Using Apache Kudu for Analytical Workloads
summary
Apache Kudu is presented as a storage layer for real-time analytical workloads that must handle rapidly-changing data at very low time intervals. The talk explains how Kudu supports this use case and concludes with a practical demonstration of a solution built with Kudu for fast-changing analytical data.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 7:00What is Apache Kudu
- 10:12Kudu architecture and features
- 19:12Kudu use cases and benefits
- 27:17High availability and reliability
- 30:12Partitioning and performance
- 34:56Integration with Big Data ecosystem
- 37:59Demo and conclusion
- 39:26Q&A
related talks
40mApache Kudu (incubating): Fast Analytics on Fast Data #bbuzz
33mKudu
40mBuild Real-time Analytic Applications: The Easy Way
39mAccelerate big data analytics with Apache Kylin
39mApache Druid 101
28mThe Heat is On: Architecting for Hot Analytics
20mAnalyzing streaming data with Apache Druid
21mPutting big data self-service analytics in the hands of business people