-
-
Notifications
You must be signed in to change notification settings - Fork 587
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
perf(allocator): use mimalloc v2 for all #7361
Conversation
✅ Deploy Preview for rspack canceled.
|
Test Compatibility Diff
Unpassed tests6 🔴 Stats chunkGroups: TODO |
The benchmark for CI is reflecting the result from the tests above. Let's see if there's any huge regression for debian from the issue. |
Summary
Upgraded mimalloc v1 to v2. According to the release:
Raw Data
macOS (using mimalloc 1.0)
Test 1
Test 2
Average
Debian (using jemalloc)
Test 1
Test 2
Average
Alpine (using mimalloc 1.0)
Test 1
Test 2
Average
macOS (using mimalloc 2.0)
Test 1
Test 2
Average
Debian (using mimalloc 2.0)
Test 1
Test 2
Test 3
Average
Alpine (using mimalloc 2.0)
Test 1
Test 2
Test 3
Average
Comparative Analysis
RSS (Resident Set Size) Analysis
Wall Clock Time Analysis
Rspack Compile Time Analysis
Performance of Mimalloc v2.0
Debian (Je vs Mi 2.0)
Alpine (Mi 1.0 vs Mi 2.0)
macOS (Mi 1.0 vs Mi 2.0)
Performance data was generated by this project (a fork from @xc2's original work), running on Apple M2 Max, 64 GB.
Checklist