All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=714901

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4rDt-wgM


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

chromium-rel-mac12-mini-8gb

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981385250711607648

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

Hi lpy@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 : lpy
  Commit : 0462cff6ac0ddd51d88e74eb2e356061bbe792b0
  Date   : Wed Apr 19 22:44:42 2017
  Subject: Node.prototype.baseURI should not be nullable

Bisect Details
  Configuration: mac_10_12_mini_8gb_perf_bisect
  Benchmark    : blink_perf.bindings
  Metric       : dom-attribute-on-prototoype/dom-attribute-on-prototoype
  Change       : 25.14% | 138.634161585 -> 103.780557816

Revision             Result                  N
chromium@465769      138.634 +- 3.51524      6      good
chromium@465789      135.352 +- 14.7517      6      good
chromium@465790      137.474 +- 7.02973      6      good
chromium@465791      111.859 +- 15.2543      6      bad       <--
chromium@465792      108.653 +- 15.3171      6      bad
chromium@465794      110.758 +- 15.1252      6      bad
chromium@465799      111.297 +- 11.0221      6      bad
chromium@465809      113.395 +- 13.0232      6      bad
chromium@465849      113.066 +- 10.2812      5      bad
chromium@465929      103.781 +- 10.7971      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.bindings

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981385250711607648

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5791906782511104


| 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!

lpy, could you take a look?

 Issue 714874  has been merged into this issue.

 Issue 714874  has been merged into this issue.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978726570990307296

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

Hi nhiroki@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 : nhiroki
  Commit : d56a35fb25dc388a0506174b9e3fda67337313ce
  Date   : Thu Apr 20 01:05:33 2017
  Subject: Worker: Introduce per-global-scope task scheduler

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : thread_times.simple_mobile_sites
  Metric       : thread_renderer_compositor_cpu_time_per_frame/thread_renderer_compositor_cpu_time_per_frame
  Change       : 16.04% | 1.73273609244 -> 2.01062924978

Revision             Result                    N
chromium@465743      1.73274 +- 0.0368176      6      good
chromium@465816      1.74595 +- 0.0264916      6      good
chromium@465835      1.7434 +- 0.048215        6      good
chromium@465840      1.73023 +- 0.0191763      6      good
chromium@465841      2.024 +- 0.0211298        6      bad       <--
chromium@465842      2.02163 +- 0.0564876      6      bad
chromium@465844      2.01144 +- 0.0445198      6      bad
chromium@465853      2.00973 +- 0.0447472      6      bad
chromium@465889      2.01063 +- 0.058996       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests thread_times.simple_mobile_sites

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978726570990307296

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5234776727879680


| 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!

Let me reassign this issue to the original owner because regression on "thread_times.simple_mobile_sites" (see c#8) is a separate issue and tracked by  issue 714874 .

Friendly Perf sheriff ping, any update on this?

lpy, any update on this?

cc-ing jbroman, blink_perf.bindings owner as well.

This is almost certainly just a result of baseURI becoming more expensive as a result of Document::baseURL becoming out-of-line and non-trivial in lpy's change:
https://crrev.com/0462cff6ac0ddd51d88e74eb2e356061bbe792b0

The choice of this particular attribute was almost certainly arbitrary, so this doesn't represent a bindings regression. WontFix.