This IBM® Redguide™ publication describes big data and analytics (BD&A) deployments that are built on IBM Spectrum Scale™. Spectrum Scale is a proven enterprise-level distributed file system that is a high-performance and cost-effective alternative to Hadoop Distributed File System (HDFS) for Hadoop analytics services.
Spectrum Scale supports varied deployment models, including Spectrum Scale File Placement Organizer (FPO) for storage-rich servers, Spectrum Scale on SAN shared storage, Spectrum Scale on IBM DeepFlash 150™, and an integrated system, called the IBM Elastic Storage™ Server (ESS). These solutions can host various analytics services, such as MapReduce and Spark, with the help of Spectrum Scale HDFS Transparency Hadoop connector (the second-generation IBM GPFS™ Hadoop Connector).
This Redguide publication is intended for technical professionals (analytics consultants, technical support staff, IT Architects, and IT Specialists) who are responsible for providing Hadoop analytics services and are interested in learning about the benefits of the use of Spectrum Scale as an alternative to HDFS.
Table of contents
Traditional Hadoop analytics solutions challenges
Spectrum Scale HDFS Transparency
Spectrum Scale BD&A solution deployment models