PROJECT TITLE :

VM-μCheckpoint: Design, Modeling, and Assessment of Lightweight In-Memory VM Checkpointing

ABSTRACT:

Checkpointing and rollback techniques enhance reliability and availability of virtual machines and their hosted IT services. This paper proposes VM-μCheckpoint, a light-weight-weight pure-software mechanism for prime-frequency checkpointing and fast recovery for VMs. Compared with existing techniques of VM checkpointing, VM-μCheckpoint tries to reduce checkpoint overhead and speed up recovery by suggests that of copy-on-write, dirty-page prediction and in-place recovery, plus saving incremental checkpoints in volatile memory. Moreover, VM-μCheckpoint deals with the issue that latency in error detection doubtless leads to corrupted checkpoints, notably when checkpointing frequency is high. We have a tendency to also made Markov models to review the supply improvements provided by VM-μCheckpoint (from ninety nine to 99.ninety eight p.c on moderately reliable hypervisors). We designed and implemented VM-μCheckpoint in the Xen VMM. The analysis results demonstrate that VM-μCheckpoint incurs an average of half dozen.three p.c overhead (in terms of program execution time) for 50 ms checkpoint intervals when executing the SPEC CINT 2006 benchmark. Error injection experiments demonstrate that VM-μCheckpoint, combined with error detection techniques in RMK, provides high coverage of recovery.