An Architecture for Fast and General Data Processingon Large Clusters
https://github.com/JerryLead/SparkInternals/tree/master/markdown
======================================================
Spark是用Scala来编写的,要搞懂Spark,学习下Scala是太有必要了!作为一个JAVA开发者,直接看Scala的编程语言书籍还是有诸多的不适应,Scala的语法太过于神奇了,简洁得让人觉得混乱不堪,不时的会把它拿来和Java语法比较下,但是直接比较还是有些难度,网上有一大堆的过来人写的资料,很是有益!
http://developer.51cto.com/art/200909/154717.htm
http://developer.51cto.com/art/200909/150625.htm
http://developer.51cto.com/art/200909/154676.htm
http://twitter.github.io/scala_school/zh_cn/index.html
http://www.artima.com/scalazine/articles/steps.html
http://www.importnew.com/3240.html
http://www.scala-china.net/discuz/forum.php