[Webkit-unassigned] [Bug 180341] New: GC should have a clock

bugzilla-daemon at webkit.org bugzilla-daemon at webkit.org
Sun Dec 3 18:52:22 PST 2017


            Bug ID: 180341
           Summary: GC should have a clock
           Product: WebKit
           Version: WebKit Nightly Build
          Hardware: All
                OS: All
            Status: NEW
          Severity: Normal
          Priority: P2
         Component: JavaScriptCore
          Assignee: webkit-unassigned at lists.webkit.org
          Reporter: fpizlo at apple.com

The JSC GC should have a time source that advances when the GC is keeping the main thread from running.  If we expose this (via internal APIs in the shell or whatever) to benchmarks, then we could switch a benchmark from measuring actual time (performance.now, preciseTime, whatever) to measuring gcTime.  Then, we would be able to see what aspect of a performance change is due to changes in amount of time spent GCing.  For changes that are meant to optimize the GC itself, this kind of clock-based analysis might be the best way of understanding the exact effect a change is having.

You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.webkit.org/pipermail/webkit-unassigned/attachments/20171204/d45c36e9/attachment.html>

More information about the webkit-unassigned mailing list