* [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
@ 2020-09-21 10:02 Yinan Wang
2020-10-12 7:59 ` Tu, Lijuan
0 siblings, 1 reply; 6+ messages in thread
From: Yinan Wang @ 2020-09-21 10:02 UTC (permalink / raw)
To: dts; +Cc: Yinan Wang
Add 2 queue case for performance check
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
test_plans/dpdk_gro_lib_test_plan.rst | 94 ++++++++++++++++++++++-----
1 file changed, 76 insertions(+), 18 deletions(-)
diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst
index ea0244c..59ac0f1 100644
--- a/test_plans/dpdk_gro_lib_test_plan.rst
+++ b/test_plans/dpdk_gro_lib_test_plan.rst
@@ -130,7 +130,7 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic
2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./testpmd -l 2-4 -n 4 \
+ ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \
--file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024
testpmd>set fwd csum
testpmd>stop
@@ -151,8 +151,8 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic
taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -182,7 +182,7 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic
2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 2::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./testpmd -l 2-4 -n 4 \
+ ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \
--file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024
testpmd>set fwd csum
testpmd>stop
@@ -203,8 +203,8 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic
taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -234,7 +234,7 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic
2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 4::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./testpmd -l 2-4 -n 4 \
+ ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \
--file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024
testpmd>set fwd csum
testpmd>stop
@@ -255,8 +255,8 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic
taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -301,7 +301,7 @@ Vxlan topology
2. Bind nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 4::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./testpmd -l 2-4 -n 4 \
+ ./testpmd -l 2-4 -n 4 --socket-mem 1024,1024 --legacy-mem \
--file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=1,client=0' -- -i --txd=1024 --rxd=1024
testpmd>set fwd csum
testpmd>stop
@@ -325,8 +325,8 @@ Vxlan topology
taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -346,8 +346,8 @@ Vxlan topology
Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m
VM side: iperf -s -f g
-Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic
-==================================================================
+Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic
+==============================================================
Test flow
=========
@@ -365,8 +365,8 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2
set fwd csum
stop
port stop 0
@@ -383,11 +383,11 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
-mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \
@@ -403,3 +403,61 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2
VM side: iperf -s
+
+Test Case6: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic
+==================================================================
+
+Test flow
+=========
+
+NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
+
+1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds::
+
+ ip netns del ns1
+ ip netns add ns1
+ ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2
+ ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up
+ ip netns exec ns1 ethtool -K enp26s0f0 tso on
+
+2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
+
+ ./dpdk-devbind.py -b igb_uio xx:xx.x
+ ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2
+ set fwd csum
+ stop
+ port stop 0
+ port stop 1
+ csum set tcp hw 0
+ csum set ip hw 0
+ csum set tcp hw 1
+ csum set ip hw 1
+ set port 0 gro on
+ set gro flush 1
+ port start 0
+ port start 1
+ start
+
+3. Set up vm with virto device and using kernel virtio-net driver::
+
+ taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \
+ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
+ -numa node,memdev=mem \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
+ -chardev socket,id=char0,path=./vhost-net \
+ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \
+ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \
+ -vnc :10 -daemonize
+
+4. In vm, config the virtio-net device with ip and turn the kernel gro off::
+
+ ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net
+ ethtool -L ens4 combined 2
+ ethtool -K ens4 gro off
+
+5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get better performance than case5::
+
+ Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2
+ VM side: iperf -s
--
2.25.1
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
2020-09-21 10:02 [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst Yinan Wang
@ 2020-10-12 7:59 ` Tu, Lijuan
0 siblings, 0 replies; 6+ messages in thread
From: Tu, Lijuan @ 2020-10-12 7:59 UTC (permalink / raw)
To: Wang, Yinan, dts; +Cc: Wang, Yinan
> Add 2 queue case for performance check
>
> Signed-off-by: Yinan Wang <yinan.wang@intel.com>
Applied failed.
