All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=730480

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-vyogQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpq7XogoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpprJ6ggM


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

chromium-rel-mac-retina
chromium-rel-mac11-air
chromium-rel-mac11-pro

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977454505410053312

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

Hi fdoray@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 : Francois Doray
  Commit : 9171a2ab9637d50fb574ebc354a859776efa9dd0
  Date   : Mon Jun 05 15:43:12 2017
  Subject: Support the BACKGROUND thread priority on Mac.

Bisect Details
  Configuration: mac_air_perf_bisect
  Benchmark    : image_decoding.image_decoding_measurement
  Metric       : ImageDecoding_avg/ImageDecoding_avg
  Change       : 93.17% | 79.2001666667 -> 152.989958333

Revision             Result                  N
chromium@476970      79.2002 +- 7.99784      6      good
chromium@476989      78.1605 +- 6.58706      6      good
chromium@476990      78.9313 +- 9.14685      6      good
chromium@476991      154.891 +- 22.8044      6      bad       <--
chromium@476992      144.418 +- 8.20578      6      bad
chromium@476994      147.274 +- 21.2867      6      bad
chromium@476998      142.248 +- 32.9534      6      bad
chromium@477007      152.99 +- 37.8063       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 image_decoding.image_decoding_measurement

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977454505410053312

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5882899733151744


| 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!

Gentle ping on this so we can get it moved of the perf sheriff backlog :)
What's the verdict fdoray? Does this CL seem likely and is there anything we could do about it? Thanks!

cc-ing benchmark owners cblume, reveman: how high-priority is this bug?

fdory, any update?

I think it has already been fixed.
The graphs represent a slice of time between A and B. The bar below each graph has a green area where you can change A and B. You'll see after B...IE after the end of the graph...the times went back down.