一.HDFS初识
http://www.cnblogs.com/xia520pi/archive/2012/05/28/2520813.html
二.Mapreduce数据流
http://www.cnblogs.com/spork/archive/2010/01/11/1644342.html
http://www.cnblogs.com/spork/archive/2010/01/11/1644346.html
http://www.cnblogs.com/spork/archive/2010/01/11/1644350.html
三.hadoop io
http://blog.youkuaiyun.com/puma_dong/article/details/24173333
四.Hadoop 新 MapReduce 框架 Yarn 详解
http://www.ibm.com/developerworks/cn/opensource/os-cn-hadoop-yarn/
五hadoop三个配置文件的参数含义说明
http://blog.youkuaiyun.com/winnkl/article/details/8098360
六分布式服务框架 Zookeeper
http://www.ibm.com/developerworks/cn/opensource/os-cn-zookeeper/
七 性能优化
http://www.cnblogs.com/datacloud/category/557215.html