Motor: A Virtual Machine for High Performance Computing

Abstract

High performance application development remains challenging, particularly for scientists making the transition to a Grid environment. In general areas of computing, virtual environments such as Java and .Net have proved successful in fostering application development. Unfortunately, these existing virtual environments do not provide the necessary high performance computing abstractions required by eScientists. In response, we propose and demonstrate a new approach to the development of a high performance virtual infrastructure: Motor is a virtual machine developed by integrating a high performance message passing library directly within a virtual infrastructure. Motor provides high performance application developers with a common runtime, garbage collection and system libraries, including high performance message passing, whilst retaining strong message passing performance.

Failure-aware resource management for high-availability computing clusters with distributed virtual machines

“…Recently, interest in using virtual machines (VMs) as the abstraction for distributed and parallel computing in general has been growing [20,24,13]. Virtual machine monitors, such as Xen [5] and VMware [46], have the potential to greatly simplify management from the perspective of resource owners and to provide great flexibility to resource users.…”

“…They provide desirable features to meet demanding requirements of computing resources in networked computing systems [20,24,13]. A most important feature provided by modern VM techniques is their ability of reconfiguration through VM migration [8,41].…”

Proactive Resource Management for Failure Resilient High Performance Computing Clusters

“…Most of existing works on virtual machine based HPC focus on infrastructure design [7,11,3] and reducing virtualization overhead [20,15,4]. However, few has investigated the reliability issue, such as avoiding, coping and recovering from failures, which is one of the hardest problems in HPC systems.…”

“…They provide desirable features to meet demanding requirements of computing resources in modern computing systems. Performance isolation, ease of management, checkpointing, migration, OS customization, and security are among the many features that make VM a powerful and popular technique for high performance computing (HPC) [7,10,11].…”

Failure-Aware Construction and Reconfiguration of Distributed Virtual Machines for High Availability Computing

“…They provide desirable features to meet demanding requirements of computing resources in cluster computing [10,13,5]. A most important feature provided by modern VM techniques is their ability of reconfiguration through VM migration [3].…”