Fix CPU and memory affinity under external resource management #3012
+33
−0
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Outdated suggestions cannot be applied.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.
Fixes CPU affinity when running inference on CPU, and when CPUs are externally managed using taskset, numactl, cgroups, Kubernetes CPU manager, NRI resource policy plugins, for instance.
Detect external CPU management and trust the external CPU manager completely. It is more likely that external manager has the big picture of all other tasks running on the system, their QoS, hardware characteristics, etc.
For instance, do not modify even memory affinity, because the external manager may know better which NUMA node has fastest memory, or which NUMA nodes have enough free memory for this inference.
Fixes #3011