New issue
Advanced search Search tips

Issue 744723 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 742808
Owner: ----
Closed: Aug 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.6% regression in thread_times.key_silk_cases at 485888:485943

Project Member Reported by nzolghadr@chromium.org, Jul 17 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jul 17 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=744723

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=ea637dbeca522c5e7b5c98b01716590e642f4c971bfc8a712cd6a2c3ec8f9108


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

android-webview-nexus5X
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jul 18 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: android_webview_arm64_aosp_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_IO_cpu_time_per_frame/thread_IO_cpu_time_per_frame


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 thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8973799886569466928


For feedback, file a bug with component Speed>Bisection

Comment 5 by hjd@chromium.org, Jul 24 2017

thread_renderer_compositor_cpu_time_per_frame recovered. Kicked bisect on thread_IO_cpu_time_per_frame.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Jul 26 2017


=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: TIMEOUT

The bisect was able to narrow the range, you can try running with:
  good_revision: 9a415af7abdaf9b1f7d2b073d3f11dbe74871e13
  bad_revision : c600ac1d2771eb57c0875a0a9fe6002238eb89fc

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_IO_cpu_time_per_frame/thread_IO_cpu_time_per_frame
  Change       : 5.59% | 3.32384798049 -> 3.50956616288

Revision             Result                    N
chromium@485672      3.32385 +- 0.054791       6      good
chromium@485848      3.3139 +- 0.0966477       6      good
chromium@485892      3.30622 +- 0.0287414      6      good
chromium@485914      3.34387 +- 0.0610183      6      good
chromium@485925      3.31497 +- 0.048875       6      good
chromium@485931      3.327 +- 0.0709055        6      good
chromium@485934      3.32868 +- 0.0426268      6      good
chromium@485936      3.41949 +- 0.0653995      6      bad
chromium@486023      3.44577 +- 0.109894       6      bad
chromium@486374      3.4309 +- 0.0979987       6      bad
chromium@487076      3.50957 +- 0.0732678      6      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 thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8973177621855427088


For feedback, file a bug with component Speed>Bisection
Mergedinto: 742808
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Alexander Timin
  Commit : 214a2f9dd64151cfb5626020d8ba74f2d72012a2
  Date   : Wed Jul 12 01:19:03 2017
  Subject: [scheduler] Refactor renderer scheduler policies.

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_other_cpu_time_per_frame/inbox_app.html?stress_hidey_bars
  Change       : 13.84% | 0.164713969353 -> 0.187340715615

Revision             Result                      N
chromium@485700      0.164714 +- 0.0049511       9      good
chromium@485738      0.165135 +- 0.00476203      6      good
chromium@485757      0.165944 +- 0.00178292      6      good
chromium@485759      0.164667 +- 0.0032706       6      good
chromium@485760      0.188879 +- 0.0150995       6      bad       <--
chromium@485762      0.188034 +- 0.0135813       6      bad
chromium@485766      0.188892 +- 0.0147252       6      bad
chromium@485775      0.19022 +- 0.0145364        6      bad
chromium@485850      0.188195 +- 0.0295295       9      bad
chromium@486000      0.187341 +- 0.0128568       6      bad

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=inbox.app.html.stress.hidey.bars thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972190343497469968


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment