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

Issue 635482 link

Starred by 1 user
Status: Duplicate
Merged: issue 635489
Owner:
█ wkorman@chromium.org
Last visit > 30 days ago
Closed: Aug 2016
Cc:
█ lushnikov@chromium.org
vmp...@chromium.org
█ petrcermak@chromium.org
chrishtr@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.6%-11.4% regression in system_health.memory_desktop at 410186:410242

Project Member Reported by petrcermak@chromium.org, Aug 8 2016 
See the link to graphs below.
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 9 2016 


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


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@410187  11699425  43962.9  5  good
chromium@410189  11738746  53843.3  5  good
chromium@410190  12997038  53843.3  5  bad
chromium@410192  13036359  43962.9  5  bad
chromium@410197  12997038  53843.3  5  bad
chromium@410206  12977377  43962.9  5  bad
chromium@410229  12997038  53843.3  5  bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 635482

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_social-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_social_vk
Relative Change: 11.09%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2105
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004896799950271088


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5325321004384256

| 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 9 2016 


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


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@410187  11699425  43962.9  5  good
chromium@410189  11738746  53843.3  5  good
chromium@410190  12997038  53843.3  5  bad
chromium@410192  13036359  43962.9  5  bad
chromium@410197  12997038  53843.3  5  bad
chromium@410206  12977377  43962.9  5  bad
chromium@410229  12997038  53843.3  5  bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 635482

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_social-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_social_vk
Relative Change: 11.09%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2105
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004896799950271088


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5325321004384256

| 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 6 by petrcermak@chromium.org, Aug 9 2016

Cc: chrishtr@chromium.org lushnikov@chromium.org vmp...@chromium.org
Owner: wkorman@chromium.org
wkorman: The bisect identified your patch (https://codereview.chromium.org/2217263003) as the most likely culprit for the regression (+1.2 MiB in cc on vk.com). Please investigate and decide on further action.

Comment 7 by petrcermak@chromium.org, Aug 9 2016

Cc: petrcermak@chromium.org
 Issue 635498  has been merged into this issue.

Comment 8 by petrcermak@chromium.org, Aug 9 2016 

 Issue 635497  has been merged into this issue.
Project Member

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

Mergedinto: 635489
Status: Duplicate (was: Assigned)

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


===== SUSPECTED CL(s) =====
Subject : Revert "Raster display item lists via a visual rect RTree."
Author  : wkorman
Commit description:
  
Meta-revert for http://crrev.com/1484163002 due to bugs found in ui/views and
DevTools.

Original change description:

    Raster display item lists via a visual rect RTree.

    Rather than caching and playing back an entire SkPicture
    when rastering a display item list for a particular
    playback rect, instead retain display items and query
    them via an RTree of their visual rects to find and
    raster only what's needed.

    Display item lists no longer support the notion of a
    bounding "layer rect" with mutable origin.

    DisplayItemListSettings proto is obsolete after this
    change as it's comprised solely of one field to allow
    switching whether to use the aforementioned now-deleted
    cached SkPicture code path. It will be deleted in a
    subsequent patch.

Revert "Raster display item lists via a visual rect RTree."

This reverts commit ccb9e13712b1632b889960d1d85d556c0139fd51.

Revert "Don't clear visual rects when finalizing display item lists for now."

This reverts commit 1adf72a0a0a3e04151cc740d15ab19655b1e7e5e.

Revert "Delete obsolete DisplayItemList::ProcessAppendedItem method definition."

This reverts commit f652746f56c59523b0440cf18b769f8ba779d15d.

BUG= 529938 , 633750 , 633869 , 634239 , 634823 , 634959 
TBR=chrishtr@chromium.org,vmpstr@chromium.org,lushnikov@chromium.org
CQ_INCLUDE_TRYBOTS=master.tryserver.blink:linux_precise_blink_rel

Review-Url: https://codereview.chromium.org/2217263003
Cr-Commit-Position: refs/heads/master@{#410190}
Commit  : 490867260447e9360b52d5c03417b000490332e0
Date    : Fri Aug 05 22:27:03 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@410187  11699425  43962.9  5  good
chromium@410189  11738746  53843.3  5  good
chromium@410190  12997038  53843.3  5  bad    <--
chromium@410192  13016698  53843.3  5  bad
chromium@410197  13036359  43962.9  5  bad
chromium@410206  13056020  0.0      5  bad
chromium@410229  13036359  43962.9  5  bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 635482

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_social-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_social_vk
Relative Change: 11.43%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2108
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004896799950271088


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5325321004384256

| 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 11 by petrcermak@chromium.org, Aug 30 2016

Labels: SystemHealth-Sheriff
►

Sign in to add a comment