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.

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

Suggestion: relative CPU/mem scheduling #251

Open
BernhardHH opened this issue Jan 14, 2020 · 0 comments
Open

Suggestion: relative CPU/mem scheduling #251

BernhardHH opened this issue Jan 14, 2020 · 0 comments

Comments

@BernhardHH
Copy link

BernhardHH commented Jan 14, 2020

Summary

When dealing with multiple slaves in varying CPU/memory configurations, it would be great to enable relative scheduling - say, one server has 8 CPUs (150% load), the other has 2 CPUs (120% load) - so least_cpu should consider the 800% vs 200% CPU ceiling and schedule the next job for server 1, even though the absolute CPU load is higher. It would also be great to be able to define CPU / mem thresholds, where no new jobs are assigned (server 2 has less than 90% CPU available, so will receive no new jobs until dropping below 110% load) and expected cpu/mem load per job so jobs would remain in the queue if there are no sufficient ressources available. This would require to get the system CPU/mem load, not only the child process.

This would help us to distribute the load more evenly.

Cheers,

Bernhard

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants