Issue metadata
Sign in to add a comment
|
8.3%-966.8% regression in loading.desktop at 479376:479579 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976620914074919696
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976618193978349216
,
Jun 16 2017
The problem seems to be mac specific.
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_air_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/TicketMaster Revision Result N chromium@479375 454.369 +- 57.6449 21 good chromium@479511 444.068 +- 51.5708 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=TicketMaster loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976620914074919696 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=4973524193640448 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
=== BISECT JOB RESULTS === Bisect failed for unknown reasons Please contact the team (see below) and report the error. Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : cpuTimeToFirstMeaningfulPaint_avg/pcv1-cold/Chosun To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Chosun loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976618193978349216 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6241747773947904 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976611752561604304
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976611744005745552
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : cpuTimeToFirstMeaningfulPaint_avg/pcv1-cold/Chosun Revision Result N chromium@479381 497.783 +- 58.0733 21 good chromium@479493 498.008 +- 51.6987 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Chosun loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976611744005745552 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6241747773947904 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976606266214683104
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_air_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/TicketMaster Revision Result N chromium@479375 460.331 +- 101.018 21 good chromium@479511 446.503 +- 52.2056 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=TicketMaster loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976611752561604304 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=4973524193640448 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : system_health.common_desktop Metric : timeToFirstMeaningfulPaint_avg/load_tools/load_tools_dropbox Revision Result N chromium@479300 245.44 +- 376.578 21 good chromium@479600 201.831 +- 247.098 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.tools.dropbox system_health.common_desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976606266214683104 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6172787242172416 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976600427979631488
,
Jun 16 2017
It looks like the bisect jobs failed: Simon, Annie, do you know why?
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976598202805606560
,
Jun 16 2017
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976597605870811504
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : system_health.common_desktop Metric : timeToFirstMeaningfulPaint_avg/load_tools/load_tools_dropbox Revision Result N chromium@479300 228.119 +- 319.488 21 good chromium@479600 226.12 +- 314.675 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.tools.dropbox system_health.common_desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976600427979631488 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6172787242172416 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu Revision Result N chromium@479381 119.99 +- 22.5741 21 good chromium@479493 119.361 +- 19.4433 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Colorado.edu loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976598202805606560 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5555391330516992 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : page_cycler_v2.basic_oopif Metric : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___booking.com Revision Result N chromium@479381 246.186 +- 74.5043 21 good chromium@479493 238.054 +- 39.3425 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...booking.com page_cycler_v2.basic_oopif Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976597605870811504 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6407211657461760 | 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 Speed>Bisection. Thank you!
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976592881204003728
,
Jun 16 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976592877655047312
,
Jun 16 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu Revision Result N chromium@479381 119.115 +- 13.4208 21 good chromium@479493 119.588 +- 13.8398 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Colorado.edu loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976592881204003728 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5555391330516992 | 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 Speed>Bisection. Thank you!
,
Jun 17 2017
=== BISECT JOB RESULTS === Perf regression found but unable to narrow commit range Build failures prevented the bisect from narrowing the range further. Bisect Details Configuration: mac_pro_perf_bisect Benchmark : page_cycler_v2.basic_oopif Metric : timeToFirstMeaningfulPaint_avg/pcv1-cold/http___booking.com Change : 4.78% | 244.661357143 -> 237.849 Suspected Commit Range 3 commits in range https://chromium.googlesource.com/chromium/src/+log/c13482980f289f9386444ffd281c5baddb79829c..e33287b05658f232d0026256007df3e4981cdfc9 Revision Result N chromium@479381 244.661 +- 33.787 14 good chromium@479382 247.406 +- 30.1086 9 good chromium@479383 --- --- build failure chromium@479384 --- --- build failure chromium@479385 238.967 +- 46.9161 21 bad chromium@479398 236.683 +- 13.5499 14 bad chromium@479409 237.408 +- 19.906 14 bad chromium@479435 236.35 +- 16.138 14 bad chromium@479493 237.849 +- 33.2559 14 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...booking.com page_cycler_v2.basic_oopif Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976592877655047312 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6407211657461760 | 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 Speed>Bisection. Thank you!
,
Jun 19 2017
Looks like the bisect bot results are different from perf bot result. bisects shows the metric in the range of 230-250 in the whole revision range, but there is a clear huge step in perf graph from around 240 to around 4700! https://chromeperf.appspot.com/report?sid=b537ef1df797f010d5fda30bae4c831be209bf4169da28631450afcb6c4cc58c&rev=479493 I'll assign it to Simon (the current bot health sheriff). Simon, I suspect this regression (and the similar ones) are due some change in the bot. Could you please take a look?
,
Jun 20 2017
,
Jun 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976222629227669904
,
Jun 21 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu Revision Result N chromium@479147 117.314 +- 17.6699 21 good chromium@479493 117.696 +- 10.9629 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Colorado.edu loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976222629227669904 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=4938410067755008 | 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 Speed>Bisection. Thank you!
,
Jun 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976215395967376576
,
Jun 21 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu Revision Result N chromium@479147 119.562 +- 18.7567 21 good chromium@479493 119.09 +- 17.9681 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Colorado.edu loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976215395967376576 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=4938410067755008 | 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 Speed>Bisection. Thank you!
,
Jun 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976162008214020240
,
Jun 21 2017
I don't see any change in the bot, looking at the before/after for loading.desktop for example on chromium-rel-mac11-pro, they both ran on seemingly identical hardware (swarming bot build129-b1). I tried kicking one off without a story filter, in case that's the issue with the non-reproducibility.
,
Jun 22 2017
=== BISECT JOB RESULTS === Bisect failed for unknown reasons Please contact the team (see below) and report the error. Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976162008214020240 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5870877129834496 | 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 Speed>Bisection. Thank you!
,
Jun 22 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8976068173680353168
,
Jun 23 2017
=== BISECT JOB RESULTS === Bisect failed for unknown reasons Please contact the team (see below) and report the error. Bisect Details Configuration: mac_pro_perf_bisect Benchmark : loading.desktop Metric : timeToFirstContentfulPaint_avg/pcv1-warm/Colorado.edu To Run This Test src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests loading.desktop Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8976068173680353168 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5870877129834496 | 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 Speed>Bisection. Thank you!
,
Aug 21 2017
kouhei: many, many bisects couldn't reproduce this change seen in perf dashboard for loading.desktop. Anything we can do besides wontfix?
,
Aug 21 2017
I think we can WontFix this as not reproducible. |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by chiniforooshan@chromium.org
, Jun 16 2017