[HADOOP-15554] Improve JIT performance for Configuration parsing

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 3.0.0
• Fix Version/s: 3.2.0, 3.1.1, 3.0.4
• Component/s: conf, performance
• Target Version/s: 3.2.0
• Assignee: Todd Lipcon
• Reporter: Todd Lipcon
• Created: 21/Jun/18 17:50
• Updated: 18/Jan/19 00:59
• Resolved: 02/Jul/18 16:32

Description

In investigating a performance regression for small tasks between Hadoop 2 and Hadoop 3, we found that the amount of time spent in JIT was significantly higher. Using jitwatch we were able to determine that, due to a combination of switching from DOM to SAX style parsing and just having more configuration key/value pairs, Configuration.loadResource is now getting compiled with the C2 compiler and taking quite some time. Breaking that very large function up into several smaller ones and eliminating some redundant bits of code improves the JIT performance measurably.

Issue Links

• causes: HADOOP-16007 Order of property settings is incorrect when includes are processed
• is related to: HADOOP-15973 Configuration: Included properties are not cached if resource is a stream