All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=604907

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxKTCtwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICghJPTuQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxICWowoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxML6oQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxOPEvgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxJmYogoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxMSvuwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxMSvuwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgxOmPvQoM


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

chromium-rel-mac-retina
chromium-rel-win10
chromium-rel-win7-dual
chromium-rel-win7-gpu-ati
chromium-rel-win7-gpu-intel
chromium-rel-win7-gpu-nvidia
chromium-rel-win7-x64-dual
chromium-rel-win8-dual
linux-release

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Temporarily disable float empty-phase optimization
Author  : wangxianzhu
Commit description:
  
BUG= 603910 

Review URL: https://codereview.chromium.org/1897823004

Cr-Commit-Position: refs/heads/master@{#388102}
Commit  : e7f53da593a30c18884a215115a99e276c3f73bd
Date    : Tue Apr 19 00:57:42 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@388095  57.8616  3.80395  12  good
chromium@388100  204.698  476.498  11  good
chromium@388101  57.2987  1.1694   5   good
chromium@388102  78.1636  1.32981  12  bad    <--
chromium@388104  79.3316  3.64685  12  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 604907

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.paint
Test Metric: large-table-background-change-with-invisible-collapsed-borders/large-table-background-change-with-invisible-collapsed-borders
Relative Change: 38.54%
Score: 0.0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/505
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014084249964044640


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5278915791159296

| 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 Tests>AutoBisect.  Thank you!

wangxianzhu: the numbers reported by the bisect are kind of crazy, but checking the graph, it looks like disabling float empty-phase optimization regressed this and then "Mark layer needsPaintPhaseFloat if a LayoutBlockFlow contains float" got the performance back to previous levels: https://codereview.chromium.org/1899063002

Is that correct? If so, I think it's fine to mark this fixed.

Yes.

Following up on the "bad_bisect" link: bisect looks okay. There was one massive outlier that made r388100 have a really high mean (one of the values was 1640.9740909090908) but the statistical bisect algorithm is resistant to one-off outliers and the bisect ran correctly.

If you look at the Telemetry JSON output, it does show a weird spike in the test results.
https://uberchromegw.corp.google.com/i/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/505/steps/Working%20on%20revision%20chromium%40388100.Waiting%20for%20chromium%40388100.Reading%20chartjson%20results%20%282%29/logs/json.output