[HDFS-4169] Add per-disk latency metrics to DataNode

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Duplicate
• Affects Version/s: 3.0.0-alpha1
• Fix Version/s: 3.0.0-alpha2
• Component/s: datanode
• Assignee: Xiaoyu Yao
• Reporter: Todd Lipcon
• Created: 08/Nov/12 21:22
• Updated: 03/Jan/17 19:36
• Resolved: 03/Jan/17 19:36

Description

Currently, if one of the drives on the DataNode is slow, it's hard to determine what the issue is. This can happen due to a failing disk, bad controller, etc. It would be preferable to expose per-drive metrics/jmx with latency statistics about how long reads/writes are taking.

Issue Links

• duplicates: HDFS-10959 Adding per disk IO statistics and metrics in DataNode.