New issue
Advanced search Search tips

Issue 868353 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Closed: Aug 6
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

8.9% regression in rasterize_and_record_micro.top_25 at 578117:578214

Project Member Reported by pmeenan@chromium.org, Jul 27

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=868353

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=7a6e194913e5b350d0825e421d7a2388a0579de4f23c2082a29e284c09a408e1


Bot(s) for this bug's original alert(s):

Android Nexus5X WebView Perf
Cc: p...@google.com
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/1382973ba40000

build: Enable ThinLTO in official Android builds. by pcc@google.com
https://chromium.googlesource.com/chromium/src/+/1ba5d6113bd0b5342119bdf2d87946a827af1792
4.489 → 4.89 (+0.4017)

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Cc: -pmeenan@chromium.org
Owner: p...@chromium.org
Cc: -p...@google.com
Status: WontFix (was: Assigned)
This seems to be another case similar to crbug.com/805582#c4 where a toolchain change caused a number of performance changes, the vast majority of which were improvements, but a few outliers were regressions. Perf reports (for my change and the two relands):

https://chromeperf.appspot.com/group_report?rev=578195
https://chromeperf.appspot.com/group_report?rev=578854
https://chromeperf.appspot.com/group_report?rev=579308

Sign in to add a comment