From: Yinan Wang <yinan.wang@intel.com>
To: dts@dpdk.org
Cc: Yinan Wang <yinan.wang@intel.com>
Subject: [dts] [PATCH v2] test_plans/vhost_cbdma_test_plan.rsttest_plans/vhost_cbdma_test_plan
Date: Fri, 2 Jul 2021 11:49:14 -0400 [thread overview]
Message-ID: <20210702154914.837623-1-yinan.wang@intel.com> (raw)
1. change cases using imix pkts for better coverage
2. add one cbdma performance case
Signed-off-by: Yinan Wang <yinan.wang@intel.com>
---
test_plans/vhost_cbdma_test_plan.rst | 212 +++++++++++++--------------
1 file changed, 102 insertions(+), 110 deletions(-)
diff --git a/test_plans/vhost_cbdma_test_plan.rst b/test_plans/vhost_cbdma_test_plan.rst
index c827adaa..325b5d87 100644
--- a/test_plans/vhost_cbdma_test_plan.rst
+++ b/test_plans/vhost_cbdma_test_plan.rst
@@ -126,103 +126,54 @@ TG --> NIC --> Vhost --> Virtio--> Vhost --> NIC --> TG
>set fwd mac
>start
-Test Case2: Split ring dynamic queue number test for DMA-accelerated vhost Tx operations
-========================================================================================
+Test Case 2: Split ring dynamic queue number test for DMA-accelerated vhost Tx operations
+=========================================================================================
-1. Bind four cbdma channels and one nic port to igb_uio, then launch vhost by below command::
+1. Bind 8 cbdma channels and one nic port to igb_uio, then launch vhost by below command::
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=2,client=1,dmas=[txq0@80:04.5;txq1@80:04.6],dmathr=1024' \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
- >set fwd mac
- >start
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=8,client=1' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
+ >set fwd mac
+ >start
2. Launch virtio-user by below command::
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 30-31 --no-pci --file-prefix=virtio \
- --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=2,server=1 \
- -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=8,server=1 \
+ -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
>set fwd mac
>start
-3. Send packets with packet size [64,1518] from packet generator with random ip, check perforamnce can get target.
+3. Send imix packets from packet generator with random ip, check perforamnce can get target.
-4. Stop vhost port, check vhost RX and TX direction both exist packtes in two queues from vhost log.
+4. Stop vhost port, check vhost RX and TX direction both exist packtes in 8 queues from vhost log.
-5. On virtio-user side, dynamic change rx queue numbers from 2 queue to 1 queues, then check one queue RX/TX can work normally::
+5. Quit vhost port and relaunch vhost with 4 queues w/ cbdma::
- testpmd>port stop all
- testpmd>port config all rxq 1
- testpmd>port config all txq 1
- testpmd>port start all
- testpmd>start
- testpmd>show port stats all
-
-6. Relaunch virtio-user with vectorized path and 2 queues::
-
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 30-31 --no-pci --file-prefix=virtio \
- --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=0,in_order=1,vectorized=1,queues=2,server=1 \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=4,client=1,dmas=[txq0@00:04.0;txq1@00:04.1;txq2@00:04.2;txq3@00:04.3],dmathr=1024' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=4 --rxq=4
>set fwd mac
>start
-7. Send packets with packet size [64,1518] from packet generator with random ip, check perforamnce can get target.
+6. Send imix packets from packet generator with random ip, check perforamnce can get target.
-8. Stop vhost port, check vhost RX and TX direction both exist packtes in queue0 from vhost log.
+7. Stop vhost port, check vhost RX and TX direction both exist packtes in 4 queues from vhost log.
-9. On vhost side, dynamic change rx queue numbers from 2 queue to 1 queues, then check one queue RX/TX can work normally::
-
- testpmd>port stop all
- testpmd>port config all rxq 1
- testpmd>port config all txq 1
- testpmd>port start all
- testpmd>start
- testpmd>show port stats all
-
-10. Relaunch vhost with another two cbdma channels and 2 queueus, check perforamnce can get target::
+8. Quit vhost port and relaunch vhost with 8 queues w/ cbdma::
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=2,client=1,dmas=[txq0@00:04.5;txq1@00:04.6],dmathr=512' \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
- >set fwd mac
- >start
-
-11. Stop vhost port, check vhost RX and TX direction both exist packtes in two queues from vhost log.
