New issue
Advanced search Search tips

Issue 679503 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 679324
Owner:
Closed: Jan 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression

Blocked on:
issue 669608



Sign in to add a comment

25.6%-42.1% regression in v8.mobile_infinite_scroll_tbmv2 at 441427:441495

Project Member Reported by benhenry@google.com, Jan 9 2017

Issue description

This seems to be only happening with tumblr...
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jan 10 2017


=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : v8.mobile_infinite_scroll_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_max/memory:chrome:all_processes:reported_by_chrome:v8:effective_size_max

Revision             Result                     N
chromium@441426      64250313 +- 122955995      30      good
chromium@441495      81693958 +- 214709527      30      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests v8.mobile_infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990906391838584400

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5809663213305856


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!
Owner: simonhatch@chromium.org
Status: Assigned (was: Untriaged)
Ok, I looked at compare samples. This should've come back with no regression found as there is a clear regression in the Results, but it didn't run intermediate CLs.

Not sure what else to do here.
Blockedon: 669608
Looks like  crbug.com/669608 
Cc: dtu@chromium.org
Maybe Dave can help here as well.
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jan 13 2017

Mergedinto: 679324
Status: Duplicate (was: Assigned)

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : dtapuska
  Commit : 5494d50ab65532c64a28e91e23b0a722ebbfe8ed
  Date   : Wed Jan 04 22:02:35 2017
  Subject: Remove the requirement to only rAF align non-blocking touch moves.

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : v8.mobile_infinite_scroll_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_max/memory:chrome:all_processes:reported_by_chrome:v8:effective_size_max
  Change       : 28.53% | 62680957.3333 -> 80561258.1333

Revision             Result                    N
chromium@441426      62680957 +- 5628584       6      good
chromium@441461      62562127 +- 2670561       6      good
chromium@441470      62191850 +- 3564296       6      good
chromium@441474      63500700 +- 3962897       6      good
chromium@441476      63347917 +- 4526003       6      good
chromium@441477      61525669 +- 2699602       6      good
chromium@441478      78941755 +- 14860680      6      bad       <--
chromium@441495      80561258 +- 10689650      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests v8.mobile_infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990647789716384560

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6460219627929600


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!

Sign in to add a comment