= 2009-09-18 = == Cloud Computing == * [http://appscale.cs.ucsb.edu/ appscale] - Open Cloud Platform for Google AppEngine Apps * Google AppEngine (GAE) 的自由軟體版 - 好像有違反 Google 授權的爭議 * 由加州聖塔芭芭拉分校(UCSB)的 RACELab 維護,可以跑在 Amazon EC2 跟 Eucalyptus 上,支援 Xen 與 KVM 的虛擬化底層。 * 技術報告: [http://www.cs.ucsb.edu/~ckrintz/papers/appscale2009-02TR.pdf AppScale: Scalable and Open AppEngine Application Development and Deployment] * http://code.google.com/p/appscale/ * 最近美國政府單位的網雲平台足見成形,唉~國科會卻只會補助"微軟 only"的計畫~失望中~ * [http://nebula.nasa.gov/ NASA 的 Nenula 網雲平台] * [  * [http://news.networkmagazine.com.tw/web/2009/09/17/15237/ Google 為美國打造政府專用私有網雲] {{{ Google即將通過聯邦資訊安全管理法案(Federal Information Security Management Act, FISMA)的IT安全要求認證。 有了 FISMA 認證及 SAS 70 稽核標準,就不用各別政府機關都來和 Google 談不同的規定。 }}} == Hadoop == * 目前 Hadoop 兩本英文書: 1. [http://oreilly.com/catalog/9780596521974/index.html Hadoop: The Definitive Guide], Tom White, O'Reilly Media 2. [http://www.apress.com/book/view/9781430219422 Pro Hadoop], Jason Venner, Apress * [http://www.cascading.org/ Cascading] is a feature rich API for defining and executing complex, scale-free, and fault tolerant data processing workflows on a Hadoop cluster. * 定義資料處理工作流程的函式庫 * [[Image(http://www.cascading.org/documentation/long-pipe-chain.png)]] * http://code.google.com/p/cascading/ * [http://coffeesgone.wordpress.com/2009/09/12/custom-data-sinks-in-cascading-for-hadoop/ Custom Data Sinks in Cascading (for Hadoop)] * [http://wiki.apache.org/hadoop/Chukwa Chukwa] is an open source data collection system for monitoring and analyzing large distributed systems. * 最近把 Ganglia 架起來,再看到 Cloudera 的兩篇 [http://www.cloudera.com/blog/2009/03/12/hadoop-metrics/ Ganglia] 和 [http://www.cloudera.com/blog/2009/07/07/hadoop-graphing-with-cacti/ Cacti] 相關的文章,大概比較能理解 Chukwa 這個專案要處理的事情應該頗為類似。比較特殊的是它要處理的是 500 至 2000 台節點的 Log 分析。 * [http://wiki.apache.org/hadoop-data/attachments/Chukwa/attachments/ChukwaPoster.pdf Chukwa Poster] (PDF) - 設計得蠻乾淨的,可以當做 SC'09 Poster 的參考。 == CDH : Cloudera's Distribution for Hadoop == * [http://www.cloudera.com/hadoop-manifest Cloudera 的 Hadoop 套件相較於官方 tar ball 的差異] * [http://www.oreillynet.com/pub/e/1379 An Introduction to Hadoop] - Presented by: Christophe Bisciglia, Tom White == Virtualization == * [http://www.citrix.com/English/aboutCitrix/caseStudies/caseStudy.asp?storyID=1690121 Citrix Case study: HSBC Bank] == Debian == * 用來畫套件相依性的 [http://packages.debian.org/debtree debtree] 終於進入 sid 套件庫了 == Green Computing == * [http://developer.yahoo.net/blogs/theater/archives/2009/07/energy_efficient_hadoop.html Yanpei Chen & Laura Keys: Energy Efficient Hadoop] * [http://www.eecs.berkeley.edu/~ychen2/ Yanpei Chen] * [http://www.eecs.berkeley.edu/~laurak/ Laura Keys] * 指導教授:[http://eecs.berkeley.edu/~randy Randy H. Katz] * 演講投影片 - [http://www.eecs.berkeley.edu/~ychen2/professional/EEMRHadoopSummit2009.ppt Towards Energy Efficient Hadoop] * 介紹中提到 datacenter 多數使用 Power Utilization Efficiency (PUE) 跟 Data Center Infrastructure Efficiency (DCiE) 兩個指標來看節能[http://perspectives.mvdirona.com/2009/06/15/PUEAndTotalPowerUsageEfficiencyTPUE.aspx 1] {{{ PUE = Total Facility Power / IT Equipment Power DCiE = IT Equipment Power / Total Facility Power * 100% }}} * [參考][http://www.thegreengrid.org/en/Global/Content/white-papers/The-Green-Grid-Data-Center-Power-Efficiency-Metrics-PUE-and-DCiE The Green Grid Data Center Power Efficiency Metrics: PUE and DCiE] * [http://news.cnet.com/8301-11128_3-10352944-54.html IBM data center gets deep energy retrofit]