Bug 1014218

Summary:	RFE: more intelligent scheduling
Product:	[Retired] Beaker	Reporter:	Jaroslav Kortus <jkortus>
Component:	scheduler	Assignee:	beaker-dev-list
Status:	CLOSED DUPLICATE	QA Contact:	tools-bugs <tools-bugs>
Severity:	unspecified	Docs Contact:
Priority:	unspecified
Version:	0.11	CC:	aigao, asaha, dcallagh, llim, qwan, rmancy
Target Milestone:	---	Keywords:	FutureFeature
Target Release:	---
Hardware:	Unspecified
OS:	Unspecified
Whiteboard:
Fixed In Version:		Doc Type:	Enhancement
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2013-10-02 01:29:59 UTC	Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:

Description Jaroslav Kortus 2013-10-01 14:24:11 UTC

Description of problem:
I'm periodically seeing a non-wise selection of nodes. I have several LC with many hosts and when the utilization of one goes high, following happens:

RS:
node-1 - scheduled
node-2 - scheduled
node-3 - scheduled
node-4 - queued

This is not wise, as there are other LCs that would be suitable for the job and have free resources. So while I've plenty of resources available, the job is delayed until one particular LC is free.

Version-Release number of selected component (if applicable):
0.11.3

How reproducible:
always

Steps to Reproduce:
1. schedule recipeset with more recipes than nodes available on one LC, while having another LC with enough resources to run it too
2. wait for it to happen :)
3.

Actual results:
job delayed, resources not used effectively

Expected results:
job scheduled on first free LC that could host it, if none is found, queue it

Additional info:

Comment 2 Dan Callaghan 2013-10-02 01:29:59 UTC


*** This bug has been marked as a duplicate of bug 709012 ***