All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=679538

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg_-3m_goM


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

android-one

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990898879784492688

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

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                 N
chromium@441046      6606089 +- 743185      21      good
chromium@441145      6663237 +- 895076      21      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.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990898879784492688

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5891720979415040


| 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/8990830484615567024

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

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                 N
chromium@441046      6525791 +- 627678      21      good
chromium@441244      6619378 +- 763705      21      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.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990830484615567024

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5875092476657664


| 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!

This looks like signal, but looking at a longer timeframe, looks like it could also be noise. Given the sigma in the bisect, this is unlikely to be able to be bisected.

Do we know where the noise is coming from? Do we need to fix this metric?

The memory.top_10_mobile looks super noisy, not really clear if that's really a regression or a false alarm.

Juan, do you have anything to say or do we need to talk about how to de-noise this metric?

Looks noisy, but the abs value is only about ~320KiB, so it's fine to ignore this alert.

Hopefully ongoing work to trigger memory dumps within Chrome (rather than from Telemetry) will help to reduce this noise.

+primiano

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990677938383245664

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990677920999313024

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990677877984265792

well the problem here is that the regression range is large, there are 5-6 v8 rolls in the range, and metric in this page is noisy. I tried kicking some bisects around the v8 rolls but very likely this is gone.

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

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                 N
chromium@441110      6694462 +- 673829      20      good
chromium@441111      6671456 +- 703229      21      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.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990677920999313024

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5796532290322432


| 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!

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

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                 N
chromium@441130      6732477 +- 752444      21      good
chromium@441131      6771664 +- 692266      20      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.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990677938383245664

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5807163944992768


| 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!

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

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus

Revision             Result                 N
chromium@441099      6735774 +- 782498      21      good
chromium@441100      6784225 +- 722372      21      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.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990677877984265792

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5847885603667968


| 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!

Alright, thanks for following up.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982580635639389344

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982576271582634336