An Open Source Project for Tuning and Analyzing MapReduce Performance in Hadoop and Spark
Donghua Chen, Runtong Zhang · IEEE Software · 2020
MapReduce parameter tuning is time consuming, and existing tuning systems are difficult to use. We present an open source project, Catla for Hadoop and Spark, to provide comprehensive MapReduce tuning, prediction, and visualization tools based on a series of optimization and machine learning methods.