Hey Steven,
I'd certainly imagine you need to run the tool on the guest to get an accurate
reading.
From what I've seen of xen boxes dom0 is running like a domU and only reporting
loads/usage of the host node itself. Not the guests.
I could be wrong, but this is what I make of it.
Iain Kay
On 18 May 2011, at 21:43, Steven wrote:
> Hi,
> I am trying to profiling disk IO caused by page miss in memory inside
> a guest OS. Both guest and host OS are Fedora 13.
> I am using the linux command sar which provide such number of major faults
> like
>
> majflt/s:
> Number of major faults the system has made per
> second, those which have required loading a memory page from disk
>
> Then I started a workloads on both the guest and host OS. As a result,
> the guest reports about 1000 majfits, while the host reports only
> around 80. So is 1000 majflt is the actual disk IO for that guest? Or
> the number of host OS is what I want. Thanks.
>
> - w
>
> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users
|