LSoVC: A Framework for Taking Live Snapshot of Virtual Cluster in the Cloud

With the widespread adoption of Cloud computing system, more and more application services based on cluster computing adopt this new computing paradigm. Live snapshot technology is usually used to ensure the reliability of data and high availability of the running virtual machines. This technology is essential to bring abilities of fault recovery and rollback to virtual clusters. Existing virtual machine live snapshot technologies are not enough to cope with the following challenges induced by taking live snapshots for a virtual cluster. One is keeping communication status among virtual machines belonging to a virtual cluster, and the other is minimizing the downtime of virtual machines when taking snapshot for a virtual cluster consisting of a large number of virtual machines. To address both challenges, this paper proposes a virtual cluster live snapshot framework which aims to preserve communication status among virtual machines belonging to a virtual cluster and to minimize the virtual machines downtime and performance overhead of live snapshot. Our experiments show that there is no lost package during taking live snapshot or restoring live snapshot, and that the average downtime of eight virtual machines in a virtual cluster is just 3% longer than that of individual virtual machine during taking live snapshot.