Today I conducted a session on Distributed Computing. It mainly focussed on MapReduce and its open source implementation-Hadoop.
The session first covered a brief idea of why we need to have distributed computing since everything is driven by need.Then It covered how a distributed file system works.It focussed on the Google File System.A demonstartion of how Hadoop works on a single node enviornment where a example very similar to the wordcount example was show. It was an election simulation where the input was the votes cast and the Hadoop Job aggregated the results.After this some finer details about Hadoop was covered which was the last topic in the session.
Some resources that are very helpful:
http://code.google.com/edu/parallel/index.html#hadoop
Slides for the session:
http://www.slideshare.net/varunthacker/distributed-computing-3635200
http://www.jakobhoman.com/search/label/Hadoop
How to setup an Hadoop enviorment:
http://www.michael-noll.com/wiki/Running_Hadoop_On_Ubuntu_Linux_%28Single-Node_Cluster%29
http://www.michael-noll.com/wiki/Running_Hadoop_On_Ubuntu_Linux_%28Multi-Node_Cluster%29
If you liked my post, feel free to subscribe to my rss feeds
BlogoSquare
One Comment