All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=593930

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDA_4OjpQoM


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

android-nexus5

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

Hi pmeenan@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


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


===== SUSPECTED CL(s) =====
Subject : Reland of Added ResourcePriorities field trial to the waterfall testing config (patchset #1 id:1 of https://codereview.chromium.org/1707723002/ )
Author  : pmeenan
Commit description:
  
Reason for revert:
Re-landing now that a fix has landed: https://codereview.chromium.org/1783433003/

Original issue's description:
> Revert of Added ResourcePriorities field trial to the waterfall testing config in preparation for launch (patchset #1 id:1 of https://codereview.chromium.org/1700253002/ )
>
> Reason for revert:
> Looks like the ResourcePriorities code is slowing down the service workers micro benchmark pretty significantly (and unexpectedly).  Disabling it until we can understand and fix why.
>
> Original issue's description:
> > Added ResourcePriorities field trial to the waterfall testing config in preparation for launch
> >
> > BUG=521744
> >
> > Committed: https://crrev.com/64bc5ddf872133174294d6bbcd4536c06c8f6398
> > Cr-Commit-Position: refs/heads/master@{#375644}
>
> TBR=asvitkine@chromium.org
> # Skipping CQ checks because original CL landed less than 1 days ago.
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> BUG=521744
>
> Committed: https://crrev.com/37b8253bbb12ee475dc053a25ba3526c5c82ef99
> Cr-Commit-Position: refs/heads/master@{#375899}

TBR=asvitkine@chromium.org
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG=521744

Review URL: https://codereview.chromium.org/1784553002

Cr-Commit-Position: refs/heads/master@{#380220}
Commit  : d093abb8ce20dbc64155e4ba5596380613412b2b
Date    : Wed Mar 09 21:21:41 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@380207         4.678679    0.142706    8           good
chromium@380214         4.7056      0.308494    12          good
chromium@380217         4.784178    0.286993    12          good
chromium@380219         4.633397    0.143872    5           good
chromium@380220         5.202136    0.153112    8           bad
chromium@380232         5.245653    0.203401    8           bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 593930

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --also-run-disabled-tests thread_times.key_mobile_sites_smooth
Test Metric: thread_renderer_main_cpu_time_per_frame/thread_renderer_main_cpu_time_per_frame
Relative Change: 12.04%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3482
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018537113291971280


| 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 label Cr-Tests-AutoBisect.  Thank you!

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


===== SUSPECTED CL(s) =====
Subject : Reland of Added ResourcePriorities field trial to the waterfall testing config (patchset #1 id:1 of https://codereview.chromium.org/1707723002/ )
Author  : pmeenan
Commit description:
  
Reason for revert:
Re-landing now that a fix has landed: https://codereview.chromium.org/1783433003/

Original issue's description:
> Revert of Added ResourcePriorities field trial to the waterfall testing config in preparation for launch (patchset #1 id:1 of https://codereview.chromium.org/1700253002/ )
>
> Reason for revert:
> Looks like the ResourcePriorities code is slowing down the service workers micro benchmark pretty significantly (and unexpectedly).  Disabling it until we can understand and fix why.
>
> Original issue's description:
> > Added ResourcePriorities field trial to the waterfall testing config in preparation for launch
> >
> > BUG=521744
> >
> > Committed: https://crrev.com/64bc5ddf872133174294d6bbcd4536c06c8f6398
> > Cr-Commit-Position: refs/heads/master@{#375644}
>
> TBR=asvitkine@chromium.org
> # Skipping CQ checks because original CL landed less than 1 days ago.
> NOPRESUBMIT=true
> NOTREECHECKS=true
> NOTRY=true
> BUG=521744
>
> Committed: https://crrev.com/37b8253bbb12ee475dc053a25ba3526c5c82ef99
> Cr-Commit-Position: refs/heads/master@{#375899}

TBR=asvitkine@chromium.org
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG=521744

Review URL: https://codereview.chromium.org/1784553002

Cr-Commit-Position: refs/heads/master@{#380220}
Commit  : d093abb8ce20dbc64155e4ba5596380613412b2b
Date    : Wed Mar 09 21:21:41 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@380207         5.184431    0.320496    8           good
chromium@380214         4.932031    0.359776    8           good
chromium@380217         5.287041    1.242612    8           good
chromium@380219         5.049427    0.456649    8           good
chromium@380220         8.476032    0.784586    5           bad
chromium@380232         8.426984    0.447652    8           bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 593930

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --also-run-disabled-tests thread_times.key_mobile_sites_smooth
Test Metric: thread_renderer_main_cpu_time_per_frame/http___www.boingboing.net
Relative Change: 54.73%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3483
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018537083108133360


| 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 label Cr-Tests-AutoBisect.  Thank you!

I'll look closer this afternoon.  The change itself wouldn't change the CPU timings but it may have changed the denominator causing more work to be done in a shorter time (it changes the sequence in how resources load).

Closing as WAI.  Nothing changed in the actual frame processing pipeline but the chhange in how the page is loaded caused a radical change in how the page renders.

The benchmark regression was specific to www.boingboing.net and the resource priority change radically improved getting content to the screen sooner (34% faster in lab testing): http://www.webpagetest.org/video/compare.php?tests=160314_KZ_70e30807b2d7e62162193293b365cdb3%2C160314_2F_eb288ed3f2dd9b9a4b42effd1606508d&thumbSize=200&ival=100&end=full