Making Utility Computing Real

IT systems in todays' enterprises are spread across organizations, are heterogeneous, and have high infrastructure and management costs. A new computing model termed as Utility Systems is emerging that consolidates IT infrastructure in centralized data centers, shares resources across users, allocates resources on-demand to user applications, and does pay-per-use accounting based on resource usage. The key to making such a paradigm real is an effective resource management solution that provides application QoS guarantees, while maintaining efficient utilization of resources. This book presents model-driven resource management techniques and mechanisms to achieve the same. The approach is based on creating application models that aid in prediction of performance and the behavior of applications. A methodology for application model-driven resource management is presented and then demonstrated and validated through a case study of a remote desktop utility system, an emerging client/sever networked model for enterprise desktops. This book is directed towards researchers in QoS management, cluster and grid computing, as well as industry practitioners designing resource management software for IT data center architectures.

Autorentext

Vanish Talwar is a Research Scientist at Hewlett-Packard Laboratories, Palo Alto, USA, investigating manageability architectures for next generation data centers. He obtained his MS and PhD degrees in Computer Science from the University of Illinois at Urbana-Champaign (UIUC), at where he received the David J. Kuck Best Masters Thesis award.

Klappentext

IT systems in todays' enterprises are spread across organizations, are heterogeneous, and have high infrastructure and management costs. A new computing model termed as Utility Systems is emerging that consolidates IT infrastructure in centralized data centers, shares resources across users, allocates resources on-demand to user applications, and does pay-per-use accounting based on resource usage. The key to making such a paradigm real is an effective resource management solution that provides application QoS guarantees, while maintaining efficient utilization of resources. This book presents model-driven resource management techniques and mechanisms to achieve the same. The approach is based on creating application models that aid in prediction of performance and the behavior of applications. A methodology for application model-driven resource management is presented and then demonstrated and validated through a case study of a remote desktop utility system, an emerging client/sever networked model for enterprise desktops. This book is directed towards researchers in QoS management, cluster and grid computing, as well as industry practitioners designing resource management software for IT data center architectures.