[YARN-1913] With Fair Scheduler, cluster can logjam when all resources are consumed by AMs

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.3.0
• Fix Version/s: 2.5.0
• Component/s: scheduler
• Assignee: Wei Yan
• Reporter: bc Wong
• Created: 08/Apr/14 16:19
• Updated: 15/Aug/14 05:44
• Resolved: 03/Jun/14 00:59

Description

It's possible to deadlock a cluster by submitting many applications at once, and have all cluster resources taken up by AMs.

One solution is for the scheduler to limit resources taken up by AMs, as a percentage of total cluster resources, via a "maxApplicationMasterShare" config.