We present a characterization of four basic terabyte size image computations on a Hadoop cluster in terms of their relative efficiency according to the modified Amdahls law. The work is motivated by the fact that there is a lack of standard benchmarks and stress tests for big image processing operations on a Hadoop computer cluster platform. Our benchmark design and evaluations were performed on one of the three microscopy image sets, each consisting of about a half of a terabyte size image volume. All image processing benchmarks executed on the NIST Raritan cluster with Hadoop were compared against baseline measurements, such as the Tera-Sort/Tera-Gen designed for Hadoop testing previously, image processing executions on a multiprocessor desktop and on NIST Raritan cluster using Java Remote Method Invocation (RMI) with multiple configurations. By applying our methodology to assessing efficiencies of computations on computer cluster configurations, we could rank computation configurations and aid scientists in measuring the benefits of running image processing on a cluster.
Proceedings Title: 2013 IEEE International Conference on Big Data
Conference Dates: October 6-9, 2013
Conference Location: San Diego, CA
Conference Title: http://www.ischool.drexel.edu/bigdata/bigdata2013/callforpaper.htm
Pub Type: Conferences
Big Data Industry Standards, Big Data Open Platform, Big Data Applications and Infrastructure