MapReduce: simplified data processing on large clusters Export

@article{citeulike:2212959, abstract = {MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a map and a reduce function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day.}, address = {New York, NY, USA}, author = {Dean, Jeffrey and Ghemawat, Sanjay}, citeulike-article-id = {2212959}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1327452.1327492}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1327452.1327492}, comment = {Consider using this for IP traffic data reduction / visualization}, doi = {10.1145/1327452.1327492}, issn = {0001-0782}, journal = {Commun. ACM}, keywords = {software\_engineering, telecommunications}, month = {January}, number = {1}, pages = {107--113}, posted-at = {2008-02-18 00:46:37}, priority = {0}, publisher = {ACM}, title = {MapReduce: simplified data processing on large clusters}, url = {http://dx.doi.org/10.1145/1327452.1327492}, volume = {51}, year = {2008} }

TY - JOUR ID - citeulike:2212959 L3 - citeulike-article-id:2212959 N2 - MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a map and a reduce function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day. IS - 1 JF - Commun. ACM SN - 0001-0782 AD - New York, NY, USA EP - 113 TI - MapReduce: simplified data processing on large clusters PB - ACM VL - 51 SP - 107 KW - software_engineering KW - telecommunications N1 - Consider using this for IP traffic data reduction / visualization AU - Dean, Jeffrey AU - Ghemawat, Sanjay PY - 2008/01// UR - http://dx.doi.org/10.1145/1327452.1327492 ER -