[HDFS-4049] hflush performance regression due to nagling delays

• Type: Bug
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Affects Version/s: 2.0.2-alpha, 3.0.0-alpha1
• Fix Version/s: 2.0.3-alpha
• Component/s: datanode, performance
• Target Version/s: 2.0.3-alpha
• Hadoop Flags: Reviewed
• Assignee: Todd Lipcon
• Reporter: Todd Lipcon
• Created: 15/Oct/12 05:17
• Updated: 12/May/16 18:11
• Resolved: 16/Oct/12 00:56

Description

HDFS-3721 reworked the way that packets are mirrored through the pipeline in the datanode. This caused two write() calls where there used to be one, which interacts badly with nagling so that there are 40ms bubbles on hflush() calls. We didn't notice this in the tests because the hflush perf test only uses a single datanode.