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

Issue 625640 link

Starred by 2 users
Status: Duplicate
Merged: issue 624309
Owner:
█ ssanfilippo@chromium.org
User never visited
Closed: Jul 2016
Cc:
█ ssanfilippo@chromium.org
ishell@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.4%-5% regression in speedometer at 402325:402362

Project Member Reported by nikolaos@chromium.org, Jul 4 2016 
See the link to graphs below.

Comment 1 by nikolaos@chromium.org, Jul 4 2016 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=625640

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgorfJuAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgou7wtwoM


Bot(s) for this bug's original alert(s):

chromium-rel-mac-retina
chromium-rel-win7-x64-dual
Project Member

Comment 2 by sheriffbot@chromium.org, Jul 5 2016

Labels: -M-53 M-54 MovedFrom-53
Moving this nonessential bug to the next milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

Comment 3 by tdres...@chromium.org, Jul 11 2016 

Started another bisect.
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, Jul 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@402344  601.765  5.13384  18  good
chromium@402362  600.873  4.43788  18  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 625640

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: AngularJS-TodoMVC/AngularJS-TodoMVC
Relative Change: 0.22%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1406
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007411314795356128


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5800320689504256

| 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, Jul 12 2016 


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


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev  N  Good?
chromium@402295                584.64   2.87182  5  good
chromium@402329                583.59   2.75622  5  good
chromium@402332                583.998  5.73449  5  good
chromium@402333                583.443  7.40977  5  good
chromium@402333,v8@e89d8b6a76  584.082  9.95151  5  good
chromium@402333,v8@08cc2d4fd9  589.718  7.65054  5  good
chromium@402333,v8@ea844f9aac  585.688  11.1584  5  good
chromium@402333,v8@fd2bf837a5  587.06   4.35049  5  good
chromium@402334                606.824  8.07266  5  bad
chromium@402338                601.484  6.23362  5  bad
chromium@402346                598.88   2.4267   5  bad
chromium@402362                601.993  2.82898  5  bad
chromium@402429                608.63   5.2485   5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 625640

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: AngularJS-TodoMVC/AngularJS-TodoMVC
Relative Change: 4.10%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1407
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007358233183655648


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5827247718531072

| 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, Jul 14 2016 


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


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev  N  Good?
chromium@402295                582.095  2.90743  5  good
chromium@402329                578.808  3.05142  5  good
chromium@402332                576.244  5.62049  5  good
chromium@402333                580.365  4.03928  5  good
chromium@402333,v8@e89d8b6a76  581.503  6.83186  5  good
chromium@402333,v8@08cc2d4fd9  584.858  4.03327  5  good
chromium@402333,v8@ea844f9aac  583.469  5.5933   5  good
chromium@402333,v8@fd2bf837a5  588.779  6.47288  5  good
chromium@402334                599.873  3.35874  5  bad
chromium@402338                602.868  5.72651  5  bad
chromium@402346                602.356  4.77613  5  bad
chromium@402362                604.621  4.28383  5  bad
chromium@402429                602.349  5.25377  5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 625640

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: AngularJS-TodoMVC/AngularJS-TodoMVC
Relative Change: 3.48%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1413
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007174039849727120


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5551938838462464

| 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, Jul 14 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@402344  602.843  3.75635  18  good
chromium@402362  601.619  3.93684  18  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 625640

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: AngularJS-TodoMVC/AngularJS-TodoMVC
Relative Change: 0.30%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1420
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007124532011497712


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5319519015272448

| 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 machenb...@chromium.org, Jul 15 2016 

Please retrigger relevant bisection jobs because http://crbug.com/628214 got fixed.
Project Member

Comment 12 by 42576172...@developer.gserviceaccount.com, Jul 15 2016

Cc: ssanfilippo@chromium.org
Owner: ssanfilippo@chromium.org

=== Auto-CCing suspected CL author ssanfilippo@chromium.org ===

Hi ssanfilippo@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 : This commit is the first step towards emitting unwinding information in
Author  : ssanfilippo
Commit description:
  the .eh_frame format as part of the jitdump generated when
FLAG_perf_prof is enabled. The final goal is allowing precise unwinding
of callchains that include JITted code when profiling V8 using perf.

Unwinding information is stored in the body of code objects after the
code itself, prefixed with its length and aligned to a 8-byte boundary.
A boolean flag in the header signals its presence, resulting in zero
memory overhead when the generation of unwinding info is disabled or
no such information was attached to the code object.

A new jitdump record type (with id 4) is introduced for specifying
optional unwinding information for code load records. The EhFrameHdr
struct is also introduced, together with a constructor to initialise it
from the associated code object.

At this stage no unwinding information is written to the jitdump, but
the infrastructure for doing so is ready in place.

BUG= v8:4899 
LOG=N

Review-Url: https://codereview.chromium.org/1993653003
Cr-Commit-Position: refs/heads/master@{#37296}
Commit  : 7d073b03c710b34f001fedd074f0ec9fbbaa5623
Date    : Mon Jun 27 15:10:41 2016


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev  N  Good?
chromium@402295                580.746  3.46472  5  good
chromium@402329                584.534  7.25042  5  good
chromium@402332                575.722  3.93932  5  good
chromium@402333                577.924  6.07182  5  good
chromium@402333,v8@e89d8b6a76  584.312  4.16731  8  good
chromium@402333,v8@e1e50f3fff  585.815  5.57665  8  good
chromium@402333,v8@7d073b03c7  601.74   7.71395  5  bad    <--
chromium@402333,v8@08cc2d4fd9  608.412  11.6688  5  bad
chromium@402334                603.196  5.4028   5  bad
chromium@402338                604.673  2.27585  5  bad
chromium@402346                605.275  3.92341  5  bad
chromium@402362                605.283  9.34661  5  bad
chromium@402429                602.5    5.79835  5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 625640

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests speedometer
Test Metric: AngularJS-TodoMVC/AngularJS-TodoMVC
Relative Change: 3.75%
Score: 99.0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1421
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007088374314173760


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6150121264250880

| 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 13 by ssanfilippo@chromium.org, Jul 15 2016 

ishell@ fixed a similar regression caused by the same commit in [1]. The stub cache appears to be very sensitive to the value of Code::flags, and this commit adds one flag. Igor should have fixed the other regression, maybe this one shares the same root cause?

[1] https://bugs.chromium.org/p/chromium/issues/detail?id=624309

Comment 14 by machenb...@chromium.org, Jul 18 2016

Cc: ishell@chromium.org

Comment 15 by ishell@chromium.org, Jul 18 2016

Mergedinto: 624309
Status: Duplicate (was: Assigned)
►

Sign in to add a comment