With more and more intelligent and interconnected devices and systems, the data companies are collecting is growing at unprecedented rates. As much as 90% of that data is unstructured, coming from social media, electronic documents, machine data, connected devices, etc., and growing at rates as high as 50% per year. This is big data.
Extracting insights from big data can make your business more agile, more competitive and provide insights that, in the past, were beyond reach. The emergence of recent technologies such as the real-time analytics processing capabilities of stream computing, high speed in-memory analytics using Apache Spark and the massive MapReduce scale-out capabilities of Hadoop® has opened the door to a world of possibilities. This has also created the need for robust infrastructures that combine computing power, memory and data bandwidth to process and move large quantities of data -- fast.
Based on this need, the IBM Power System S812LC was used to design a solution to create a big data environment built on a heritage of strong resiliency, availability and security -- the IBM Data Engine for Hadoop and Spark - Power Systems Edition.
The IBM Data Engine for Hadoop and Spark - Power Systems Edition
With a data-centric design, this Linux-based solution offers a tightly-integrated and performance-optimized infrastructure for in-memory Spark and MapReduce-based Hadoop big data workloads. The IBM Data Engine for Hadoop and Spark can be tailored specifically to meet your Big Data workloads by using a simple building block approach to match the mix of memory, networking and storage to application requirements. This approach gives you the best possible infrastructure for your big data workload.
IBM Data Engine for Hadoop and Spark
An IBM System Reference Guide
Features and benefits
Power S812LC delivers 2.3X BETTER performance per dollar spent for Spark workloads1
1 All results are based on IBM Internal Testing of 10 SparkBench benchmarks consisting of SQL RDD Relation, Twitter, Pageview Streaming, PageRank, Logistic Regression, SVD++, TriangleCount, SVM, MF, SQL Hive
- IBM Power System S812LC 10 cores / 80 threads, 1 X POWER8; 2.9GHz, 256 GB memory, Ubuntu 15.04, Spark 1.4, OpenJDK 1.8
- Intel Xeon HP DL380; 24 cores / 48 threads, 2 X E5-2690 v3; 2.6GHz , 256 GB memory. Ubuntu 15.04, Spark 1.4, OpenJDK 1.8
- Pricing is based on web prices for S812LC and HP DL380