All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=645588

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg4f_ViAkM


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

chromium-rel-mac-retina

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9001970664699982272

===== 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@415307  212.799  5.26064  18  good
chromium@415344  211.89   5.61382  18  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 645588

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: toBlob_duration/toBlob_duration
Relative Change: 1.56%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1646
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9001970664699982272


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5390148810833920

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9001966948486020544

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@415307  213.015  5.0006   27  good
chromium@415312  216.085  5.95538  8   bad
chromium@415317  218.775  2.84186  8   bad
chromium@415326  217.283  5.65808  27  bad
chromium@415344  216.548  2.63648  18  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 645588

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: toBlob_duration/toBlob_duration
Relative Change: 1.24%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1647
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9001966948486020544


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6352807613956096

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9001683594463301152

===== 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@415307  212.611  8.23203  18  good
chromium@415344  213.364  3.32823  18  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 645588

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: toBlob_duration/toBlob_duration
Relative Change: 1.53%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1651
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9001683594463301152


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5790337421803520

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9001669241905213920

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

Hi zmo@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 : Enable core profile GL on Mac OSX
Author  : zmo
Commit description:
  
BUG=635081
TEST=mac bots
NOTRY=true
R=kbr@chromium.org,erikchen@chromium.org

Review-Url: https://codereview.chromium.org/2251263002
Cr-Commit-Position: refs/heads/master@{#415350}
Commit  : 1eb4627c819627991316dc07225cb76d7f3b7e35
Date    : Tue Aug 30 18:03:26 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@415107  213.63   2.44686  5  good
chromium@415247  208.788  5.40211  5  good
chromium@415317  216.994  4.27387  5  good
chromium@415335  214.553  4.90477  5  good
chromium@415344  216.388  2.35224  5  good
chromium@415348  214.847  5.63279  5  good
chromium@415349  216.787  3.40231  5  good
chromium@415350  232.851  3.89191  5  bad    <--
chromium@415352  235.672  4.42518  5  bad
chromium@415386  228.015  4.97956  5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 645588

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: toBlob_duration/toBlob_duration
Relative Change: 6.73%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1653
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9001669241905213920


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5848897790935040

| 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!

Friendly perf sheriffing ping to follow up on potential regressions.

I am really overwhelmed with pushing WebGL2 out in M55, so anyone that can take a look is greatly appreciated. Otherwise I'll try my best to allocate some time (will be very challenging though)

I'll triage and find an owner for this.

Note that if was really the switch to the Core Profile we will either have to deeply investigate what slowed down and try to fix or work around it, or close this as WontFix. We simply can't go back to the Compatibility Profile at this point.

Any status update on this?

Hey vmiura, how's the triage going?

zmo@ do you think you have more time to look into this?

I'd like to ask that we find another engineer to help Mo with this bug. It probably requires expertise in the 2D canvas context backend to understand exactly where the performance regression is, and switching back to the compatibility profile on macOS is not a viable option -- it would disable WebGL 2.0 and all future work relying on more advanced OpenGL features past 2.1 + extensions.

vmiura: it looks like we didn't find anyone. Should we keep this open?

@fserb, would you mind investigating this?

fserb, any update?

I'm going to call this WontFix. The switch to the Core Profile on macOS was required in order to ship new features and move Chrome's graphics stack forward, and since this bug has been sitting around uninvestigated for over a year, it clearly isn't a top priority.