CONFLICT (content): Merge conflict in test_plans/dpdk_gro_lib_test_plan.rst
error: Failed to merge in the changes.
Patch failed at 0001 test_plans/dpdk_gro_lib_test_plan.rst
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
2020-11-04 12:13 Yinan Wang
@ 2020-11-11 3:23 ` Tu, Lijuan
0 siblings, 0 replies; 6+ messages in thread
From: Tu, Lijuan @ 2020-11-11 3:23 UTC (permalink / raw)
To: Wang, Yinan, dts; +Cc: Wang, Yinan
> Add dpdk gro test with 2 queues.
>
> Signed-off-by: Yinan Wang <yinan.wang@intel.com>
Applied
^ permalink raw reply [flat|nested] 6+ messages in thread
* [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
@ 2020-11-04 12:13 Yinan Wang
2020-11-11 3:23 ` Tu, Lijuan
0 siblings, 1 reply; 6+ messages in thread
From: Yinan Wang @ 2020-11-04 12:13 UTC (permalink / raw)
To: dts; +Cc: Yinan Wang
Add dpdk gro test with 2 queues.
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
test_plans/dpdk_gro_lib_test_plan.rst | 141 ++++++++++++++++++--------
1 file changed, 99 insertions(+), 42 deletions(-)
diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst
index 60a0123..fac61aa 100644
--- a/test_plans/dpdk_gro_lib_test_plan.rst
+++ b/test_plans/dpdk_gro_lib_test_plan.rst
@@ -89,27 +89,27 @@ Modify the testpmd code as following::
Modify the dpdk code as following::
- diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
- index b38a4b6b1..573250dbe 100644
- --- a/drivers/net/vhost/rte_eth_vhost.c
- +++ b/drivers/net/vhost/rte_eth_vhost.c
- @@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev,
- dev_info->min_rx_bufsize = 0;
-
- dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |
- - DEV_TX_OFFLOAD_VLAN_INSERT;
- - dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
- + DEV_TX_OFFLOAD_VLAN_INSERT |
- + DEV_TX_OFFLOAD_UDP_CKSUM |
- + DEV_TX_OFFLOAD_TCP_CKSUM |
- + DEV_TX_OFFLOAD_IPV4_CKSUM |
- + DEV_TX_OFFLOAD_TCP_TSO;
- + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |
- + DEV_RX_OFFLOAD_TCP_CKSUM |
- + DEV_RX_OFFLOAD_UDP_CKSUM |
- + DEV_RX_OFFLOAD_IPV4_CKSUM |
- + DEV_RX_OFFLOAD_TCP_LRO;
- }
+diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
+index b38a4b6b1..573250dbe 100644
+--- a/drivers/net/vhost/rte_eth_vhost.c
++++ b/drivers/net/vhost/rte_eth_vhost.c
+@@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev,
+ dev_info->min_rx_bufsize = 0;
+
+ dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |
+- DEV_TX_OFFLOAD_VLAN_INSERT;
+- dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
++ DEV_TX_OFFLOAD_VLAN_INSERT |
++ DEV_TX_OFFLOAD_UDP_CKSUM |
++ DEV_TX_OFFLOAD_TCP_CKSUM |
++ DEV_TX_OFFLOAD_IPV4_CKSUM |
++ DEV_TX_OFFLOAD_TCP_TSO;
++ dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |
++ DEV_RX_OFFLOAD_TCP_CKSUM |
++ DEV_RX_OFFLOAD_UDP_CKSUM |
++ DEV_RX_OFFLOAD_IPV4_CKSUM |
++ DEV_RX_OFFLOAD_TCP_LRO;
+ }
Test flow
=========
@@ -148,11 +148,11 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -200,11 +200,11 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -252,11 +252,11 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -278,11 +278,10 @@ Test Case4: DPDK GRO test with vxlan traffic
Vxlan topology
--------------
VM Host
-
50.1.1.2 50.1.1.1
- \| |
+ | |
1.1.2.3 1.1.2.4
- \|------------Testpmd------------|
+ |------------Testpmd------------|
1. Connect two nic port directly, put nic2 into another namesapce and create Host VxLAN port::
@@ -323,11 +322,11 @@ Vxlan topology
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 13 qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
