[YARN-4217] Failed AM attempt retries on same failed host

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Duplicate
• Affects Version/s: 2.7.1
• Component/s: applications
• Assignee: Unassigned
• Reporter: Eric Payne
• Created: 01/Oct/15 16:04
• Updated: 14/Oct/19 15:38
• Resolved: 02/Oct/15 13:23

Description

This happens when the cluster is maxed out. One node is going bad, so everything that happens on it fails, so the bad node is never busy. Since the cluster is maxed out, when the RM looks for a node with available resources, it will always find the almost bad one because nothing can run on it so it has available resources.

Issue Links

• duplicates: YARN-2005 Blacklisting support for scheduling AMs