All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=732853

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg5r-_twkM


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

chromium-rel-win7-gpu-ati

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976884393186546160

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/load_media/load_media_youtube

Revision             Result                   N
chromium@477552      15156007 +- 4874497      21      good
chromium@477611      14975053 +- 4445747      21      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.media.youtube system_health.memory_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976884393186546160

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5287720110260224


| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976875997831533744

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/load_media/load_media_youtube

Revision             Result                   N
chromium@477552      14880614 +- 3002724      21      good
chromium@477611      15330794 +- 4949421      21      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.media.youtube system_health.memory_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976875997831533744

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5287720110260224


| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970983495444291344

Looks like there is a broad range over which the regression could have occurred. Kicked the bisect over a wider range.

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

Hi danakj@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 : danakj
  Commit : f4730d5033656a932a06a3d6465fd3be9591b9c3
  Date   : Wed Jun 07 15:30:30 2017
  Subject: cc: Make DisplayItemList hold a single PaintOpBuffer directly.

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/load_media/load_media_youtube
  Change       : 24.62% | 14594711.3333 -> 18187813.3333

Revision             Result                   N
chromium@477308      14594711 +- 165.739      6      good
chromium@477508      15073916 +- 2930970      6      good
chromium@477608      14549615 +- 246781       6      good
chromium@477633      15008344 +- 1968164      6      good
chromium@477646      16036506 +- 3134830      6      good
chromium@477652      14594698 +- 197.727      6      good
chromium@477655      15008378 +- 2573521      6      good
chromium@477657      15314205 +- 2750762      6      good
chromium@477658      17812164 +- 60344.7      6      bad       <--
chromium@477708      18187813 +- 1924531      6      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.media.youtube system_health.memory_desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970983495444291344


For feedback, file a bug with component Speed>Bisection

danajk: ping? This is a 2.4MiB regression on memory in youtube.

This was because of PaintOpBuffer's single-paint-op optimization, which was removed, and the regression recovered.