Bug 132508 - REGRESSION(r167889): ~1.5% Regression in DYEBench
Summary: REGRESSION(r167889): ~1.5% Regression in DYEBench
Status: NEW
Alias: None
Product: WebKit
Classification: Unclassified
Component: JavaScriptCore (show other bugs)
Version: 528+ (Nightly build)
Hardware: Unspecified Unspecified
: P2 Normal
Assignee: Nobody
URL:
Keywords: Regression
Depends on:
Blocks:
 
Reported: 2014-05-02 18:15 PDT by Ryosuke Niwa
Modified: 2014-05-02 20:07 PDT (History)
3 users (show)

See Also:


Attachments
A/B test result (104.08 KB, text/html)
2014-05-02 18:15 PDT, Ryosuke Niwa
no flags Details
More testing (186.86 KB, text/html)
2014-05-02 20:07 PDT, Ryosuke Niwa
no flags Details

Note You need to log in before you can comment on or make changes to this bug.
Comment 1 Ryosuke Niwa 2014-05-02 18:15:57 PDT
Created attachment 230727 [details]
A/B test result
Comment 2 Ryosuke Niwa 2014-05-02 18:18:43 PDT
Looks like EmberJS-TodoMVC/CompletingAllItems regressed the most.
Comment 3 Ryosuke Niwa 2014-05-02 20:07:18 PDT
Created attachment 230733 [details]
More testing

s_maxForgivenDeletes=1 is ~1% regression but s_maxForgivenDeletes=3 is still 1.5-2% regression :(

So we might need to do something a little more clever than just tweaking the numbers here.