All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=592296

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDAv5W8ugoM


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

linux-release

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


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379484         5392.875    358.214396  8           good
chromium@379484,skia@a917eba6ea5350.8      42.716507   5           good
chromium@379485         5752.375    76.56918    8           bad

Bisect job ran on: linux_perf_bisect
Bug ID: 592296

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.cold.blank_page
Test Metric: foreground_tab_load_complete/foreground_tab_load_complete
Relative Change: 7.45%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6279
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018878633322338912


| 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 label Cr-Tests-AutoBisect.  Thank you!

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


===== SUSPECTED CL(s) =====
Subject : add setter on SkPaint that takes sk_sp
Author  : reed
Commit description:
  
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1769803002

TBR=

Review URL: https://codereview.chromium.org/1769803002
Commit  : a917eba6ea8a6936f2c9271e487b14d14b99c98e
Date    : Sun Mar 06 00:39:25 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379484         5107.777778 502.696906  27          good
chromium@379484,skia@a917eba6ea5092.125    43.082769   8           bad
chromium@379485         5108.888889 97.466066   18          bad

Bisect job ran on: linux_perf_bisect
Bug ID: 592296

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.cold.blank_page
Test Metric: foreground_tab_request_start/foreground_tab_request_start
Relative Change: 2.87%
Score: 0.0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6281
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018878595333756608


| 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 label Cr-Tests-AutoBisect.  Thank you!

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


===== SUSPECTED CL(s) =====
Subject : add setter on SkPaint that takes sk_sp
Author  : reed
Commit description:
  
BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1769803002

TBR=

Review URL: https://codereview.chromium.org/1769803002
Commit  : a917eba6ea8a6936f2c9271e487b14d14b99c98e
Date    : Sun Mar 06 00:39:25 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379484         3263.555556 130.927488  27          good
chromium@379484,skia@a917eba6ea3085.76     7.366682    5           bad
chromium@379485         3208.622222 161.362535  18          bad

Bisect job ran on: linux_perf_bisect
Bug ID: 592296

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.cold.blank_page
Test Metric: messageloop_start_time/messageloop_start_time
Relative Change: 2.67%
Score: 0.0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6280
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018878611540893952


| 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 label Cr-Tests-AutoBisect.  Thank you!

Pretty sure this is not a real regression. There is one Chromium CL in the range, r379485, which is a Skia roll. The Skia roll consists of two commits, one of which is a revert of the other. So there's no net change in Chrome.

About the bisect behavior here:
- The bisect doesn't run on skia@992854d because that's the same as chromium@379485.
- The bisect is not giving up when there's no a significant regression. https://codereview.chromium.org/1778233002 is up to make it give up sooner.