Fix node count and tasks-per-node in mache.parallel#376
Merged
xylar merged 2 commits intoE3SM-Project:mainfrom Apr 2, 2026
Merged
Fix node count and tasks-per-node in mache.parallel#376xylar merged 2 commits intoE3SM-Project:mainfrom
mache.parallel#376xylar merged 2 commits intoE3SM-Project:mainfrom
Conversation
We should always be allocating the minimum number of nodes on which the number of tasks will fit.
We want as many tasks per node as possible so idle nodes are potentially available for other work.
Collaborator
Author
|
I will test this in combination with other mache 3.3.0 changes. |
Collaborator
Author
TestingI was able to see that I got the expected, reduced number of nodes with this fix. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
First, we don't want to request more nodes than the number of tasks, which is currently happening under Slurm for small jobs.
Second, we don't really want to be spreading runs across all allocated nodes, we want to request the minimum number of nodes that will hold the run. This is because we want the option in the not-to-distant future (in Polaris at least) to run multiple tasks in parallel as resources allow.
Checklist
Testingcomment, if appropriate, in the PR documents testing used to verify the changes