Very interesting talk on Apache Flink

Apache Flink talk & presentation

Presentation Slides

This was a great intro to Apache Flink and comparisons to other technologies like Apache Hadoop MapReduce, Apache Storm, and Apache Spark. I am taking this with a grain of salt at the moment, until I can see it for myself though 🙂

The discussion at the end regarding this new player being widely adopted was very interesting also; some were hesitant to pick it up because of what they imagined to be only minor benefits and appeared that change just wasn’t in their future. I believe the more efficient technology will win as, what appear to be, minor efficiencies may be what allows for processing at the next jump in big data++. Exploding data could turn minor into a major win.

 

Additional references:
Infoworld article – Apache Flink: New Hadoop contender squares off against Spark

Data Artisans – High-throughput, low-latency, and exactly-once stream processing with Apache Flink