Taking snapshots of virtual networked environments

The capture of global, consistent snapshots of a distributed computing session or system is essential to the system's reliability, manageability, and accountability. Despite the large body of work at the application, library, and operating system levels, we identify a void in the spectrum of distributed snapshot techniques: taking snapshots of the entire distributed runtime environment. Such capability has unique applicability in a number of application scenarios. In this paper, we realize such capability in the context of virtual networked environments. More specifically, by adapting and implementing a distributed snapshot algorithm, we enable the capture of causally consistent snapshots of virtual machines in a virtual networked environment. The snapshot-taking operations do not require any modification to the applications or operating systems running inside the virtual environment. Preliminary evaluation results indicate that our technique incurs acceptable overhead and small disruption to the normal operation of the virtual environment.