New issue
Advanced search Search tips

Issue 831089 link

Starred by 1 user
Status: WontFix
Merged: issue 826829
Owner:
dproy@chromium.org
Closed: Apr 2018
Cc:
cbruni@chromium.org
benjhayden@chromium.org
dproy@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

96.8% regression in v8.runtime_stats.top_25 at 545919:546054

Project Member Reported by cbruni@chromium.org, Apr 10 2018
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Apr 10 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=831089

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=70f23c093321d680eb57a0fe64b218c953c5e2ffddc024c9a1701c70eecee41e


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

chromium-rel-mac12

Comment 6 by cbruni@chromium.org, Apr 10 2018 

Probably just land-revert, in some cases it looks like a real regression though.
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Apr 10 2018 

😿 Pinpoint job stopped with an error.
https://pinpoint-dot-chromeperf.appspot.com/job/12ec292cc40000
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Apr 11 2018

Cc: dproy@chromium.org benjhayden@chromium.org
Owner: dproy@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14ebb6bcc40000

Get navigation info without using FrameLoader snapshots by dproy@chromium.org
https://chromium.googlesource.com/catapult/+/5d35a2c7122c1ac4a9a37e7743a19f628f25a38b

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 9 by cbruni@chromium.org, Apr 11 2018 

I presume this might have modified TTI?
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Apr 11 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12ef166cc40000

Get navigation info without using FrameLoader snapshots by dproy@chromium.org
https://chromium.googlesource.com/catapult/+/5d35a2c7122c1ac4a9a37e7743a19f628f25a38b

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 11 by dproy@chromium.org, Apr 11 2018

Mergedinto: 826829
Status: Duplicate (was: Assigned)

Comment 12 by dproy@chromium.org, Apr 12 2018

Status: WontFix (was: Duplicate)
Unduplicating upon further investigation

Looks like TTI was not being computed for this page before my change, so DomContentLoadedEnd was used as the end time for runtime stats metric [1]. Now that TTI is unbroken, and TTI happens later than DCL, it is expected for this count metric to be bigger. Marking as WontFix.

[1] https://cs.chromium.org/chromium/src/third_party/catapult/tracing/tracing/metrics/v8/runtime_stats_metric.html?l=157&rcl=60096370137d978b562ac9589eb417c329461989
►

Sign in to add a comment