[HDFS-5239] Allow FSNamesystem lock fairness to be configurable

• Type: Sub-task
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.0.0-alpha, 3.0.0-alpha1
• Fix Version/s: 0.23.10, 2.3.0
• Component/s: namenode
• Hadoop Flags: Reviewed
• Assignee: Daryn Sharp
• Reporter: Daryn Sharp
• Created: 20/Sep/13 14:27
• Updated: 15/Jun/17 05:27
• Resolved: 23/Sep/13 15:30

Description

The fairness of the FSNamesystem#fsLock is hardcoded to true. Using an unfair lock provides a negligible increase to throughput. However this is due to bottlenecks elsewhere in the system. In combination with other changes, such as RPC layer and audit logging, preliminary tests show up to a 5X improvement for a read heavy workload.

Issue Links

• is related to: HDFS-11345 Document the configuration key for FSNamesystem lock fairness