[Vaccination 2021] An Overview of the Starburst Trino Query Optimizer (Karol Sobczak)
Starburst unlocks the value of data by making it fast and easy to analyze anywhere. Starburst queries data across any database, making it instantly actionable for organizations. With Starburst, teams can lower the total cost of their infrastructure and analytics investments, use the tools that work best for their business, and our open source Trino roots prevent data lock-in. Trusted by companies like Comcast, FINRA, and Condé Nast, Starburst helps companies make better decisions faster on all data. Starburst is the primary contributor to the open source Trino query engine, a fast distributed SQL query engine for big data analytics. In addition to the standard challenges that face database and query engine developers, the data federation capabilities that make Trino a central part of an open data ecosystem present unique challenges. Moreover, Starburst, as an open-core company, is making large investments in the performance of Trino and their proprietary distribution of Trino. The talk will cover the evolution of the Trino query optimizer and how it has been engineered to overcome the challenges of federation and remain competitive in a crowded field. The talk will also discuss where the engine is headed in the future.
This talk is part of the Vaccination Database (Second Dose) Tech Talk Seminar Series.
Karol Sobczak is a founder at Starburst Data, the company behind the open source Trino query engine, a committer to Trino, and the tech lead for Starburst’s performance team. Trino is a fast distributed SQL query engine for big data analytics. Prior to cofounding Starburst Data, Karol worked on SQL-on-Hadoop products such as Presto at Teradata and Hadapt which was acquired by Teradata.
More Info: https://db.cs.cmu.edu/seminar2021-dose2#db7