Export Citations
Energy Efficient Servers: Blueprints for Data Center Optimization introduces engineers and IT professionals to the power management technologies and techniques used in energy efficient servers. The book includes a deep examination of different features used in processors, memory, interconnects, I/O devices, and other platform components. It outlines the power and performance impact of these features and the role firmware and software play in initialization and control. Using examples from cloud, HPC, and enterprise environments, the book demonstrates how various power management technologies are utilized across a range of server utilization. It teaches the reader how to monitor, analyze, and optimize their environment to best suit their needs. It shares optimization techniques used by data center administrators and system optimization experts at the worlds most advanced data centers. What youll learn Develop a deep understanding of power management in modern servers from data center and systems software to low-level processor technologies and all the pieces in-between. Build an understanding of technologies used in cores, caches, memory, system agents, processor interconnects, and PCI-E to manage power. Learn techniques for monitoring and characterizing server power management technologies including component and system level impact. Develop strategies to improve infrastructure utilization and cost-effectiveness, to guide configuration and purchasing decisions, and to enhance application deployment. Learn new techniques to optimize a server for energy efficiency while still meeting the service level requirements of software, related systems in the data center, and end customers.Who this book is for Primarily: Engineers and IT professionals. More broadly, the book appeals to a wide technologist audience anyone who designs or relies on a server to run services and applications from software engineers, to system administrators, to equipment and system manufacturers, to data center operators. Table of ContentsForeword/Preface Chapter 1: Why Data Center Efficiency MattersChapter 2: CPU and Memory Power ManagementChapter 3: Memory and I/O Power ManagementChapter 4: Software ArchitectureChapter 5: BIOS and Management FirmwareChapter 6: Operating SystemsChapter 7: MonitoringChapter 8: Characterization and OptimizationChapter 9: Data Center ManagementChapter 10: Terms and Technology Appendix
Cited By
- Haj-Yahya J, Kim J, Yağlikçi A, Puddu I, Orosa L, Luna J, Alser M and Mutlu O IChannels Proceedings of the 48th Annual International Symposium on Computer Architecture, (985-998)
- Li C, Feng D, Hua Y and Wang F (2019). A high-performance and endurable SSD cache for parity-based RAID, Frontiers of Computer Science: Selected Publications from Chinese Universities, 13:1, (16-34), Online publication date: 1-Feb-2019.
- Narayanan V, Baranowski M, Ryzhyk L, Rakamarić Z and Burtsev A RedLeaf Proceedings of the Workshop on Hot Topics in Operating Systems, (37-44)
- Sharafzadeh E, Kohroudi S, Asyabi E and Sharifi M Yawn Proceedings of the 10th ACM SIGOPS Asia-Pacific Workshop on Systems, (91-98)
- Sourouri M, Raknes E, Reissmann N, Langguth J, Hackenberg D, Schöne R and Kjeldsberg P Towards fine-grained dynamic tuning of HPC applications on modern multi-core architectures Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, (1-12)
- Garraghan P, Al-Anii Y, Summers J, Thompson H, Kapur N and Djemame K A unified model for holistic power usage in cloud datacenter servers Proceedings of the 9th International Conference on Utility and Cloud Computing, (11-19)
- Procaccianti G, Lago P and Diesveld W Energy Efficiency of ORM Approaches Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, (1-10)
Index Terms
- Energy Efficient Servers: Blueprints for Data Center Optimization
Recommendations
Energy Efficient Distributed Systems for Storage Servers
INCOS '11: Proceedings of the 2011 Third International Conference on Intelligent Networking and Collaborative SystemsThe electric power consumption of servers hasto be reduced in information systems in order to realize green societies. In information systems, clients issue requests to servers and the servers spend electric power to handle the requests. We have to ...
Energy-Efficient Redundant Execution of Processes in a Fault-Tolerant Cluster of Servers
This paper investigates into fault tolerance of cluster of servers and their energy efficiency to realize a reliable and energy aware server cluster system. A client issues a request to one server in a server cluster and the server sends a reply to the ...
Energy-efficient dynamic clusters of servers
Electric power consumed by servers has to be reduced in order to realize green societies. We consider computation (CP) and storage (ST) types of application processes performed on servers in this paper, where CPU and storage drives are mainly used, ...