All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=909049

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=fc5380706f465aafb3521dd59c11852a61dc78811f6796a782afbe186a3b1ed2


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

Android Nexus5X WebView Perf
Android Nexus6 WebView Perf
mac-10_12_laptop_low_end-perf

speedometer - Benchmark documentation link:
  None

system_health.memory_mobile - Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

rendering.mobile - Benchmark documentation link:
  https://bit.ly/rendering-benchmarks

loading.mobile - Benchmark documentation link:
  https://bit.ly/loading-benchmarks

system_health.memory_desktop - Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/177524c0140000

📍 Found significant differences after each of 2 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/177524c0140000

Apply morx if there's no GSUB! by behdad@behdad.org
https://chromium.googlesource.com/external/github.com/harfbuzz/harfbuzz/+/14ff3cbe0f30dea24e1bb175b1e8e41039f6afdc
memory:chrome:all_processes:reported_by_chrome:malloc:effective_size: 5.634e+07 → No values

Roll HarfBuzz to 2.1.1 plus AAT fixes by drott@chromium.org
https://chromium.googlesource.com/chromium/src/+/c67f53b0b70f33c47159d37f7e59bb44399b0d09
memory:chrome:all_processes:reported_by_chrome:malloc:effective_size: No values → 2.479e+08

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

The pinpoint message turns out to be useless, as all it triggers on is a build failure on an intermediate commit of this roll. Reported as  issue 909626 .

For Blink triage: taking a stab at sub component based on commits in pinpoint. Since this may be in error, please re-classify as appropriate :)

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/13db80cfe40000

I moved the Mac failures potentially related to the HarfBuzz AAT roll to  issue 908552 . The remaining ones on this issue are Android failures, that I do not expect to have anything to do with the HarfBuzz AAT roll. Unassigining myself.

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/13db80cfe40000

Revert "[config] Disable scheduled script streaming field trial" by leszeks@chromium.org
https://chromium.googlesource.com/chromium/src/+/83ec360fbb41f7b81a628417b1aa5f13daaa622d
memory:webview:all_processes:reported_by_chrome:malloc:effective_size: 3.908e+07 → 4.097e+07 (+1.895e+06)

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

WAI, we're compiling more on more threads.