New issue
Advanced search Search tips

Issue 710185 link

Starred by 0 users
Status: WontFix
Owner: ----
Closed: Aug 2017
Cc:
gab@chromium.org
lukasza@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

7%-39.4% regression in page_cycler_v2.typical_25 at 462961:463090

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=710185

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_IfIqAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg_KDwsAoM


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

chromium-rel-win7-gpu-intel
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, Apr 12 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : page_cycler_v2.typical_25
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___www.flickr.com_search_?q_monkeys_f_hp

Revision             Result                  N
chromium@462960      2065.15 +- 1801.05      18      good
chromium@463090      2151.71 +- 1763.34      20      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.flickr.com.search..q.monkeys.f.hp page_cycler_v2.typical_25

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982664642059457840

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6616971832983552


| 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 6 by 42576172...@developer.gserviceaccount.com, Apr 12 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg

Revision             Result                   N
chromium@462960      42.5794 +- 1.84112       21      good
chromium@463090      42.5071 +- 0.433943      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982557950411887264

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5222709753020416


| 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 13 2017

Cc: chcunningham@chromium.org
Owner: chcunningham@chromium.org

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

Hi chcunningham@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 : chcunningham
  Commit : 8aeee0b5c65d2ea16d2c52839cf80bcf99273555
  Date   : Fri Apr 07 22:41:40 2017
  Subject: Simplify/Cleanup MediaClient

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg
  Change       : 0.24% | 45.4858607143 -> 45.5932892857

Revision             Result                    N
chromium@462900      45.4859 +- 0.188163       14      good
chromium@462963      45.6717 +- 0.185089       6       good
chromium@462994      45.621 +- 0.0840752       6       good
chromium@463010      45.4536 +- 0.123169       6       good
chromium@463017      45.5509 +- 0.175308       6       good
chromium@463021      45.5354 +- 0.110249       6       good
chromium@463023      45.566 +- 0.268018        6       good
chromium@463024      45.5825 +- 0.0528827      6       good
chromium@463025      46.2056 +- 0.259715       6       bad       <--
chromium@463150      45.5933 +- 0.355798       14      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982483343215919280

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5247321538822144


| 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 m...@chromium.org, Apr 13 2017 

chcunningham: Wait a sec on this, the bisect results don't seem to match the alert graphs. There may be an infra issue here.
Project Member

Comment 12 by 42576172...@developer.gserviceaccount.com, Apr 13 2017 


=== BISECT JOB RESULTS ===
Perf regression found but unable to continue

Bisect was stopped because a commit couldn't be classified as either
good or bad.


Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/image_decoding.html?webp

Revision             Result                   N
chromium@462741      25.814 +- 0.536037       21      good
chromium@462936      25.8934 +- 0.526157      21      unknown
chromium@463131      25.922 +- 0.631366       21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=image.decoding.html.webp image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982397588973985392

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6113638991003648


| 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 13 by 42576172...@developer.gserviceaccount.com, Apr 13 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/image_decoding.html?jpg

Revision             Result                   N
chromium@462960      26.1998 +- 1.16557       21      good
chromium@463090      26.2408 +- 0.955296      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982397571727185744

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6413915455488000


| 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 14 2017

Cc: lukasza@chromium.org
Owner: lukasza@chromium.org

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

Hi lukasza@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 : lukasza
  Commit : 6710dbd5124741db004176153c87c609435e7788
  Date   : Fri Apr 07 20:58:03 2017
  Subject: Revert of [reland] Do not block in SimpleThread::Start(). (patchset #1 id:1 of https://codereview.chromium.org/2801073005/ )

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/image_decoding.html?jpg
  Change       : 0.61% | 30.1792571429 -> 30.3637111111

Revision             Result                   N
chromium@462960      30.1793 +- 0.356833      14      good
chromium@462993      30.2639 +- 0.146854      6       good
chromium@462997      30.2291 +- 0.366752      14      good
chromium@462998      30.4939 +- 0.363725      6       bad       <--
chromium@462999      30.3473 +- 0.328635      14      bad
chromium@463001      30.4677 +- 0.380127      9       bad
chromium@463009      30.4357 +- 0.384143      9       bad
chromium@463025      30.5043 +- 0.279532      6       bad
chromium@463090      30.3637 +- 0.557383      9       bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982386493940134256

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6413915455488000


| 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 16 by lukasza@chromium.org, Apr 14 2017

Cc: gab@chromium.org
Owner: fdoray@chromium.org
fdoray@, could you please take a look?  My revert is necessary to avoid test flakiness introduced by r462912 and caught by sheriff-o-matic.

