This paper presents a general energy management system for High Performance Computing (HPC) clusters and cloud infrastructures that powers off cluster nodes when they are not being used, and conversely powers them on when they are needed. This system can be integrated with different HPC cluster middleware, such as Batch-Queuing Systems or Cloud Management Systems, and can also use different mec...

Through earth and space modeling and the ongoing launches of satellites to gather data, NASA has become one of the largest producers of data in the world. These large data sets necessitated the creation of a Data Management System (DMS) to assist both the users and the administrators of the data. Halcyon Systems Inc. was contracted by the NASA Center for Computational Sciences (NCCS) to produce...

This report aims to catalogue and briefly describe Distributed Cluster Computing Environments (DCCE) as well as newly established Cluster Management Software (CMS) projects. The document started out as part of a review commissioned by the UK government on Cluster Computing [1], and followed two other reports: a historic review of Cluster Computing produced by the Manchester Computing Centre [2]...

Advanced general-purpose parallel systems should be able to support diverse applications with diier-ent resource requirements without compromising eeec-tiveness and eeciency. We present a new resource management model for cluster computing that allows multiple scheduling policies to co-exist dynamically. In particular, we have built Octopus, an extensible and distributed hierarchical scheduler ...

Energy consumption is a major and costly problem in data centers. For many workloads, a large fraction of energy goes to powering idle machines that are not doing any useful work. There are two causes of this inefficiency: low server utilization and a lack of power proportionality. We focus on addressing this problem for two workloads: (1) a traditional, front-end web server workload and (2) an...

Reducing the complexity of the hardware and software components of Linux cluster systems can significantly improve management infrastructure scalability. Moving parts, in particular hard drives, generate excess heat and have the highest failure rates among cluster node components. The use of diskless nodes simplifies deployment and management, improves overall system reliability, and reduces op...

Cluster computing offers many advantages as a highly cost-effective and often scalable approach for highperformance computing in general, and most recently as a basis for hardware-reconfigurable systems. To achieve the full potential of performance of reconfigurable HPC systems, a runtime configuration service is required. Centralized configuration services are a natural starting point but tend...

3