5.95% perf_reftest_singletons svg-text-getExtentOfChar-1.html (Windows) regression on Tue August 18 2026
Categories
(Firefox Build System :: Toolchains, defect)
Tracking
(firefox-esr140 unaffected, firefox-esr153 unaffected, firefox154 unaffected, firefox155 unaffected, firefox156 fix-optional, firefox157 affected)
| Tracking | Status | |
|---|---|---|
| firefox-esr140 | --- | unaffected |
| firefox-esr153 | --- | unaffected |
| firefox154 | --- | unaffected |
| firefox155 | --- | unaffected |
| firefox156 | --- | fix-optional |
| firefox157 | --- | affected |
People
(Reporter: performance-sheriff-bot, Assigned: glandium)
References
(Regression)
Details
(4 keywords)
Perfherder has detected a talos performance regression from push 0d975b238e7ec55c4ac4776afcd9318d3134cc68. As author of one of the patches included in that push, we need your help to address this regression.
Please acknowledge, and begin investigating this alert within 3 business days, or the patch(es) may be backed out in accordance with our regression policy.
| Regression | Test | Platform | Options | Absolute values [old vs new] |
|---|---|---|---|---|
| 6% | perf_reftest_singletons svg-text-getExtentOfChar-1.html (doc) | windows11-64-24h2-shippable | e10s fission stylo webrender | 607.79 ms -> 643.92 ms |
| Improvement | Test | Platform | Options | Absolute values [old vs new] |
|---|---|---|---|---|
| 5% | perf_reftest_singletons svg-text-textLength-1.html (doc) | windows11-64-24h2-shippable | e10s fission stylo webrender | 9.37 ms -> 8.89 ms |
Support & Actionable Steps
For questions, please contact fbilt@mozilla.com. You can also find help on Slack (#perf-help) or Matrix (#perftest).
Action guide details:
- See the guide to handling regression bugs for investigation steps.
- Review the alert summary for affected tests, graphs, and comparisons.
- Check the PerfCompare results.
- Tests on Try: Run all tests using
./mach try perf --alert 52257(See documentation link for details). - Test locally: To run the tests locally use
./mach perftest 52257 - Profiling jobs: Trigger jobs from Treeherder job view or request them from fbilt@mozilla.com.
Comment 1•3 months ago
|
||
Set release status flags based on info from the regressing bug 1977771
| Assignee | ||
Updated•2 months ago
|
Comment 2•2 months ago
|
||
Glandium, could you please set a severity for this bug?
Comment 3•2 months ago
|
||
Set release status flags based on info from the regressing bug 1977771
Updated•2 months ago
|
Comment 4•2 months ago
|
||
It has been over 3 days with no activity on this performance regression.
:glandium, since you are the author of the regressor, bug 1977771, which triggered this performance alert, could you please provide a progress update?
If this regression is something that fixes a bug, changes the baseline of the regression metrics, or otherwise will not be fixed, please consider closing it as WONTFIX. See this documentation for more information on how to handle regressions.
For additional information/help, please needinfo the performance sheriff who filed this alert (they can be found in comment #0), or reach out in #perftest, or #perfsheriffs on Element.
For more information, please visit BugBot documentation.
| Assignee | ||
Comment 5•2 months ago
|
||
The LLVM upstream change that triggers this is https://github.com/llvm/llvm-project/commit/b1a93cfc32fbe912bb9b97796145501ea453d1bd. It causes both regressions and improvements, where improvements are more numerous (much much more than what comment 0 points at), and seems like a win overall.
The specific test highlighted by this bug does have some performance problems of its own, and a small difference in codegen associated with the LLVM change indirectly causing some register spill has a disproportionate impact. The test itself seems to illustrate some bad performance properties of the CharIterator code in SVGTextFrame.cpp. Some improvements there look like they could improve the test result by 2 orders of magnitude or close. I will file a separate bug about this.
Description
•