Fix excessive mmap-ing in LMDB (cherrypick of #11513) #11516
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Outdated suggestions cannot be applied.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.
Problem
Core dumps collected on macOS are very large currently because they include all mmap'd data. According to
vmmap
, this is because LMDB ismmap
'ing 1.7TB of data. And... it is! But not intentionally.Solution
ShardedLmdb
was not dividing themax_size
by the number of shards, and since each shard used their own LMDBEnvironment
, we were ending up with16 * max_size
mmap
'd. Additionally, we had set some of our databases to sizes that are well beyond what we expect the database to grow to when GC is running consistently.Result
It is now possible to gather core dumps on macOS, which should assist in the debugging of #11364.
[ci skip-build-wheels]