New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 633192 link

Starred by 2 users

Issue metadata

Status: WontFix
Owner:
Last visit > 30 days ago
Closed: Aug 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.1%-14.1% regression in system_health.memory_desktop at 407855:407904

Project Member Reported by petrcermak@chromium.org, Aug 1 2016

Issue description

See the link to graphs below.
 

===== 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@407854  17590955  682978   12  good
chromium@407904  17809408  370728   8   bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_media-memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/load_media_youtube
Relative Change: 3.63%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6776
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005529203281191376


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5831573530738688

| 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!

===== BISECT JOB RESULTS =====
Status: completed


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev  N  Good?
chromium@407854                      25096.0  0.0      5  good
chromium@407879                      25096.0  0.0      5  good
chromium@407882                      25096.0  0.0      5  good
chromium@407883                      25096.0  0.0      5  good
chromium@407883,catapult@db2aa902c9  25096.0  0.0      5  good
chromium@407884                      25484.0  0.0      5  bad
chromium@407885                      25484.0  0.0      5  bad
chromium@407889                      25484.0  0.0      5  bad
chromium@407904                      25484.0  0.0      5  bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_search-memory:chrome:all_processes:reported_by_chrome:font_caches:effective_size_avg/load_search_baidu
Relative Change: 1.55%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6802
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005161852206611520


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5789532209807360

| 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!
Don't know what happened here, but the bisect essentially blamed on https://codereview.chromium.org/2181243003, which is pretty much impossible because it changes the Catapult dashboard which has nothing to do with Chrome's executable. I'll try another bisect.

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@407854  58644.0  0.0      5  good
chromium@407879  58644.0  0.0      5  good
chromium@407882  58644.0  0.0      5  good
chromium@407883  58644.0  0.0      5  good
chromium@407884  59032.0  0.0      5  bad
chromium@407889  59032.0  0.0      5  bad
chromium@407904  59032.0  0.0      5  bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:font_caches:effective_size_avg/load_tools_weather
Relative Change: 0.66%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6811
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004902103339183904


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5829291393155072

| 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!
I think the bisect is actually pointing at https://codereview.chromium.org/2181093002 --- can the fake flash version cause performance test differences?
Cc: waff...@chromium.org aiolos@chromium.org
+waffles, aiolos see #9

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@407854  58644.0  0.0      5  good
chromium@407879  58644.0  0.0      5  good
chromium@407882  58644.0  0.0      5  good
chromium@407883  58644.0  0.0      5  good
chromium@407884  59032.0  0.0      5  bad
chromium@407889  59032.0  0.0      5  bad
chromium@407904  59032.0  0.0      5  bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:font_caches:effective_size_avg/load_tools_weather
Relative Change: 0.66%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6811
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004902103339183904


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5829291393155072

| 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!
Yes, this is likely https://codereview.chromium.org/2181093002, since before that change, it's possible that the perf test wasn't loading Flash at all (because the version was so low (old) that it was forbidden).

See thoughts at https://bugs.chromium.org/p/chromium/issues/detail?id=623804#c18; the guidance I received is that we should be testing with Flash anyways (if Flash is indeed present on the page) as that is closest to the real user experience. Along those lines, maybe close as wontfix?
Status: WontFix (was: Assigned)
#13: Yes, I agree that we should fix this small regression (388 bytes) as WontFix.
Project Member

Comment 16 by 42576172...@developer.gserviceaccount.com, Aug 10 2016


===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@407854  25096.0  0.0      5  good
chromium@407879  25096.0  0.0      5  good
chromium@407882  25096.0  0.0      5  good
chromium@407883  25096.0  0.0      5  good
chromium@407884  25484.0  0.0      5  bad
chromium@407889  25484.0  0.0      5  bad
chromium@407904  25484.0  0.0      5  bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_search-memory:chrome:all_processes:reported_by_chrome:font_caches:effective_size_avg/load_search_baidu
Relative Change: 1.55%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6827
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004902103339183904


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5829291393155072

| 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!
Project Member

Comment 18 by 42576172...@developer.gserviceaccount.com, Aug 17 2016


===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@407854  25096.0  0.0      5  good
chromium@407879  25096.0  0.0      5  good
chromium@407882  25096.0  0.0      5  good
chromium@407883  25096.0  0.0      5  good
chromium@407884  25484.0  0.0      5  bad
chromium@407889  25484.0  0.0      5  bad
chromium@407904  25484.0  0.0      5  bad

Bisect job ran on: win_perf_bisect
Bug ID: 633192

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_search-memory:chrome:all_processes:reported_by_chrome:font_caches:effective_size_avg/load_search_baidu
Relative Change: 1.55%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6827
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004902103339183904


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5829291393155072

| 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!
Labels: SystemHealth-Sheriff
Labels: -Performance-Sheriff

Sign in to add a comment