New issue
Advanced search Search tips

Issue 919481 link

Starred by 1 user
Status: Assigned
Owner:
peria@chromium.org
Cc:
jgruber@chromium.org
peria@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: Windows
Pri: 3
Type: Bug-Regression



Sign in to add a comment

3.5%-50.5% regression in system_health.memory_desktop at 617030:617078

Project Member Reported by jgruber@chromium.org, Jan 7 
Most of the graphs are a return to baseline.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jan 7 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=919481

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=573e82f5d7ab5184fb49afc2720645ea9b95a96e7b124a0b5d76010565f207c5


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

Win 7 Nvidia GPU Perf
Win 7 Perf

v8.browsing_desktop - Benchmark documentation link:
  None

system_health.memory_desktop - Benchmark documentation link:
  https://bit.ly/system-health-benchmarks
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jan 7

Cc: peria@chromium.org
Owner: peria@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/13d66a11940000

binding: Drop a runtime enabled flag for V8ContextSnapshot by peria@chromium.org
https://chromium.googlesource.com/chromium/src/+/ff19f4443204410b3be71c476d23c716db18c800
memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size: 2.133e+07 → 3.147e+07 (+1.013e+07)

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

Benchmark documentation link:
  None

Comment 4 by peria@chromium.org, Jan 8

Labels: -Pri-2 -Performance-Sheriff-V8 OS-Windows Pri-3
Once I landed a buggy CL and it reduced memory usages in a wrong way. A fix CL seems to regress it.
Let me take time to check few regressions that look actual.
►

Sign in to add a comment