38. Vdpa Sample Application
The vdpa sample application creates vhost-user sockets by using the vDPA backend. vDPA stands for vhost Data Path Acceleration which utilizes virtio ring compatible devices to serve virtio driver directly to enable datapath acceleration. As vDPA driver can help to set up vhost datapath, this application doesn’t need to launch dedicated worker threads for vhost enqueue/dequeue operations.
38.1. Testing steps
This section shows the steps of how to start VMs with vDPA vhost-user backend and verify network connection & live migration.
38.1.1. Build
To compile the sample application see Compiling the Sample Applications.
The application is located in the vdpa
sub-directory.
38.1.2. Start the vdpa example
./vdpa [EAL options] -- [--client] [--interactive|-i] or [--iface SOCKET_PATH]
where
- –client means running vdpa app in client mode, in the client mode, QEMU needs to run as the server mode and take charge of socket file creation.
- –iface specifies the path prefix of the UNIX domain socket file, e.g. /tmp/vhost-user-, then the socket files will be named as /tmp/vhost-user-<n> (n starts from 0).
- –interactive means run the vdpa sample in interactive mode, currently 4
internal cmds are supported:
- help: show help message
- list: list all available vdpa devices
- create: create a new vdpa port with socket file and vdpa device address
- quit: unregister vhost driver and exit the application
Take IFCVF driver for example:
./vdpa -c 0x2 -n 4 --socket-mem 1024,1024 \
-w 0000:06:00.3,vdpa=1 -w 0000:06:00.4,vdpa=1 \
-- --interactive
Note
Here 0000:06:00.3 and 0000:06:00.4 refer to virtio ring compatible devices, and we need to bind vfio-pci to them before running vdpa sample.
- modprobe vfio-pci
- ./usertools/dpdk-devbind.py -b vfio-pci 06:00.3 06:00.4
Then we can create 2 vdpa ports in interactive cmdline.
vdpa> list
device id device address queue num supported features
0 0000:06:00.3 1 0x14c238020
1 0000:06:00.4 1 0x14c238020
2 0000:06:00.5 1 0x14c238020
vdpa> create /tmp/vdpa-socket0 0000:06:00.3
vdpa> create /tmp/vdpa-socket1 0000:06:00.4
38.1.3. Start the VMs
qemu-system-x86_64 -cpu host -enable-kvm \
<snip>
-mem-prealloc \
-chardev socket,id=char0,path=<socket_file created in above steps> \
-netdev type=vhost-user,id=vdpa,chardev=char0 \
-device virtio-net-pci,netdev=vdpa,mac=00:aa:bb:cc:dd:ee,page-per-vq=on \
After the VMs launches, we can login the VMs and configure the ip, verify the network connection via ping or netperf.
Note
Suggest to use QEMU 3.0.0 which extends vhost-user for vDPA.
38.1.4. Live Migration
vDPA supports cross-backend live migration, user can migrate SW vhost backend VM to vDPA backend VM and vice versa. Here are the detailed steps. Assume A is the source host with SW vhost VM and B is the destination host with vDPA.
- Start vdpa sample and launch a VM with exact same parameters as the VM on A, in migration-listen mode:
B: <qemu-command-line> -incoming tcp:0:4444 (or other PORT))
- Start the migration (on source host):
A: (qemu) migrate -d tcp:<B ip>:4444 (or other PORT)
- Check the status (on source host):
A: (qemu) info migrate