All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=700875

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg1OLC3AgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgtOyvtgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg1OOztwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg1O6IqAsM


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

android-nexus5
android-webview-nexus6
chromium-rel-win7-dual
chromium-rel-win8-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8985236153117815600

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8985236110321062000

Looks like this is only for the JQuery sub-test in speedometer.

Todo: Check if speedometer-turbo also regressed.

Overall score improved by around 8% on these platforms, so this looks isolated to the jQuery subtest. As such, I don't think this is a blocker, but we might want to take a look at jQuery since we didn't see this regression in previous analysis.

This is the same regression we also had on --future: https://chromeperf.appspot.com/report?sid=23b4a3e9b8219fc5dcc356fe6a5af7f898b1711a8d98cd34d6005e367368683a

Nothing blocking but might be nice for an analysis or follow-up if there is time. 

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

Hi jbroman@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 : jbroman
  Commit : e42b6912ec7a355b4575435a21e618e7aa277e42
  Date   : Thu Mar 09 14:19:48 2017
  Subject: Avoid a separate heap allocation for DOMWrapperMap.

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : speedometer
  Metric       : jQuery-TodoMVC/jQuery-TodoMVC
  Change       : 1.28% | 605.206678571 -> 612.056785714

Revision             Result                  N
chromium@455713      605.207 +- 23.4134      14      good
chromium@455732      601.086 +- 11.592       6       good
chromium@455741      599.903 +- 27.7565      9       good
chromium@455742      610.794 +- 15.0496      9       bad       <--
chromium@455743      615.449 +- 30.9994      14      bad
chromium@455744      622.917 +- 23.4918      9       bad
chromium@455746      612.561 +- 16.5143      9       bad
chromium@455750      611.036 +- 28.8943      21      bad
chromium@455787      612.057 +- 19.6994      14      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 speedometer

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8985236110321062000

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5855422239473664


| 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!

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Michael Hablich
  Commit : 7c3936c67a6361371d9a00d83e2c03ecc603ce76
  Date   : Thu Mar 09 08:05:42 2017
  Subject: Version 5.9.34.1 (Turn on I+TF)

Bisect Details
  Configuration: win_8_perf_bisect
  Benchmark    : speedometer
  Metric       : jQuery-TodoMVC/jQuery-TodoMVC
  Change       : 2.88% | 741.617916667 -> 762.9475

Revision                           Result                  N
chromium@455707                    741.618 +- 17.3558      6      good
chromium@455716                    744.477 +- 23.6369      6      good
chromium@455718                    743.733 +- 14.7063      6      good
chromium@455719                    739.203 +- 14.9214      6      good
chromium@455719,v8@7c3936c67a      766.915 +- 9.60013      6      bad       <--
chromium@455719,v8@fbffc377e3      760.164 +- 10.718       6      bad
chromium@455720                    767.126 +- 14.1315      6      bad
chromium@455724                    762.415 +- 11.7853      6      bad
chromium@455741                    766.776 +- 14.5006      6      bad
chromium@455774                    762.948 +- 19.9096      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 speedometer

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8985236153117815600

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5492614003949568


| 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!

Are we taking that or do we want to "fix" it?

not blocking for launch

Blocking to show relationship but de-priotizing because it is not important for M59.

Benedikt, can you characterize the nature of the jQuery regression? That is, do we have any chance to address it with targeted work...

So far, we haven't found anything that would address it. It seems to be the slower Ignition baseline again.