@article{SchildgenJoergDossingeretal., author = {Schildgen, Johannes and J{\"o}rg, Thomas and Dossinger, Manuel and Deßloch, Stefan}, title = {Marimba: A framework for making MapReduce jobs incremental}, series = {Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014, 27 June 2014 - 02 July 2014, Anchorage, AK, USA}, journal = {Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014, 27 June 2014 - 02 July 2014, Anchorage, AK, USA}, publisher = {IEEE}, doi = {10.1109/BigData.Congress.2014.27}, abstract = {Many MapReduce jobs for analyzing Big Data require many hours and have to be repeated again and again because the base data changes continuously. In this paper we propose Marimba, a framework for making MapReduce jobs incremental. Thus, a recomputation of a job only needs to process the changes since the last computation. This accelerates the execution and enables more frequent recomputations, which leads to results which are more up-to-date. Our approach is based on concepts that are popular in the area of materialized views in relational database systems where a view can be updated only by aggregating changes in base data upon the previous result.}, language = {en} }