All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=725944

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDguuvztwoM


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

android-webview-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978699957543179440

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

Hi clemensh@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 : Clemens Hammacher
  Commit : df1cb4e87ee9ba19be78c02c5b516dc0888d6d6d
  Date   : Tue May 23 14:18:29 2017
  Subject: Avoid emitting redundant safepoint info

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:v8:effective_size_avg/long_running_tools/long_running_tools_gmail-foreground
  Change       : 2.51% | 10223240.549 -> 10479746.6797

Revision                           Result                  N
chromium@474027                    10223241 +- 228786      6      good
chromium@474056                    10075566 +- 581618      9      good
chromium@474070                    10019816 +- 599471      9      good
chromium@474071                    10185214 +- 362356      6      good
chromium@474071,v8@6128f2cf59      10043168 +- 402257      6      good
chromium@474071,v8@df1cb4e87e      10677010 +- 562543      6      bad       <--
chromium@474071,v8@8655861e0a      10561828 +- 715040      9      bad
chromium@474072                    10636974 +- 298491      6      bad
chromium@474074                    10713124 +- 454457      6      bad
chromium@474077                    10662729 +- 223284      6      bad
chromium@474084                    10479747 +- 425033      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=long.running.tools.gmail.foreground system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978699957543179440

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5307884587450368


| 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!

Suspecting wrong bisect. My CL was reverted with the roll-back to V8 version 6.0.286 in 474293, but the graphs did not change there.

Also, I don't see any situation in which my CL would increase memory usage.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978526352004728528

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

Suspected Commit
  Author : danakj
  Commit : 4188df86ebb468a6723b1c5855c75be8e4ae91a3
  Date   : Tue May 23 20:05:29 2017
  Subject: Avoid quickReject() when rastering a cc::DrawingDisplayItem.

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:skia:effective_size_avg/load_media/load_media_youtube
  Change       : 6.64% | 48348.0 -> 51556.0

Revision             Result                 N
chromium@473893      48348.0 +- 0.0         6      good
chromium@473961      48348.0 +- 0.0         6      good
chromium@473995      48348.0 +- 0.0         6      good
chromium@474012      48348.0 +- 0.0         6      good
chromium@474013      48348.0 +- 0.0         6      good
chromium@474014      51556.0 +- 0.0         6      bad       <--
chromium@474015      51556.0 +- 0.0         6      bad
chromium@474017      52790.0 +- 6758.9      6      bad
chromium@474021      51556.0 +- 0.0         6      bad
chromium@474029      51556.0 +- 0.0         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 --story-filter=load.media.youtube system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978526352004728528

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6070278083313664


| 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!