- -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,macaddr=00:00:00:08:e8:aa,addr=1f -net user,hostfwd=tcp:127.0.0.1:6001-:22 \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu16.img \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -net nic,vlan=2,macaddr=00:00:00:08:e8:aa,addr=1f -net user,vlan=2,hostfwd=tcp:127.0.0.1:6001-:22 \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on \
@@ -347,8 +346,8 @@ Vxlan topology
Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m
VM side: iperf -s -f g
-Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic
-==================================================================
+Test Case5: DPDK GRO test with 2 queues using tcp/ipv4 traffic
+==============================================================
Test flow
=========
@@ -366,8 +365,8 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
./dpdk-devbind.py -b igb_uio xx:xx.x
- ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2
set fwd csum
stop
port stop 0
@@ -384,11 +383,11 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
3. Set up vm with virto device and using kernel virtio-net driver::
- taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \
+ taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \
-cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem \
-mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \
- -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
-chardev socket,id=char0,path=./vhost-net \
-netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \
-device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \
@@ -404,3 +403,61 @@ NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2
VM side: iperf -s
+
+Test Case6: DPDK GRO test with two queues and two CBDMA channels using tcp/ipv4 traffic
+=======================================================================================
+
+Test flow
+=========
+
+NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
+
+1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds::
+
+ ip netns del ns1
+ ip netns add ns1
+ ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2
+ ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up
+ ip netns exec ns1 ethtool -K enp26s0f0 tso on
+
+2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
+
+ ./dpdk-devbind.py -b igb_uio xx:xx.x
+ ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-31 -n 4 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2 --nb-cores=2
+ set fwd csum
+ stop
+ port stop 0
+ port stop 1
+ csum set tcp hw 0
+ csum set ip hw 0
+ csum set tcp hw 1
+ csum set ip hw 1
+ set port 0 gro on
+ set gro flush 1
+ port start 0
+ port start 1
+ start
+
+3. Set up vm with virto device and using kernel virtio-net driver::
+
+ taskset -c 31 /home/qemu-install/qemu-4.2.1/bin/qemu-system-x86_64 -name us-vhost-vm1 \
+ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
+ -numa node,memdev=mem \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu2004.img \
+ -chardev socket,id=char0,path=./vhost-net \
+ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \
+ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \
+ -vnc :10 -daemonize
+
+4. In vm, config the virtio-net device with ip and turn the kernel gro off::
+
+ ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net
+ ethtool -L ens4 combined 2
+ ethtool -K ens4 gro off
+
+5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput, should be larger than 10Gbits/sec::
+
+ Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2
+ VM side: iperf -s
--
2.25.1
^ permalink raw reply [flat|nested] 6+ messages in thread
