All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=730119

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpufh-ggM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg5qryqAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg5pj89goM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpr-syQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpr-siQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpo73ugoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgppHI5AkM


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

chromium-rel-win10
chromium-rel-win7-gpu-nvidia

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977508179883889392

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

Hi hans@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 : hans
  Commit : ba2ff9ad0d643a443575c839e56ae9edf7106643
  Date   : Mon Jun 05 02:02:06 2017
  Subject: Revert of "win: Set is_clang=true by default over the weekend."

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/tulip2.mp4_gpu
  Change       : 1.88% | 23577.3333333 -> 24020.6666667

Revision             Result                  N
chromium@476917      23577.3 +- 59.5091      6      good
chromium@476920      23493.3 +- 102.554      6      good
chromium@476921      23924.0 +- 128.623      6      bad       <--
chromium@476922      23934.7 +- 72.5902      6      bad
chromium@476923      24003.3 +- 132.353      6      bad
chromium@476928      23966.0 +- 76.4722      6      bad
chromium@476938      23918.7 +- 50.8068      6      bad
chromium@476958      24020.7 +- 124.376      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 media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977508179883889392

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5781074111627264


| 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!

 Issue 730118  has been merged into this issue.

> These regressions all appear to be a retrun to a previous average from ~100 revisions prior. Likely some change landed and reverted. Bisects just to be sure.

Yes, looks like this is from the end of the clang on winows experiment last weekend.

I'll mark it wontfix since there's nothing to do at the moment, but it's nice to know we'll improve this when we turn on clang for real.

 Issue 730538  has been merged into this issue.

 Issue 732312  has been merged into this issue.

 Issue 734568  has been merged into this issue.

 Issue 736189  has been merged into this issue.