All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=774555

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=d6c829e5a511b57c2f26d439aae35ac4eacd976932e8f08600bf503644f1cc4d


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

android-webview-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8965831120338583376

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

Hi sunxd@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 : sunxd
  Commit : 48493dc45de06867eec97e7944f56d511e3c4578
  Date   : Thu Oct 12 20:25:14 2017
  Subject: cc: make solid color picture layer tiling respect device scale factor

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:webview:all_processes:reported_by_os:system_memory:native_heap:proportional_resident_size_avg/foreground/http_m_youtube_com_results_q_science
  Change       : 1.20% | 27991298.2222 -> 28326260.0

Revision             Result                  N
chromium@508377      27991298 +- 525924      9       good
chromium@508435      27951476 +- 575718      6       good
chromium@508439      28131700 +- 320314      9       good
chromium@508441      28112585 +- 703702      9       good
chromium@508442      28422223 +- 655909      14      bad       <--
chromium@508443      28456649 +- 519393      9       bad
chromium@508450      28513311 +- 400515      6       bad
chromium@508464      28366310 +- 536897      9       bad
chromium@508492      28326260 +- 343222      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=http.m.youtube.com.results.q.science 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/8965831120338583376


For feedback, file a bug with component Speed>Bisection

 Issue 775235  has been merged into this issue.

 Issue 775287  has been merged into this issue.

 Issue 775377  has been merged into this issue.

 Issue 776487  has been merged into this issue.

I assume the memory regression is due to two facts:

1) We didn't scale solid color picture layers at all even if the device_scale_factor * page_scale_factor is not 1. This is a bug and we can ignore memory regression brought by the fix. Since we are painting a larger area.

2) The previous fixing patch failed to deal with occlusion correctly, I have a WIP patch that fixes that issue, and we can wait and see if the regression can be fixed as well.

Issue 776784 has been merged into this issue.

Issue 776785 has been merged into this issue.

 Issue 776742  has been merged into this issue.

 Issue 776749  has been merged into this issue.

 Issue 776743  has been merged into this issue.

 Issue 776748  has been merged into this issue.

sunxd: any update on the WIP patch from #8?

The patch mentioned in comment 8 was landed on Oct 25: https://chromium-review.googlesource.com/c/chromium/src/+/738352.

It looks like the bug stops reproducing after that date. I would suggest we can mark it as fixed?