From: Yinan Wang <yinan.wang@intel.com>
To: dts@dpdk.org
Cc: Yinan Wang <yinan.wang@intel.com>
Subject: [dts] [PATCH v1] test_plans/vm2vm_virtio_net_perf_test_plan.rst
Date: Tue, 24 Nov 2020 12:00:55 -0500 [thread overview]
Message-ID: <20201124170055.72207-1-yinan.wang@intel.com> (raw)
Delete vhost dequeue zero copy test cases since this feature has been removed in 20.11.
Add split ring cbdma enable test and check the performance.
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
.../vm2vm_virtio_net_perf_test_plan.rst | 120 +++++-------------
1 file changed, 34 insertions(+), 86 deletions(-)
diff --git a/test_plans/vm2vm_virtio_net_perf_test_plan.rst b/test_plans/vm2vm_virtio_net_perf_test_plan.rst
index 2988e174..a5692d4b 100644
--- a/test_plans/vm2vm_virtio_net_perf_test_plan.rst
+++ b/test_plans/vm2vm_virtio_net_perf_test_plan.rst
@@ -40,8 +40,9 @@ Description
This test plan test vhost tx offload (TSO and UFO) function by verifing the TSO/cksum in the TCP/IP
stack enabled environment and UFO/cksum in the UDP/IP stack enabled environment with vm2vm split ring
and packed ring vhost-user/virtio-net mergeable path. Also add case to check the payload of large packet
-is valid with vm2vm split ring and packed ring vhost-user/virtio-net mergeable and non-mergeable dequeue
-zero copy test. For packed virtqueue virtio-net test, need qemu version > 4.2.0 and VM kernel version > v5.1.
+is valid with vm2vm split ring and packed ring vhost-user/virtio-net mergeable and non-mergeable.
+Meanwhile, this plan also check function and performance of split ring enqueue operation with CBDMA channels.
+For packed virtqueue virtio-net test, need qemu version > 4.2.0 and VM kernel version > v5.1.
Test flow
=========
@@ -51,16 +52,16 @@ Virtio-net <-> Vhost <-> Testpmd <-> Vhost <-> Virtio-net
Test Case 1: VM2VM split ring vhost-user/virtio-net test with tcp traffic
=========================================================================
-1. Launch the Vhost sample by below commands::
+1. Launch the Vhost sample on socket 0 by below commands::
rm -rf vhost-net*
./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1' \
--vdev 'net_vhost1,iface=vhost-net1,queues=1' -- -i --nb-cores=2 --txd=1024 --rxd=1024
testpmd>start
-2. Launch VM1 and VM2::
+2. Launch VM1 and VM2 on socket 1::
- qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 1 -m 4096 \
+ taskset -c 32 qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 1 -m 4096 \
-object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16.img \
-chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
@@ -71,7 +72,7 @@ Test Case 1: VM2VM split ring vhost-user/virtio-net test with tcp traffic
-netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce \
-device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on -vnc :10
- qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 1 -m 4096 \
+ taskset -c 33 qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 1 -m 4096 \
-object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16-2.img \
-chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
@@ -104,19 +105,19 @@ Test Case 1: VM2VM split ring vhost-user/virtio-net test with tcp traffic
Port 1 should have rx packets above 1522
-Test Case 2: VM2VM split ring vhost-user/virtio-net dequeue zero-copy test with tcp traffic
-===========================================================================================
+Test Case 2: VM2VM split ring vhost-user/virtio-net CBDMA enable test with tcp traffic
+======================================================================================
1. Launch the Vhost sample by below commands::
rm -rf vhost-net*
- ./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=2 --txd=1024 --rxd=1024
+ ./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dmas=[txq0@00:04.0],dmathr=512' \
+ --vdev 'net_vhost1,iface=vhost-net1,queues=1,dmas=[txq0@00:04.1],dmathr=512' -- -i --nb-cores=2 --txd=1024 --rxd=1024
testpmd>start
-2. Launch VM1 and VM2::
+2. Launch VM1 and VM2 on socket 1::
- qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 1 -m 4096 \
+ taskset -c 32 qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 1 -m 4096 \
-object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16.img \
-chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
@@ -127,7 +128,7 @@ Test Case 2: VM2VM split ring vhost-user/virtio-net dequeue zero-copy test with
-netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce \
-device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on -vnc :10
- qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 1 -m 4096 \
+ taskset -c 33 qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 1 -m 4096 \
-object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
-numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16-2.img \
-chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
@@ -159,6 +160,8 @@ Test Case 2: VM2VM split ring vhost-user/virtio-net dequeue zero-copy test with
Port 0 should have tx packets above 1522
Port 1 should have rx packets above 1522
+7. Check throughput and compare with case1, case2 performance should larger than case1.
