[YARN-4280] CapacityScheduler reservations may not prevent indefinite postponement on a busy cluster

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.6.1, 2.8.0, 2.7.1
• Fix Version/s: 2.8.0, 3.0.0-alpha1
• Component/s: capacity scheduler
• Hadoop Flags: Reviewed
• Assignee: Kuhu Shukla
• Reporter: Kuhu Shukla
• Created: 20/Oct/15 14:22
• Updated: 20/Sep/18 21:57
• Resolved: 03/Aug/16 19:07

Description

Consider the following scenario:

There are 2 queues A(25% of the total capacity) and B(75%), both can run at total cluster capacity. There are 2 applications, appX that runs on Queue A, always asking for 1G containers(non-AM) and appY runs on Queue B asking for 2 GB containers.
The user limit is high enough for the application to reach 100% of the cluster resource.

appX is running at total cluster capacity, full with 1G containers releasing only one container at a time. appY comes in with a request of 2GB container but only 1 GB is free. Ideally, since appY is in the underserved queue, it has higher priority and should reserve for its 2 GB request. Since this request puts the alloc+reserve above total capacity of the cluster, reservation is not made. appX comes in with a 1GB request and since 1GB is still available, the request is allocated.

This can continue indefinitely causing priority inversion.

Issue Links

• causes: YARN-8804 resourceLimits may be wrongly calculated when leaf-queue is blocked in cluster with 3+ level queues