Meta uses Presto extensively for batch. Come learn about the architecture of Meta’s batch usage, how Presto is tuned in batch clusters, how monitoring and reliability is set up, and the future direction with Spark.
In this talk, we provide a glimpse at the results of our latest benchmark test which compares the speed and cost of processing data inside Snowflake (ELT) vs. processing and serving prepared live tables from a data lake using Upsolver (ETL).