Questions[qemu](server)

We are using Ubuntu 12.04 with the following parameters:

• Dell R910
• Kernel 3.2.0-25-generic #40-Ubuntu SMP x86_64 x86_64 x86_64 GNU/Linux
• kvm 1:84+dfsg-0ubuntu16+1.0+noroms+0ubuntu13
• qemu-kvm 1.0+noroms-0ubuntu13
• qemu-common 1.0+noroms-0ubuntu13
• qemu-kvm 1.0+noroms-0ubuntu13
• 4 x Intel(R) Xeon(R) CPU E7- 4870 @ 2.40GHz (each with 10 physical cores, HT and Intel VT enabled)
• The Windows guests currently have no VirtIO, but that will change soon

We are running several Windows guests on this machine, one of them is Windows 2003 32 Bit, another one Windows 2008 (64 Bit). We are currently struggling with performance issues and played around with the CPU models.

We usually use "qemu-system-x86_64 for our Windows 32 Bit guest, e.g.:

/usr/bin/qemu-system-x86_64 -S -M pc-1.0 -cpu qemu32 -enable-kvm -m 4096 -smp 4,sockets=4,cores=1,threads=1 [...] 

The performance of this guest turned out to be a bit low. We didn't run any benchmark yet, but let's say that copying large amount of data (files) inside the VM from one directory to the other goes much faster when we switch the CPU model from "-cpu qemu32" to "-cpu Nehalem". Files which took around 2:40h to copy now copy within 40 minutes. Of course this is not a high quality test and there is much room for having a more professional attempt. But this is a clear indicator that choosing the correct CPU model could affect the guest's performance heavily.

Now I got curious and ran:

qemu-x86_64 -cpu ?
x86           [n270]
x86         [athlon]
x86       [pentium3]
x86       [pentium2]
x86        [pentium]
x86            [486]
x86        [coreduo]
x86          [kvm32]
x86         [qemu32]
x86          [kvm64]
x86       [core2duo]
x86         [phenom]
x86         [qemu64]

And:

kvm -cpu ?model
 x86       Opteron_G3  AMD Opteron 23xx (Gen 3 Class Opteron)
 x86       Opteron_G2  AMD Opteron 22xx (Gen 2 Class Opteron)
 x86       Opteron_G1  AMD Opteron 240 (Gen 1 Class Opteron)
 x86          Nehalem  Intel Core i7 9xx (Nehalem Class Core i7)
 x86           Penryn  Intel Core 2 Duo P9xxx (Penryn Class Core 2)
 x86           Conroe  Intel Celeron_4x0 (Conroe/Merom Class Core 2)
 x86           [n270]  Intel(R) Atom(TM) CPU N270   @ 1.60GHz
 x86         [athlon]  QEMU Virtual CPU version 1.0
 x86       [pentium3]
 x86       [pentium2]
 x86        [pentium]
 x86            [486]
 x86        [coreduo]  Genuine Intel(R) CPU           T2600  @ 2.16GHz
 x86          [kvm32]  Common 32-bit KVM processor
 x86         [qemu32]  QEMU Virtual CPU version 1.0
 x86          [kvm64]  Common KVM processor
 x86       [core2duo]  Intel(R) Core(TM)2 Duo CPU     T7700  @ 2.40GHz
 x86         [phenom]  AMD Phenom(tm) 9550 Quad-Core Processor
 x86         [qemu64]  QEMU Virtual CPU version 1.0

With all these different versions, it's a bit hard to guess at. "Nehalem" seems to be the most performant one on that list. Now I wonder, how to tell which CPU model is the best for my guest? Browsing the Internet, I found the following ressources:

• http://rwmj.wordpress.com/2010/10/08/32-or-64-bit-virtual-cpu-in-kvm/
• http://www.linux-kvm.org/page/Tuning_KVM

When I read those sites correctly, they are claiming that "-cpu host" might bring the best performance. I don't have any worries about migration yet, since both KVM hosts are equipped equally (exactely the same hardware).

So, what do experienced KVM admins recommend? Is there a golden rule or even a matrix, like "this model is the best for that guest OS"?

My apologies if I could find out this information by my own - I ran various Google searches and browsed many websites. I was not able to find something which answers my question.

I'm using qemu/kvm whith bridged networking. In the host machine there are several "vnetX" network interfaces without IP. I'm looking for a way to know which vnetX belong to a virtual machine.

I tried to match the MAC Address values on these interfaces with the MACs on the virtual machines (or the XML which defines them), but doesn't match.

There's brctl show which shows the vnet interfaces that belongs to a bridge, but this is not useful info.

Is there a way to know that relation? Thx!!

What is the difference between KVM and Qemu? As I understand, latter is able to provide "user mode emulation" which means that one can run a single executable built for some other architecture like this:

# file busybox-sparc 
busybox-sparc: ELF 32-bit MSB executable, SPARC, version 1 (SYSV), statically linked, stripped
# qemu-sparc busybox-sparc ls
Packages_arm     Packages_i386    arm              busybox-armv6l   busybox-i686     busybox-powerpc  busybox-sparc    busybox-x86_64   i386
# 

..and "computer emulation", which means that not only dynamic binary translation is performed, but whole virtual machine is emulated(video card, sound card, network cards, optical devices etc). For example:

# qemu-system-sparc64 -hda hda.img -cdrom debian-6.0.5-sparc-CD-1.iso -boot d

As I have understood, Qemu does not know how to take advantage of hardware virtualization(for example Intel VT-x or AMD-V solutions on x86 architecture) and this is the case where KVM can help- one can start Qemu with KVM support. However, does KVM provide any other functionality besides access for emulation programs to hardware-assisted virtualization on specific hardware architectures? Is it possible to create whole(CPU, video card, I/O devices etc) virtual machine using only KVM? If yes, then which programs should one use for creating and controlling this virtual machine?

we are using kvm/qemu with qcow2-images for our virtual machines.

qcow2 has this nice feature where the image file only allocates the actually needed space by the virtual-machine. but how do i shrink back the image file, if the virtual machine's allocated space gets smaller?

example:

1.) i create a new image with qcow2 format, size 100GB

2.) i use this image to install ubuntu. installation needs about 10 gb, the image-file grows up to about 10GB. nothing unexpected so far.

3.) i fill up the image with about 40 GB of additional data. the image-file grows up to 50GB. i am ok with that :-)

4.) this is where it gets strange: i delete all of the 40GB data on the image, but the image-size still eats up 50GB.

question: how do i free up that 40GB of data and shrink the image to the only needed 10 GB?

thanks in advance, berni

I have been reading about KVM and Qemu for sometime. As of now I have a clear understanding of what they do.

KVM supports hardware virtualization to provide near native performance to the Guest Operating sytems. On the other hand QEmu emulates the target operating system.

What I am confused is to what level these two co-ordinate. Like

1. Who manages the sharing of RAM and/or memory?
2. Who schedules I/O operations?