Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Summarizing scores in generic_scheduler done sequentially #46027

Closed
yastij opened this issue May 18, 2017 · 9 comments
Closed

Summarizing scores in generic_scheduler done sequentially #46027

yastij opened this issue May 18, 2017 · 9 comments
Assignees
@yastij
Labels
sig/scheduling Categorizes an issue or PR as relevant to SIG Scheduling.

Comments

@yastij
Copy link
Member

yastij commented May 18, 2017 •
edited

Is this a request for help? (If yes, you should use our troubleshooting guide and community support channels, see http://kubernetes.io/docs/troubleshooting/.): No.

What keywords did you search in Kubernetes issues before filing this one? (If you have found any duplicates, you should instead reply there.):

generic_scheduling
scheduler
scoring

Is this a BUG REPORT or FEATURE REQUEST? : FEATURE REQUEST

in /kubernetes/plugin/pkg/scheduler/core/generic_scheduler.go the function PrioritizeNodes Prioritizes the nodes, but at some point (line 374) :

for i := range nodes {
		result = append(result, schedulerapi.HostPriority{Host: nodes[i].Name, Score: 0})
		for j := range priorityConfigs {
			result[i].Score += results[j][i].Score * priorityConfigs[j].Weight
		}
	}

Summarizing all scores is done sequentially, maybe we should consider parallelizing it using wq ?
@yastij
Copy link
Member Author

yastij commented May 18, 2017

/sig scheduling

@k8s-ci-robot k8s-ci-robot added the sig/scheduling Categorizes an issue or PR as relevant to SIG Scheduling. label May 18, 2017
@yastij
Copy link
Member Author

yastij commented May 18, 2017

/assign

@resouer
Copy link
Contributor

resouer commented May 19, 2017 •
edited

Does this improve performance? Seems not too much help at first glance ...

@yastij
Copy link
Member Author

yastij commented May 19, 2017 •
edited

if you want i can submit a fix + benchmark on a high number of nodes by sunday

EDIT : i think the

	// TODO: Consider parallelizing it.

was added by @wojtek-t any insight on this one before benchmarking it ?

@resouer
Copy link
Contributor

resouer commented May 21, 2017

Yes, please send a benchmark.

@wojtek-t
Copy link
Member

I think this won't improve much. There are a bunch of places that would benefit more from.

@yastij
Copy link
Member Author

yastij commented May 22, 2017

indeed, maybe we should remove the TODO then.

@wojtek-t
Copy link
Member

I'm fine with removing TODO.

@yastij
Copy link
Member Author

yastij commented May 22, 2017 •
edited

submitting PR after WH then.

yastij added a commit to yastij/kubernetes that referenced this issue May 23, 2017
@yastij
removing this todo after discussion (kubernetes#46027)
a348a4e
@yastij yastij mentioned this issue May 23, 2017
Merged
k8s-github-robot pushed a commit that referenced this issue May 23, 2017
Merge pull request #46285 from yastij/scheduling-delete-todo
f8815c9 
Automatic merge from submit-queue

removing generic_scheduler todo after discussion (#46027)

**What this PR does / why we need it**:

**Which issue this PR fixes** #46027 

**Special notes for your reviewer**: just a quick clean cc @wojtek-t 

**Release note**:
```release-note
```
@yastij yastij closed this as completed May 23, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@yastij yastij

Labels
sig/scheduling Categorizes an issue or PR as relevant to SIG Scheduling.
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@resouer @yastij @wojtek-t @k8s-ci-robot