[dts] [PATCH v1] test_plans/vf_interrupt_pmd: add vf multi queues interrupt test cases with i40e driver

Tu, Lijuan lijuan.tu at intel.com
Fri Feb 21 03:03:08 CET 2020


Applied, thanks

> -----Original Message-----
> From: dts [mailto:dts-bounces at dpdk.org] On Behalf Of Yinan
> Sent: Thursday, February 20, 2020 4:33 AM
> To: dts at dpdk.org
> Cc: Wang, Yinan <yinan.wang at intel.com>
> Subject: [dts] [PATCH v1] test_plans/vf_interrupt_pmd: add vf multi queues
> interrupt test cases with i40e driver
> 
> From: Wang Yinan <yinan.wang at intel.com>
> 
> Signed-off-by: Wang Yinan <yinan.wang at intel.com>
> ---
>  test_plans/vf_interrupt_pmd_test_plan.rst | 76 ++++++++++++++++++++++-
>  1 file changed, 75 insertions(+), 1 deletion(-)
> 
> diff --git a/test_plans/vf_interrupt_pmd_test_plan.rst
> b/test_plans/vf_interrupt_pmd_test_plan.rst
> index 8f91b14..a8ed3d8 100644
> --- a/test_plans/vf_interrupt_pmd_test_plan.rst
> +++ b/test_plans/vf_interrupt_pmd_test_plan.rst
> @@ -190,4 +190,78 @@ Test Case4: VF interrupt pmd in VM with vfio-pci
> 
>  7. Check if threads on core 2 have returned to sleep mode::
> 
> -    L3FWD_POWER: lcore 2 sleeps until interrupt triggers
> \ No newline at end of file
> +    L3FWD_POWER: lcore 2 sleeps until interrupt triggers
> +
> +Test Case5: vf multi-queue interrupt with vfio-pci on i40e
> +==========================================================
> +
> +1. Generate NIC VF, then bind it to vfio drvier::
> +
> +    echo 1 > /sys/bus/pci/devices/0000\:04\:00.0/sriov_numvfs
> +    modprobe vfio-pci
> +    usertools/dpdk-devbind.py --bind=vfio-pci 0000:04:10.0(vf_pci)
> +
> +  Notice:  If your PF is kernel driver, make sure PF link is up when your start
> testpmd on VF.
> +
> +2. Start l3fwd-power with VF::
> +
> +    examples/l3fwd-power/build/l3fwd-power -c 3f -n 4 -m 2048 -- -P -p 0x1 -
> -config="(0,0,1),(0,1,2),(0,2,3),(0,3,4)"
> +
> +3. Send UDP packets with random ip and dest mac = vf mac addr::
> +
> +      for x in range(0,10):
> +
> + sendp(Ether(src="00:00:00:00:01:00",dst="vf_mac")/IP(src='2.1.1.' +
> + str(x),dst='2.1.1.5')/UDP()/"Hello!0",iface="tester_intf")
> +
> +4. Check if threads on all cores have waked up::
> +
> +    L3FWD_POWER: lcore 1 is waked up from rx interrupt on port 0 queue 0
> +    L3FWD_POWER: lcore 2 is waked up from rx interrupt on port 0 queue 1
> +    L3FWD_POWER: lcore 3 is waked up from rx interrupt on port 0 queue 2
> +    L3FWD_POWER: lcore 4 is waked up from rx interrupt on port 0 queue
> + 3
> +
> +Test Case6: VF multi-queue interrupt in VM with vfio-pci on i40e
> +===============================================================
> =
> +
> +1. Generate NIC VF, then bind it to vfio drvier::
> +
> +    echo 1 > /sys/bus/pci/devices/0000\:88:00.1/sriov_numvfs
> +    modprobe vfio-pci
> +    usertools/dpdk-devbind.py --bind=vfio-pci 0000:88:0a.0(vf_pci)
> +
> +  Notice:  If your PF is kernel driver, make sure PF link is up when your start
> testpmd on VF.
> +
> +2. Passthrough VF 0 to VM0 and start VM0::
> +
> +    taskset -c 4,5,6,7,8 qemu-system-x86_64 \
> +    -name vm0 -enable-kvm -pidfile /tmp/.vm0.pid -daemonize -monitor
> unix:/tmp/vm0_monitor.sock,server,nowait \
> +    -device e1000,netdev=nttsip1  -netdev
> user,id=nttsip1,hostfwd=tcp:127.0.0.1:6000-:22 \
> +    -device vfio-pci,host=0000:88:0a.0,id=pt_0 -cpu host -smp 5 -m 10240 \
> +    -chardev socket,path=/tmp/vm0_qga0.sock,server,nowait,id=vm0_qga0 -
> device virtio-serial \
> +    -device virtserialport,chardev=vm0_qga0,name=org.qemu.guest_agent.0
> -vnc :11 \
> +    -drive
> + file=/home/osimg/noiommu-
> ubt16.img,format=qcow2,if=virtio,index=0,medi
> + a=disk
> +
> +  Notice: VM needs Kernel version > 4.8.0, mostly linux distribution don't
> support vfio-noiommu mode by default, so testing this case need rebuild
> kernel to enable vfio-noiommu.
> +
> +3. Bind VF 0 to the vfio-pci driver::
> +
> +    modprobe -r vfio_iommu_type1
> +    modprobe -r vfio
> +    modprobe vfio enable_unsafe_noiommu_mode=1
> +    modprobe vfio-pci
> +    usertools/dpdk-devbind.py -b vfio-pci 0000:00:04.0
> +
> +4.Start l3fwd-power in VM::
> +
> +    ./build/l3fwd-power -l 0-3 -n 4 -m 2048 -- -P -p 0x1 --
> config="(0,0,0),(0,1,1),(0,2,2),(0,3,3)"
> +
> +5. Send UDP packets with random ip and dest mac = vf mac addr::
> +
> +    for x in range(0,10):
> +     sendp(Ether(src="00:00:00:00:01:00",dst="vf_mac")/IP(src='2.1.1.'
> + + str(x),dst='2.1.1.5')/UDP()/"Hello!0",iface="tester_intf")
> +
> +6. Check if threads on core 0 to core 3 can be waked up in VM::
> +
> +    L3FWD_POWER: lcore 0 is waked up from rx interrupt on port 0 queue 0
> +    L3FWD_POWER: lcore 1 is waked up from rx interrupt on port 0 queue 1
> +    L3FWD_POWER: lcore 2 is waked up from rx interrupt on port 0 queue 2
> +    L3FWD_POWER: lcore 3 is waked up from rx interrupt on port 0 queue
> + 3
> \ No newline at end of file
> --
> 2.17.1



More information about the dts mailing list