v1.18: accounts-db: fix 8G+ memory spike during hash calculation (backport of #1308) #1318
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
![mergify[bot]](https://avatars.githubusercontent.com/in/10562?s=60&v=4){kind=small}
|
Why I want to backport this: it's a one line change, and it's not hard to reason about. We've seen big stake nodes struggle especially badly with jemalloc stopping random threads to release memory. This removes a 8G alloc/dealloc spike, and I wouldn't be surprised if this fix alone improved skip rate on those nodes. |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## v1.18 #1318 +/- ##
=======================================
Coverage 81.6% 81.6%
=======================================
Files 827 827
Lines 225432 225434 +2
=======================================
+ Hits 184067 184071 +4
+ Misses 41365 41363 -2 |
CriesofCarrots
approved these changes
May 13, 2024
We were accidentally doing several thousands 4MB allocations - even during incremental hash - which added up to a 8G+ memory spikes over ~2s every ~30s. Fix by using Vec::new() in the identity function. Empirically 98%+ reduces join arrays with less than 128 elements, and only the last few reduces join large vecs. Because realloc does exponential growth we don't see pathological reallocation but reduces do at most one realloc (and often 0 because of exp growth). (cherry picked from commit 2c71685)
alessandrod
force-pushed
the
mergify/bp/v1.18/pr-1308
branch
from
c9417f1
to
0b45bdb
Compare
t-nelson
approved these changes
Jun 17, 2024
anwayde
pushed a commit
to firedancer-io/agave
that referenced
this pull request
Jul 23, 2024
…kport of anza-xyz#1308) (anza-xyz#1318) accounts-db: fix 8G+ memory spike during hash calculation (anza-xyz#1308) We were accidentally doing several thousands 4MB allocations - even during incremental hash - which added up to a 8G+ memory spikes over ~2s every ~30s. Fix by using Vec::new() in the identity function. Empirically 98%+ reduces join arrays with less than 128 elements, and only the last few reduces join large vecs. Because realloc does exponential growth we don't see pathological reallocation but reduces do at most one realloc (and often 0 because of exp growth). (cherry picked from commit 2c71685) Co-authored-by: Alessandro Decina <alessandro.d@gmail.com>
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.
We were accidentally doing several thousands 4MB allocations - even during incremental hash - which added up to a 8G+ memory spikes over ~2s every ~30s.
Fix by using Vec::new() in the identity function. Empirically 98%+ reduces join arrays with less than 128 elements, and only the last few reduces join large vecs. Because realloc does exponential growth we don't see pathological reallocation but reduces do at most one realloc (and often 0 because of exp growth).
This is an automatic backport of pull request #1308 done by Mergify.