Abstract :
Summary form only given. Workload characterization is a critical activity when designing and implementing computing platforms. Inadequate understanding of the way typical workloads will stress out the different subsystems can lead to inefficient setups, where one component impairs the performance of the entire system. LexisNexis Risk Solutions, a RELX Group Division, originally designed and developed the open source HPCC Systems platform, a Big Data processing and analytics distributed system used to power all of its data and analytical services. As part of the design of the HPCC Systems platform, careful analysis of the different expected workloads provided valuable insight that helped with the engineering of a highly efficient system. During this presentation, we will review the different workloads typical in a Big Data enterprise and analyze the decisions that go into the design and implementation of a Big Data platform.
