All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=719502

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgiungzwsM


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

linux-release

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8980153874566333120

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8980153866568796272

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

Hi yhirano@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 : yhirano
  Commit : bb924e1897f5b4c67325dbfbdf2441e7f0686d53
  Date   : Wed May 03 18:42:19 2017
  Subject: Separate preaload matching from MemoryCache

Bisect Details
  Configuration: linux_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstMeaningfulPaint_avg/browse_media/browse_media_pinterest
  Change       : 129.67% | 905.935629627 -> 1593.32075

Revision             Result                  N
chromium@469042      905.936 +- 1661.37      9      good
chromium@469045      771.467 +- 1046.36      9      good
chromium@469046      1291.46 +- 1012.89      9      bad       <--
chromium@469047      1863.53 +- 3954.41      9      bad
chromium@469052      1583.69 +- 2170.31      6      bad
chromium@469062      1442.54 +- 1137.56      6      bad
chromium@469081      1117.13 +- 476.439      6      bad
chromium@469119      1593.32 +- 1972.8       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=browse.media.pinterest system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980153866568796272

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5818984521269248


| 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!

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

Suspected Commit
  Author : yhirano
  Commit : bb924e1897f5b4c67325dbfbdf2441e7f0686d53
  Date   : Wed May 03 18:42:19 2017
  Subject: Separate preaload matching from MemoryCache

Bisect Details
  Configuration: linux_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstMeaningfulPaint_avg/browse_media/browse_media_pinterest
  Change       : 242.64% | 1422.23794444 -> 2197.11058333

Revision             Result                  N
chromium@469042      1422.24 +- 6660.68      9      good
chromium@469045      1274.83 +- 5903.18      9      good
chromium@469046      2021.26 +- 6531.58      9      bad       <--
chromium@469047      2528.81 +- 7279.52      9      bad
chromium@469052      1286.92 +- 603.396      6      bad
chromium@469062      2448.1 +- 5610.78       6      bad
chromium@469081      2115.69 +- 4985.03      6      bad
chromium@469119      2197.11 +- 4489.03      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=browse.media.pinterest system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980153874566333120

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6067361540472832


| 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!

 Issue 719503  has been merged into this issue.

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/97c0d877b1aff4ac84138c3eab71d994ead93b14

commit 97c0d877b1aff4ac84138c3eab71d994ead93b14
Author: yhirano <yhirano@chromium.org>
Date: Thu May 11 05:39:25 2017

Revert "Separate preaload matching from MemoryCache"

This CL reverts [1] due to performance regressions.

1: https://chromium.googlesource.com/chromium/src/+/bb924e1897f5b4c67325dbfbdf2441e7f0686d53

BUG= 695939 ,  719502 
TBR=japhet@chromium.org

Review-Url: https://codereview.chromium.org/2867333002
Cr-Commit-Position: refs/heads/master@{#470825}

[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/LayoutTests/fast/dom/HTMLLinkElement/link-and-subresource-test-expected.txt
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/LayoutTests/http/tests/preload/multiple-meta-csp.html
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/LayoutTests/http/tests/resources/srcset-helper.js
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/LayoutTests/permissionclient/image-permissions-expected.txt
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/core/loader/DocumentLoader.cpp
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/core/loader/LinkLoaderTest.cpp
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/platform/loader/BUILD.gn
[delete] https://crrev.com/053f34e3a33c62ff262483e92223971aae60de9d/third_party/WebKit/Source/platform/loader/fetch/PreloadKey.h
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/platform/loader/fetch/ResourceFetcher.cpp
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/platform/loader/fetch/ResourceFetcher.h
[modify] https://crrev.com/97c0d877b1aff4ac84138c3eab71d994ead93b14/third_party/WebKit/Source/platform/loader/fetch/ResourceFetcherTest.cpp

I reverted the suspected CL, so the regression should be fixed.

I'll keep this issue open for a while, as I'll reland the CL with additional changes.

See also:  issue 723179 .

How was this fixed? Any more confirmation you can provide?

See #8.