All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=654856

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgzYqbvwoM


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

android-nexus5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8999069151747425312

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@423961  22.2171  1.40784  5  good
chromium@424052  28.5178  1.9551   5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 654856

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests v8.infinite_scroll_tbmv2
Test Metric: v8-gc-latency-mark-compactor_avg/v8-gc-latency-mark-compactor_avg
Relative Change: 28.36%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4225
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8999069151747425312


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5848615103234048

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998513857482988144

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

Hi mlippautz@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


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


===== SUSPECTED CL(s) =====
Subject : [heap] Remove PromotionMode used by Scavenger
Author  : mlippautz
Commit description:
  
The scavenger should never consider mark bits for promotion/copy as this creates
weird livetimes at the start of incremental marking. E.g. consider an object
marked black by the marker at the start of incremental marking. A scavenge would
promote it to the old generation although it could --and for short-living
objects actually does-- become unreachable during marking

Also, keeping this invariant significantly simplifies young generation mark
compacting as we can compare against the scavenging decision without keeping
different sets of markbits.

BUG=chromium:651354
R=hpayer@chromium.org

Review-Url: https://codereview.chromium.org/2397713002
Cr-Commit-Position: refs/heads/master@{#40026}
Commit  : f88fe51a00bb66d6e47e1e12193cb5125dfa63b1
Date    : Thu Oct 06 10:14:23 2016


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev  N  Good?
chromium@423961                27.6432  3.31871  8  good
chromium@423984                26.5474  2.70934  4  good
chromium@423990                27.4395  1.34134  5  good
chromium@423993                28.9916  2.12518  5  good
chromium@423995                26.5883  1.66909  8  good
chromium@423995,v8@6d9b2e129a  27.1974  2.54175  8  good
chromium@423995,v8@f88fe51a00  34.5588  2.23137  8  bad    <--
chromium@423995,v8@1411c7628b  35.794   2.55253  5  bad
chromium@423995,v8@d874e0dca7  32.972   4.14915  7  bad
chromium@423995,v8@a03ac68c55  34.0864  1.9334   8  bad
chromium@423995,v8@a105dafa96  34.2016  3.29943  5  bad
chromium@423996                35.7024  5.38766  5  bad
chromium@424007                32.5354  2.31643  5  bad
chromium@424052                33.1208  1.71985  8  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 654856

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests v8.infinite_scroll_tbmv2
Test Metric: v8-gc-latency-mark-compactor_max/v8-gc-latency-mark-compactor_max
Relative Change: 20.63%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4247
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8998513857482988144


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5881642931978240

| 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!

Graphs recovered probably due to other changes.

The mode was added in may under the assumption that we require it for wrapper tracing. This is no longer true so we removed the mode that made the scavenger dependent on markbits. 

We actually require this now to go forward with a new young generation collector.