Fault Tolerant HDFS r/w with Apache Apex; and Apex (native Hadoop) benchmarks

Do come to pick up Apache Apex T-Shirts.

This presentation will cover deep dive into file operators, and extending Yahoo! streaming benchmarks to Apache Apex (next generation native Hadoop platform that does both streaming and batch)

Agenda:

6:00pm: Food, Drinks, Socialize

6:15pm: Deep dive into how operators read from and write to files for exactly-once semantics - Chandni Singh, committer Apache Apex

7:00pm: Q&A

7:15pm: Extending Yahoo Streaming computation Benchmark to Apache Apex - Sandesh Hegde, committer Apache Apex

8:00pm: Mingle, Food, Drinks

Abstract:

Talk #1: Deep dive into how operators reads and writes from/to files in an idempotent manner. This will cover file input operator, file splitter, block reader on the input side and file output operator on the output side. We will present how these operators are made scalable and fault tolerant with the hooks provided by Apache Apex platform.

Talks #2: Extending Yahoo Streaming computation Benchmark to Apache Apex

• Application topology

• Comparison of results between Storm, Flink and Apex

• Variation of the Apex Benchmarking App with event time and 'results query' support

• Demo

@ApacheApex (https://twitter.com/apacheapex), meetup presentations (http://www.slideshare.net/ApacheApex/presentations), meetup recordings (https://www.youtube.com/user/datatorrent), download (https://www.datatorrent.com/download/datatorrent-community-edition-download/), Apache Apex releases (http://apex.incubator.apache.org/downloads.html), docs (http://apex.incubator.apache.org/docs.html)