[DRILL-4800] Improve parquet reader performance

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 1.9.0
• Labels: doc-complete
• Assignee: Parth Chandra
• Reporter: Parth Chandra
• Reviewer: Kunal Khatua
• Created: 22/Jul/16 18:48
• Updated: 25/Sep/18 01:44
• Resolved: 05/Nov/16 00:19

Description

Reported by a user in the field -

We're generally getting read speeds of about 100-150 MB/s/node on PARQUET scan operator. This seems a little low given the number of drives on the node - 24. We're looking for options we can improve the performance of this operator as most of our queries are I/O bound.