowoverhead communication-induced checkpointing protocols ensuring rollback-dependency trackability property

摘要

Communication-induced checkpointing (CIC) protocols aim at finding consistent global checkpoint from which a system can safely restartwithout the risk of domino effect. CIC class gives processes themaximumautonomy for taking their local checkpointswhile directs themtotake forced checkpointswhen harm patterns are detected. Such patterns can constitute of non-causally doubled Z-paths that violate the causal relation and can cause checkpoints uselessness, which results in hidden dependencies between checkpoints. Ensuring the absence of hidden dependencies hence means the ensure of the Rollback-Dependency Trackability (RDT) property. Reducing the control information overhead is the main aim of our proposals. Our first proposal is called CSFDAS (Constant Size Fixed Dependency After Send), and the second is called CSRDTParner (Constant SizeRDTPartner). Unlike to the previous works, the newproposed protocols use direct dependency clocks instead of transitive dependency vectors while keeping only a constant size of control information on messages. Conducted simulations show that the new protocols achieve a good performance compared to the RDT protocols proposed so far in the literature.