[AVRO-2696] Improve Avro Double and Float Encode Performance

• Type: Improvement
• Status: Closed
• Priority: Minor
• Resolution: Fixed
• Fix Version/s: 1.10.0
• Assignee: David Mollitor
• Reporter: David Mollitor
• Created: 17/Jan/20 21:30
• Updated: 02/Jul/20 12:22
• Resolved: 29/Mar/20 10:37

Description

I was looking at how Avro encodes Doubles and Floats and comparing it to Java's.

So, I checked it out and found that the Java version for Floats is faster than Avro using the Avro perf tests:

# Avro Impl
FloatTest.encode  thrpt    3  273709210.133 ± 49629107.871  ops/s
FloatTest.encode  thrpt    3  271515727.631 ± 57405372.266  ops/s

# Java Impl
FloatTest.encode  thrpt    3  278234438.923 ± 34633982.243  ops/s
FloatTest.encode  thrpt    3  284801936.136 ± 52273884.157  ops/s

Interestingly, I wasn't able to reproduce this gain with Doubles. Avro's version was faster. However, we can remove the bitwise mask (Java doesn't bother to do it).

https://github.com/openjdk/jdk/blob/6bab0f539fba8fb441697846347597b4a0ade428/src/java.base/share/classes/java/io/Bits.java#L105

Issue Links

• links to: GitHub Pull Request #776