Case Study: Yahoo Japan Corporation achieves stable, high-performance big data analytics with Hortonworks

Building a Stable Platform for Big Data in Business

Yahoo Japan Corporation needed a more stable way to manage rapidly growing big data workloads as its Hadoop environment expanded to nearly 6,000 nodes and 75PB of data. With hundreds of internal users relying on the platform, the company faced operational instability and a need to strengthen its technical capabilities, and turned to Hortonworks and Hortonworks Data Platform (HDP) for support.

Hortonworks helped Yahoo Japan Corporation build a mission-critical analytics platform by consolidating clusters, migrating to new HDP clusters, and using tools like Apache Hive on Apache Tez and Apache Ambari. The results included stable large-cluster operations, improved performance, and a 2.4x increase in throughput per cost, with throughput in some areas improving by about 30x.

Yahoo Japan Corporation

Tetsuya Hibino

Manager of the Data Platform Group, Data & Science Solutions Department