Issue metadata
Sign in to add a comment
|
27.7%-44.1% regression in system_health.memory_desktop at 410302:410319 |
||||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Aug 9 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004795793155436624
,
Aug 10 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410311 14345229 1774784 8 good chromium@410315 13755891 62303.7 12 good chromium@410316 15050989 2127453 12 good chromium@410317 19196026 681694 8 bad chromium@410319 18395509 1990672 8 bad Bisect job ran on: winx64ati_perf_bisect Bug ID: 635925 Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:partition_alloc:effective_size_avg/browse_social_twitter Relative Change: 20.60% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1498 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795793155436624 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5873712360849408 | 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!
,
Aug 10 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004741667819577984
,
Aug 10 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410311 14345229 1774784 8 good chromium@410315 13755891 62303.7 12 good chromium@410316 15050989 2127453 12 good chromium@410317 19196026 681694 8 bad chromium@410319 18395509 1990672 8 bad Bisect job ran on: winx64ati_perf_bisect Bug ID: 635925 Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:partition_alloc:effective_size_avg/browse_social_twitter Relative Change: 20.60% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1498 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795793155436624 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5873712360849408 | 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!
,
Aug 10 2016
,
Aug 10 2016
The bisect identified r410317 (V8 roll) as the culprit, but failed to descend into it (issue 636310): https://chromium.googlesource.com/v8/v8/+log/fbcbbfc7..743b9df1 machenbach,littledan,lpy,cbruni,verwaest,ahaas,neis,jyan: Could you please check if your change might have caused this?
,
Aug 10 2016
I'm a bit surprised by the extent of the regression. I presume this is the sum over several runs/sites. I've introduce a 1K elements instantiation cache (https://codereview.chromium.org/2170743003), that should maximally cause a 8KB regression on a 64bit platform. This is work in progress and should drop back to normal once the refactoring is complete.
,
Aug 10 2016
It's the average for a single story over several runs. The story opens Twitter and then clicks on a link and navigates back (repeatedly, different link each time): https://cs.chromium.org/chromium/src/tools/perf/page_sets/system_health/browsing_stories.py?l=188
,
Aug 11 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004649000557707408
,
Aug 11 2016
===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : Reland of [api] Clean up scopes and precheck instantiations cache (patchset #1 id:1 of https://codereview.chromium.org/2216903003/ ) Author : cbruni Commit description: Reason for revert: asan failures are caused by a flaky stack-verflow (see https://codereview.chromium.org/2218033002 for a fix). Original issue's description: > Revert of [api] Clean up scopes and precheck instantiations cache (patchset #3 id:40001 of https://codereview.chromium.org/2206773003/ ) > > Reason for revert: > [Sheriff] Leads to mac asan failures: > https://build.chromium.org/p/client.v8/builders/V8%20Mac64%20ASAN/builds/7835 > > Original issue's description: > > [api] Clean up scopes and precheck instantiations cache > > > > Make sure all the scopes used in api-natives.cc have inlineable constructors > > and destructors. Additionally directly precheck the instantiations cache before > > trying to enter the InvokeScope which sets the save_context. > > > > BUG=chromium:630217 > > > > Committed: https://crrev.com/a2496b942cad524f0f3144b107936eaa9a7c9fd5 > > Cr-Commit-Position: refs/heads/master@{#38346} > > TBR=yangguo@chromium.org,cbruni@chromium.org > # Skipping CQ checks because original CL landed less than 1 days ago. > NOPRESUBMIT=true > NOTREECHECKS=true > NOTRY=true > BUG=chromium:630217 > > Committed: https://crrev.com/e1b5cb43a9b90546ff5d6cea89ba17c485e842fb > Cr-Commit-Position: refs/heads/master@{#38356} TBR=yangguo@chromium.org,machenbach@chromium.org # Skipping CQ checks because original CL landed less than 1 days ago. NOPRESUBMIT=true NOTREECHECKS=true NOTRY=true BUG=chromium:630217 Review-Url: https://codereview.chromium.org/2217353002 Cr-Commit-Position: refs/heads/master@{#38401} Commit : 56c8814c0bfca2f4993a4f23537aed1ac4363a6f Date : Fri Aug 05 20:24:16 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410311 17892145 1640611 8 good chromium@410315 17974039 2372019 8 good chromium@410316 18684001 1198454 5 good chromium@410316,v8@6b2d24fe8f 17384711 851043 5 good chromium@410316,v8@4943f72272 16739267 206763 5 good chromium@410316,v8@56c8814c0b 22497850 1313797 5 bad <-- chromium@410317 21657015 999279 8 bad chromium@410319 22430325 1072077 8 bad Bisect job ran on: win_x64_perf_bisect Bug ID: 635925 Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:partition_alloc:effective_size_avg/browse_social_twitter Relative Change: 23.19% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_x64_perf_bisect/builds/1399 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795793155436624 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5873712360849408 | 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!
,
Aug 30 2016
|
|||||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||||
Comment 1 by petrcermak@chromium.org
, Aug 9 2016