%0 Conference Paper %1 Dean:2004:MSD:1251254.1251264 %A Dean, Jeffrey %A Ghemawat, Sanjay %B Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation - Volume 6 %C Berkeley, CA, USA %D 2004 %I USENIX Association %K Distributed FaultTolerance Functional MapReduce Programming %P 137--149 %T MapReduce: Simplified Data Processing on Large Clusters %U http://static.usenix.org/event/osdi04/tech/full_papers/dean/dean.pdf %X MapReduce is a programming model and an associated implementation for processing and generating large data sets. Users specify a map function that processes a key/value pair to generate a set of intermediate key/value pairs, and a reduce function that merges all intermediate values associated with the same intermediate key. Many real world tasks are expressible in this model, as shown in the paper.</p> <p>Programs written in this functional style are automatically parallelized and executed on a large cluster of commodity machines. The run-time system takes care of the details of partitioning the input data, scheduling the program's execution across a set of machines, handling machine failures, and managing the required inter-machine communication. This allows programmers without any experience with parallel and distributed systems to easily utilize the resources of a large distributed system.</p> <p>Our implementation of MapReduce runs on a large cluster of commodity machines and is highly scalable: a typical MapReduce computation processes many terabytes of data on thousands of machines. Programmers find the system easy to use: hundreds of MapReduce programs have been implemented and upwards of one thousand MapReduce jobs are executed on Google's clusters every day.

@inproceedings{Dean:2004:MSD:1251254.1251264, abstract = {MapReduce is a programming model and an associated implementation for processing and generating large data sets. Users specify a map function that processes a key/value pair to generate a set of intermediate key/value pairs, and a reduce function that merges all intermediate values associated with the same intermediate key. Many real world tasks are expressible in this model, as shown in the paper.</p> <p>Programs written in this functional style are automatically parallelized and executed on a large cluster of commodity machines. The run-time system takes care of the details of partitioning the input data, scheduling the program's execution across a set of machines, handling machine failures, and managing the required inter-machine communication. This allows programmers without any experience with parallel and distributed systems to easily utilize the resources of a large distributed system.</p> <p>Our implementation of MapReduce runs on a large cluster of commodity machines and is highly scalable: a typical MapReduce computation processes many terabytes of data on thousands of machines. Programmers find the system easy to use: hundreds of MapReduce programs have been implemented and upwards of one thousand MapReduce jobs are executed on Google's clusters every day.}, acmid = {1251264}, added-at = {2012-07-05T15:26:24.000+0200}, address = {Berkeley, CA, USA}, author = {Dean, Jeffrey and Ghemawat, Sanjay}, biburl = {https://www.bibsonomy.org/bibtex/24c9b449cf04c48568fe470986a117e68/gron}, booktitle = {Proceedings of the 6th conference on Symposium on Opearting Systems Design \& Implementation - Volume 6}, description = {MapReduce}, interhash = {c853fc61c156362ffecdf9302fe7c33f}, intrahash = {4c9b449cf04c48568fe470986a117e68}, keywords = {Distributed FaultTolerance Functional MapReduce Programming}, location = {San Francisco, CA}, numpages = {1}, pages = {137--149}, publisher = {USENIX Association}, series = {OSDI'04}, timestamp = {2012-07-05T15:27:48.000+0200}, title = {MapReduce: Simplified Data Processing on Large Clusters}, url = {http://static.usenix.org/event/osdi04/tech/full_papers/dean/dean.pdf}, year = 2004 }