Apache Spark is a fast, general purpose cluster computing platform. Spark provides a number of processing models including batch processing, iterative algorithms, stream processing and interactive queries. These operations are optimized for speed, enabling the analysis of very large data sets much faster than using traditional map reduce processing.
Furthermore, these operations are integrated in Spark making it easy to combine different types of operations in a single application, and relieving the burden of managing separate tools.
The z Systems platform with its performance, security, integrity, scalability and resilience is the ideal place to run analytic workloads. Big data analytics can help augment what we already know through the wealth of information stored in transactional systems, applications and data warehouses. That is why many clients choose to co-locate their data warehouse and transaction processing solutions with their data analytics engines.