New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 696079 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Not on Chrome anymore
Closed: Feb 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

11.5%-52.5% regression in blink_perf.canvas at 451896:452027

Project Member Reported by m...@chromium.org, Feb 24 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Feb 25 2017


=== BISECT JOB RESULTS ===
NO Perf regression found, tests failed to produce values

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : blink_perf.dom
  Metric       : long-sibling-list/long-sibling-list


To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.dom

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986733814195971952

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5335567417475072


| 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 Speed>Bisection.  Thank you!

Comment 5 by m...@chromium.org, Feb 25 2017

Re-running bisect. The graphs are QUITE clear there's a stair-step down.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Feb 25 2017


=== BISECT JOB RESULTS ===
NO Perf regression found, tests failed to produce values

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : blink_perf.canvas
  Metric       : getImageData/getImageData


To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.canvas

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986718830256780320

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6652345066192896


| 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 Speed>Bisection.  Thank you!

Comment 7 by m...@chromium.org, Feb 25 2017

Status: WontFix (was: Untriaged)
Graphs have recovered.
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Apr 11 2017

Cc: nainar@chromium.org
Owner: nainar@chromium.org

=== Auto-CCing suspected CL author nainar@chromium.org ===

Hi nainar@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


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

Suspected Commit
  Author : nainar
  Commit : 8b6c7b7ce5a36d8eda49dd6e60c5e7c8f5c7277f
  Date   : Wed Feb 22 10:52:39 2017
  Subject: Call Element::rebuildLayoutTree from Document::updateStyle directly

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : blink_perf.dom
  Metric       : long-sibling-list/long-sibling-list
  Change       : 11.58% | 168.394020354 -> 148.887688372

Revision             Result                  N
chromium@451939      168.394 +- 3.34838      6      good
chromium@451983      166.452 +- 4.0719       6      good
chromium@451986      165.283 +- 6.41915      6      good
chromium@451987      148.238 +- 5.12309      6      bad       <--
chromium@451988      149.444 +- 6.98084      6      bad
chromium@451989      148.23 +- 2.78261       6      bad
chromium@451994      148.322 +- 1.96924      6      bad
chromium@452005      147.605 +- 1.98813      6      bad
chromium@452027      148.888 +- 1.77618      5      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.dom

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982619859571362400

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5335567417475072


| 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 Speed>Bisection.  Thank you!

Sign in to add a comment