reduce contention on startup index generation #31006
Merged
Conversation
This file contains 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
Codecov Report
@@ Coverage Diff @@
## master #31006 +/- ##
=======================================
Coverage 81.5% 81.5%
=======================================
Files 728 728
Lines 205479 205483 +4
=======================================
+ Hits 167560 167565 +5
+ Misses 37919 37918 -1 |
brooksprumo
approved these changes
Mar 31, 2023
| @@ -1087,13 +1093,16 @@ impl<T: IndexValue, U: DiskIndexValue + From<T> + Into<T>> InMemAccountsIndex<T, | |||
| /// These were collected for this bin when we did batch inserts in the bg flush threads. | |||
| /// Insert these into the in-mem index, then return the duplicate (Slot, Pubkey) | |||
| pub(crate) fn populate_and_retrieve_duplicate_keys_from_startup(&self) -> Vec<(Slot, Pubkey)> { | |||
| let mut write = self.startup_info.lock().unwrap(); | |||
| let inserts = self.startup_info.insert.lock().unwrap(); | |||
There was a problem hiding this comment.
nit: Could collapse this into the assert! as well, right?
assert!(self.startup_info.insert.lock().unwrap().is_empty());(Does not need to go into this PR)
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Outdated suggestions cannot be applied.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.
Problem
See #30711
As part of #30736, we stopped writing duplicate entries to the disk index and held them for later.
The issue is the duplicate code shared a mutex with the insertion code.
This meant that insertion into the index from the 432k append vecs was blocking while a disk bucket was flushing. This slowed down overall index generation time which slows down startup time.
Summary of Changes
separate the 2 parts of startup index generation into their own mutexes. This does not affect steady state operation at all.
Fixes #