2008-11-03

• Devaraj Das 來訪 - 13:05 抵達桃園國際機場

• 設定中群電腦教室為 Hadoop 實驗平台
  • 安裝 JDK, ant, subversion

    $ sudo apt-get install sun-java6-jdk ant subversion
    

  • 下載 Hadoop 0.19 branch

    $ svn co http://svn.apache.org/repos/asf/hadoop/core/branches/branch-0.19/ hadoop-0.19
    

  • 把 hadoop 0.19 branch 打包放到 ​http://trac.nchc.org.tw/hadoop/
• 建立簡報 Broadcast 平台

  $ wget http://nchc.dl.sourceforge.net/sourceforge/vnc-reflector/vnc_reflector-1.2.4.tar.gz
  $ tar zxvf vnc_reflector-1.2.4.tar.gz
  $ 
  

• Flex 參數傳遞 - 用 ​FlashVars

Virtualization

• ​Create a LAN for Virtual Servers with KVM and VDE
  • ​vde2 - Virtual Distributed Ethernet
• ​What can you TEACH us about High Performance Computing?
  • 這個網站的主旨跟我明年度想做的目標相當吻合～
• ​http://workspace.globus.org/ - Nimbus: 基於 Globus 的 Virtual Cluster 管理機制

HPC

• SC'08 - ​HPC 20 週年了!!!

• 關於 HPC 的 P = 是 Performance , Power 還是 Productivity? - ​Is supercomputing just about performance?

  It's all too easy to focus HPC budgets on the hardware and, increasingly, the electricity. That's understandable. The hardware is something that buyers and their bosses can clearly see has been obtained with the money; you can kick it, although I wouldn't recommend it.
  
  人們很容易專注在高速運算的硬體採購預算（當然近來也越來越關切電力開銷）。這很容易理解，因為硬體是採購者還有他們的老闆都可以清楚看到用錢堆砌出來的成果。（你可以踢它，縱使我不建議這麼做）
  
  Investing in other aspects of productivity — such as people, processes and software — may seem less concrete and provides nothing kickable, but in reality the business case may be even easier.
  
  投資在其他生產力－如人力、流程和軟體－或許看起來不怎麼具體（也踢不到），但事實上執行起來反而比要容易些。
  

Open Source

• 2008-11-03~07 : ​Ubuntu Open Week
• ​Using Calc to manage schedules

dsh like

• ​Parallel SSH execution and a single shell to control them all
  • ​Parallel ssh (pssh)
  • ​Cluster SSH
  • ​ClusterIt