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

Issue 732721 link

Starred by 1 user
Status: Duplicate
Merged: issue 732701
Owner:
█ hamelphi@chromium.org
Last visit > 30 days ago
Closed: Jun 2017
Cc:
█ hamelphi@chromium.org
█ alexclarke@chromium.org
fdoray@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

7.6% regression in memory.top_10_mobile at 478703:478723

Project Member Reported by alexclarke@chromium.org, Jun 13 2017 
See the link to graphs below.

Comment 1 by alexclarke@chromium.org, Jun 13 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=732721

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg1tbTugkM


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

android-webview-nexus5X
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 14 2017

Cc: fdoray@chromium.org
Owner: fdoray@chromium.org

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

Hi fdoray@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 : Francois Doray
  Commit : a50035b77e0529cb0c916d19e18da91152c6dc69
  Date   : Mon Jun 12 19:45:49 2017
  Subject: Extract code from LazyInstance::Pointer() to a helper function.

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:webview:all_processes:reported_by_os:system_memory:java_heap:proportional_resident_size_avg/foreground/https_www_google_co_uk_hl_en_q_science
  Change       : 8.31% | 6150485.33333 -> 6661802.66667

Revision             Result                  N
chromium@478702      6150485 +- 42730.8      6      good
chromium@478713      6252203 +- 69188.9      6      good
chromium@478718      6294187 +- 87582.4      6      good
chromium@478721      3565909 +- 46220.1      6      good
chromium@478722      3605504 +- 107124       6      good
chromium@478723      6661803 +- 71806.7      6      bad       <--

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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 memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976918071792682832

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5054423459430400


| 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 7 by 42576172...@developer.gserviceaccount.com, Jun 15 2017

Mergedinto: 732701
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Marijn Kruisselbrink
  Commit : dda8780efac5966b275b8b7beeabe951b9d9c133
  Date   : Mon Jun 12 19:42:06 2017
  Subject: Implement retry behavior for several leveldb env methods in mojo env.

Bisect Details
  Configuration: android_nexus7_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/https_www_google_co_uk_hl_en_q_science
  Change       : 7.86% | 8252708.0 -> 8901731.33333

Revision             Result                   N
chromium@478669      8252708 +- 91948.5       6      good
chromium@478700      8288816 +- 134225        6      good
chromium@478715      8249144 +- 31566.4       6      good
chromium@478719      8261955 +- 18581.8       6      good
chromium@478720      8913959 +- 2048028       6      bad       <--
chromium@478721      8891909 +- 2072481       6      bad
chromium@478723      8561643 +- 92506.0       6      bad
chromium@478730      10139575 +- 2819527      6      bad
chromium@478791      8901731 +- 2062236       6      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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 memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976797287419481008

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6743348682948608


| 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, Jun 15 2017 


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

Suspected Commit
  Author : Marijn Kruisselbrink
  Commit : dda8780efac5966b275b8b7beeabe951b9d9c133
  Date   : Mon Jun 12 19:42:06 2017
  Subject: Implement retry behavior for several leveldb env methods in mojo env.

Bisect Details
  Configuration: android_nexus7_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/foreground/https_www_google_co_uk_hl_en_q_science
  Change       : 5.74% | 31655244.0 -> 33471137.3333

Revision             Result                   N
chromium@478669      31655244 +- 0.0          9       good
chromium@478700      31655244 +- 0.0          9       good
chromium@478715      31655244 +- 0.0          9       good
chromium@478719      31655244 +- 0.0          9       good
chromium@478720      33056076 +- 3906734      14      bad       <--
chromium@478721      32865840 +- 3248369      9       bad
chromium@478723      33471137 +- 1989211      6       bad
chromium@478730      33107959 +- 3081673      9       bad
chromium@478791      33471137 +- 1989211      6       bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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 memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976797260870017024

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5003693184778240


| 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 9 by 42576172...@developer.gserviceaccount.com, Jun 15 2017

Cc: hamelphi@chromium.org
Owner: hamelphi@chromium.org

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

Hi hamelphi@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 : hamelphi
  Commit : a33125bccd08d77590b3ee8907d85ca5a042c78a
  Date   : Mon Jun 12 19:40:57 2017
  Subject: Send UMA recording state to TranslateRanker.

Bisect Details
  Configuration: android_nexus7_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_os:gpu_memory:proportional_resident_size_avg/foreground/https_www_google_co_uk_hl_en_q_science
  Change       : 23.43% | 90034176.0 -> 109535687.111

Revision             Result                     N
chromium@478669      90034176 +- 11980654       14      good
chromium@478700      91264146 +- 538291         14      good
chromium@478715      89934702 +- 17710122       14      good
chromium@478718      89492334 +- 24704699       21      good
chromium@478719      91465435 +- 1035401        14      bad       <--
chromium@478724      112385463 +- 50791983      14      bad
chromium@478730      107754642 +- 53666864      14      bad
chromium@478791      109535687 +- 39148311      9       bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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 memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976797244803124112

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5628697832325120


| 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