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

Issue 639755 link

Starred by 1 user
Status: WontFix
Owner:
nedngu...@google.com
Closed: Dec 2016
Cc:
█ eakuefner@chromium.org
nedngu...@google.com
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression

Blocked on:
issue 641133


Sign in to add a comment

3.4%-4.3% regression in speedometer at 413329:413335

Project Member Reported by hablich@chromium.org, Aug 22 2016 
See the link to graphs below.
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 22 2016 


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


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@413333  1797.0   51.5786  9  good
chromium@413335  1842.07  28.8042  9  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 639755

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: EmberJS-TodoMVC/EmberJS-TodoMVC
Relative Change: 2.27%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/749
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003644223570392784


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5826940854861824

| 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 5 by 42576172...@developer.gserviceaccount.com, Aug 22 2016 


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


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@413333  1797.0   51.5786  9  good
chromium@413335  1842.07  28.8042  9  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 639755

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: EmberJS-TodoMVC/EmberJS-TodoMVC
Relative Change: 2.27%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/749
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003644223570392784


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5826940854861824

| 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 7 by 42576172...@developer.gserviceaccount.com, Aug 22 2016 


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


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev  N   Good?
chromium@413328                      1767.33  58.193   8   good
chromium@413332                      1766.71  30.3317  5   good
chromium@413333                      1780.73  32.1727  14  good
chromium@413333,catapult@8fdfb52f84  1827.05  52.8016  16  good
chromium@413333,catapult@0389892bfa  1790.87  40.9323  3   good
chromium@413334                      1887.46  67.9353  11  bad
chromium@413335                      1871.47  54.0785  5   bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 639755

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: EmberJS-TodoMVC/EmberJS-TodoMVC
Relative Change: 3.97%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/751
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003626106868311664


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5830860448727040

| 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 9 by 42576172...@developer.gserviceaccount.com, Aug 23 2016 


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


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev  N  Good?
chromium@413333                      1775.7   36.7375  8  good
chromium@413333,catapult@8fdfb52f84  1762.59  11.2887  8  good
chromium@413333,catapult@0389892bfa  1774.72  51.3061  8  good
chromium@413334                      1891.82  97.256   8  bad
chromium@413335                      1824.56  36.0456  8  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 639755

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: EmberJS-TodoMVC/EmberJS-TodoMVC
Relative Change: 2.82%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/750
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003644223570392784


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5826940854861824

| 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!

Comment 10 by hablich@chromium.org, Aug 25 2016

Cc: eakuefner@chromium.org
Owner: sullivan@chromium.org
not sure what to do with that bisect.

Comment 11 by sullivan@chromium.org, Aug 25 2016

Blockedon: 641133
Something is wrong with the bisect into catapult rolls. Blocking this on  bug 641133 .

Comment 13 by sullivan@chromium.org, Nov 14 2016

Owner: ----
I kicked off two more bisects now that the blocker is closed, but this looks very noisy to me.
Project Member

Comment 14 by 42576172...@developer.gserviceaccount.com, Nov 14 2016

Cc: nedngu...@google.com
Owner: nedngu...@google.com

=== Auto-CCing suspected CL author nednguyen@google.com ===

Hi nednguyen@google.com, 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 : [telemetry] Wire TsProxy through telemetry's network stack.
Author  : nednguyen
Commit description:
  
This patch makes all the network access of Chrome browser
under test go through the ts_proxy server.

When a platform instance in telemetry is initiated, we set up
a ts_proxy_server for that platform & forward the ts_proxy's
port when the platform is remote platform.

For any newly created instance of WPR, we route the
ts_proxy_server' outbounds to that WPR server's ports.

Traffic between Chrome & static local server will also go
through ts_proxy_server but doesn't require any extra
code for routing because ts_proxy automatically routes
"localhost://*" url to the right host.

Any Chrome instance to be started will be routed to either
ts_proxy_server' port or its corresponding forwarded port.

ts_proxy_server is only killed when telemetry process ends.

BUG=catapult:#2584

Review-Url: https://codereview.chromium.org/2250583004
Commit  : 9fcccf0b65703994c9541273f00a993806a95356
Date    : Fri Aug 19 10:53:21 2016


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev  N   Good?
chromium@413328                      1784.17  807.261  50  good
chromium@413332                      1749.4   887.307  50  good
chromium@413333                      1753.65  462.431  50  good
chromium@413333,catapult@9fcccf0b65  1835.39  615.277  50  bad    <--
chromium@413333,catapult@55f40152f4  1822.33  473.323  50  bad
chromium@413333,catapult@8fdfb52f84  1802.04  481.56   50  bad
chromium@413334                      1809.66  517.118  50  bad
chromium@413335                      1822.07  403.766  50  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 639755

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests speedometer
Test Metric: EmberJS-TodoMVC/EmberJS-TodoMVC
Relative Change: 2.12%

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/881
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8996000386133595728


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5816276142784512

| 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!

Comment 15 by benhenry@google.com, Dec 21 2016

Status: WontFix (was: Assigned)
These will all be invalid as they are specific to Samsung S5s, which we do not trust to give us a signal and have subsequently removed from the waterfalls. If you think this regression is real, please re-open.
►

Sign in to add a comment