Balancing the compute, storage, and network resources in an Apache Hadoop* cluster enabled the full benefit of the latest Intel® processors, solid state drives, Intel® Ethernet Converged Network Adapters, and the Intel® Distribution for Apache Hadoop Software. Building a balanced infrastructure from these components enabled reducing the time required to complete a workload from about four hours to about seven minutes, a reduction of approximately 97 percent. Results such as these pave the way for low-cost, near-real-time data analytics.
Apache Hive* overview
The Intel® Distribution for Apache Hadoop* Software
Apache HDFS* overview.
Apache Pig* overview.
Apache MapReduce overview.