All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=783621

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=31a9cdb021a73e49d24cdc660fee72404efb7f9085f09479b2a0d0e4ae01cb6c


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

android-webview-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8963323638815024608

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

Hi kouhei@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 : Kouhei Ueno
  Commit : e1cfaee91ad08478fbd956fcd73d570032702397
  Date   : Thu Nov 09 08:23:01 2017
  Subject: Revert "Make script cache hits async"

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : blink_perf.owp_storage
  Metric       : IDBFactory::open/IDBFactory::open
  Change       : 211.52% | 2.96480833333 -> 9.23590833334

Revision             Result                   N
chromium@515117      2.96481 +- 0.348592      6      good
chromium@515120      3.14775 +- 0.41792       6      good
chromium@515121      9.04603 +- 0.872475      6      bad       <--
chromium@515122      9.08865 +- 1.28451       6      bad
chromium@515123      9.26091 +- 1.07792       6      bad
chromium@515129      9.23591 +- 0.657265      6      bad

Please refer to the following doc on diagnosing blink_perf regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/speed/benchmark_harnesses/blink_perf.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 blink_perf.owp_storage

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8963323638815024608


For feedback, file a bug with component Speed>Bisection

 Issue 783624  has been merged into this issue.

 Issue 783625  has been merged into this issue.

 Issue 783766  has been merged into this issue.

 Issue 783794  has been merged into this issue.

 Issue 783632  has been merged into this issue.

 Issue 783908  has been merged into this issue.

This was a revert of a CL which caused loading.desktop regression. We plan to reland the CL after tweak.

Ongoing discussion at https://groups.google.com/a/chromium.org/forum/?utm_medium=email&utm_source=footer#!msg/scheduler-dev/RZRjVPFLMLY/mTrtJWphCQAJ

 Issue 784345  has been merged into this issue.

 Issue 787439  has been merged into this issue.

 Issue 787438  has been merged into this issue.

kouhei: any update here?

Ping.

japhet: Would you give updates on https://chromium-review.googlesource.com/c/chromium/src/+/737481 ?

I've got a CL that attempts to re-land making script cache hits async without the perf regressions it caused at https://chromium-review.googlesource.com/c/chromium/src/+/762078

I haven't been pushing it very hard, though, because it's sufficiently hacky that I'm worried that it's not worth the mess.

Removing Performance-Sheriff label, as reverts aren't the type of regression that sheriffs should ping on.