[MAPREDUCE-5489] MR jobs hangs as it does not use the node-blacklisting feature in RM requests

• Type: Bug
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Fix Version/s: 2.2.0
• Target Version/s: 2.2.0
• Hadoop Flags: Reviewed
• Assignee: Zhijie Shen
• Reporter: Yesha Vora
• Created: 30/Aug/13 21:02
• Updated: 30/Jun/15 07:14
• Resolved: 03/Oct/13 21:15

Description

When RM restarted, if during restart one NM went bad (bad disk), NM got blacklisted by AM and RM keeps giving the containers on the same node even though AM doesn't want it there.

Need to change AM to specifically blacklist node in the RM requests.

Issue Links

• is blocked by: YARN-1141 Updating resource requests should be decoupled with updating blacklist
• is related to: YARN-1133 AMRMClient should be able to blacklist nodes, and specify them in AllocateRequest
• is related to: MAPREDUCE-5559 Reconsidering the policy of ignoring the blacklist after reaching the threshold