All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=626372

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg0v39qQkM


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

linux-release

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


===== TESTED REVISIONS =====
Revision                         Mean      Std Dev      N  Good?
chromium@403932                  0.135467  0.000770214  5  good
chromium@403935                  0.134467  0.000241882  5  good
chromium@403936                  0.1355    0.00168428   5  good
chromium@403936,skia@2f5792a06c  0.134833  0.000258535  5  good
chromium@403936,skia@afd6340d56  0.135342  0.00096708   5  good
chromium@403936,skia@0d28e574ac  0.135258  0.000157012  5  good
chromium@403937                  0.1402    0.000822534  5  bad
chromium@403938                  0.140258  0.000961679  5  bad
chromium@403943                  0.141342  0.003029     5  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 626372

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests rasterize_and_record_micro.top_25_smooth
Test Metric: record_time/record_time
Relative Change: 4.34%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6580
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007780841814133808


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6437622767943680

| 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!

Trying again with more iterations.

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


===== TESTED REVISIONS =====
Revision                         Mean      Std Dev      N  Good?
chromium@403900                  0.151242  0.000691842  5  good
chromium@403925                  0.15085   0.000340547  5  good
chromium@403932                  0.151567  0.00077426   5  good
chromium@403935                  0.151117  0.000248956  5  good
chromium@403936                  0.151474  0.000777262  8  good
chromium@403936,skia@2f5792a06c  0.15275   0.00261861   8  good
chromium@403936,skia@afd6340d56  0.15285   0.00112253   5  good
chromium@403936,skia@0d28e574ac  0.151825  0.00116272   5  good
chromium@403937                  0.157448  0.00150656   8  bad
chromium@403938                  0.157608  0.000901195  5  bad
chromium@403950                  0.1573    0.000791338  5  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 626372

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests rasterize_and_record_micro.top_25_smooth
Test Metric: record_time/record_time
Relative Change: 4.01%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6581
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007717766293625904


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5806676435795968

| 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!

Odd the bot can't narrow this down.

Skia folks, could you please check if your patches might have regressed this metric?

https://chromium.googlesource.com/skia.git/+log/1e2a702c1959..52fa668dc589

Might be https://chromium.googlesource.com/skia.git/+/41c27e15ec2740850700f1b82038ce0f7a632481 where I enabled a peep-hole optimization. I will re-disable it in a new CL to see if that helps.

@Reed: did you re-disable peep-hole optimization? Can you update the status?

reverted

Perf sheriff ping: reminder to follow up on possible performance issues

Sorry for the long triage delay here.

reed: the revert on Jul 20 seems to have fixed it:
https://codereview.chromium.org/2159423003
That includes:
2016-07-20 reed re-disable save/restore peephole optimization

Should we mark this fixed, or do you intend to re-land?

I think we're gonna keep this off.