Issue metadata
Sign in to add a comment
|
507% regression in media.tough_video_cases at 397715:397782 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jun 15 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : Modify ImageTransportSurfaceOverlayMac to allow pipelining Author : ericrk Commit description: This change allows 1 additional frame of pipelining in ImageTransportSurfaceOverlayMac by switching from a glFinish based approach to a glFence based one. Tested for CA framerate regressions - the following cases starve CA when used with a simple glFlush. This solution (and the previous glFinish) appear to successfully prevent CA starvation: Animometer - bouncing png images: https://trac.webkit.org/export/HEAD/trunk/PerformanceTests/Animometer/developer.html?test-interval=20&display=progress-bar&controller=adaptive&frame-rate=50&kalman-process-error=1&kalman-measurement-error=4&time-measurement=performance&suite-name=SVGsuite&test-name=SVGbouncingPNGimages&complexity=200 Both glFinish and glFence produce ~50 fps in CA/Chrome. WebGL Liquid Face: http://alteredqualia.com/xg/examples/liquid_face.html For liquid face, note that with the glFinish, CA framerate is slightly higher than Chrome reported framerate (20 vs 15) - with the new approach, they match more closely (16 vs 15). This may be a negative, but is still much better than the starvation which is seen with glFlush (5 vs 15). Improvements: Telemetry smoothness.top_25_smooth: This change produces good improvements in first_gesture_scroll_update_latency, mean_input_event_latency, and mean_main_thread_scroll_latency, without any significant regressions. See: https://drive.google.com/file/d/0B2nwXDxTDpGGU215X2xYTE9Bdnc/view?usp=sharing Animometer Benchmark: This change produces good improvements in a number of animometer benchmarks. See: https://docs.google.com/spreadsheets/d/1qK6LfDVMKydbKfkGEi1DuGoSqY2wPJAjPiAL1CCUW-4/edit?usp=sharing 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 Review-Url: https://codereview.chromium.org/2028303002 Cr-Commit-Position: refs/heads/master@{#397738} Commit : 54e8e3975826ceb886a7e0d8ec07bb38b1192311 Date : Fri Jun 03 17:19:46 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@397714 554.0 25.9422 5 good chromium@397731 572.6 21.5476 5 good chromium@397736 559.2 35.0457 5 good chromium@397737 572.5 40.7308 4 good chromium@397738 3654.4 151.998 5 bad <-- chromium@397740 3468.2 168.524 5 bad chromium@397748 3479.0 272.156 4 bad chromium@397782 3526.0 189.056 5 bad Bisect job ran on: mac_hdd_perf_bisect Bug ID: 619976 Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests media.tough_video_cases Test Metric: idle_wakeups_total/idle_wakeups_total Relative Change: 536.46% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/577 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9009860547887848768 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5863424651689984 | 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!
,
Jun 15 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : Modify ImageTransportSurfaceOverlayMac to allow pipelining Author : ericrk Commit description: This change allows 1 additional frame of pipelining in ImageTransportSurfaceOverlayMac by switching from a glFinish based approach to a glFence based one. Tested for CA framerate regressions - the following cases starve CA when used with a simple glFlush. This solution (and the previous glFinish) appear to successfully prevent CA starvation: Animometer - bouncing png images: https://trac.webkit.org/export/HEAD/trunk/PerformanceTests/Animometer/developer.html?test-interval=20&display=progress-bar&controller=adaptive&frame-rate=50&kalman-process-error=1&kalman-measurement-error=4&time-measurement=performance&suite-name=SVGsuite&test-name=SVGbouncingPNGimages&complexity=200 Both glFinish and glFence produce ~50 fps in CA/Chrome. WebGL Liquid Face: http://alteredqualia.com/xg/examples/liquid_face.html For liquid face, note that with the glFinish, CA framerate is slightly higher than Chrome reported framerate (20 vs 15) - with the new approach, they match more closely (16 vs 15). This may be a negative, but is still much better than the starvation which is seen with glFlush (5 vs 15). Improvements: Telemetry smoothness.top_25_smooth: This change produces good improvements in first_gesture_scroll_update_latency, mean_input_event_latency, and mean_main_thread_scroll_latency, without any significant regressions. See: https://drive.google.com/file/d/0B2nwXDxTDpGGU215X2xYTE9Bdnc/view?usp=sharing Animometer Benchmark: This change produces good improvements in a number of animometer benchmarks. See: https://docs.google.com/spreadsheets/d/1qK6LfDVMKydbKfkGEi1DuGoSqY2wPJAjPiAL1CCUW-4/edit?usp=sharing 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 Review-Url: https://codereview.chromium.org/2028303002 Cr-Commit-Position: refs/heads/master@{#397738} Commit : 54e8e3975826ceb886a7e0d8ec07bb38b1192311 Date : Fri Jun 03 17:19:46 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@397714 576.5 20.0774 6 good chromium@397731 568.4 20.4524 5 good chromium@397736 576.0 17.9861 5 good chromium@397737 585.6 28.1567 5 good chromium@397738 3659.2 143.891 5 bad <-- chromium@397740 3531.4 114.975 5 bad chromium@397748 3668.5 53.2698 4 bad chromium@397782 3506.83 210.513 6 bad Bisect job ran on: mac_hdd_perf_bisect Bug ID: 619976 Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests media.tough_video_cases Test Metric: idle_wakeups_total/idle_wakeups_total Relative Change: 506.03% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/578 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9009860532077101424 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5873682375770112 | 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 ddorwin@chromium.org
, Jun 14 2016