* [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
@ 2020-08-21 11:28 Yinan Wang
0 siblings, 0 replies; 6+ messages in thread
From: Yinan Wang @ 2020-08-21 11:28 UTC (permalink / raw)
To: dts; +Cc: Yinan Wang
Add cbdma enable case in dpdk gro lib test plan
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
test_plans/dpdk_gro_lib_test_plan.rst | 60 ++++++++++++++++++++++++++-
1 file changed, 58 insertions(+), 2 deletions(-)
diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst
index 1ec8c23..b71023e 100644
--- a/test_plans/dpdk_gro_lib_test_plan.rst
+++ b/test_plans/dpdk_gro_lib_test_plan.rst
@@ -275,8 +275,6 @@ Test Case4: DPDK GRO test with vxlan traffic
Vxlan topology
--------------
-::
-
VM Host
50.1.1.2 50.1.1.1
| |
@@ -347,3 +345,61 @@ Vxlan topology
Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m
VM side: iperf -s -f g
+
+Test Case5: DPDK GRO test with CBDMA enable using tcp/ipv4 traffic
+==================================================================
+
+Test flow
+=========
+
+NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
+
+1. Connect two nic port directly, put nic2 into another namesapce and turn on the tso of this nic port by below cmds::
+
+ ip netns del ns1
+ ip netns add ns1
+ ip link set enp26s0f0 netns ns1 # [enp216s0f0] is the name of nic2
+ ip netns exec ns1 ifconfig enp26s0f0 1.1.1.8 up
+ ip netns exec ns1 ethtool -K enp26s0f0 tso on
+
+2. Bind cbdma port and nic1 to igb_uio, launch vhost-user with testpmd and set flush interval to 1::
+
+ ./dpdk-devbind.py -b igb_uio xx:xx.x
+ ./x86_64-native-linuxapp-gcc/app/testpmd -l 29-30 -n 4 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net,queues=2,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=1024' -- -i --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ testpmd>set fwd csum
+ testpmd>stop
+ testpmd>port stop 0
+ testpmd>port stop 1
+ testpmd>csum set tcp hw 0
+ testpmd>csum set ip hw 0
+ testpmd>csum set tcp hw 1
+ testpmd>csum set ip hw 1
+ testpmd>set port 0 gro on
+ testpmd>set gro flush 1
+ testpmd>port start 0
+ testpmd>port start 1
+ testpmd>start
+
+3. Set up vm with virto device and using kernel virtio-net driver::
+
+ taskset -c 31 /home/qemu-install/qemu-3.0/bin/qemu-system-x86_64 -name us-vhost-vm1 \
+ -cpu host -enable-kvm -m 2048 -object memory-backend-file,id=mem,size=2048M,mem-path=/mnt/huge,share=on \
+ -numa node,memdev=mem \
+ -mem-prealloc -monitor unix:/tmp/vm2_monitor.sock,server,nowait -netdev user,id=yinan,hostfwd=tcp:127.0.0.1:6005-:22 -device e1000,netdev=yinan \
+ -smp cores=1,sockets=1 -drive file=/home/osimg/ubuntu1910.img \
+ -chardev socket,id=char0,path=./vhost-net \
+ -netdev type=vhost-user,id=mynet1,chardev=char0,vhostforce,queues=2 \
+ -device virtio-net-pci,mac=52:54:00:00:00:01,netdev=mynet1,mrg_rxbuf=on,csum=on,gso=on,host_tso4=on,guest_tso4=on,mq=on,vectors=15 \
+ -vnc :10 -daemonize
+
+4. In vm, config the virtio-net device with ip and turn the kernel gro off::
+
+ ifconfig ens4 1.1.1.2 up # [ens3] is the name of virtio-net
+ ethtool -L ens4 combined 2
+ ethtool -K ens4 gro off
+
+5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log can get better performance than case 1::
+
+ Host side : taskset -c 35 ip netns exec ns1 iperf -c 1.1.1.2 -i 1 -t 60 -m -P 2
+ VM side: iperf -s
--
2.17.1
^ permalink raw reply [flat|nested] 6+ messages in thread
* [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst
@ 2020-08-20 10:12 Yinan Wang
0 siblings, 0 replies; 6+ messages in thread
From: Yinan Wang @ 2020-08-20 10:12 UTC (permalink / raw)
