All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=611579

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9MTUvwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9IebqAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9J7MswoM


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

android-nexus5

=== Auto-CCing suspected CL author bungeman@google.com ===

Hi bungeman@google.com, 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 : Move SkTypeface to sk_sp.
Author  : bungeman
Commit description:
  
Review-Url: https://codereview.chromium.org/1933393002
Commit  : 6296da736fbf40aae881650c239420f64e576c3f
Date    : Wed May 11 19:38:18 2016


===== TESTED REVISIONS =====
Revision                         Mean     Std Dev  N  Good?
chromium@393034                  3340.34  9.27377  6  good
chromium@393056                  3341.72  10.2817  5  good
chromium@393067                  3352.0   6.36743  5  good
chromium@393067,skia@717abfd2a9  3351.24  14.0635  5  good
chromium@393067,skia@c8699321b9  3347.65  6.04857  5  good
chromium@393067,skia@6296da736f  3502.56  13.4298  5  bad    <--
chromium@393068                  3485.15  10.4747  5  bad
chromium@393069                  3475.37  22.8216  5  bad
chromium@393070                  3497.74  11.5593  5  bad
chromium@393073                  3480.18  23.0103  5  bad
chromium@393078                  3475.28  15.4687  5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 611579

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.intl_ar_fa_he
Test Metric: warm_times/page_load_time
Relative Change: 4.18%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3689
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9012829812498157408


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5906222155300864

| 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 Skia change looks like a possibly interesting thing to blame, but this CL was actually reverted shortly after it landed. A similar CL was landed later, but I see nothing on the graphs which correlates with the later re-land.

Moving this nonessential bug to the next milestone.

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

Metrics seem to have subsequently regressed further. Trying another bisect.  

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/9005460447052225856

=== Auto-CCing suspected CL author bungeman@google.com ===

Hi bungeman@google.com, 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 : Move SkTypeface to sk_sp.
Author  : bungeman
Commit description:
  
Review-Url: https://codereview.chromium.org/1933393002
Commit  : 6296da736fbf40aae881650c239420f64e576c3f
Date    : Wed May 11 19:38:18 2016


===== TESTED REVISIONS =====
Revision                         Mean     Std Dev  N  Good?
chromium@393034                  6647.3   10.5139  6  good
chromium@393056                  6650.79  18.6024  5  good
chromium@393067                  6647.39  7.69581  5  good
chromium@393067,skia@717abfd2a9  6642.8   5.57682  5  good
chromium@393067,skia@c8699321b9  6650.52  7.01583  5  good
chromium@393067,skia@6296da736f  6747.12  6.30562  5  bad    <--
chromium@393068                  6738.73  13.143   5  bad
chromium@393069                  6735.75  19.1445  5  bad
chromium@393070                  6745.59  19.7223  5  bad
chromium@393073                  6736.95  19.0987  5  bad
chromium@393078                  6720.65  12.8929  5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 611579

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.intl_ko_th_vi
Test Metric: cold_times/page_load_time
Relative Change: 1.09%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3912
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005460447052225856


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5335213958234112

| 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!

Perf sheriff ping: reminder to follow up on possible performance issues

bungeman: are you looking into this?

ping. bungeman, could you please update this bug with whether you're looking into this?

Please see comment #3. The CL in question was reverted and a similar but different CL landed much later. No regression has been blamed on this later CL (afaict) so I doubt the blamed CL is interesting. I left this open so any further issues could be determined, but it appears the bisection is trapped in this local optimum. If no different CL can be blamed in this period then this issue should just be closed.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8999435601888065424

Ok, thanks. It looks like there were two regressions right after each other, and only one of them recovered. I'm starting a bisect on the later range.

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4205
Failure reason: the build has failed due to infrastructure failure.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8997796959602229904

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4285
Failure reason: the build has failed due to infrastructure failure.
Additional errors:
The metric was not found in the test output.
Either of the initial "good" or "bad" revisions failed to be tested or built.

Simon - is there anything we can do at this point?

As bungeman@ mentions in #12, the CL was reverted in a skia roll later on. A lot of the graphs recovered, although no fully pointing to perhaps a secondary regression in the range. We have no way currently of bisecting prior to Nov 9 though, and no way of "ignoring" this CL to bisect the other (will be possible with Pinpoint). Will WontFix this.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982604011939730320