Loading…
NOTE: The event will be held in Central Daylight Time (CDT), UTC -5.

View More Details for Open Source Summit + Embedded Linux Conference North America 2020
Registration Information.
Back To Schedule
Wednesday, July 1 • 12:15pm - 1:05pm
Breaking Out of the Proprietary Cage: Real-time Data Warehouses Come to Open Source - Robert Hodges, Altinity LTD

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
SQL data warehouses are the foundation of high performance analytic solutions on structured information like market tick data or network flow logs. Until recently this type of application has been dominated by proprietary solutions. The situation changed radically with ClickHouse, an Apache 2.0 SQL data warehouse that meets or exceeds performance of Vertica, Redshift, and other closed-source implementations. This talk starts with a quick history of data warehouses including recent open source offerings. We then dive into ClickHouse and study optimizations it uses to achieve record-setting speed. These include compression, vectorized query processing, SIMD instructions, and efficient pre-aggregation through materialized views. Finally we'll show how open source tools like Kafka and Grafana combine with ClickHouse to create complete solutions that offer sub-second response on datasets running into trillions of rows and ingested at millions of events per second. The resulting stack enables users to add real-time analytics to any application without the constraints of proprietary licenses. It's a key open source innovation for the age of big data.

Speakers
avatar for Robert  Hodges

Robert Hodges

CEO, Altinity
Robert Hodges is a data geek who has worked on or with 20 different DBMS types since 1983. He currently works on ClickHouse, a popular open source data warehouse. Besides databases, his technical interests including distributed systems, Kubernetes, and security. In his day job he... Read More →



Wednesday July 1, 2020 12:15pm - 1:05pm CDT
OS Databases Theater