[dts] [PATCH v1] test_plans: add packed ring vectorized cases in pvp_multi_paths_vhost_single_core_performance_test_plan

[Tu, Lijuan]

Applied, thanks

> -----Original Message-----
> From: dts [mailto:dts-bounces at dpdk.org] On Behalf Of Yinan
> Sent: Sunday, April 26, 2020 5:31 AM
> To: dts at dpdk.org
> Cc: Wang, Yinan <yinan.wang at intel.com>
> Subject: [dts] [PATCH v1] test_plans: add packed ring vectorized cases in
> pvp_multi_paths_vhost_single_core_performance_test_plan
> 
> From: Wang Yinan <yinan.wang at intel.com>
> 
> Signed-off-by: Wang Yinan <yinan.wang at intel.com>
> ---
>  ...vhost_single_core_performance_test_plan.rst | 18 +++++++-----------
>  1 file changed, 7 insertions(+), 11 deletions(-)
> 
> diff --git
> a/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan.rs
> t
> b/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan.rs
> t
> index e56bec6..5306538 100644
> ---
> a/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan.rs
> t
> +++
> b/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan
> +++ .rst
> @@ -38,10 +38,6 @@ Benchmark PVP virtio single core performance with 10
> tx/rx paths. Includes merge  inorder mergeable, inorder non-mergeable,
> virtio 1.1 mergeable, virtio 1.1 non-mergeable，virtio 1.1 inorder  mergeable,
> virtio 1.1 inorder non-mergeable, virtio1.1 vectorized path.
>  Give 2 cores for virtio and 1 core for vhost, set io fwd at virtio side to lower
> the virtio workload.
> -Note: Virtio 1.1 vectorizedized path need below three initial requirements:
> -    1. AVX512 is allowed in config file and supported by compiler
> -    2. Host cpu support AVX512F
> -    3. ring size is power of two
> 
>  Test flow
>  =========
> @@ -103,7 +99,7 @@ Test Case 3: vhost single core performance test with
> inorder mergeable path
> 
>  2. Launch virtio-user by below command::
> 
> -    ./testpmd -l 7-9 -n 4 --legacy-mem --file-prefix=virtio \
> +    ./testpmd -l 7-9 -n 4 --file-prefix=virtio \
>      --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-
> net,queues=1,in_order=1,mrg_rxbuf=1 \
>      -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --rss-ip --nb-cores=2 --
> txd=1024 --rxd=1024
>      >set fwd io
> @@ -167,7 +163,7 @@ Test Case 6: vhost single core performance test with
> non-mergeable path  2. Launch virtio-user by below command::
> 
>      ./testpmd -l 7-9 -n 4 --file-prefix=virtio \
> -    --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-
> net,queues=1,in_order=0,mrg_rxbuf=0 \
> +
> + --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-net,queues=1,in
> + _order=0,mrg_rxbuf=0,vectorized=1 \
>      -- -i --tx-offloads=0x0 --enable-hw-vlan-strip --rss-ip --nb-cores=2 --
> txd=1024 --rxd=1024
>      >set fwd io
>      >start
> @@ -188,7 +184,7 @@ Test Case 7: vhost single core performance test with
> vectorized_rx path  2. Launch virtio-user by below command::
> 
>      ./testpmd -l 7-9 -n 4 --file-prefix=virtio \
> -    --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-
> net,queues=1,in_order=0,mrg_rxbuf=0 \
> +
> + --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-net,queues=1,in
> + _order=0,mrg_rxbuf=0,vectorized=1 \
>      -- -i --tx-offloads=0x0 --nb-cores=2 --txd=1024 --rxd=1024
>      >set fwd io
>      >start
> @@ -230,7 +226,7 @@ Test Case 9: vhost single core performance test with
> virtio 1.1 inorder non-merg  2. Launch virtio-user by below command::
> 
>      ./testpmd -l 7-9 -n 4 --file-prefix=virtio \
> -    --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-
> net,queues=1,packed_vq=1,mrg_rxbuf=0,in_order=1,packed_vec=1 \
> +
> + --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-net,queues=1,pa
> + cked_vq=1,mrg_rxbuf=0,in_order=1,vectorized=1 \
>      -- -i --rx-offloads=0x10 --rss-ip --nb-cores=2 --txd=1024 --rxd=1024
>      >set fwd io
>      >start
> @@ -238,12 +234,12 @@ Test Case 9: vhost single core performance test
> with virtio 1.1 inorder non-merg  3. Send packet with packet generator with
> different packet size, check the throughput.
> 
>  Test Case 10: vhost single core performance test with virtio 1.1 vectorized
> path -
> ================================================================
> =============
> +===============================================================
> ========
> +=========
> 
>  1. Bind one port to igb_uio, then launch vhost by below command::
> 
>      rm -rf vhost-net*
> -    ./testpmd -l 3-4 -n 4 --socket-mem 1024,1024 --legacy-mem --no-pci --file-
> prefix=vhost \
> +    ./testpmd -l 3-4 -n 4 --no-pci --file-prefix=vhost \
>      --vdev 'net_vhost0,iface=vhost-net,queues=1' -- -i --nb-cores=1 --txd=1024
> --rxd=1024
>      testpmd>set fwd mac
>      testpmd>start
> @@ -251,7 +247,7 @@ Test Case 10: vhost single core performance test with
> virtio 1.1 vectorized path  2. Launch virtio-user by below command::
> 
>      ./testpmd -l 7-9 -n 4 --file-prefix=virtio \
> -    --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-
> net,queues=1,packed_vq=1,mrg_rxbuf=0,in_order=1,packed_vec=1 \
> +
> + --vdev=virtio_user0,mac=00:11:22:33:44:10,path=./vhost-net,queues=1,pa
> + cked_vq=1,mrg_rxbuf=0,in_order=1,vectorized=1 \
>      -- -i --rss-ip --nb-cores=2 --txd=1024 --rxd=1024
>      >set fwd io
>      >start
> --
> 2.17.1