Comment 19 by fdoray@chromium.org, Apr 18 2017

Status: Assigned (was: Untriaged)
Re-running a bisect. Since landing https://codereview.chromium.org/2664953004 didn't cause a performance improvement, it is unexpected that reverting it https://codereview.chromium.org/2804393002 causes a performance regression.
Project Member

Comment 20 by 42576172...@developer.gserviceaccount.com, Apr 18 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : page_cycler_v2.typical_25
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___www.flickr.com_search_?q_monkeys_f_hp

Revision             Result                 N
chromium@462960      2087.36 +- 1315.0      20      good
chromium@463090      1956.07 +- 50.847      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.flickr.com.search..q.monkeys.f.hp page_cycler_v2.typical_25

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981970047277143936

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5871235667329024


| 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 22 by 42576172...@developer.gserviceaccount.com, Apr 18 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg

Revision             Result                   N
chromium@462960      45.4661 +- 0.401779      21      good
chromium@463090      45.4986 +- 0.457919      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981970049560572992

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6468315846803456


| 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 25 by 42576172...@developer.gserviceaccount.com, Apr 18 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : page_cycler_v2.typical_25
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___www.flickr.com_search_?q_monkeys_f_hp

Revision             Result                  N
chromium@462960      2175.71 +- 1464.21      18      good
chromium@463090      2078.86 +- 1258.84      17      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.flickr.com.search..q.monkeys.f.hp page_cycler_v2.typical_25

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981963646854936192

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5871235667329024


| 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 26 by 42576172...@developer.gserviceaccount.com, Apr 18 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/image_decoding.html?jpg

Revision             Result                   N
chromium@462960      30.309 +- 0.816328       21      good
chromium@463090      30.2729 +- 0.654477      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=image.decoding.html.jpg image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981957553439052640

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6397289234432000


| 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 28 by 42576172...@developer.gserviceaccount.com, Apr 18 2017

Cc: bpastene@chromium.org
Owner: bpastene@chromium.org

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

Hi bpastene@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 : bpastene
  Commit : 51cdcbaa84f6221a9b9b2957bbb5f750e6414c1b
  Date   : Fri Apr 07 19:39:05 2017
  Subject: chromium.android.fyi: Fix the expiration value of tests on L low-end bot

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/image_decoding.html?jpg
  Change       : 0.64% | 30.0680666667 -> 30.2613

Revision             Result                    N
chromium@462960      30.0681 +- 0.0997267      6      good
chromium@462963      30.2351 +- 0.0967813      6      good
chromium@462964      30.2696 +- 0.25119        9      good
chromium@462965      30.4597 +- 0.204054       6      bad       <--
chromium@462969      30.2319 +- 0.140456       6      bad
chromium@462977      30.3424 +- 0.304843       6      bad
chromium@462993      30.2769 +- 0.178193       6      bad
chromium@463025      30.365 +- 0.121021        6      bad
chromium@463090      30.2613 +- 0.243831       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=image.decoding.html.jpg image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981952322446767136

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6397289234432000


| 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 29 by 42576172...@developer.gserviceaccount.com, Apr 18 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg

Revision             Result                  N
chromium@462960      42.6871 +- 2.00571      21      good
chromium@463090      42.6464 +- 1.96732      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981956096306442048

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6468315846803456


| 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 30 by bpastene@chromium.org, Apr 18 2017

Cc: -bpastene@chromium.org
Owner: ----
Status: Available (was: Assigned)
Definitely not mine.
Project Member

Comment 32 by 42576172...@developer.gserviceaccount.com, Apr 19 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : page_cycler_v2.typical_25
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___www.flickr.com_search_?q_monkeys_f_hp

Revision             Result                  N
chromium@462960      2708.48 +- 124.363      21      good
chromium@463090      2705.38 +- 53.7627      20      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.flickr.com.search..q.monkeys.f.hp page_cycler_v2.typical_25

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981861661666145504

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5871235667329024


| 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 34 by 42576172...@developer.gserviceaccount.com, Apr 19 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : page_cycler_v2.typical_25
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___www.flickr.com_search_?q_monkeys_f_hp

Revision             Result                  N
chromium@462960      42.6871 +- 2.00571      21      good
chromium@463090      42.6464 +- 1.96732      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.flickr.com.search..q.monkeys.f.hp page_cycler_v2.typical_25

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981850323509765600

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6468315846803456


| 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 37 by 42576172...@developer.gserviceaccount.com, Apr 26 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg

Revision             Result                  N
chromium@462960      42.7835 +- 2.45495      21      good
chromium@463090      42.6504 +- 1.3111       21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981218825737705392

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5871235667329024


| 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 38 by 42576172...@developer.gserviceaccount.com, Apr 27 2017 


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

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg

Revision             Result                  N
chromium@462960      42.6871 +- 2.00571      21      good
chromium@463090      42.6464 +- 1.96732      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981210274967995792

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6468315846803456


| 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 39 by m...@chromium.org, May 2 2017

Cc: -m...@chromium.org

Comment 40 by chcunningham@chromium.org, Jun 12 2017

Cc: -chcunningham@chromium.org

Comment 41 by sullivan@chromium.org, Aug 17 2017

Status: WontFix (was: Available)
Bisect can't repro.
►

Sign in to add a comment