MapReduce
1. Map: (K, V) -> (K', V')
2. 合并相同K'值的項(xiàng)
(K', V') -> (K', V' *)
3. Reduce
(K', V'*) -> 新的(K,V)
Hadoop實(shí)現(xiàn)自動(dòng)的 Fail-over, Redistribute M/R tasks
Hadoop為Master/Slave結(jié)構(gòu)
1 Master ( Job Tracker) / M Slave (Task Tracker)
HDFS
文件分成固定塊大小,“Write Once", 只能有一個(gè)寫
HDFS也是Master/Salve結(jié)構(gòu)
1 NameNode / N DataNode
其他相關(guān)資源:
Distributed Systems課程 http://www.cs.brandeis.edu/~cs147a/
對(duì)HBase的評(píng)測: www.cs.duke.edu/~kcd/hadoop/
Cloud9: A library for Hadoop http://www.umiacs.umd.edu/~jimmylin/cloud9/umd-hadoop-dist/cloud9-docs/index.html
Cloud Computing課程: http://www.umiacs.umd.edu/~jimmylin/cloud-computing/index.html
UCSD的Network Services課程: http://www-cse.ucsd.edu/classes/fa07/cse124/assignments.html
Virginia的入門課 http://www.cs.virginia.edu/~cbs6n/hadoop/
Hadoop的監(jiān)控 http://www.x-trace.net/wiki/doku.php
Scaling up Hadoop (超強(qiáng),改善Hadoop) http://www.cs.washington.edu/homes/ak/clusterworkshop/slides/YahooHadoopDISC08.pdf
(此人開了咨詢公司 http://www.spinnakerlabs.com/ )
Washington的課程 http://www.cs.washington.edu/education/courses/cse490h/07sp/index.html
Distributed Systems課程 http://www.cs.williams.edu/~jeannie/cs339/index.html
http://pages.cs.wisc.edu/~dusseau/Classes/CS739/index.html
Parrallel Processing http://www.cs.colostate.edu/~cs575dl/