The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/592e5575b9e6783b72e9e186f9709f0d515cf4b2

commit 592e5575b9e6783b72e9e186f9709f0d515cf4b2
Author: Charlie Andrews <charliea@google.com>
Date: Thu Jun 22 00:25:07 2017

Disable performance_browser_tests on Win 7 and Win 7 Nvidia GPU

TBR=nednguyen@google.com,miu@chromium.org

Bug:  735679 
Change-Id: I17f2519c250e2b4e9da5b1ff05e0e5d4ca117b39
Reviewed-on: https://chromium-review.googlesource.com/544235
Commit-Queue: Charlie Andrews <charliea@chromium.org>
Reviewed-by: Charlie Andrews <charliea@chromium.org>
Cr-Commit-Position: refs/heads/master@{#481372}
[modify] https://crrev.com/592e5575b9e6783b72e9e186f9709f0d515cf4b2/testing/buildbot/chromium.perf.json
[modify] https://crrev.com/592e5575b9e6783b72e9e186f9709f0d515cf4b2/tools/perf/core/perf_data_generator.py

Assigning to the benchmark owner to figure out why this is failing.

It's also failing on Win 7 ATI GPU Perf: https://build.chromium.org/p/chromium.perf/builders/Win%207%20ATI%20GPU%20Perf

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8975534187724413248

=== BISECT JOB RESULTS ===
NO Test failure found

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : performance_browser_tests
  Metric       : CastV2Performance_gpu_24fps/audio_jitter

Revision             Exit Code      N
chromium@482621      0 +- N/A       20      good
chromium@482879      0 +- N/A       20      bad

To Run This Test
  .\src\out\Release_x64\performance_browser_tests.exe --test-launcher-print-test-stdio=always --enable-gpu

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975534187724413248

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5360672596033536


| 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!

From looking at the revisions when the tests started failing the common across those ranges seems to be  "ozone/drm: Remove unnecessary GbmBufferBase class". Kristian, this be the cause?

 Issue 765005  has been merged into this issue.

Broadening this, because it looks like it's now flaky on all Windows platforms (with Intel GPUs? I can't tell). About to submit a patch that disables it on more platforms.

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/3eb8ad77b5d7bb0984a4f0f943cbd66e2c12c9b4

commit 3eb8ad77b5d7bb0984a4f0f943cbd66e2c12c9b4
Author: Charlie Andrews <charliea@chromium.org>
Date: Fri Sep 15 23:03:50 2017

Disable all currently failing smoothness stories

At this point, we've had several entangled changes land on top of the
original smoothness failures, so we're going to need help from someone
on the smoothness team to get these stories reenabled.

As it stands, these are causing a _lot_ of redness on the waterfall.

TBR=vmiura@chromium.org

Bug:  735679 
Change-Id: Ic40968caf5b5469c3102604ecf81898b4de16ffd
Reviewed-on: https://chromium-review.googlesource.com/669743
Reviewed-by: Charlie Andrews <charliea@chromium.org>
Commit-Queue: Charlie Andrews <charliea@chromium.org>
Cr-Commit-Position: refs/heads/master@{#502424}
[modify] https://crrev.com/3eb8ad77b5d7bb0984a4f0f943cbd66e2c12c9b4/tools/perf/benchmarks/smoothness.py