Uh oh!
There was an error while loading. Please reload this page.
branch-4.1: [fix](function) avoid ICU default-locale contention #66440 - #67071
Merged
Conversation
### What problem does this PR solve? Issue Number: close#66439 Problem Summary: ICU's `UnicodeString::toLower()` / `toUpper()` with no explicit Locale argument internally calls `locale_get_default_69()`, which acquires a global mutex. Under concurrent multi-threaded LOWER/UPPER/INITCAP evaluation on UTF-8 data (e.g. a 20 TB Hudi scan with `lower(event_id) LIKE '%pattern%'` predicates), this mutex becomes a severe CPU bottleneck — flame graphs show 82% of CPU samples in `native_queued_spin_lock_slowpath` below `locale_get_default_69`. Passing `icu::Locale::getRoot()` explicitly bypasses the default-locale lookup entirely, eliminating the lock contention. This also makes case conversion deterministic across BE hosts regardless of process environment locale. ### Release note Yes: LOWER/UPPER/INITCAP now use the ICU root locale for case conversion, making results independent of the process default locale. This is a behavior change for deployments where the BE process runs under a non-root locale (e.g. Turkish locale would have mapped 'I' to 'ı' (dotless i) instead of 'i'). ### Check List (For Author) - Test: BE unit tests (function_string_lower_test, function_string_upper_test, function_initcap, function_string_case_root_locale_test) - Behavior changed: Yes — case conversion now uses root locale instead of process default locale - Does this need documentation: No ### PS flame graph before this commit: <img width="1456" height="908" alt="image" src="https://github.com/user-attachments/assets/6326988e-9005-4a11-9bd3-fc9e4db3e0fd" /> flame graph after this commit: <img width="1444" height="906" alt="image" src="https://github.com/user-attachments/assets/1879b713-a134-49fc-9822-6f04c0ad54d9" /> which gains a 17-times speedup in our case.
hello-stephen
commented
Aug 24, 2026
Contributor
Thank you for your contribution to Apache Doris. Please clearly describe your PR:
|
hello-stephen
commented
Aug 24, 2026
Contributor
run buildall |
hello-stephen
commented
Aug 24, 2026
Contributor
BE Regression && UT Coverage ReportIncrement line coverage Increment coverage report
|
yiguolei
approved these changes
Aug 25, 2026
ContributorAuthor
PR approved by anyone and no changes requested. |
ContributorAuthor
PR approved by at least one committer and no changes requested. |
Uh oh!
There was an error while loading. Please reload this page.
This file contains hidden or 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
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Cherry-picked from #66440