To: dts; +Cc: Yinan Wang
Add vhost code change before test
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
test_plans/dpdk_gro_lib_test_plan.rst | 43 +++++++++++++++++----------
1 file changed, 27 insertions(+), 16 deletions(-)
diff --git a/test_plans/dpdk_gro_lib_test_plan.rst b/test_plans/dpdk_gro_lib_test_plan.rst
index 410ae68..1ec8c23 100644
--- a/test_plans/dpdk_gro_lib_test_plan.rst
+++ b/test_plans/dpdk_gro_lib_test_plan.rst
@@ -84,12 +84,31 @@ Modify the testpmd code as following::
parse_ethernet(eth_hdr, &info);
l3_hdr = (char *)eth_hdr + info.l2_len;
+Also modify the dpdk code as following::
+
+ --- a/drivers/net/vhost/rte_eth_vhost.c
+ +++ b/drivers/net/vhost/rte_eth_vhost.c
+ @@ -1071,8 +1071,14 @@ eth_dev_info(struct rte_eth_dev *dev,
+ dev_info->min_rx_bufsize = 0;
+ dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS |
+ - DEV_TX_OFFLOAD_VLAN_INSERT;
+ - dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
+ + DEV_TX_OFFLOAD_VLAN_INSERT |
+ + DEV_TX_OFFLOAD_UDP_CKSUM |
+ + DEV_TX_OFFLOAD_TCP_CKSUM |
+ + DEV_TX_OFFLOAD_IPV4_CKSUM |
+ + DEV_TX_OFFLOAD_TCP_TSO;
+ + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |
+ + DEV_RX_OFFLOAD_TCP_CKSUM |
+ + DEV_RX_OFFLOAD_UDP_CKSUM |
+ + DEV_RX_OFFLOAD_IPV4_CKSUM |
+ + DEV_RX_OFFLOAD_TCP_LRO;
+ }
+
Test flow
=========
-::
-
- NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
+NIC2(In kernel) -> NIC1(DPDK) -> testpmd(csum fwd) -> Vhost -> Virtio-net
Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic
=========================================================
@@ -121,9 +140,7 @@ Test Case1: DPDK GRO lightmode test with tcp/ipv4 traffic
testpmd>port start 1
testpmd>start
-3. Set up vm with virto device and using kernel virtio-net driver:
-
- ::
+3. Set up vm with virto device and using kernel virtio-net driver::
taskset -c 13 \
qemu-system-x86_64 -name us-vhost-vm1 \
@@ -176,9 +193,7 @@ Test Case2: DPDK GRO heavymode test with tcp/ipv4 traffic
testpmd>port start 1
testpmd>start
-3. Set up vm with virto device and using kernel virtio-net driver:
-
- ::
+3. Set up vm with virto device and using kernel virtio-net driver::
taskset -c 13 \
qemu-system-x86_64 -name us-vhost-vm1 \
@@ -231,9 +246,7 @@ Test Case3: DPDK GRO heavymode_flush4 test with tcp/ipv4 traffic
testpmd>port start 1
testpmd>start
-3. Set up vm with virto device and using kernel virtio-net driver:
-
- ::
+3. Set up vm with virto device and using kernel virtio-net driver::
taskset -c 13 \
qemu-system-x86_64 -name us-vhost-vm1 \
@@ -308,9 +321,7 @@ Vxlan topology
testpmd>port start 1
testpmd>start
-3. Set up vm with virto device and using kernel virtio-net driver:
-
- ::
+3. Set up vm with virto device and using kernel virtio-net driver::
taskset -c 13 \
qemu-system-x86_64 -name us-vhost-vm1 \
@@ -335,4 +346,4 @@ Vxlan topology
5. Start iperf test, run iperf server at vm side and iperf client at host side, check throughput in log::
Host side : ip netns exec t2 iperf -c 50.1.1.2 -i 2 -t 60 -f g -m
- VM side: iperf -s -f g
\ No newline at end of file
+ VM side: iperf -s -f g
--
2.17.1
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2020-11-11 3:23 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-21 10:02 [dts] [PATCH v1] test_plans/dpdk_gro_lib_test_plan.rst Yinan Wang
2020-10-12 7:59 ` Tu, Lijuan
-- strict thread matches above, loose matches on Subject: below --
2020-11-04 12:13 Yinan Wang
2020-11-11 3:23 ` Tu, Lijuan
2020-08-21 11:28 Yinan Wang
2020-08-20 10:12 Yinan Wang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).