Issue metadata
Sign in to add a comment
|
34.9% regression in blink_perf.svg at 391631:391665 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391626 152.812 1.0668 5 good chromium@391643 155.915 0.698335 5 good chromium@391651 156.606 0.858306 5 good chromium@391653 156.504 1.36412 5 good chromium@391654 154.928 0.198448 5 good chromium@391655 220.527 0.674697 5 bad <-- chromium@391659 214.646 1.07867 5 bad Bisect job ran on: mac_10_10_perf_bisect Bug ID: 609775 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-visible-collapsed-borders/large-table-background-change-with-visible-collapsed-borders Relative Change: 40.46% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2112 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013418420486162096 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5223674961985536 | 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!
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391630 162.21 5.19107 5 good chromium@391647 164.863 1.70389 5 good chromium@391651 166.24 3.91623 5 good chromium@391653 162.922 2.13002 5 good chromium@391654 164.901 1.78652 5 good chromium@391655 212.609 2.38984 5 bad <-- chromium@391663 216.353 1.87754 5 bad Bisect job ran on: mac_retina_perf_bisect Bug ID: 609775 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-visible-collapsed-borders/large-table-background-change-with-visible-collapsed-borders Relative Change: 33.38% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1288 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013418456493888336 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5231991629283328 | 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!
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391618 157.172 0.579514 5 good chromium@391640 160.637 0.829086 5 good chromium@391651 159.802 0.795939 5 good chromium@391654 160.364 0.523375 5 good chromium@391655 246.259 0.743898 5 bad <-- chromium@391656 252.259 4.59645 5 bad chromium@391661 232.933 3.80547 5 bad Bisect job ran on: mac_10_11_perf_bisect Bug ID: 609775 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-visible-collapsed-borders/large-table-background-change-with-visible-collapsed-borders Relative Change: 48.20% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_11_perf_bisect/builds/623 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013418236242120608 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5905418878976000 | 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!
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391630 306.787 6.02274 5 good chromium@391648 315.184 15.5874 5 good chromium@391653 319.073 12.6096 5 good chromium@391654 305.814 7.33424 5 good chromium@391655 392.435 21.0447 5 bad <-- chromium@391657 440.585 64.8575 5 bad chromium@391665 397.995 9.15393 5 bad Bisect job ran on: mac_hdd_perf_bisect Bug ID: 609775 Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.svg Test Metric: Cowboy_transform/Cowboy_transform Relative Change: 29.73% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/530 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013419314767207040 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5242292034600960 | 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!
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391630 314.815 14.1395 5 good chromium@391648 316.455 17.1419 5 good chromium@391653 310.958 13.025 5 good chromium@391654 305.31 5.33223 5 good chromium@391655 404.636 16.4014 5 bad <-- chromium@391657 414.255 24.1348 5 bad chromium@391665 393.721 13.9604 5 bad Bisect job ran on: mac_hdd_perf_bisect Bug ID: 609775 Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.svg Test Metric: Cowboy_transform/Cowboy_transform Relative Change: 25.06% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/531 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013419306589378112 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5893747842220032 | 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!
,
May 6 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : This change enables GPU Raster on OSX. Author : ericrk Commit description: I've compiled a bit of benchmark data to support turning this on - https://docs.google.com/a/google.com/document/d/1RPEnillJOaOKW47t9DYuttQkvWDo7ilx9KDB_nJnwpc/edit?usp=sharing Still filling in more data, but I'm pretty happy with the results so far. In a number of cases we have a performance win, and in most cases we have a power win. Checking this in now will give us a long canary period before the next branch point to catch any issues. BUG= 542959 CQ_INCLUDE_TRYBOTS=tryserver.chromium.linux:linux_optional_gpu_tests_rel;tryserver.chromium.mac:mac_optional_gpu_tests_rel;tryserver.chromium.win:win_optional_gpu_tests_rel;tryserver.blink:mac_blink_rel Review-Url: https://codereview.chromium.org/1881053003 Cr-Commit-Position: refs/heads/master@{#391655} Commit : 8325892c2efdef8cff86ba16e7569f8b424daeda Date : Wed May 04 22:14:40 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@391630 300.267 1.05391 5 good chromium@391643 304.283 0.643819 5 good chromium@391650 306.536 4.41262 5 good chromium@391653 305.31 2.17137 5 good chromium@391654 309.108 3.56658 5 good chromium@391655 475.829 3.42922 5 bad <-- chromium@391656 475.092 2.33118 5 bad chromium@391681 472.645 10.0868 5 bad Bisect job ran on: mac_hdd_perf_bisect Bug ID: 609775 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-visible-collapsed-borders/large-table-background-change-with-visible-collapsed-borders Relative Change: 57.41% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/532 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013418190296312864 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5862488264933376 | 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 alexclarke@chromium.org
, May 6 2016