All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=759641

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=8d31398edd82bc6d4486b39bf3929b94d97d3bc1715998cab4b09b1817c5f250


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

android-nexus7v2

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970001985113640656

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

Hi khushalsagar@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 : Khushal
  Commit : 4ad05f3ae24fedcb1fc0438787d2ba4a5c61e520
  Date   : Thu Aug 17 23:13:43 2017
  Subject: cc: Use src_rect for checker-imaging size veto.

Bisect Details
  Configuration: android_nexus7_perf_bisect
  Benchmark    : thread_times.key_mobile_sites_smooth
  Metric       : thread_raster_cpu_time_per_frame/http___slashdot.org_
  Change       : 55.79% | 0.544574948581 -> 0.84838227106

Revision             Result                     N
chromium@495354      0.544575 +- 0.029938       6      good
chromium@495371      0.545269 +- 0.0194275      6      good
chromium@495372      0.845947 +- 0.035204       6      bad       <--
chromium@495373      0.829403 +- 0.0314489      6      bad
chromium@495374      0.826805 +- 0.0375317      6      bad
chromium@495376      0.840426 +- 0.0455128      6      bad
chromium@495380      0.841936 +- 0.0240638      6      bad
chromium@495388      0.84165 +- 0.0138288       6      bad
chromium@495421      0.848382 +- 0.0441363      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...slashdot.org. thread_times.key_mobile_sites_smooth

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970001985113640656


For feedback, file a bug with component Speed>Bisection

With this change, the image decode that was earlier happening on a background worker thread is now being done on the raster worker. Which is the intended effect to avoid async decoding of images used multiple times with small subsets.

For the same change there is an improvement in thread_other_cpu_time_per_frame which is where the decode was being done before this change. See https://chromeperf.appspot.com/report?sid=4b4d18758dbf2c85744496a92a4851422fd1fbf79af695e42a00e95bcf7b5d34

In effect, this is not a regression.

 Issue 760151  has been merged into this issue.

 Issue 760153  has been merged into this issue.

 Issue 760154  has been merged into this issue.