All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=603922

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-LzHqQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-PzQuAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-KHppwoM


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

chromium-rel-win7-dual

Trying some more bisects.

Bisect re-kicked with wider revision range.

Details on the below link:
-------------------------------
https://chromeperf.appspot.com/group_report?bug_id=603922

Thank you!

Based on the current bisect results, the most likely patch looks like:
https://chromium.googlesource.com/chromium/src/+/8c0c32361a933e23ed11c206413c381588fe44d8

I'm not particularly convinced though, so I've kicked off another bisect here. https://chromeperf.appspot.com/buildbucket_job_status/9013038191656258560

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@386738  2275.33  2.28198  18  good
chromium@386788  2274.31  3.59232  18  bad

Bisect job ran on: win_perf_bisect
Bug ID: 603922

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_non_empty_paint_time/first_non_empty_paint_time
Relative Change: 0.04%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6507
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013038191656258560


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5876798223548416

| 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 Tests>AutoBisect.  Thank you!

My change just changed

  invalidate(oldRect);
  invalidate(newRect);

to

  if (oldRect.contains(newRect)) {
    invalidate(oldRect);
  } else if (newRect.contains(oldRect)) {
    invalidate(newRect);
  } else {
    invalidate(oldRect);
    invalidate(newRect);
  }

which has nothing to do with the benchmarks.

Kicked another bisect on "startup.warm.blank_page / window_display_time" 
https://chromeperf.appspot.com/buildbucket_job_status/9012208734595531216

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N   Good?
chromium@386738  97.655   0.452114  18  good
chromium@386788  99.8012  7.43873   18  bad

Bisect job ran on: win_perf_bisect
Bug ID: 603922

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests startup.warm.blank_page
Test Metric: window_display_time/window_display_time
Relative Change: 5.90%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6527
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9012208734595531216


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5897260974473216

| 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 Tests>AutoBisect.  Thank you!

Moving this nonessential bug to the next milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

Most of these metrics seem to have recovered.  I kicked off a bisect on ChromiumPerf/chromium-rel-win7-dual/startup.warm.blank_page / window_display_time / ref  since that only just recently recovered and its not too noisy.

It has really recovered. The regression was temporary due to my diagnosing code which has been disabled. Sorry for overlooking this bug.

Never mind #11. It's totally unrelated.

This issue has been moved once and is lower than Pri-1. Removing the milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8999606336149631248

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N   Good?
chromium@386738  136.298  0.667454  18  good
chromium@386788  136.477  0.533228  18  bad

Bisect job ran on: win_perf_bisect
Bug ID: 603922

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_main_frame_load_time/first_main_frame_load_time
Relative Change: 0.14%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6978
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8999606336149631248


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5238125314441216

| 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 Tests>AutoBisect.  Thank you!

The main regressions in this bug are recovered.