On Apr 30, 3:26 pm, Evan Martin <e...@chromium.org> wrote:
> On Thu, Apr 30, 2009 at 3:13 PM, Peter Kasting <pkast...@chromium.org> wrote:
> > On Thu, Apr 30, 2009 at 1:50 PM, cpu <c...@chromium.org> wrote:
>
> >> Inhttp://src.chromium.org/viewvc/chrome?view=rev&revision=14983I
> >> removed a CoInitialize()/CoUnInitialize() pair in the renderer process
> >> of your favorite browser.
>
> > Does this make starting a renderer process any faster?
>
> Looks like it made startup 2ms faster. :P
>
Heh, indeed it did made XP 3% faster and Vista 2.5% faster. I was
expecting no speedup because the dlls that get loaded are hot, having
been just loaded in the browser process.
and to think I once like COM, but I digress...
> http://build.chromium.org/buildbot/perf/xp-release-dual-core/startup/...,
> click the point on the far right where the graph jogs down.
>
> The closest we have to tracking renderer startup is the new tab
> startuphttp://build.chromium.org/buildbot/perf/xp-release-dual-core/new-tab-...
> but that is so slow this change may be lost in the noise.
--~--~---------~--~----~------------~-------~--~----~
Chromium Developers mailing list: chromium-dev@googlegroups.com
View archives, change email options, or unsubscribe:
http://groups.google.com/group/chromium-dev
-~----------~----~----~----~------~----~------~--~---