New issue
Advanced search Search tips

Issue 710205 link

Starred by 1 user
Status: WontFix
Owner:
skau@chromium.org
Closed: May 2017
Cc:
m...@chromium.org
skau@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression

Blocked on:
issue 711039


Sign in to add a comment

1.2%-288% regression in page_cycler_v2.intl_ar_fa_he at 462291:462751

Project Member Reported by m...@chromium.org, Apr 10 2017 
See the link to graphs below.

Comment 1 by m...@chromium.org, Apr 10 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=710205

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_PGTqwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_MfEswoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_KDVtAsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_MOHtQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvMjB-ggM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_LSBvAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvL-84wgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_PzMoQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_KC6-AoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvMfJtQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvPLCrwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP_uoAsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP_uoAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_MiGsQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvJnlhAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvPKdsQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvN_KqQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvKOeqAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvNPspQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvI7argsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_NSnuAsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvIGZ5AgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvPHkvwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3I-djwsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvPCrkQgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvPLJoAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvIP0hAsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP_u4AoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvNyajgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvJ3V5wgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvOW6vgsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_JKooQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvMjBugsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3LGIyQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvOW6vgkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP-5sQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP-5sQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvP_uoAoM


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

android-nexus5X
android-nexus6
android-one
android-webview-nexus6

Comment 4 by m...@chromium.org, Apr 12 2017

Blockedon: 711039
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Apr 13 2017 


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

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-warm/http___ynet.co.il_

Revision             Result                  N
chromium@462290      2700.84 +- 138.223      21      good
chromium@462744      2708.74 +- 173.101      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...ynet.co.il. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982418387016812064

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5011335097614336


| 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!
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Apr 14 2017

Cc: skau@chromium.org
Owner: skau@chromium.org

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

Hi skau@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 : skau
  Commit : 74cea7ee6f641c6f59970a45bc6a5ec334020131
  Date   : Thu Apr 06 00:23:56 2017
  Subject: Fix style for aggregate initializer.

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-warm/http___ynet.co.il_
  Change       : 1.84% | 2683.331 -> 2732.76721429

Revision             Result                  N
chromium@462290      2683.33 +- 147.964      14      good
chromium@462291      3491.9 +- 65.1131       6       bad       <--
chromium@462292      3467.64 +- 109.01       6       bad
chromium@462294      3455.36 +- 159.559      6       bad
chromium@462298      2840.78 +- 1333.04      21      bad
chromium@462304      2730.83 +- 107.699      14      bad
chromium@462318      2748.48 +- 74.7307      6       bad
chromium@462347      2729.76 +- 201.227      21      bad
chromium@462402      2731.28 +- 147.417      14      bad
chromium@462517      2733.4 +- 133.79        14      bad
chromium@462744      2732.77 +- 175.783      14      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...ynet.co.il. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982401595250092704

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5011335097614336


| 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 9 by skau@chromium.org, Apr 14 2017 

Is the compiler doing something funny?  This is an aggregate initialization.  In this case, brace elision is supposed to be optional but since clang was complaining, they were added.  The CL should be a no-op.

http://en.cppreference.com/w/cpp/language/aggregate_initialization

Comment 10 by skau@chromium.org, Apr 14 2017 

Also, I'm not quite sure how to read the chart but it looks like the runtime is within the margin of error.

Comment 11 by m...@chromium.org, Apr 14 2017 

Some of the metrics are failing with a 200% increase, so definitely not margin of error. I'll kick-off another bisect job on a different metric to determine whether it really is your change, or some other change.
Project Member

Comment 13 by 42576172...@developer.gserviceaccount.com, Apr 15 2017 


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

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstContentfulPaint_avg/pcv1-warm/http___ynet.co.il_

Revision             Result                  N
chromium@462250      274.279 +- 99.1603      21      good
chromium@462800      279.893 +- 98.8794      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...ynet.co.il. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982300012444496784

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4507585631223808


| 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!
Project Member

Comment 15 by 42576172...@developer.gserviceaccount.com, Apr 15 2017 


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

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstContentfulPaint_avg/pcv1-warm/http___ynet.co.il_

Revision             Result                  N
chromium@462250      267.584 +- 128.338      21      good
chromium@462800      273.496 +- 123.226      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...ynet.co.il. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982269474395746000

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4507585631223808


| 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!
Project Member

Comment 17 by 42576172...@developer.gserviceaccount.com, Apr 16 2017 


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

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-warm/http___www.masrawy.com_

Revision             Result                  N
chromium@462290      722.856 +- 107.098      21      good
chromium@462744      714.439 +- 87.1906      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.masrawy.com. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982171262649660848

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4507585631223808


| 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 18 by skau@chromium.org, Apr 17 2017 

The bisect results seem inconclusive.
Project Member

Comment 20 by 42576172...@developer.gserviceaccount.com, Apr 25 2017 


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

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_es_fr_pt-BR
  Metric       : timeToFirstContentfulPaint_avg/pcv1-warm/http___elmundo.es_

Revision             Result                  N
chromium@462290      402.687 +- 124.124      21      good
chromium@462744      397.821 +- 154.649      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...elmundo.es. page_cycler_v2.intl_es_fr_pt-BR

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981530101034973440

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4507585631223808


| 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 21 by m...@chromium.org, May 2 2017

Status: WontFix (was: Untriaged)
Looks like things recovered.
►

Sign in to add a comment