Varada has made available a new feature enabling data teams to accelerate by 10x-100x queries running on Trino clusters (formerly known as PrestoSQL), directly on the data lake. This new capability follows Varada’s product launch in late 2020.
In addition to the option to deploy Varada as an independent data lake analytics platform, Varada can now be deployed alongside existing Trino clusters and apply its adaptive indexing-based acceleration technology.
SQL queries can continue running as is, with no additional configurations. It is currently available on AWS and is compatible with all Trino and previous PrestoSQL versions.
“Varada learns and analyzes Trino workloads to apply the optimal cache and indexing strategy autonomously,” explained Eran Vanounou, CEO at Varada. “Enabling Trino clusters to leverage Varada’s acceleration is as simple as installing a .JAR file to the nodes. Any query using presto-hive to access the data lake, such as S3 or HDFS, can benefit from Varada’s unprecedented query performance.”
Trino is an open source distributed SQL query engine that allows for querying data right where it lives. Among other advantages, Trino can run analytic queries against any size of data source.
The platform will soon be compatible with PrestoDB, along with expected availability on Google Cloud Platform and Azure clusters.