[KUDU-2380] Selective predicates when selecting high number of columns burns CPU in SerializeRowBlock

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 1.8.0
• Component/s: perf, tserver
• Target Version/s: 1.8.0
• Assignee: Todd Lipcon
• Reporter: Todd Lipcon
• Created: 27/Mar/18 16:16
• Updated: 11/Jun/19 19:01
• Resolved: 11/Jun/19 19:01

Description

Testing a table with 280 columns, I found the following performance characteristic:

• scanning all 280 columns with a selective non-key predicate which matches 0 rows took 8.28s
• scanning no columns (count query) with the same predicate which matches 0 rows took 314ms.

This suggests that we are burning 96% of our CPU doing useless work for this query.