Issue metadata
Sign in to add a comment
|
84.7% regression in smoothness.gpu_rasterization.top_25_smooth at 464923:464949 |
||||||||||||||||||||||
Issue descriptionThe benchmarks' duration go from 10 minutes to 25 minutes and is now back at 19 minutes. There is no change to this benchmark as far as I know. Before log: https://luci-logdog.appspot.com/v/?s=chrome%2Fbb%2Fchromium.perf%2FAndroid_Nexus6_Perf__2_%2F5594%2F%2B%2Frecipes%2Fsteps%2Fsmoothness.gpu_rasterization.top_25_smooth%2F0%2Fstdout After log: https://luci-logdog.appspot.com/v/?s=chrome%2Fbb%2Fchromium.perf%2FAndroid_Nexus6_Perf__2_%2F5602%2F%2B%2Frecipes%2Fsteps%2Fsmoothness.gpu_rasterization.top_25_smooth%2F0%2Fstdout I suspect this has something to with the lab
,
Apr 24 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981401963623521840
,
Apr 24 2017
,
Apr 25 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: android_nexus6_perf_bisect Benchmark : smoothness.gpu_rasterization.top_25_smooth Metric : benchmark_duration/benchmark_duration Revision Result N chromium@464922 9.48701 +- 8.79177 19 good chromium@464949 9.87993 +- 1.19833 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.gpu_rasterization.top_25_smooth Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8981401963623521840 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5784317575299072 | 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!
,
Apr 25 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981372009401943248
,
Apr 25 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: android_nexus6_perf_bisect Benchmark : smoothness.gpu_rasterization.top_25_smooth Metric : benchmark_duration/benchmark_duration Revision Result N chromium@464922 9.88808 +- 0.697393 21 good chromium@464949 9.86773 +- 0.641357 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.gpu_rasterization.top_25_smooth Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8981372009401943248 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5784317575299072 | 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!
,
Apr 26 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981248666747995184
,
Apr 26 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: android_nexus6_perf_bisect Benchmark : smoothness.gpu_rasterization.top_25_smooth Metric : benchmark_duration/benchmark_duration Revision Result N chromium@464922 9.88808 +- 0.697393 21 good chromium@464949 9.86773 +- 0.641357 21 bad To Run This Test src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.gpu_rasterization.top_25_smooth Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8981248666747995184 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5784317575299072 | 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!
,
Jul 18 2017
,
Feb 5 2018
,
Feb 6 2018
Ned, this bug is pretty old. Do you think it's still relevant?
,
Feb 6 2018
Nope, the graphs are all recovered |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by nedngu...@google.com
, Apr 24 2017