Changes between Version 9 and Version 10 of HyperTable

Timestamp:

Mar 20, 2008, 9:32:21 AM (16 years ago)

Author:

sunny

Comment:

--

HyperTable

@@ -1 @@
-= Hypertable 源起 =
+[[PageOutline]]
+
+= Hypertable Knowledge Database =
+
+== 【Hypertable 源起】 ==
     搜尋引擎公司Zvents以Google的9位研究人員在2006年發表的Bigtable(簡稱BT，Google內部使用的文件儲存系統)設計規格為基礎[FYI]《[http://labs.google.com/papers/bigtable-osdi06.pdf Bigtable：結構化數據的分佈存儲系統]》，推出了一款開放源碼的分散式數據儲存系統Hypertable專案。以 C++ 撰寫，可架在 HDFS 和 KFS 上，按照1000節點比例設計，0.9 alpha測試版已經在10個節點上測試過，儘管還在初期階段，但已有不錯的效能：寫入 28M 列的資料，各節點寫入速率可達 7MB/s，讀取速率可達 1M cells/s。
 
-= Hypertable 簡介 =
+== 【Hypertable 簡介】 ==
     總結來說Hypertable是一個高效能，分散式，開放源碼，與欄位導向的資料庫，可以儲存,處理叢集電腦上大量的節構化與非結構化的資料，Hypertable提供C++的API及HQL(Hypertable Query Language)給用戶端來存取資料庫內容。Hypertable的用途並不是為了取代傳統的資料庫管理系統(像是MySQL與Oracle DB)，而是為了可以儲存與管理大量的資料集。傳統的關連式資料庫RDBMs(Relational Database Management)是交易導向式，提供許多進階功能給使用者查詢結構化的資料庫內容。Hypertable為了逹到規模可彈性調整以及高效能的輸出，捨棄像是RDBMs常在使用的join或其他query的功能特色，MySQL之類的RDBMs系統屬於row-oriented較適合用於寫入動作較頻繁的工作負載情形，Hypertable屬於column-oriented較適合讀取動作較頻繁的工作負載情形。Hypertable建構於分散式檔案系統(DFS)之上，目前有許多DFS系統，任一DFS均可架設Hypertable，一套DFS可以讓許多機器看起來就好像單一虛擬磁碟，而且都均有容錯與備份機制，因此DFSs可以結合許多叢集電腦的儲存資源，提供高速與大資料量的存取效能，故Hypertable架構在DFS之上也就可以提供高速與高容量的資料庫儲存空間。   
-= How it works =
-= Source Code Documentation Tree(Doxygen) =
- * Hypertable: [http://140.110.138.176/hypertable/html/inherits.html Documentation Tree]
-= Performance =
- * [http://code.google.com/p/hypertable/wiki/PerformanceTestAOLQueryLog PerformanceTestAOLQueryLog]
+== 【How it works】 ==
+== 【Performance】 ==
+ * Performance Test: [http://code.google.com/p/hypertable/wiki/PerformanceTestAOLQueryLog AOL Query Log](from Google)
   * Machine Profile
    * 8 data nodes
@@ -16 +18 @@
       * 4 x 7200 RPM SATA drives (mounted JBOD)
   * The AOL query logs were inserted into an 8-node Hypertable cluster. The average size of each row key was ~7 bytes and each value was ~15 bytes. The insert rate (with 4 simultaneous insert processes) was approximately 410K inserts/s. The table was scanned at a rate of approximately 671K cells/s.
-= How we use it =
-
-= Similar Project =
+== 【How we use it】 ==
+== 【Similar Project】 ==
  * [http://hadoop.apache.org/hbase/ HBase]: Bigtable-like structured storage for Hadoop HDFS
   * Hypertable is based very closely on the design of Bigtable, with a few modifications. Hypertable is designed for speed and is written in C++, while Hbase is in Java.
@@ -25 +26 @@
  * [http://diststore.com/ DistStore]
   * DistStore is a family of lightweight Thrift based web services which are extremely scalable in both throughput and dataset size. Its purpose is to offer a simple and flexible data storage solution that can grow with your project from inception to millions of users.
-= How To Install =
- * [http://trac.nchc.org.tw/cloud/wiki/HyperTable/HowToInstall Hypertable installation guide]
-= Reference =
+== 【Reference】 ==
  * [http://www.hypertable.org/ HyperTable 官方網站]
  * [http://my.donews.com/eraera/2006/09/26/swogzstwtqdnwlfrzgsljctkjsbrtuiumxzj/ 翻譯:Google大表(BigTable)] - [http://labs.google.com/papers/bigtable-osdi06.pdf 原文(PDF)]
@@ -38 +37 @@
  * [http://mmdays.com/2008/02/14/cloud-computing/ Cloud Computing 雲端運算]
  * [http://ieeexplore.ieee.org/iel3/4957/13637/00626582.pdf A Hypertabular Visualizer of Query Results]
-= Related News =
+== 【Related News】 ==
  * [http://news.sina.com.tw/tech/sinacn/cn/2008-02-19/154038229686.shtml 微軟收購雅虎存在諸多障礙]
  * [http://www.linuxworld.com/news/2008/020608-hypertable.html Zvents releases open-source cluster database]
+== 【Technology】 ==
+ * Hypertable Installation Guide: [http://trac.nchc.org.tw/cloud/wiki/HyperTable/HowToInstall How to install]
+ * Hypertable Documentation Tree: [http://140.110.138.176/hypertable/html/inherits.html Source Code Documentation Tree](Doxygen)
+ * Hypertable Query Language(HQL) Guide: [http://trac.nchc.org.tw/cloud/wiki/HyperTable/HQLTutorial HQL Hwo To]