All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=664215

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg4_SftQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgo_DjlQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgk-f8qAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgo7KZ3woM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg4-qBzQgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgk6OAsAsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgk9XTsQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg05ryowoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgk922uAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg057FuQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgk73TpwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg07rnswoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg09zvqwsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg04P-rgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg0775oQsM


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

android-nexus5
android-nexus5X
android-nexus7v2
android-nexus9
android-one
chromium-rel-mac-retina
chromium-rel-mac10
chromium-rel-mac11
chromium-rel-win7-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8996359459324666656

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982667490496586672

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

Hi reillyg@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 : reillyg
  Commit : 963ec6df64089bef6867ccdc608101d5fc06d5c0
  Date   : Sat Nov 05 01:13:13 2016
  Subject: Port messages sent by WebIDBDatabaseImpl to Mojo.

Bisect Details
  Configuration: mac_10_10_perf_bisect
  Benchmark    : storage.indexeddb_endure_tracing
  Metric       : idb-transaction-commits/Action_Test/indexeddb-endure-testCreateAndDeleteDatabases

Revision             Result                   N
chromium@430109      0.947077 +- 4.65529      300      good
chromium@430110      1.08279 +- 7.18457       300      bad       <--
chromium@430111      1.10469 +- 7.00778       300      bad
chromium@430113      1.07107 +- 6.69795       300      bad
chromium@430117      1.07202 +- 6.5363        300      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests storage.indexeddb_endure_tracing

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982667490496586672

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4961078511927296


| 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 Speed>Bisection.  Thank you!

so for more info, this is timing IndexedDBTransaction::Commit (https://cs.chromium.org/chromium/src/content/browser/indexed_db/indexed_db_transaction.cc?q=IndexedDBTransaction::Commit&l=288)

I'm not super sure what this means

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982576486428779568

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : reillyg
  Commit : 963ec6df64089bef6867ccdc608101d5fc06d5c0
  Date   : Sat Nov 05 01:13:13 2016
  Subject: Port messages sent by WebIDBDatabaseImpl to Mojo.

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : storage.indexeddb_endure_tracing
  Metric       : idb-transaction-commits/Action_Test/indexeddb-endure-testReadCacheWithoutIndex
  Change       : 12.87% | 1.35268489583 -> 1.526796875

Revision             Result                    N
chromium@430101      1.35268 +- 0.0545537      6      good
chromium@430108      1.34124 +- 0.048308       6      good
chromium@430109      1.36402 +- 0.0756975      6      good
chromium@430110      1.49133 +- 0.0695484      6      bad       <--
chromium@430111      1.49579 +- 0.0756237      6      bad
chromium@430114      1.50219 +- 0.128306       6      bad
chromium@430127      1.48989 +- 0.0964802      6      bad
chromium@430152      1.5268 +- 0.0886828       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=indexeddb.endure.testReadCacheWithoutIndex storage.indexeddb_endure_tracing

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982576486428779568

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4961078511927296


| 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 Speed>Bisection.  Thank you!

Since there is an owner, this bug is not untriaged. Updating the status.

Removing myself as owner. dmurph@, please triage if this is an issue we can/should fix.

Hm.. this is commit time. Interesting. We can't revert the change, it's part of the new architecture, so I'm going to label this as wontfix. I have no idea why this changed cause this behavior though, it didn't change indexeddb internals too much.