Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8988416362939675216

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

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:heap:old_space:effective_size_avg/load_news/load_news_qq

Revision             Result                  N
chromium@435050      2610679 +- 34881.3      21      good
chromium@435150      2606321 +- 61154.9      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=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.news.qq system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988416362939675216

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5802133816868864


| 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/8988410501638298544

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

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:heap:old_space:effective_size_avg/load_news/load_news_qq

Revision             Result                  N
chromium@435103      2609499 +- 40688.4      21      good
chromium@435108      2607616 +- 55657.0      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=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.news.qq system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988410501638298544

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5312660150681600


| 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/8988405479366525664

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

Hi yukishiino@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 : yukishiino
  Commit : 5b2adfa4d4e2fb6b74d177625605dcece20a40b7
  Date   : Tue Nov 29 09:53:57 2016
  Subject: binding: Makes non-cross-origin-accessible attrs be accessor props.

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:heap:old_space:effective_size_avg/load_news/load_news_qq
  Change       : 7.32% | 2436990.66667 -> 2615398.66667

Revision             Result                  N
chromium@434326      2436991 +- 8188.44      6      good
chromium@434647      2438447 +- 3671.82      6      good
chromium@434807      2451099 +- 3302.49      6      good
chromium@434887      2451995 +- 4490.11      6      good
chromium@434927      2452388 +- 8119.22      6      good
chromium@434937      2452739 +- 5597.93      6      good
chromium@434940      2454011 +- 7681.79      6      good
chromium@434941      2454553 +- 14050.1      6      good
chromium@434942      2592495 +- 18963.7      6      bad       <--
chromium@434947      2584467 +- 10601.3      6      bad
chromium@434967      2593935 +- 19274.0      6      bad
chromium@435608      2615399 +- 10308.1      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=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.news.qq system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988405479366525664

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5259821315522560


| 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!

ulan@, could you triage this issue?  I guess this is a dup of LargeObjectSpace's issue discussed at  Issue 670352 .

yukishiino@, sorry I thought I'd already replied to this.

It looks like something is off on the chromeperf bots - the bisect in #6 seems unrelated. It only finds a 150K increase while graphs show a 1M jump. Not sure what's going on.

> ulan@, could you triage this issue?
Sorry, I am swamped with other issues. Please use your best judgement here.

Closing as WontFix since the issue is not reproducible through bisects.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982620220319050000

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982580353108355312