Flink 1.0 - Continuous Streaming Application Framework (Talk by Flink Committer)

We are doing a first Remote session from Germany.

Abstract

The talk will discuss some fundamental patterns and problems behind continuous streaming applications in general, and how we built Apache Flink 1.0 to handle these problems.

Agenda

• Flink stack and runtime

• Techniques in Flink to achieve an end-to-end fault tolerant integration

• Fault tolerance (exactly once)

• Process data streams by "event time" or "processing time"

• Handle out-of-order event streams

• Stateful programs, and save points to manage state (migrating, repairing, or versioning live streaming programs)

• Integration with Apache Kafka - High-availability

Speaker Bio:

Stephan Ewen is Apache Flink committer, and co-founder and CTO of data Artisans. Before founding data Artisans, Stephan was leading the development of Apache Flink since the early days of the project. Stephan holds a PhD in Computer Science from TU Berlin.