+
Test Case 3: VM2VM split ring vhost-user/virtio-net test with udp traffic
=========================================================================
@@ -262,14 +265,14 @@ Test Case 4: Check split ring virtio-net device capability
tx-tcp-ecn-segmentation: on
tx-tcp6-segmentation: on
-Test Case 5: VM2VM virtio-net split ring mergeable zero copy test with large packet payload valid check
-=======================================================================================================
+Test Case 5: VM2VM virtio-net split ring mergeable CBDMA enable test with large packet payload valid check
+==========================================================================================================
1. Launch the Vhost sample by below commands::
rm -rf vhost-net*
- ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ ./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dmas=[txq0@80:04.0],dmathr=0' \
+ --vdev 'net_vhost1,iface=vhost-net1,queues=1,dmas=[txq0@80:04.1],dmathr=0' -- -i --nb-cores=2 --txd=1024 --rxd=1024
testpmd>start
2. Launch VM1 and VM2::
@@ -310,14 +313,14 @@ Test Case 5: VM2VM virtio-net split ring mergeable zero copy test with large pac
Under VM1, run: `scp [xxx] root@1.1.1.8:/` [xxx] is the file name
-Test Case 6: VM2VM virtio-net split ring non-mergeable zero copy test with large packet payload valid check
-===========================================================================================================
+Test Case 6: VM2VM virtio-net split ring non-mergeable CBDMA enable test with large packet payload valid check
+==============================================================================================================
1. Launch the Vhost sample by below commands::
rm -rf vhost-net*
- ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ ./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1' \
+ --vdev 'net_vhost1,iface=vhost-net1,queues=1,dmas=[txq0@80:04.1],dmathr=0' -- -i --nb-cores=2 --txd=1024 --rxd=1024
testpmd>start
2. Launch VM1 and VM2::
@@ -413,62 +416,7 @@ Test Case 7: VM2VM packed ring vhost-user/virtio-net test with tcp traffic
Port 0 should have tx packets above 1522
Port 1 should have rx packets above 1522
-Test Case 8: VM2VM packed ring vhost-user/virtio-net dequeue zero-copy test with tcp traffic
-============================================================================================
-
-1. Launch the Vhost sample by below commands::
-
- rm -rf vhost-net*
- ./testpmd -l 2-4 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=2 --txd=1024 --rxd=1024
- testpmd>start
-
-2. Launch VM1 and VM2::
-
- qemu-system-x86_64 -name vm1 -enable-kvm -cpu host -smp 1 -m 4096 \
- -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
- -numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16.img \
- -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
- -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \
- -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \
- -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6002-:22 \
- -chardev socket,id=char0,path=./vhost-net0 \
- -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce \
- -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:01,disable-modern=false,mrg_rxbuf=on,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,packed=on -vnc :10
-
- qemu-system-x86_64 -name vm2 -enable-kvm -cpu host -smp 1 -m 4096 \
- -object memory-backend-file,id=mem,size=4096M,mem-path=/mnt/huge,share=on \
- -numa node,memdev=mem -mem-prealloc -drive file=/home/osimg/ubuntu16-2.img \
- -chardev socket,path=/tmp/vm2_qga0.sock,server,nowait,id=vm2_qga0 -device virtio-serial \
- -device virtserialport,chardev=vm2_qga0,name=org.qemu.guest_agent.2 -daemonize \
- -monitor unix:/tmp/vm2_monitor.sock,server,nowait -device e1000,netdev=nttsip1 \
- -netdev user,id=nttsip1,hostfwd=tcp:127.0.0.1:6003-:22 \
- -chardev socket,id=char0,path=./vhost-net1 \
- -netdev type=vhost-user,id=netdev0,chardev=char0,vhostforce \
