Issue metadata
Sign in to add a comment
|
9.5% regression in octane at 436735:436762 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Dec 8 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8993852759752155136
,
Dec 8 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8993852740988712640
,
Dec 8 2016
===== BISECT JOB RESULTS =====
Status: failed
=== Bisection aborted ===
The bisect was aborted because Infra Failure: Step('Working on revision chromium@436736,v8@9c9c8d7bb5.install ChromePublic.apk') returned 2
Please contact the the team (see below) if you believe this is in error.
===== TESTED REVISIONS =====
Revision Mean Std Dev N Good?
chromium@436734 7491.88 218.785 8 good
chromium@436736 7530.0 143.443 8 good
chromium@436737 7068.4 134.466 5 bad
chromium@436738 7037.6 184.378 5 bad
chromium@436741 7101.4 333.306 5 bad
chromium@436748 7003.0 161.784 5 bad
chromium@436762 7011.8 79.9175 5 bad
Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 672404
Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests octane
Test Metric: Total/Score
Relative Change: 6.41%
Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/973
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8993852759752155136
Not what you expected? We'll investigate and get back to you!
https://chromeperf.appspot.com/bad_bisect?try_job_id=5855559415234560
| 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!
,
Dec 8 2016
===== BISECT JOB RESULTS =====
Status: failed
=== Bisection aborted ===
The bisect was aborted because Infra Failure: Step('Working on revision chromium@436736,v8@9c9c8d7bb5.install ChromePublic.apk') returned 2
Please contact the the team (see below) if you believe this is in error.
===== TESTED REVISIONS =====
Revision Mean Std Dev N Good?
chromium@436734 7542.0 108.268 8 good
chromium@436736 7486.13 160.04 8 good
chromium@436737 7105.6 90.5052 5 bad
chromium@436738 7094.6 337.51 5 bad
chromium@436741 7148.4 362.347 5 bad
chromium@436748 7094.2 228.217 5 bad
chromium@436762 7135.8 254.34 5 bad
Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 672404
Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests octane
Test Metric: Total/Score
Relative Change: 5.39%
Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/974
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8993852740988712640
Not what you expected? We'll investigate and get back to you!
https://chromeperf.appspot.com/bad_bisect?try_job_id=5818681349636096
| 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!
,
Dec 8 2016
+simonhatch: Looks like the bisect is having a problem descending into this v8 roll: https://codereview.chromium.org/2557693003
,
Dec 8 2016
This is bizarre, the zip downloaded was only 13mb. Builder is here: https://build.chromium.org/p/tryserver.chromium.perf/builders/android_arm64_perf_bisect_builder/builds/2038 Ideally the bisect shouldn't just fail completely like this, but I'd also like to figure out what went wrong on that builder.
,
Dec 8 2016
,
Dec 8 2016
,
Dec 16 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8993101146446731744
,
Dec 16 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : [heap] Ensure finalization of incremental marking even if all allocations Author : ulan Commit description: come from the runtime. This patch fixes an issue of heap growing to max capacity when incremental marking is finished but cannot finalize due to GC stack guard not triggering. It can happen if all allocations come from the runtime, for example, from JSON parser or compiler. Now before expanding the heap we check if we are above the allocation limit and the incremental marking needs to be finalized. If so we do not expand the heap and force GC, which will finalize the incremental marking. The check is performed for paged spaces and large-object space. BUG=chromium:670675 Review-Url: https://codereview.chromium.org/2552613004 Cr-Commit-Position: refs/heads/master@{#41524} Commit : fdc0aa0c97952e56686157b1023a8085885357b4 Date : Tue Dec 06 14:06:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@436736 7534.83 81.6874 6 good chromium@436736,v8@2da865d8a4 7551.17 150.475 6 good chromium@436736,v8@ca74343a70 7573.5 74.2395 6 good chromium@436736,v8@fdc0aa0c97 7096.67 323.712 6 bad <-- chromium@436736,v8@9c9c8d7bb5 7093.0 307.151 6 bad chromium@436737 7069.83 274.836 6 bad Bisect job ran on: android_nexus5X_perf_bisect Bug ID: 672404 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests octane Test Metric: Total/Score Relative Change: 6.17% Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/999 Job details: https://chromeperf.appspot.com/buildbucket_job_status/8993101146446731744 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5825267530989568 | 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! |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by ulan@google.com
, Dec 8 2016