Packing Algorithms for Big Data Replay on Multicore
M. Zhanikeev
Abstract
This chapter discusses optimization in a new environment created as an alternative to Hadoop/MapReduce. The core idea is to bring the bulk from now-passive shard nodes to a dedicated machine and replay it locally while a large number of jobs are running on multicore. This chapter discusses optimization methods for machines with a large number of cores and processing jobs. This chapter also discusses how the new architecture can easily accommodate advanced Big Data-related statistics, namely streaming algorithms.
Keywords
Packing algorithms; Big Data replay method; Massively multicore; Hadoop; MapReduce; Data streaming
10.1 Introduction
This chapter discusses ...
Get Big Data now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
