All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=865683

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=16706dc16799e9391f912578fd35bfebbb9057bdd5647d51c830427b52e94099


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

health-plan-clankium-phone
health-plan-webview-low-end-phone
health-plan-webview-phone
perf-go-phone-1024
perf-go-phone-512
perf-go-webview-phone

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8940541539302357024

This corresponds to a large ~1 MiB regression appearing quite close to the M69 branch point.

May not block release, but it is negating some significant memory savings that had been achieved during development for this milestone.

+benhenry, +ushesh

=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: INFRA_FAILURE

The bisect was able to narrow the range, you can try running with:
  good_revision: 4a9d09e563df548cea6a3ad93a7c4f293a8f7633
  bad_revision : 5b7648dcf47af986f69d54b9a6011f51a8092020

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: webview-low-end-phone-perf-bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:webview:all_processes:reported_by_os:system_memory:native_heap:proportional_resident_size_avg/background/after_https_m_facebook_com_rihanna
  Change       : 4.38% | 8329730.66667 -> 8694786.66667

Revision                                       Result                  N
android-chrome@74662f91c8                      8329731 +- 47645.9      6      good
android-chrome@74662f91c8,chromium@575926      8350723 +- 27830.7      6      good
android-chrome@74662f91c8,chromium@575929      8352088 +- 33452.1      6      good
android-chrome@74662f91c8,chromium@575931      8692397 +- 16315.6      6      bad
android-chrome@74662f91c8,chromium@575935      8667821 +- 22384.8      6      bad
android-chrome@1032e70048                      8676355 +- 53697.7      6      bad
android-chrome@4e67b217c5                      8670552 +- 33577.2      6      bad
android-chrome@22c1f49355                      8694787 +- 91173.2      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-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=https.m.facebook.com.rihanna 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/8940541539302357024


For feedback, file a bug with component Speed>Bisection

That bisect nailed it down pretty close to basically one of:
r575931 Set "application/octet-stream" content type for empty <input type=file>
r575930 Update V8 to version 6.9.426.

The v8 roll is: https://chromium.googlesource.com/v8/v8/+log/3df683e6..65ea3e26

And from there the culprit is pretty much likely:

Revert "[embedded-builtins] Enable on all arches except x86 for benchmarks"
https://chromium.googlesource.com/v8/v8/+/46a78fbedfcd458f5d35097bdf1a9947644f4b0e

So I guess this is pretty much expected, as the revert is just taking back the memory improvements we had seen on  issue 856027 .

Assigning to sigurds mostly FYI on memory/performance changes due to embedded-builtins.

 Issue 865697  has been merged into this issue.

For now, this has been reverted on 69. We plan on relanding soon on 70, which should fix the regression.

Thanks for the heads up. Feel free to close this bug or keep it to track any related work for the re-land.