All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=725953

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgus2a5QoM


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

android-nexus5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978699819551629072

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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:all_processes:reported_by_os:system_memory:native_heap:proportional_resident_size_avg/background/after_http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                   N
chromium@472751      34541598 +- 837982       21      good
chromium@472825      34663698 +- 1286055      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 memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978699819551629072

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5881627256815616


| 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/8978684158304940608

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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:all_processes:reported_by_os:system_memory:native_heap:proportional_resident_size_avg/background/after_http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                   N
chromium@472751      34551692 +- 1419406      21      good
chromium@472825      34559640 +- 1025504      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 memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978684158304940608

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5881627256815616


| 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/8976999539079254160

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

Hi machenbach@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 : Michael Achenbach
  Commit : 9fd599ef98ce3dbe978732761b77c51eb41a506d
  Date   : Thu May 18 12:11:20 2017
  Subject: [MB] Add concurrent marking bots

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/background
  Change       : 2.28% | 4914629.53333 -> 5026791.2

Revision                           Result                  N
chromium@472700                    4914630 +- 15595.4      6      good
chromium@472795                    4924701 +- 23362.2      6      good
chromium@472843                    4926972 +- 14479.4      6      good
chromium@472855                    4924087 +- 17843.1      6      good
chromium@472855,v8@5e9939214e      4921479 +- 13495.4      6      good
chromium@472855,v8@cd1325a890      3959032 +- 1901450      6      good
chromium@472855,v8@9fd599ef98      5031144 +- 4625.91      6      bad       <--
chromium@472856                    5025899 +- 12883.6      6      bad
chromium@472857                    5024995 +- 14242.0      6      bad
chromium@472858                    5024647 +- 18779.2      6      bad
chromium@472861                    5027238 +- 11499.2      6      bad
chromium@472867                    5030720 +- 7539.44      6      bad
chromium@472890                    5026791 +- 13803.3      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 memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976999539079254160

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6132162153152512


| 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!

That's not a code, just some infra config change. Can't influence performance. Please try again...

Looks like some kind of blip, doesn't repro on bisect bots.