All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=784856

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=b0e62d62749e62a043fc607219a48131d685395875c96562395f3eb902d58520


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

android-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8962941081655376720

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/foreground/http_en_m_wikipedia_org_wiki_Science
  Change       : 1.36% | 43452580.9524 -> 44043061.7143

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/6587416636be38b0501a12f12959fa8e39fe88c9..ee5fc7dddbdc9c5a76857c7524a418cb6cb13f76


Revision             Result                   N
chromium@515354      43452581 +- 2289705      21       good
chromium@515403      43461048 +- 1813505      21       good
chromium@515427      43584792 +- 1015781      14       good
chromium@515432      43361205 +- 1519750      14       good
chromium@515433      ---                      ---      build failure
chromium@515434      43905335 +- 863973       9        bad
chromium@515435      44075296 +- 1889536      9        bad
chromium@515441      43916259 +- 1648787      14       bad
chromium@515451      44043062 +- 1768270      14       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=http.en.m.wikipedia.org.wiki.Science memory.top_10_mobile

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8962941081655376720


For feedback, file a bug with component Speed>Bisection

Looks like it's probably https://chromium.googlesource.com/chromium/src/+/fef357976519f0c2a29d6a6b7c8fcab05c7c90f4

I reviewed https://chromium.googlesource.com/chromium/src/+/fef357976519f0c2a29d6a6b7c8fcab05c7c90f4 and don't see how this can be causing an increase in the use of memory. Also, the wikipedia mobile (and desktop) site doesn't use CacheStorage nor service workers, so the code in the aforementioned change wouldn't be executed. The above change landed in #515433, but looking at this graph https://chromeperf.appspot.com/report?sid=bbdecd1cd07ab2bb2ab6480f002269ca46160eb30aeeddc2da7f79a8b4aef2b1&start_rev=513746&end_rev=516025 the uptick in memory usage appears to start earlier. My guess is that the offending change landed in Point ID: 514800 (on the chart), which includes a bunch of other changes, and a v8 roll.

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/129c78c4840000

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14c21118840000

Kicking off a few more bisects.

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/14c21118840000

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/129c78c4840000

Test score is current back down to (actually lower than) the score before this bug was filed.