I just came across this slide about drizzle where they claim to achieve sub-millisecond latency and they compare with Flink, https://www.slideshare.net/SparkSummit/drizzlelow-latency-execution-for-apache-spark-spark-summit-east-talk-by-shivaram-venkataraman
The normal drizzle still performs a bit worse than Flink, but the optimized-drizzle goes really crazy with the latency. How is this even possible? I thought that such performance is almost not possible because of the interaction of data over the network and the time it takes. Any insights and whether Flink has any plans to respond back? Thanks & Regards Biplob -- Sent from: http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/
