Ok. This is what I've learned so far about device access in Hyper-V.
For device access in Hyper-V, there are two underlying methods:- Emulated and VSP/VSC devices.
Emulated devices are just like the devices you have seen or used in Virtual Server 2005 R2. Whenever the virtual machine or VM attempts to access I/O, the hypervisor traps that request and the I/O gets emulated in the parent partition. This approach is highly compatible across most of the OS, but it has its own overhead and slow.
To overcome the above mentioned I/O performance issues, VSP/VSC devices have been developed in Windows Server 2008 Hyper-V. The hidden caveat is, these are supported only on specific OS. Of course, Windows 2003 and above is supported. This approach requires VSC drivers in the guest OS which looks like normal drivers in windows. With VSC drivers, I/O is not trapped by the hypervisor as it does in emulated one - rather the VSC drivers directly communicates with VSP's over VMBUS and operates much faster than emulated devices.
Ok, now we know the two underlying methods available for device access. Let's take a look at the type of disk contoller Hyper-V provides for storage. The excerpt below has shamelessly been copied from here.
There are two types of disk controllers that Hyper-V supports: SCSI and IDE. There are two IDE controllers and four SCSI controllers available.
Each IDE controller can have two devices. You can't boot from a SCSI controller. This means an IDE disk will be required. The boot disk will be IDE controller 0 Device 0. If you want a CDROM it will consume an IDE device slot.
EACH SCSI controller can support up to 255 devices.
Both SCSI and IDE can support pass-through, Fixed, Dynamic, Sparse, and Delta drives (see http://blogs.msdn.com/tvoellm/archive/2007/10/13/what-windows-server-virtualization-aka-viridian-storage-is-best-for-you.aspx). The difference lies in how the controllers are actually implemented. The IDE controller is emulated where as the SCSI controller is synthetic. So what does this mean?
The IDE controller implements a well-known IDE controller and this means there is extra processing before the I/O is sent to the disk. This processing occurs in vmwp.exe (a user mode process that exists for each started VM. More on this in a later post). Once the IDE emulation is complete the I/O is sent into the Root Partition’s I/O Stack. I/O completion requires a trip back to vmwp.exe.
The SCSI controller is not emulated. The SCSI controller uses VMBUS (Virtual Machine BUS. More on this in a later post). The I/O's pass from the Child (aka Guest) Partition to the root over VMBUS and enter the I/O stack. You can already see one less process/machine context switch is required because vmwp.exe does not get invoked. Once and I/O completes its completion is sent over VMBUS.
There is a lot more to how both the IDE and SCSI controllers work however the descriptions below should help you to understand why SCSI controllers are the right choice for the best performance.
One of the main reasons you can't boot off of SCSI device is because it is implemented as a synthetic device in Hyper-V and the VMBUS is not available during the boot. Rest of the devices such as CD, IDE, Legacy Network Adapter and Floppy is supported though.
Note: Since Hyper-V is not RTM'ed all numbers are subject to change as are the behaviors.