Bug 147313

Summary: [WK2][iOS] WebContent process main thread should have fixed priority
Product: WebKit Reporter: Chris Dumez <cdumez>
Component: WebKit2Assignee: Chris Dumez <cdumez>
Status: RESOLVED FIXED    
Severity: Normal CC: barraclough, kling, rniwa, sam
Priority: P1 Keywords: InRadar
Version: 528+ (Nightly build)   
Hardware: iPhone / iPad   
OS: Unspecified   
Attachments:
Description Flags
Patch
none
Patch
none
Patch none

Chris Dumez
Reported 2015-07-26 20:50:55 PDT
WebContent process main thread should have fixed priority on iOS 9. Priority decay regresses PLT and fixing the priority gives up a ~3% progression on warm PLT.
Attachments
Patch (2.02 KB, patch)
2015-07-26 20:54 PDT, Chris Dumez 		no flags
DetailsFormatted DiffDiff
Patch (1.91 KB, patch)
2015-07-26 21:23 PDT, Chris Dumez 		no flags
DetailsFormatted DiffDiff
Patch (1.90 KB, patch)
2015-07-26 21:30 PDT, Chris Dumez 		no flags
DetailsFormatted DiffDiff
Show Obsolete (2) View All Add attachment proposed patch, testcase, etc.
Chris Dumez
Comment 1 2015-07-26 20:51:09 PDT
rdar://problem/22003112
Chris Dumez
Comment 2 2015-07-26 20:54:12 PDT
Created attachment 257541 [details] Patch
Sam Weinig
Comment 3 2015-07-26 21:04:47 PDT
Comment on attachment 257541 [details] Patch View in context: https://bugs.webkit.org/attachment.cgi?id=257541&action=review > Source/WebKit2/WebProcess/cocoa/WebProcessCocoa.mm:176 > + if (parameters.uiProcessBundleIdentifier == "com.apple.mobilesafari") Why only for MobileSafari? If this is a good idea for MobileSafari, why isn't it a good idea all he time?
Chris Dumez
Comment 4 2015-07-26 21:06:13 PDT
(In reply to comment #3) > Comment on attachment 257541 [details] > Patch > > View in context: > https://bugs.webkit.org/attachment.cgi?id=257541&action=review > > > Source/WebKit2/WebProcess/cocoa/WebProcessCocoa.mm:176 > > + if (parameters.uiProcessBundleIdentifier == "com.apple.mobilesafari") > > Why only for MobileSafari? If this is a good idea for MobileSafari, why > isn't it a good idea all he time? Please see radar for more information.
Chris Dumez
Comment 5 2015-07-26 21:23:01 PDT
Created attachment 257542 [details] Patch
Chris Dumez
Comment 6 2015-07-26 21:23:46 PDT
(In reply to comment #3) > Comment on attachment 257541 [details] > Patch > > View in context: > https://bugs.webkit.org/attachment.cgi?id=257541&action=review > > > Source/WebKit2/WebProcess/cocoa/WebProcessCocoa.mm:176 > > + if (parameters.uiProcessBundleIdentifier == "com.apple.mobilesafari") > > Why only for MobileSafari? If this is a good idea for MobileSafari, why > isn't it a good idea all he time? I removed the check as discussed offline.
Darin Adler
Comment 7 2015-07-26 21:24:10 PDT
Comment on attachment 257542 [details] Patch View in context: https://bugs.webkit.org/attachment.cgi?id=257542&action=review Yuck. > Source/WebKit2/WebProcess/cocoa/WebProcessCocoa.mm:173 > +#if (TARGET_OS_IPHONE && __IPHONE_OS_VERSION_MIN_REQUIRED >= 90000) No need for the parentheses.
Chris Dumez
Comment 8 2015-07-26 21:30:01 PDT
Created attachment 257544 [details] Patch
Chris Dumez
Comment 9 2015-07-26 22:09:47 PDT
Comment on attachment 257544 [details] Patch Clearing flags on attachment: 257544 Committed r187412: <http://trac.webkit.org/changeset/187412>
Chris Dumez
Comment 10 2015-07-26 22:09:55 PDT
All reviewed patches have been landed. Closing bug.
Note You need to log in before you can comment on or make changes to this bug.