Bug 44808

Summary: REGRESSION(r66115): 2% perf regression in chromium intl page cycler
Product: WebKit Reporter: Tony Chang <tony>
Component: Page LoadingAssignee: Dave Hyatt <hyatt>
Status: RESOLVED WONTFIX    
Severity: Normal CC: darin
Priority: P2 Keywords: InRadar
Version: 528+ (Nightly build)   
Hardware: PC   
OS: OS X 10.5   
Attachments:
Description Flags
perf test none

Tony Chang
Reported 2010-08-27 18:35:05 PDT
Created attachment 65799 [details] perf test The chromium intl1 page cycler has noticed a small perf regression after r66115. Here are some graphs (click on the graph to see checkins and the spike is associated with my checking of rolling webkit from 66079 to 66240). http://build.chromium.org/buildbot/perf/xp-release-dual-core/intl1/report.html?history=150&header=&thumbnail=undefined&rev=-1 http://build.chromium.org/buildbot/perf/vista-release-dual-core/intl1/report.html?history=150&header=&thumbnail=undefined&rev=-1 http://build.chromium.org/buildbot/perf/mac-release-10.6/intl1/report.html?history=150&header=&thumbnail=undefined&rev=-1 I made a reduced test case and bisected the webkit revisions to narrow it down to this change. I'll include the reduced perf test on this bug.
Attachments
perf test (3.13 MB, application/zip)
2010-08-27 18:35 PDT, Tony Chang 		no flags
Details
View All Add attachment proposed patch, testcase, etc.
Tony Chang
Comment 1 2010-08-27 18:40:43 PDT
On my machine, the perf test in the attachment shows about a 10% perf regression.
Alexey Proskuryakov
Comment 2 2011-01-20 17:02:02 PST
<rdar://problem/8896006>
Stephen Chenney
Comment 3 2013-04-09 16:09:59 PDT
LayoutTest failures for Chromium are being marked WontFix. The Bug is still accessible and referenced from TestExpectations.
Note You need to log in before you can comment on or make changes to this bug.