Presto on AWS Journey at Twilio – Lesson Learned and Optimization – Aakash Pradeep & Badri Tripathy
Twilio as a leader in cloud communication platforms is very heavy on data and data-based decision making. Most data related use cases are currently powered by the Presto engine. Two years back we started the Journey with Presto in Twilio and today the system has scaled to a multi-PB data lakehouse and supports more than 75k queries per day. In this journey, we learned a lot about how to effectively operationalize Presto on AWS and some of the tricks to have better query reliability, query performance, guard-railing the clusters and save cost. With this talk, we want to share this experience with the community.
Building Large-scale Query Operators and Window Functions for Prestissimo using Velox – Aditi Pandit
In this talk, Aditi Pandit, Principal Software Engineer at Ahana and Presto/Velox contributor, will throw the covers back on some of the most interesting portions of working in Prestissimo and Velox. The talk will be based on the experience of implementing the windowing functions in Velox. It will cover the nitty gritty on the vectorized operator, memory management and spilling. This talk is perfect for anyone who is using Presto in production and wants to understand more about the internals, or someone who is new to Presto and is looking for a deep technical understanding of the architecture.
Updates from the New PrestoDB C++ Execution Engine – Deepak Majeti, Ahana & Dave Cohen, Intel
This talk will provide an overview of an ongoing effort to enable the new PrestoDB C++ execution engine, code-named Prestissimo, and its use of the Velox library with the ability to run the TPC-H benchmark with good performance.
Prestissimo – Presto-on-Velox for Faster More Efficient Queries – Orri Erling, Meta
We built a drop-in replacement for the Presto worker using C++ and Velox and saw a dramatic improvements in CPU efficiency and latency for interactive queries. We embraced adaptive execution provided by Velox to efficiently evaluate filters pushed down into scan and automatically enable array-based aggregations and joins. We make extensive use of dictionary encodings to achieve zero-copy execution throughout the engine. We allow for vectorization friendly function implementations, provide ASCII-only fast paths and many other tricks. We’d like to share our learnings, early results and future plans. We are looking forward to invite the community to join our efforts in building the next generation of Presto together.