On-Demand Recordings from PrestoCon’s, Webinars, Meetups, and more
While using the Presto Iceberg connector, the in-heap cache in Presto is likely overloaded. In this talk, Beinan and Chunxu will share the design, implementation, and optimization of the off-heap cache to address the scalability challenges. You will learn how to cache Iceberg data and metadata for the Presto Iceberg connector, followed by future work on improving table scans using Apache Arrow.
Apache Iceberg is an open table format for huge analytic datasets. The Presto Iceberg connector consolidates the SQL engine and the table format, to empower high-performant data analytics. Here, Beinan and Chunxu would like to discuss and share the architectural design of the Presto Iceberg connector, advanced Iceberg feature support (such as native iceberg connector, row-level deletion, and iceberg v2 support), and the future roadmap.
Prism is a gateway service for all Presto queries at Uber. It addresses Uber specific needs in four main areas – resource management, query gating, monitoring, and security. It is responsible for proxying over three million weekly queries from 6000+ weekly active users across all of Uber. Presto has variable execution times due to high multi-tenancy at Uber. Prism helps in overcoming those challenges using features like query routing, load balancing, query gating, session parameter checks, failover clusters which helps in maintaining a 99.9% availability and reliability SLA for Presto at Uber. Functionality – Query Execution: 1. Async execution API returns data stream 2. Async execution API returns File Descriptor – Routing – Prism can route queries to different clusters based on client sources. Other functionalities: Load Balancing, Query Gating, Failover, Session Properties, Security
Apache Iceberg is an open table format for huge analytic datasets. At Twitter, engineers are working on the Presto-Iceberg connector, aiming to bring high-performance data analytics on Iceberg to the Presto ecosystem. Here, Chunxu would like to share what they have learned during the development, hoping to shed light on the future work of interactive queries.