And Presto; an Open-Source SQL-on-Hadoop Engine from Facebook
Facebook announced that it is taking its SQL query engine for Hadoop, dubbed Presto, open source.
The offering is widely considered far faster than other data warehouse frameworks including Hive, which Facebook actually developed several years ago. Facebook software engineer Martin Traverso actually said Presto was upwards of ten times faster than Hive.
Facebook currently uses Presto for interactive queries against several of its internal data stores, including their 300PB data warehouse. Over 1,000 Facebook employees use Presto daily to run more than 30,000 queries that in total scan over a petabyte each per day. Companies including Airbnb and Dropbox also use the solution.
Presto, of course, is far from the only SQL-on-Hadoop engine. Cloudera offers Impala, Google offers Dremel, and several including Hortonworks’ Stinger project, and Pivotal’s HAWQ are all clamoring for developer and analyst attention.