[MAPREDUCE-5251] Reducer should not implicate map attempt if it has insufficient space to fetch map output

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 0.23.7, 2.0.4-alpha
• Fix Version/s: 0.23.10, 2.1.1-beta
• Component/s: mrv2
• Target Version/s: 0.23.10
• Hadoop Flags: Reviewed
• Assignee: Ashwin Shankar
• Reporter: Jason Darrell Lowe
• Created: 15/May/13 13:50
• Updated: 03/Sep/14 23:52
• Resolved: 26/Jul/13 17:59

Description

A job can fail if a reducer happens to run on a node with insufficient space to hold a map attempt's output. The reducer keeps reporting the map attempt as bad, and if the map attempt ends up being re-launched too many times before the reducer decides maybe it is the real problem the job can fail.

In that scenario it would be better to re-launch the reduce attempt and hopefully it will run on another node that has sufficient space to complete the shuffle. Reporting the map attempt is bad and relaunching the map task doesn't change the fact that the reducer can't hold the output.

Issue Links

• is duplicated by: MAPREDUCE-4852 Reducer should not signal fetch failures for disk errors on the reducer's side
• relates to: TEZ-952 Port MAPREDUCE-5209, MAPREDUCE-5251