- -device virtio-net-pci,netdev=netdev0,mac=52:54:00:00:00:02,disable-modern=false,mrg_rxbuf=on,csum=on,guest_csum=on,host_tso4=on,guest_tso4=on,guest_ecn=on,packed=on -vnc :12
-
-3. On VM1, set virtio device IP and run arp protocal::
-
- ifconfig ens3 1.1.1.2
- arp -s 1.1.1.8 52:54:00:00:00:02
-
-4. On VM2, set virtio device IP and run arp protocal::
-
- ifconfig ens3 1.1.1.8
- arp -s 1.1.1.2 52:54:00:00:00:01
-
-5. Check the iperf performance between two VMs by below commands::
-
- Under VM1, run: `iperf -s -i 1`
- Under VM2, run: `iperf -c 1.1.1.2 -i 1 -t 60`
-
-6. Check both 2VMs can receive and send big packets to each other::
-
- testpmd>show port xstats all
- Port 0 should have tx packets above 1522
- Port 1 should have rx packets above 1522
-
-Test Case 9: VM2VM packed ring vhost-user/virtio-net test with udp traffic
+Test Case 8: VM2VM packed ring vhost-user/virtio-net test with udp traffic
==========================================================================
1. Launch the Vhost sample by below commands::
@@ -523,7 +471,7 @@ Test Case 9: VM2VM packed ring vhost-user/virtio-net test with udp traffic
Port 0 should have tx packets above 1522
Port 1 should have rx packets above 1522
-Test Case 10: Check packed ring virtio-net device capability
+Test Case 9: Check packed ring virtio-net device capability
============================================================
1. Launch the Vhost sample by below commands::
@@ -571,14 +519,14 @@ Test Case 10: Check packed ring virtio-net device capability
tx-tcp-ecn-segmentation: on
tx-tcp6-segmentation: on
-Test Case 11: VM2VM packed ring virtio-net mergeable dequeue zero copy test with large packet payload valid check
-=================================================================================================================
+Test Case 10: VM2VM packed ring virtio-net mergeable with large packet payload valid check
+==========================================================================================
1. Launch the Vhost sample by below commands::
rm -rf vhost-net*
- ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1' \
+ --vdev 'net_vhost1,iface=vhost-net1,queues=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
testpmd>start
2. Launch VM1 and VM2::
@@ -619,14 +567,14 @@ Test Case 11: VM2VM packed ring virtio-net mergeable dequeue zero copy test with
Under VM1, run: `scp [xxx] root@1.1.1.8:/` [xxx] is the file name
-Test Case 12: VM2VM packed ring virtio-net non-mergeable dequeue zero copy test with large packet payload valid check
-=====================================================================================================================
+Test Case 11: VM2VM packed ring virtio-net non-mergeable with large packet payload valid check
+==============================================================================================
1. Launch the Vhost sample by below commands::
rm -rf vhost-net*
- ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1,dequeue-zero-copy=1' \
- --vdev 'net_vhost1,iface=vhost-net1,queues=1,dequeue-zero-copy=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ ./testpmd -c 0xF0000000 -n 4 --no-pci --file-prefix=vhost --vdev 'net_vhost0,iface=vhost-net0,queues=1' \
+ --vdev 'net_vhost1,iface=vhost-net1,queues=1' -- -i --nb-cores=1 --txd=1024 --rxd=1024
testpmd>start
2. Launch VM1 and VM2::
--
2.25.1
next reply other threads:[~2020-11-24 8:12 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-24 17:00 Yinan Wang [this message]
2020-11-26 8:21 ` Tu, Lijuan
2020-12-01 17:25 Yinan Wang
2020-12-07 7:29 ` Tu, Lijuan
2020-12-15 23:08 Yinan Wang
2020-12-21 7:28 ` Tu, Lijuan
2021-02-23 15:26 Yinan Wang
2021-03-02 2:23 ` Tu, Lijuan
2021-04-07 15:52 [dts] [PATCH V1] test_plans/vm2vm_virtio_net_perf_test_plan.rst Yinan Wang
2021-04-08 8:56 ` Tu, Lijuan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201124170055.72207-1-yinan.wang@intel.com \
--to=yinan.wang@intel.com \
--cc=dts@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).