-
-Test Case3: CBDMA threshold value check
-========================================
-
-1. Bind four cbdma port to igb_uio, then launch vhost by below command::
-
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-2 -n 4 \
- --vdev 'eth_vhost0,iface=vhost-net,queues=2,client=1,dmas=[txq0@80:04.0;txq1@80:04.1],dmathr=512' --vdev 'eth_vhost1,iface=vhost-net1,queues=2,client=1,dmas=[txq0@80:04.2;txq1@80:04.3],dmathr=4096' -- \
- -i --nb-cores=1 --rxq=2 --txq=2
- >start
-
-2. Launch virtio-user1::
-
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 7-8 \
- --no-pci --file-prefix=virtio1 \
- --vdev=net_virtio_user1,mac=00:01:02:03:04:05,path=./vhost-net1,queues=2,server=1,packed_vq=0,mrg_rxbuf=1,in_order=0,queue_size=4096 \
- -- -i --nb-cores=1 --rxq=2 --txq=2
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=8,client=1,dmas=[txq0@80:04.0;txq1@80:04.1;txq2@80:04.2;txq3@80:04.3;txq4@80:04.4;txq5@80:04.5;txq6@80:04.6;txq7@80:04.7],dmathr=1024' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
+ >set fwd mac
>start
-3. Launch virtio-user0::
-
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 5-6 \
- --no-pci --file-prefix=virtio \
- --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=./vhost-net,queues=2,server=1,packed_vq=0,mrg_rxbuf=1,in_order=0,queue_size=4096 \
- -- -i --nb-cores=1 --rxq=2 --txq=2
- >start
-
-4. Check the cbdma threshold value for each vhost port can be config correct from vhost log::
+9. Send imix packets from packet generator with random ip, check perforamnce can get target.
- dma parameters: vid0,qid0,dma*,threshold:512
- dma parameters: vid0,qid2,dma*,threshold:512
- dma parameters: vid1,qid0,dma*,threshold:4096
- dma parameters: vid1,qid2,dma*,threshold:4096
+10. Stop vhost port, check vhost RX and TX direction both exist packtes in 8 queues from vhost log.
-Test Case 4: PVP packed ring all path with DMA-accelerated vhost enqueue
+Test Case 3: PVP packed ring all path with DMA-accelerated vhost enqueue
========================================================================
Packet pipeline:
@@ -293,65 +244,106 @@ TG --> NIC --> Vhost --> Virtio--> Vhost --> NIC --> TG
>set fwd mac
>start
-Test Case5: Packed ring dynamic queue number test for DMA-accelerated vhost Tx operations
-=========================================================================================
+Test Case 4: Packed ring dynamic queue number test for DMA-accelerated vhost Tx operations
+==========================================================================================
-1. Bind four cbdma channels and one nic port to igb_uio, then launch vhost by below command::
+1. Bind 8 cbdma channels and one nic port to igb_uio, then launch vhost by below command::
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=2,client=1,dmas=[txq0@80:04.5;txq1@80:04.6],dmathr=1024' \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
- >set fwd mac
- >start
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=8,client=1' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
+ >set fwd mac
+ >start
2. Launch virtio-user by below command::
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 30-31 --no-pci --file-prefix=virtio \
- --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=2,server=1,packed_vq=1 \
- -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
+ --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=8,server=1,packed_vq=1 \
+ -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
>set fwd mac
>start
-3. Send imix packets [64,1518] from packet generator with random ip, check perforamnce can get target.
+3. Send imix packets from packet generator with random ip, check perforamnce can get target.
-4. Stop vhost port, check vhost RX and TX direction both exist packets in two queues from vhost log.
+4. Stop vhost port, check vhost RX and TX direction both exist packtes in 8 queues from vhost log.
-5. On virtio-user side, dynamic change rx queue numbers from 2 queue to 1 queues, then check one queue RX/TX can work normally::
+5. Quit vhost port and relaunch vhost with 4 queues w/ cbdma::
- testpmd>port stop all
- testpmd>port config all rxq 1
- testpmd>port config all txq 1
- testpmd>port start all
- testpmd>start
- testpmd>show port stats all
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=4,client=1,dmas=[txq0@80:04.0;txq1@80:04.1;txq2@80:04.2;txq3@80:04.3],dmathr=1024' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=4 --rxq=4
+ >set fwd mac
+ >start
-6. Relaunch virtio-user with vectorized path and 2 queues::
+6. Send imix packets from packet generator with random ip, check perforamnce can get target.
