[ARROW-6417] [C++][Parquet] Non-dictionary BinaryArray reads from Parquet format have slowed down since 0.11.x

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.15.0
• Component/s: C++, Python
• Labels: pull-request-available
• External issue URL: https://github.com/apache/arrow/issues/22788
• Assignee: Unassigned
• Reporter: Wes McKinney
• Created: 02/Sep/19 17:59
• Updated: 11/Jan/23 07:47
• Resolved: 14/Oct/19 20:50

Description

In doing some benchmarking, I have found that binary reads seem to be slower from Arrow 0.11.1 to master branch. It would be a good idea to do some basic profiling to see where we might improve our memory allocation strategy (or whatever the bottleneck turns out to be)

Issue Links

• links to: GitHub Pull Request #5268
• links to: GitHub Pull Request #5297