Issue metadata
Sign in to add a comment
|
1%-1.2% regression in system_health.memory_mobile at 410333:410350 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Aug 9 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004795666280354432
,
Aug 10 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1119437 540.033 5 good chromium@410338 1123430 1460.55 5 bad chromium@410339 1124109 2322.33 5 bad chromium@410340 1125190 4172.44 5 bad chromium@410342 1124333 1277.52 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 0.44% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1509 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795666280354432 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780247430037504 | 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
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004713642146219728
,
Aug 10 2016
The bisect blamed r410338 (V8 roll) as the culprit, but it failed to descend into it (issue 636310): https://chromium.googlesource.com/v8/v8/+log/c0b5119c..cbb22d3c hpayer: From a quick glance, it looks like https://codereview.chromium.org/2224823003 could be the culprit. WDYT? +cc neis, machenbach, verwaest, rmcilroy, neis, oth (authors of other patches in the roll).
,
Aug 10 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1119437 540.033 5 good chromium@410338 1123430 1460.55 5 bad chromium@410339 1124109 2322.33 5 bad chromium@410340 1125190 4172.44 5 bad chromium@410342 1124333 1277.52 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 0.44% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1509 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795666280354432 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780247430037504 | 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 11 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004621082239228672
,
Aug 11 2016
===== BISECT JOB RESULTS ===== Status: completed === Bisection aborted === The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression. Please contact the the team (see below) if you believe this is in error. === Warnings === The following warnings were raised by the bisect job: * Bisect failed to reproduce the regression with enough confidence. ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1826540 8141.74 8 good chromium@410342 1828339 6995.89 8 bad Bisect job ran on: android_nexus7_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/load_news_hackernews Relative Change: 0.20% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus7_perf_bisect/builds/3199 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004795666280354432 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780247430037504 | 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 12 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004541563745713408
,
Aug 12 2016
I do not think it is my change, moreover this CL got reverted. Since code space increases it may be one of the interpreter changes in the regression range. Ross, WDYT?
,
Aug 12 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004529793720549808
,
Aug 12 2016
It's possible that this could be related to "[interpreter] Inline ForInFilter stub" - https://codereview.chromium.org/2220343002, there was another potential regression (that increased the size of the handler by ~1.5KB so depending on the number of isolates, I guess this could have caused this). There is also another possible regression in issue 635826 on this CL, so I will revert it and see if this regression recovers. The regression could also related to issue 635801 - the CL changed startup timing which seems to have effected GC measurement timing.
,
Aug 12 2016
The following revision refers to this bug: https://chromium.googlesource.com/v8/v8.git/+/bbd0a093ca770daa286ea9469c5c851bb8230b9c commit bbd0a093ca770daa286ea9469c5c851bb8230b9c Author: rmcilroy <rmcilroy@chromium.org> Date: Fri Aug 12 14:00:08 2016 Revert of [interpreter] Inline ForInFilter stub. (patchset #1 id:1 of https://codereview.chromium.org/2220343002/ ) Reason for revert: Speculative revert to possible performance regressions. BUG=chromium:635826, chromium:635930 Original issue's description: > [interpreter] Inline ForInFilter stub. > > BUG= v8:4280 > LOG=N > > Committed: https://crrev.com/2bf0b8c8ed5d0c93982c8c227e93622aceecea16 > Cr-Commit-Position: refs/heads/master@{#38420} TBR=oth@chromium.org # Not skipping CQ checks because original CL landed more than 1 days ago. BUG= v8:4280 Review-Url: https://codereview.chromium.org/2238283002 Cr-Commit-Position: refs/heads/master@{#38623} [modify] https://crrev.com/bbd0a093ca770daa286ea9469c5c851bb8230b9c/src/interpreter/interpreter.cc
,
Aug 13 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410332 1117616 1163.0 8 good chromium@410332,v8@552601bb5f 1117056 2392.89 8 good chromium@410333 1121280 2059.22 5 bad chromium@410334 1119738 1776.13 5 bad chromium@410335 1120973 2256.12 5 bad chromium@410338 1123706 1353.57 5 bad chromium@410343 1123232 1064.93 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 0.53% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1517 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004541563745713408 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780162939977728 | 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 13 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004447759997537280
