Issue metadata
Sign in to add a comment
|
3.1%-204.1% regression in system_health.memory_desktop at 489886:490078 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jul 31 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972529359957568880
,
Aug 1 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_10_11_perf_bisect Benchmark : page_cycler_v2_site_isolation.basic_oopif Metric : timeToFirstContentfulPaint_avg/pcv1-cold/http___booking.com Change : 9.72% | 186.630571429 -> 204.762777778 Suspected Commit Range 3 commits in range https://chromium.googlesource.com/chromium/src/+log/7b133f7a628429e59d18371456152694f9ab5480..8e7b09023501bc23c8c38c09c2b30e23c40f3523 Revision Result N chromium@489915 186.631 +- 49.1089 14 good chromium@489942 216.366 +- 186.945 14 good chromium@489958 198.08 +- 108.824 14 good chromium@489959 --- --- build failure chromium@489960 --- --- build failure chromium@489961 262.853 +- 205.559 14 bad chromium@489966 282.184 +- 271.402 14 bad chromium@489969 235.424 +- 203.005 14 bad chromium@490022 204.763 +- 108.569 9 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_site_isolation.basic_oopif More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8972529359957568880 For feedback, file a bug with component Speed>Bisection
,
Aug 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970614765031488560
,
Aug 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970614708891896496
,
Aug 21 2017
Split off some unrelated smoothness regressions into bug 757591 . Kicked off a few bisects. +erikchen, perezju: these graphs go up and down a LOT. is it expected?
,
Aug 21 2017
> these graphs go up and down a LOT Which ones, specifically? Are you referring to: gpu:effective_size_avg v8:heap:effective_size_avg v8:effective_size_avg or something else entirely? The v8 metrics are known to be noisy. I started a discussion: https://bugs.chromium.org/p/chromium/issues/detail?id=736506#c2 But the v8 team wanted to keep alerting on them. The bug is still open. :(
,
Aug 21 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Daniele Castagna Commit : b5168e0d1731a1e4b8e6da22bdac6d08f6ab41a2 Date : Thu Jul 27 17:15:53 2017 Subject: viz: Align OutputSurface and BufferQueue in flight buffers. Bisect Details Configuration: mac_10_12_perf_bisect Benchmark : memory.desktop Metric : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/TrivialAnimationPageSharedPageState Change : 38.08% | 20229768.0 -> 27933945.7778 Revision Result N chromium@489905 20229768 +- 0.0 6 good chromium@489962 20229768 +- 0.0 6 good chromium@489990 20229768 +- 0.0 6 good chromium@489997 20229768 +- 0.0 6 good chromium@489999 20812310 +- 4943035 9 good chromium@490000 20812310 +- 4943035 9 good chromium@490001 25822230 +- 2957872 6 bad <-- chromium@490004 24729964 +- 3677118 6 bad chromium@490018 27933946 +- 5035495 6 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=TrivialAnimationPageSharedPageState memory.desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8970614765031488560 For feedback, file a bug with component Speed>Bisection
,
Aug 21 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Daniele Castagna Commit : b5168e0d1731a1e4b8e6da22bdac6d08f6ab41a2 Date : Thu Jul 27 17:15:53 2017 Subject: viz: Align OutputSurface and BufferQueue in flight buffers. Bisect Details Configuration: mac_10_12_perf_bisect Benchmark : system_health.memory_desktop Metric : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/browse_social/browse_social_tumblr_infinite_scroll Change : 31.75% | 17577619.3333 -> 23159174.8889 Revision Result N chromium@489905 17577619 +- 37781.8 6 good chromium@489962 17572323 +- 39695.7 6 good chromium@489990 17588526 +- 0.0 6 good chromium@489997 17561259 +- 29869.1 6 good chromium@489999 17561259 +- 29869.1 6 good chromium@490000 17561417 +- 29708.8 6 good chromium@490001 23517810 +- 1242565 6 bad <-- chromium@490004 23710762 +- 979833 6 bad chromium@490018 23159175 +- 1299023 6 bad Please refer to the following doc on diagnosing memory regressions: https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md 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=browse.social.tumblr.infinite.scroll system_health.memory_desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8970614708891896496 For feedback, file a bug with component Speed>Bisection |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jul 31 2017