All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=724079

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6qH8ogsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgmrCX6goM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6vm1oAkM


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

chromium-rel-mac11-air
linux-release

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979252291836579920

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: mac_air_perf_bisect
  Benchmark    : blink_perf.layout
  Metric       : floats_10_1000/floats_10_1000

Revision             Result                 N
chromium@471179      724.1 +- 97.4818       21      good
chromium@471248      729.093 +- 127.76      21      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 blink_perf.layout

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979252291836579920

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6431111749566464


| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979220191963514400

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: mac_air_perf_bisect
  Benchmark    : blink_perf.layout
  Metric       : floats_10_1000/floats_10_1000
  Change       : 3.59% | 711.525444444 -> 735.2965

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/47778d3b6f6e5da0a698689d9c4c3e7e3cf0f51e..5e53c60ebe374282c8c2864a8e6d1d864afa221a


Revision             Result                  N
chromium@471179      711.525 +- 12.7817      9        good
chromium@471184      714.085 +- 21.9876      9        good
chromium@471186      717.579 +- 26.05        14       good
chromium@471187      ---                     ---      build failure
chromium@471188      723.614 +- 23.3864      14       bad
chromium@471197      729.177 +- 20.5878      6        bad
chromium@471214      722.246 +- 20.2556      8        bad
chromium@471248      735.297 +- 30.337       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 blink_perf.layout

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979220191963514400

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6431111749566464


| 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!

rune: the build before yours failed, so we can't be certain, but it looks like there is a regression in blink_perf.layout at r471188. Can you take a look?

Looking at "All the graphs for this bug", it looks to me like it recovered.

I've run flexbox-column-wrap and flexbox-column-nowrap locally on Linux with a recent master, and with the suspected CL reverted off that master without being able to reproduce the regression. The floats_10_1000 was reported for mac_air and the graph is clearly recovered and showing better results than before the regression.

Closing.