Fix for sameNode functionality of ATS with flux. #170
Merged
Conversation
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
Member
Author
|
Also, I bumped the ats version number to 7.0.122 so I could do a public beta install and test the fix. M ats/atsMachines/fluxScheduled.py |
Call get_physical_nodes during init. Need to call this immediately to cache the hardware nodes before any jobs start running. The logic inspects the 'free' nodes reported by flux, which will change during the run, so inspect it immediately, before starting jobs then save the list of hardware nodes.
dawson6
force-pushed
the
feature/dawson/2026-01-08-samenode
branch
from
641e558 to
b4e9580
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Update to map arbitrary strings in the ats 'same_node" option to an actual physical node at run time.
See the test/HelloSameNode directory for test cases.
Basically, one can specify that independent tests are required to run on the same node, and assign an arbitrary string
to specify the node. If two tests have the same string, they will run on the same node. For example:
t1=test (..., same_node='nodeA')
t2=testif(..., same_node='nodeA')
t3=test (..., same_node='nodeB')
t4=testif(..., same_node='nodeB')
t5=test (..., same_node='nodeC')
t6=testif(..., same_node='nodeC')
test 1 and 2 will run on the same node.
test 3 and 4 will run on the same node
test 5 and 6 will run on the same node
The number of node strings is allowed to be greater than the number of physical nodes. The above would work on a 2 node allocation. The ats flux module will wrap around when assigning the tests to nodes. So nodeA and nodeC would be on the same allocation as well (the first node in the allocation). nodeB would be on the seconde node in the allocation.