On 18 August 2014 07:09, Tony Su wrote:
> Unless someone says differently,
> I believe that doesn't change the likely fact that the main KVM is
> different than what you are doing and would perform much better.
No, Julio is correct. The KVM functionality was all merged
into upstream QEMU, and th
Hi everyone,
I would like to know the following information of the guest application
executed in QEMU:
- the number of guest instructions executed per each function call
- the number of memory access instructions
- the address and size of each executed load / store
It it possible to extract
On 8/18/2014 2:26 PM, Mie Ite wrote:
Hi everyone,
I would like to know the following information of the guest application
executed in QEMU:
- the number of guest instructions executed per each function call
- the number of memory access instructions
- the address and size of each executed lo
Why are you using e1000 and not virtio? The virtio drives have
significantly better performance Ubuntu should also have native
support for them.
On 8/17/2014 10:34 PM, JHM wrote:
Salutations to all members, first off. This is my first post in the
discussion group.
I searched for this to
You could look at the KVM perf support, but I'm unsure if that gives you
enough detail: http://www.linux-kvm.org/page/Perf_events
On 8/18/2014 8:26 AM, Mie Ite wrote:
Hi everyone,
I would like to know the following information of the guest application
executed in QEMU:
- the number of gue
> From: "Mie Ite"
>
> I would like to know the following information of the guest
> application executed in QEMU:
>
> - the number of guest instructions executed per each function call
> - the number of memory access instructions
> - the address and size of each executed load / store
>
> It it
Is there any program that gives a good view of the space used in the
repository by various files? I know that the space use will vary
depending on what is packed and exactly how the packing is going, but
I've got a situation where I don't need exact information; rather I'm
looking for particular f
On 18 August 2014 15:32, Dale R. Worley wrote:
> The "per each function call" metric is tricky, because you'd need to
> define what a "function call" is.
In particular, on some guest CPU architectures it's genuinely
not possible to reliably distinguish function call return from a
computed branch.
Well, I'll humbly apologize for wasting everyone's time :(
Our client connections are coming from Brazil and the server is hosted in
Canada. Turns out, the ISP we are using had issues that were resolved last
night. I haven't changed any qemu parameters for the last couple of days.
Last night we ha
