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

Issue 751052 link

Starred by 4 users

Issue metadata

Status: Duplicate
Owner: ----
Closed: Aug 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.3%-4.8% regression in system_health.memory_mobile at 489986:490297

Project Member Reported by hjd@google.com, Aug 1 2017

Issue description

Splitting from https://bugs.chromium.org/p/chromium/issues/detail?id=750696 since the CL blamed there is after these regressions.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751052

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=0e41cc92591185ee5c7748a34b64294f4d5874cbff9f296fa6cf65a739bedd21


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

android-nexus5
android-nexus7v2
android-one
android-webview-nexus5X

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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/load_tools/load_tools_drive

Revision             Result                   N
chromium@489985      23883627 +- 1487380      21      good
chromium@490179      24064086 +- 856820       21      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 --story-filter=load.tools.drive system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972471044174963008


For feedback, file a bug with component Speed>Bisection

=== 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: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:malloc:effective_size_avg/load_news/load_news_nytimes

Revision             Result                   N
chromium@490220      38879187 +- 1710460      21      good
chromium@490259      39042410 +- 1682088      21      unknown
chromium@490297      39241053 +- 1187264      21      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 --story-filter=load.news.nytimes system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972470941239734928


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/load_media/load_media_dailymotion

Revision             Result                  N
chromium@489985      20882163 +- 593237      21      good
chromium@490179      20842775 +- 308812      21      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 --story-filter=load.media.dailymotion system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972470917051181088


For feedback, file a bug with component Speed>Bisection
Cc: u...@chromium.org
Owner: u...@chromium.org

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

Hi ulan@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 : Ulan Degenbaev
  Commit : 2cc8fdfb47226101b958da465d64803368fb7c76
  Date   : Thu Jul 27 11:09:24 2017
  Subject: [heap] Re-implement weak cell tracking in the marker.

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/https_m_facebook_com_rihanna
  Change       : 2.12% | 5321503.33333 -> 5208914.66667

Revision                           Result                  N
chromium@489985                    5321503 +- 1382.36      6      good
chromium@490010                    5321615 +- 1256.45      6      good
chromium@490022                    5321623 +- 528.406      6      good
chromium@490025                    5321153 +- 1370.25      6      good
chromium@490027                    5320770 +- 900.857      6      good
chromium@490027,v8@2cc8fdfb47      5210363 +- 2369.99      6      bad       <--
chromium@490027,v8@6a75fcd4df      5210277 +- 1713.04      6      bad
chromium@490027,v8@e4bbf92be3      5209797 +- 2729.62      6      bad
chromium@490027,v8@9836cdb1ad      5210377 +- 2054.52      6      bad
chromium@490028                    5210345 +- 2943.28      6      bad
chromium@490034                    5182315 +- 148440       6      bad
chromium@490082                    5210058 +- 2765.37      6      bad
chromium@490179                    5208915 +- 1593.8       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

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972470932696055472


For feedback, file a bug with component Speed>Bisection
Cc: alexclarke@chromium.org
 Issue 751988  has been merged into this issue.

Comment 13 by u...@chromium.org, Aug 3 2017

Owner: ----
Removing myself from the owner because bisect in #9 is about improvement in memory usage.   Issue 751988  is also about improvement.

Regressions did not bisect to my CL. 
 Issue 752174  has been merged into this issue.
 Issue 751990  has been merged into this issue.

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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/load_tools/load_tools_drive

Revision             Result                  N
chromium@489985      24058401 +- 810244      21      good
chromium@490179      24041959 +- 497851      21      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 --story-filter=load.tools.drive system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972257831337394816


For feedback, file a bug with component Speed>Bisection
 Issue 752016  has been merged into this issue.

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

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:malloc:effective_size_avg/load_news/load_news_nytimes

Revision             Result                   N
chromium@490220      38743111 +- 827181       21      good
chromium@490297      38845955 +- 1143722      21      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 --story-filter=load.news.nytimes system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972257700647578832


For feedback, file a bug with component Speed>Bisection
Mergedinto: 750299
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Helen Li
  Commit : 73f7cac54a1108eac07d5c7c3367f979a899a0bd
  Date   : Thu Jul 27 14:57:57 2017
  Subject: [wpr-go] Switch system_health_mobile.json to use go

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:malloc:effective_size_avg/load_news/load_news_nytimes
  Change       : 2.38% | 38173454.6667 -> 39081099.6667

Revision             Result                  N
chromium@489872      38173455 +- 493716      6       good
chromium@489905      38322803 +- 820624      9       good
chromium@489922      38264276 +- 664331      9       good
chromium@489923      38727617 +- 563642      6       bad       <--
chromium@489924      38784380 +- 528421      6       bad
chromium@489926      38839749 +- 386160      6       bad
chromium@489930      38696947 +- 652207      14      bad
chromium@489938      38786361 +- 478284      9       bad
chromium@490004      38803436 +- 429458      6       bad
chromium@490135      38849354 +- 533277      6       bad
chromium@490397      39081100 +- 327057      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 --story-filter=load.news.nytimes system_health.memory_mobile

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972202218891608464


For feedback, file a bug with component Speed>Bisection
Thanks for triaging the alerts. The increase in reported_by_chrome:malloc look reasonable to me.

Sign in to add a comment