[qob] don’t use unbounded threads reading results #13634
Merged
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Outdated suggestions cannot be applied.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.
CHANGELOG: fix a bug which caused jobs with a large number of partitions (close to 100k) to run out of memory on the driver after all partitions finish.
Cap number of threads allocated when reading results of a cda on the driver.
Still waiting on a test to confirm this fixes the bad scaling with number of partitions.We were reading cda results with a threadpool containing one thread per partition, but kept all but 1000 threads blocked. This changes to use a threadpool of 1000 threads.
We still use a surprising amount of memory when reading results, but this change will likely allow jobs with ~100k partitions to complete.
fixes #13533