,
Aug 13 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410332 1117616 1163.0 8 good chromium@410332,v8@552601bb5f 1117056 2392.89 8 good chromium@410333 1121280 2059.22 5 bad chromium@410334 1119738 1776.13 5 bad chromium@410335 1120973 2256.12 5 bad chromium@410338 1123706 1353.57 5 bad chromium@410343 1123232 1064.93 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 0.53% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1517 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004541563745713408 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780162939977728 | 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 13 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410332 1231539 1688.07 5 good chromium@410337 1236024 1356.65 8 good chromium@410337,v8@642c184fb4 1240312 1495.83 8 bad chromium@410337,v8@2b10616b77 1241843 1652.51 5 bad chromium@410338 1242368 1280.8 5 bad chromium@410339 1242195 1560.41 5 bad chromium@410340 1246074 10881.8 5 bad chromium@410342 1241184 214.663 5 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.78% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2012 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004529793720549808 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5852412611395584 | 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 13 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004435579355301664
,
Aug 13 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410332 1231539 1688.07 5 good chromium@410337 1236024 1356.65 8 good chromium@410337,v8@642c184fb4 1240312 1495.83 8 bad chromium@410337,v8@2b10616b77 1241843 1652.51 5 bad chromium@410338 1242368 1280.8 5 bad chromium@410339 1242195 1560.41 5 bad chromium@410340 1246074 10881.8 5 bad chromium@410342 1241184 214.663 5 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.78% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2012 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004529793720549808 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5852412611395584 | 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 14 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004355273338807136
,
Aug 14 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004342965739516896
,
Aug 15 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1236616 1486.81 8 good chromium@410337,v8@642c184fb4 1240268 1918.78 8 bad chromium@410337,v8@2b10616b77 1241096 22.6274 8 bad chromium@410338 1243661 3528.61 5 bad chromium@410339 1242426 1749.55 5 bad chromium@410340 1241747 1474.02 5 bad chromium@410342 1241856 1459.25 5 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.42% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2015 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004541563745713408 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780162939977728 | 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 15 2016
Reverting the ForInFilter inlining didn't impact this regression. The bisects are pointing at 642c184fb4 "[ast] Remove obsolete DECLARE_NODE_TYPE macro.". From a quick look at the CL I don't see how it might have impacted memory usage, but maybe there is something subtle that changed. Georg could you take a look?
,
Aug 15 2016
=== Auto-CCing suspected CL author oth@chromium.org === Hi oth@chromium.org, the bisect results pointed to your CL below as possibly causing a regression. Please have a look at this info and see whether your CL be related. ===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : [interpreter] Inline ForInFilter stub. Author : oth Commit description: BUG= v8:4280 LOG=N Review-Url: https://codereview.chromium.org/2220343002 Cr-Commit-Position: refs/heads/master@{#38420} Commit : 2bf0b8c8ed5d0c93982c8c227e93622aceecea16 Date : Mon Aug 08 09:07:15 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1236948 1159.08 8 good chromium@410337,v8@2bf0b8c8ed 1240346 576.178 5 bad <-- chromium@410337,v8@642c184fb4 1240044 1406.23 8 bad chromium@410337,v8@2b10616b77 1241747 1474.02 5 bad chromium@410338 1242477 1687.77 5 bad chromium@410339 1243341 1259.35 5 bad chromium@410340 1241907 1927.66 5 bad chromium@410342 1241696 1359.53 5 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.43% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2016 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004529793720549808 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5852412611395584 | 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 15 2016
rmcilroy: You were absolutely right that the regression was due to https://codereview.chromium.org/2220343002. Shall we mark this issue as fixed then (or do you want to keep it for re-landing)?
,
Aug 15 2016
Petr: If this is fixed then marking as fixed is fine (I don't intend to re-land the CL in question). However is this fixed? On the graphs, two have recovered, but at a point much earlier than I did the revert. The other two still haven't recovered even after the revert.
,
Aug 15 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004258656024820704
,
Aug 15 2016
rmcilroy: Good point. I kicked off another bisect on a different bot to see if there was another regression at the same time.
