[Webkit-unassigned] [Bug 146448] JavaScriptCore performance is very bad on Windows

bugzilla-daemon at webkit.org bugzilla-daemon at webkit.org
Thu Aug 13 10:36:44 PDT 2015


https://bugs.webkit.org/show_bug.cgi?id=146448

--- Comment #61 from peavo at outlook.com ---
(In reply to comment #60)
> (In reply to comment #59)
> > Now that we've cut over to Visual Studio 2015, do we still need any of these
> > changes?
> 
> I believe the changes related to the reduced use of locks, and the stack
> bounds optimization (by checking current fiber), are still valid.

I guess locking will spend some time waiting for the lock in some cases, so removing unneeded locking should be a good thing. Also, updateStackLimit() seems to be called many times from other places than the api locking, so I believe it makes sense to check whether a new fiber is running. Please correct me if I am wrong :)

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.webkit.org/pipermail/webkit-unassigned/attachments/20150813/a3474412/attachment.html>


More information about the webkit-unassigned mailing list