Dear all,
we're adding dynamically an IVSHMEM device on a VM that is already
running, but apparently this is not visible in DPDK, while it is
correctly recognized by the Guest OS.
This is the list of steps we execute:
1) Launch a new Guest VM with Qemu
2) Create a new IVSHMEM metadata file in the Host
3) Map that file as a new IVSHMEM device in the Guest
For this step, we use the "device_add" command from Qemu:
(qemu) device_add ivshmem,size=2048M,shm=fd:/dev/hugepages
/rtemap_0:0x0:0x40000000:/dev/zero:0x0:0x3fffc000:/var/run
/.dpdk_ivshmem_metadata_vm_1:0x0:0x4000
4) List the available PCI devices in the Guest with "lspci":
$ sudo lspci
00:04.0 RAM memory: Red Hat, Inc Virtio Inter-VM shared memory
==> hence, the Guest OS correctly recognizes the new device
5) Lauch a DPDK simple application such as 'helloworld' in the Guest:
$ sudo ./build/helloworld -c 0x1 -n 4
EAL: Detected lcore 0 as core 0 on socket 0
EAL: Detected lcore 1 as core 0 on socket 0
EAL: Support maximum 128 logical core(s) by configuration.
EAL: Detected 2 lcore(s)
EAL: VFIO modules not all loaded, skip VFIO support...
EAL: Searching for IVSHMEM devices...
EAL: No IVSHMEM configuration found!
EAL: Setting up memory...
==> Hence, the DPDK app in the Guest OS doesn't recognize the new
device.
An additional observations that may be important here.
If we reboot the Guest and re-lauch the same DPDK as before, the IVSHMEM
is correclty detected by the DPDK app:
$ sudo reboot
....
$ sudo ./build/helloworld -c 0x1 -n 4
EAL: Detected lcore 0 as core 0 on socket 0
EAL: Detected lcore 1 as core 0 on socket 0
EAL: Support maximum 128 logical core(s) by configuration.
EAL: Detected 2 lcore(s)
EAL: VFIO modules not all loaded, skip VFIO support...
EAL: Searching for IVSHMEM devices...
EAL: Parsing metadata for "vm_1"
EAL: Found IVSHMEM device 00:04.0
EAL: Memory segment mapped: 0x7f8b40d8c000 (len 3937000) at offset
0xd8c000
EAL: IVSHMEM segment found, size: 0x3936ec0
EAL: Setting up memory...
Finally, this is what the DPDK programming guide says about IVSHMEM:
-----------------------------------------------------------------------
http://dpdk.org/doc/guides/prog_guide/ivshmem_lib.html
Currently, there is no hot plug support for QEMU IVSHMEM devices, so one
cannot add additional memory to an IVSHMEM device once it has been
created. Therefore, the correct sequence to run an IVSHMEM application
is to run host application first, obtain the command lines for each
IVSHMEM device and then run all QEMU instances with guest applications
afterwards.
-----------------------------------------------------------------------
To our understanding, IVSHMEM HotPlug is supported, but we cannot resize
dynamically the memory.
Is that correct?
fulvio
