[HDFS-13046] consider load of datanodes when read blocks of file

• Type: New Feature
• Status: Open
• Priority: Minor
• Resolution: Unresolved
• Assignee: hu xiaodong
• Reporter: hu xiaodong
• Created: 23/Jan/18 05:32
• Updated: 08/Feb/18 17:21

Description

When sorting block locations, we just consider the distance of datanodes. can we consider the load of datanodes? We can add a configuration such as 'dfs.namenode.reading.considerLoad', if set to true, then sort the blocklocations by load of the datanodes, otherwise sort by distance.