- 出版社: Morgan and Claypool Life Sciences; 2nd Revised edition (2013年7月30日)
- 丛书名: Synthesis Lectures on Computer Architecture
- 平装: 154页
- 语种： 英语
- ISBN: 1627050094
- 条形码: 9781627050098
- 商品尺寸: 19 x 0.9 x 23.5 cm
- 商品重量: 281 g
- ASIN: 1627050094
- 用户评分: 分享我的评价
- 亚马逊热销商品排名: 图书商品里排第1,264,034名 (查看图书商品销售排行榜)
The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines (英语) 平装 – 2013年7月30日
Jimmy Clidaras led Google's datacenter engineering program through multiple generations starting in 2004, with a special emphasis on energy- and cost-efficient design. He was the first director of Google's Platforms Infrastructure Engineering team, responsible for power, cooling, embedded software, and datacenter R&D engineering. Jimmy's original background is in aerospace engineering, having worked at Harris Corporation and E-Systems, where he developed space-flight hardware for communication and research satellites. He holds degrees in audio engineering ('84) and mechanical engineering ('94, Florida Atlantic University). He is currently a Distinguished Datacenter Engineer at Google and a Distinguished Alumnus of FAU. He remains engaged in datacenter research activities, continuing the search for disruptive technologies. Urs H lzle served as Google's first vice president of engineering and leads the development of Google's technical infrastructure. His current responsibilities include the design and operation of the servers, networks, datacenters, and software infrastructure that power Google. He is also renowned for both his red socks and his free-range Leonberger, Yoshka (Google's original top dog). Urs grew up in Switzerland and received a master's degree in computer science from ETH Z rich and, as a Fulbright scholar, a Ph.D. from Stanford. While at Stanford (and then a start-up later acquired by Sun Microsystems) he invented fundamental techniques used in most of today's leading Java compilers. Before joining Google he was a professor of computer science at the University of California, Santa Barbara. He is a Fellow of the ACM, a member of the Swiss Academy of Technical Sciences and the National Academy of Engineering, and serves on the board of the US World Wildlife Fund as well as the Open Networking Foundation.
Introduction Workloads and Software Infrastructure Hardware Building Blocks Datacenter Basics Energy and Power Efficiency Modeling Costs Dealing with Failures and Repairs Closing Remarks
|5 星 (0%)|
|4 星 (0%)|
|3 星 (0%)|
|2 星 (0%)|
|1 星 (0%)|
What I was hoping for was a deeper look into the requirements of a platform-as-a-service infrastructure to enable optimal utilization of data center resources by auto-provisioning heterogeneous services across commodity hardware. In this model, VMs are eliminated by standardizing services to run on a single operating system version, running multiple different services on the same server, and componetizing them through kernel-level containers (LXC). This wasn't covered.
The book is written by key Google technologists that certainly know the subject. But it feels like a lot of useful stuff was omitted, probably due to corporate trade secrets. Frequently, an interesting discussion abruptly ends with a brief "qualitative" description. Whereas it'd be valuable for a reader to continue and provide some "quantitative" data.