,
Aug 16 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410322 1114908 1084.42 8 good chromium@410329 1117528 1830.74 8 good chromium@410332 1117164 1734.75 8 good chromium@410334 1121708 2033.01 8 bad chromium@410335 1120346 1140.48 5 bad chromium@410347 1124109 1253.04 5 bad chromium@410372 1127443 5165.97 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 1.16% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1519 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004258656024820704 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5294282466918400 | 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 16 2016
The bisect failed because it ran for 24 hours. Let's continue narrowing down the range...
,
Aug 16 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004165710995805392
,
Aug 16 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004165565018826352
,
Aug 16 2016
rmcilroy: I'd be surprised if this is related to my change.
,
Aug 16 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410322 1114908 1084.42 8 good chromium@410329 1117528 1830.74 8 good chromium@410332 1117164 1734.75 8 good chromium@410334 1121708 2033.01 8 bad chromium@410335 1120346 1140.48 5 bad chromium@410347 1124109 1253.04 5 bad chromium@410372 1127443 5165.97 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 1.16% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1519 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004258656024820704 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5294282466918400 | 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 17 2016
=== Auto-CCing suspected CL author bmeurer@chromium.org === Hi bmeurer@chromium.org, the bisect results pointed to your CL below as possibly causing a regression. Please have a look at this info and see whether your CL be related. ===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : [turbofan] Add initial support for growing stores. Author : bmeurer Commit description: Introduce a dedicated MaybeGrowFastElements simplified operator, which tries to grow a fast elements backing store for a given element that should be added to an array/object. Use that to lower a growing keyed store to a sequence of 1) check index is a valid array index, 2) check stored value, 3) maybe grow elements backing store (and deoptimize if it would normalize), and 4) store the actual element. The actual growing is done by two dedicated GrowFastDoubleElements and GrowFastSmiOrObjectElements builtins, which are very similar to the GrowArrayElementsStub that is used by Crankshaft. Drive-by-fix: Turn CopyFixedArray into CopyFastSmiOrObjectElements builtin, similar to the new growing builtins, so we don't need to inline the store+write barrier for the elements into all optimized code objects anymore. Also fix a bug in the OperationTyper for NumberSilenceNaN, which was triggered by this change. BUG= v8:5272 Review-Url: https://codereview.chromium.org/2227493002 Cr-Commit-Position: refs/heads/master@{#38418} Commit : e6822a8338c70ab476e545da95d958c23ac366f9 Date : Mon Aug 08 08:44:27 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410332 1116400 1223.91 8 good chromium@410332,v8@552601bb5f 1116716 1431.89 8 good chromium@410332,v8@e6822a8338 1120403 1416.09 5 bad <-- chromium@410332,v8@0c699a5819 1119852 1302.65 8 bad chromium@410333 1121677 2781.76 5 bad chromium@410334 1120474 1960.95 5 bad Bisect job ran on: android_one_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_tools_stackoverflow Relative Change: 0.41% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1523 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004165710995805392 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5839577286180864 | 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 17 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004072952108856336
,
Aug 17 2016
===== BISECT JOB RESULTS ===== Status: completed === Bisection aborted === The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression. Please contact the the team (see below) if you believe this is in error. === Warnings === The following warnings were raised by the bisect job: * Bisect failed to reproduce the regression with enough confidence. ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1238472 7387.63 8 good chromium@410342 1241348 1488.94 8 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.06% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2024 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004258656024820704 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5294282466918400 | 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 22 2016
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9003650813814735088
,
Aug 22 2016
===== BISECT JOB RESULTS ===== Status: failed ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@410337 1236616 1486.81 8 good chromium@410337,v8@642c184fb4 1240268 1918.78 8 bad chromium@410337,v8@2b10616b77 1241096 22.6274 8 bad chromium@410338 1243661 3528.61 5 bad chromium@410339 1242426 1749.55 5 bad chromium@410340 1241747 1474.02 5 bad chromium@410342 1241856 1459.25 5 bad Bisect job ran on: android_nexus9_perf_bisect Bug ID: 635930 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile Test Metric: load_news-memory:chrome:all_processes:reported_by_chrome:v8:heap:code_space:effective_size_avg/load_news_qq Relative Change: 0.42% Score: 0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/2015 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004541563745713408 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5780162939977728 | 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 22 2016
,
Aug 30 2016
,
Sep 14 2016
,
Jul 14 2017
This regression is too old to be actionable. Closing as wontfix. |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by petrcermak@chromium.org
, Aug 9 2016