bugfix: use larger mempool parameters to avoid running out of pinnables #3810
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Outdated suggestions cannot be applied.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.
Very wide (i.e., 128 pes per node) nonsmp runs of message intensive applications ran into message allocation errors with the prior memory pool settings. These appear as failures to fi_enable with an error message that maps to "address already in use". The latter appears to be a misleading error message as the actual bug appears to be an exhaustion of the number of pinned segments that can be enabled onto the fabric.
This can be avoided by increasing the expand size we use in the memory pool and related quantities for the overall sizing of the pool. Thereby reducing the total quantity of base addresses being pinned, bound, and enabled.