|
|
|
|
|
|
|
|
|
|
xen-users
Re: [Xen-users] 32bit or 64bit dom0?
On Tue, Jan 26, 2010 at 09:09:00AM -0800, Grant McWilliams wrote:
> > Â Â Â -- Pasi
> >
> > Â Â That depends one whether you consider (up to) 20% worth
> considering! I'd
> > Â Â be willing to change for 5%.
> >
> > Â
> Â [3][1]http://www.phoronix.com/scan.php?page=article&item=616&num=1
> >
>
> Hmm.. did you paste wrong url? That url only has 32b vs. 64b?
>
> Here's 32b vs. 32b PAE benchmark:
> [2]http://www.phoronix.com/scan.php?page=article&item=ubuntu_32_pae
>
> Although that benchmark must have something wrong with the 32 vs 64
> numbers..
> the different can't be THAT big.
>
> "In the fourteen tests for this article we did not find using Ubuntu's
> 32-bit PAE kernel
> to have a dramatic performance impact whether it be positive or
> negative.
>
> Granted, we were using just 4GB of system memory that is common to
> many desktops,
> but if using 8GB, 16GB, or even a greater memory capacity the
> performance
> penalties are perhaps higher. "
> -- Pasi
>
> Yes I did! Thanks. Here try this.
>
> [3]http://www.phoronix.com/scan.php?page=article&item=ubuntu_32_pae&num=1
> Grant McWilliams
>
> I either posted two quick or too late! So the quote was saying that PAE
> didn't have an impact over a stock 32 bit kernel
> but if you compare it to the 64 bit kernel there's a serious hit. In the
> tests they did the 64 bit kernel was faster by quite a bit
> in every way. I've blindly been using 64 bit kernels wherever possible but
> this helps me know that I've benefited from it.
>
That "Apache Benchmark" must be wrong, THAT huge difference can't be true.
But yeah, in general 64b should be faster nowadays compared to 32b or 32b PAE,
since it has a lot more registers to use etc..
32b vs 32b PAE doesn't seem to be big difference, at least not with 4 GB of RAM.
Also PAE gives you possibility to use NX protection..
-- Pasi
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users
|
|
|
|
|