All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=781152

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=9953868ad671882f4ba3bf9853e17c9f58138cabeb6de8deaaf796ffb68d2a88


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

chromium-rel-win10
chromium-rel-win7-dual
chromium-rel-win7-gpu-intel
chromium-rel-win7-x64-dual
chromium-rel-win8-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8963957293440696304

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

Hi zmo@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 : Zhenyao Mo
  Commit : 39d8a7f229e1330e72724895eb4730b7108e47a0
  Date   : Mon Oct 30 13:45:42 2017
  Subject: Revert "One step further into moving GPU feature decisions to GPU process"

Bisect Details
  Configuration: win_x64_perf_bisect
  Benchmark    : v8.browsing_desktop
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/browse_news/browse_news_flipboard
  Change       : 8.92% | 22083156.8764 -> 24053126.9887

Revision             Result                   N
chromium@512468      22083157 +- 1882655      6       good
chromium@512478      22583901 +- 504019       6       good
chromium@512483      22431522 +- 2085880      9       good
chromium@512484      22048597 +- 3701889      14      good
chromium@512485      23469660 +- 1465144      9       bad       <--
chromium@512486      23697201 +- 843769       6       bad
chromium@512488      24025639 +- 1535610      6       bad
chromium@512507      24053127 +- 2060156      6       bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=browse.news.flipboard v8.browsing_desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8963957293440696304


For feedback, file a bug with component Speed>Bisection

My CL is pure revert of three previously landed CL. It can't be responsible for this regression. Unassign myself.

Looking at the graphs, I see an improvement that contains 
 0728a85617eae06098373349af80c28ce26b60fd

Is it not possible that the initial CL improved the metrics and the revert causes a regression?

That's possible, but there is nothing I can do.

I am still working on relanding my reverted work, but they may not take the same path and may not have the original perf impact.

Well, you don't have to have a fix ready. In this case it is enough to just attribute it to the change.

 Issue 781196  has been merged into this issue.

 Issue 782342  has been merged into this issue.

 Issue 781652  has been merged into this issue.