New issue
Advanced search Search tips

Issue 628111 link

Starred by 1 user
Status: Duplicate
Merged: issue 628120
Owner:
bmeu...@chromium.org
Closed: Jul 2016
Cc:
jarin@chromium.org
mythria@chromium.org
rmcilroy@chromium.org
bmeu...@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 1
Type: Bug-Regression



Sign in to add a comment

4.7%-82.2% regression in top_10_mobile_memory_ignition at 405075:405124

Project Member Reported by hablich@chromium.org, Jul 14 2016

Comment 3 by hablich@chromium.org, Jul 14 2016

Cc: jarin@chromium.org rmcilroy@chromium.org
Components: Blink>JavaScript>Compiler
Labels: -Pri-2 Pri-1
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, Jul 14 2016 


===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@405110  13594183  766947   12  good
chromium@405120  13614794  870582   15  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628111

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests top_10_mobile_memory_ignition
Test Metric: memory:chrome:all_processes:reported_by_chrome:v8:effective_size_max/https___m.facebook.com_rihanna
Relative Change: 4.30%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/334
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007176177861654592


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6653222190579712

| 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!

Comment 5 by hablich@chromium.org, Jul 14 2016

Cc: mythria@chromium.org
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jul 14 2016 


===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@405106  11045065  274268   18  good
chromium@405120  11035338  276989   18  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 628111

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests top_10_mobile_memory_ignition
Test Metric: memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_max/http___yandex.ru_touchsearch?text_science
Relative Change: 0.39%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6593
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007160842110276384


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5807659043782656

| 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!
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Jul 14 2016 


===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@405110  8076926  1304851  12  good
chromium@405124  8237640  1120578  18  bad

Bisect job ran on: winx64nvidia_perf_bisect
Bug ID: 628111

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests top_10_mobile_memory_ignition
Test Metric: memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_avg/http___yandex.ru_touchsearch?text_science
Relative Change: 3.92%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64nvidia_perf_bisect/builds/1716
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007160829507285920


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6620861759488000

| 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!
Project Member

Comment 12 by 42576172...@developer.gserviceaccount.com, Jul 15 2016

Mergedinto: 628120
Status: Duplicate (was: Assigned)

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [perf] Change google.com to google.co.uk in top_10_mobile_memory and dual_browser page sets.
Author  : mythria
Commit description:
  
In the top10_mobile page set google.com gets redirected to google.ca. This
sometimes causes problems in telemetry with scrolling. As a short term fix,
replace google.com with google.co.uk in the page set. We cannot change it
to google.ca because memory_top_10_mobile uses the same page set but with
a different wpr that has a recording of google.co.uk. Updated dual_browser
page set to be consistent with top_10_mobile page set.

Also recorded new wprs for memory_top_10_mobile, dual_browser and
top_10_mobile_memory.

BUG= chromium:617914 
LOG=N
CQ_INCLUDE_TRYBOTS=tryserver.chromium.perf:android_s5_perf_cq;tryserver.chromium.perf:mac_retina_perf_cq

Review-Url: https://codereview.chromium.org/2138133003
Cr-Commit-Position: refs/heads/master@{#405099}
Commit  : c5acd3851a2f34de15dd89119f0be48c22a9aa72
Date    : Wed Jul 13 09:04:39 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@405073  8601472   724293   5  good
chromium@405092  7866197   996125   5  good
chromium@405097  7621728   1002564  5  good
chromium@405098  8475022   411990   5  good
chromium@405099  11799381  213265   5  bad    <--
chromium@405101  11542779  349565   5  bad
chromium@405110  11654970  307949   5  bad

Bisect job ran on: win_x64_perf_bisect
Bug ID: 628111

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests top_10_mobile_memory_ignition
Test Metric: memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_max/http___www.amazon.com_gp_aw_s_?k_nexus
Relative Change: 35.50%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_x64_perf_bisect/builds/1326
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007089389955331136


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5046228451065856

| 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!
Project Member

Comment 13 by 42576172...@developer.gserviceaccount.com, Jul 15 2016 


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [perf] Change google.com to google.co.uk in top_10_mobile_memory and dual_browser page sets.
Author  : mythria
Commit description:
  
In the top10_mobile page set google.com gets redirected to google.ca. This
sometimes causes problems in telemetry with scrolling. As a short term fix,
replace google.com with google.co.uk in the page set. We cannot change it
to google.ca because memory_top_10_mobile uses the same page set but with
a different wpr that has a recording of google.co.uk. Updated dual_browser
page set to be consistent with top_10_mobile page set.

Also recorded new wprs for memory_top_10_mobile, dual_browser and
top_10_mobile_memory.

BUG= chromium:617914 
LOG=N
CQ_INCLUDE_TRYBOTS=tryserver.chromium.perf:android_s5_perf_cq;tryserver.chromium.perf:mac_retina_perf_cq

Review-Url: https://codereview.chromium.org/2138133003
Cr-Commit-Position: refs/heads/master@{#405099}
Commit  : c5acd3851a2f34de15dd89119f0be48c22a9aa72
Date    : Wed Jul 13 09:04:39 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@405073  7149299   947502   5  good
chromium@405092  6961674   1230823  5  good
chromium@405097  7548421   907198   5  good
chromium@405098  6950221   867148   5  good
chromium@405099  11559069  344457   5  bad    <--
chromium@405101  11322214  450272   5  bad
chromium@405109  12012626  368666   5  bad

Bisect job ran on: winx64_10_perf_bisect
Bug ID: 628111

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests top_10_mobile_memory_ignition
Test Metric: memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_max/http___www.amazon.com_gp_aw_s_?k_nexus
Relative Change: 68.03%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64_10_perf_bisect/builds/600
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007089400548587456


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5839781557174272

| 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