New issue
Advanced search Search tips

Issue 818673 link

Starred by 1 user
Status: WontFix
Owner:
jonr...@chromium.org
Closed: Jul 11
Cc:
kenrb@chromium.org
simonhatch@chromium.org
dtu@chromium.org
piman@chromium.org
kylec...@chromium.org
jonr...@chromium.org
sullivan@chromium.org
rmcilroy@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

2.1%-2.5% regression in system_health.memory_mobile at 540521:540559

Project Member Reported by rmcilroy@chromium.org, Mar 5 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Mar 5 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=818673

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=4216fa386d326ec6237199a9c2ce646ff1dcac4c2e7bff220ee5a8b66ec4a218


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

android-nexus6
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Mar 6 2018

Cc: kenrb@chromium.org jonr...@chromium.org kylec...@chromium.org piman@chromium.org
Owner: jonr...@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14fe5ce2440000

Rate Limit RenderFrameMetadataObserver by jonross@chromium.org
https://chromium.googlesource.com/chromium/src/+/13c8861d8d297b2dcb54b7a68eda0d09a6ea2c0e

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Mar 7 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/12f09462440000

Comment 8 by jonr...@chromium.org, Mar 7 2018

Owner: ----
Status: Untriaged (was: Assigned)
I've re-ran the pinpoint with a change where the RenderFrameMetadataObserver execution is disabled. It found no difference.

I've kicked off a new bisect.
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Mar 7 2018

Owner: jonr...@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/15f4ee62440000

Rate Limit RenderFrameMetadataObserver by jonross@chromium.org
https://chromium.googlesource.com/chromium/src/+/13c8861d8d297b2dcb54b7a68eda0d09a6ea2c0e

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Mar 7 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/121b9292440000

Rate Limit RenderFrameMetadataObserver by jonross@chromium.org
https://chromium.googlesource.com/chromium/src/+/13c8861d8d297b2dcb54b7a68eda0d09a6ea2c0e

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 13 by 42576172...@developer.gserviceaccount.com, Mar 7 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/17f09462440000
Project Member

Comment 14 by 42576172...@developer.gserviceaccount.com, Mar 7 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/13f09462440000
Project Member

Comment 17 by 42576172...@developer.gserviceaccount.com, Mar 9 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/17e2f82a440000

Not for Review - Pinpoint revert RFMO rate limit by jonross@chromium.org
https://chromium-review.googlesource.com/c/chromium/src/+/956409/2

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 18 by 42576172...@developer.gserviceaccount.com, Mar 9 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/158ebe1a440000

Not for Review - Pinpoint revert RFMO rate limit by jonross@chromium.org
https://chromium-review.googlesource.com/c/chromium/src/+/956409/2

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 19 by jonr...@chromium.org, Mar 9 2018

Owner: ----
Status: Untriaged (was: Assigned)
I'm sending this back for triage.

Looking at the traces the jump in memory is occurring in the Browser process, whereas my change affected the Renderer process.

I've also ran 3 different Pinpoints each of which showed no difference
  - Disabling the logic changes of my patch, so my code didn't run
  - Reverting the data structure change, in case that caused it
  - Reverting the entire change

The non-android graphs also show this chart as very flaky with my change in range of those flakes.

Then android graphs all have a large spike up at the range of my patch, but afterwards return to being flaky.

Comment 20 by sullivan@chromium.org, Mar 16 2018

Cc: simonhatch@chromium.org dtu@chromium.org sullivan@chromium.org
+dtu, can you take a look at what is going on with the bisects and try jobs in this bug? Two of the bisects point to jonross's CL, but see comment 19 and also no-repro bisect in #5.

Comment 21 by dtu@chromium.org, Mar 16 2018 

Looks like the full revert jobs failed because the patch didn't apply cleanly. I'm going to re-try the Pinpoint jobs with a rebased revert. (https://chromium-review.googlesource.com/c/chromium/src/+/965404)
Project Member

Comment 24 by 42576172...@developer.gserviceaccount.com, Mar 16 2018

Owner: dtu@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12e2cf21440000

Revert "Rate Limit RenderFrameMetadataObserver" by dtu@chromium.org
https://chromium-review.googlesource.com/c/chromium/src/+/965404/2

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 25 by 42576172...@developer.gserviceaccount.com, Mar 16 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12f594e1440000

Revert "Rate Limit RenderFrameMetadataObserver" by dtu@chromium.org
https://chromium-review.googlesource.com/c/chromium/src/+/965404/2

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 26 by sullivan@chromium.org, Mar 16 2018

Owner: jonr...@chromium.org
Assigning back to jonross as the try job with patch applied cleanly reproduces the regression.
Project Member

Comment 28 by 42576172...@developer.gserviceaccount.com, Mar 19 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/168daeb9440000
Project Member

Comment 30 by 42576172...@developer.gserviceaccount.com, Mar 19 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/129bf0f9440000
Project Member

Comment 33 by 42576172...@developer.gserviceaccount.com, Mar 19 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/16aba529440000
Project Member

Comment 34 by 42576172...@developer.gserviceaccount.com, Mar 20 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/14f5ae25440000
Project Member

Comment 37 by 42576172...@developer.gserviceaccount.com, Mar 21 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/148e7095440000
Project Member

Comment 38 by 42576172...@developer.gserviceaccount.com, Mar 21 2018 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/12f7f405440000
Project Member

Comment 40 by 42576172...@developer.gserviceaccount.com, Jul 10 

📍 Job complete. See results below.
https://pinpoint-dot-chromeperf.appspot.com/job/11e68ab8a40000

Comment 41 by jonr...@chromium.org, Jul 11

Status: WontFix (was: Assigned)
This regression was only seen on the android-nexus6 variant. Which has since become deprecated and removed.

This regression was also seen before a lot of work was done on Viz and RenderFrameMetadata observer on Android.

Since the original regression the charts did recover before taking the bots offline.

I haven't seen this regression on other androids.

I'm marking as Wont Fix do to the only bot showing the regression being gone.
►

Sign in to add a comment