A2-VM: A Cooperative Java VM with Support for Resource-Awareness and Cluster-Wide Thread Scheduling?

Abstract. In today’s scenarios of large scale computing and service pro-viding, the deployment of distributed infrastructures, namely computer clusters, is a very active research area. In recent years, the use of Grids, Utility and Cloud Computing, shows that these are approaches with growing interest and applicability, as well as scientific and also commer-cial impact. This work presents the design and implementation issues of a cooperative VM for a distributed execution environment that is resource-aware and policy-driven. Nodes cooperate to achieve efficient management of the available local and global resources. We propose A2-VM, a cooperative cluster-enabled virtual execution environment for Java, to be deployed on Grid sites and Cloud data-centers that usually comprise a number of federated clusters. This cooperative VM has the ability to monitor base mechanisms (e.g. thread scheduling, garbage collection, memory or net-work consumptions) to assess application’s performance and reconfigure these mechanisms in run-time according to previously defined resource allocation policies. We have designed this new cluster runtime by extending the Jikes Re-search Virtual Machine to incorporate resource awareness (namely re-source consumption and restrictions), and extending the TerraCotta DSO with a distributed thread scheduling mechanism driven by policies that take into account resource utilization. In this paper we also discuss the cost of activating such mechanisms, focusing on the overhead of measur-ing/metering resource usage and performing policy evaluation.