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 30-31 --no-pci --file-prefix=virtio \
- --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=0,in_order=1,vectorized=1,queues=2,server=1,packed_vq=1 \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
+7. Stop vhost port, check vhost RX and TX direction both exist packtes in 4 queues from vhost log.
+
+8. Quit vhost port and relaunch vhost with 8 queues w/ cbdma::
+
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
+ --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=8,client=1,dmas=[txq0@80:04.0;txq1@80:04.1;txq2@80:04.2;txq3@80:04.3;txq4@80:04.4;txq5@80:04.5;txq6@80:04.6;txq7@80:04.7],dmathr=1024' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=8 --rxq=8
>set fwd mac
>start
-7. Send imix packets [64,1518] from packet generator with random ip, check perforamnce can get target.
+9. Send imix packets from packet generator with random ip, check perforamnce can get target.
-8. Stop vhost port, check vhost RX and TX direction both exist packets in queue0 from vhost log.
+10. Stop vhost port, check vhost RX and TX direction both exist packtes in 8 queues from vhost log.
-9. On vhost side, dynamic change rx queue numbers from 2 queue to 1 queues, then check one queue RX/TX can work normally::
+Test Case 5: Compare PVP split ring performance between CPU copy, CBDMA copy and Sync copy
+==========================================================================================
+
+1. Bind one cbdma port and one nic port which on same numa to igb_uio, then launch vhost by below command::
+
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 2-3 --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=1,client=1,dmas=[txq0@00:01.0],dmathr=1024' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ >set fwd mac
+ >start
+
+2. Launch virtio-user with inorder mergeable path::
+
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 5-6 --no-pci --file-prefix=virtio \
+ --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=1,server=1 \
+ -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024
+ >set fwd mac
+ >start
+
+3. Send packets with 64b and 1518b seperately from packet generator, record the throughput as sync copy throughput for 64b and cbdma copy for 1518b::
- testpmd>port stop all
- testpmd>port config all rxq 1
- testpmd>port config all txq 1
- testpmd>port start all
- testpmd>start
testpmd>show port stats all
-10. Relaunch vhost with another two cbdma channels and 2 queueus, check perforamnce can get target::
+4.Quit vhost side, relaunch with below cmd::
- ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 28-29 \
- --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=2,client=1,dmas=[txq0@00:04.5;txq1@00:04.6],dmathr=512' \
- -- -i --nb-cores=1 --txd=1024 --rxd=1024 --txq=2 --rxq=2
- >set fwd mac
- >start
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 2-3 --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=1,client=1,dmas=[txq0@00:01.0],dmathr=2000' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ >set fwd mac
+ >start
+
+5. Send packets with 1518b from packet generator, record the throughput as sync copy throughput for 1518b::
+
+ testpmd>show port stats all
+
+6. Quit two testpmd, relaunch vhost by below command::
+
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 2-3 --file-prefix=vhost --vdev 'net_vhost0,iface=/tmp/s0,queues=1' \
+ -- -i --nb-cores=1 --txd=1024 --rxd=1024
+ >set fwd mac
+ >start
+
+7. Launch virtio-user with inorder mergeable path::
+
+ ./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -n 4 -l 5-6 --no-pci --file-prefix=virtio \
+ --vdev=net_virtio_user0,mac=00:01:02:03:04:05,path=/tmp/s0,mrg_rxbuf=1,in_order=1,queues=1 \
+ -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --nb-cores=1 --txd=1024 --rxd=1024
+ >set fwd mac
+ >start
+
+8. Send packets with 64b from packet generator, record the throughput as cpu copy for 64b::
+
+ testpmd>show port stats all
+
+9. Check performance can meet below requirement::
-11. Stop vhost port, check vhost RX and TX direction both exist packets in two queues from vhost log.
+ (1)CPU copy vs. sync copy delta < 10% for 64B packet size
+ (2)CBDMA copy vs sync copy delta > 5% for 1518 packet size
--
2.25.1
reply other threads:[~2021-07-02 7:05 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20210702154914.837623-1-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).