test suite reviews and discussions
 help / color / mirror / Atom feed
From: Yinan <yinan.wang@intel.com>
To: dts@dpdk.org
Cc: Wang Yinan <yinan.wang@intel.com>
Subject: [dts] [PATCH v1] test_plans: add packed ring vectorized cases in pvp_multi_paths_vhost_single_core_performance_test_plan
Date: Sat, 25 Apr 2020 21:30:44 +0000	[thread overview]
Message-ID: <20200425213044.100379-1-yinan.wang@intel.com> (raw)

From: Wang Yinan <yinan.wang@intel.com>

Signed-off-by: Wang Yinan <yinan.wang@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.rst b/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan.rst
index e56bec6..5306538 100644
--- a/test_plans/pvp_multi_paths_vhost_single_core_performance_test_plan.rst
+++ 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,packed_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,packed_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


             reply	other threads:[~2020-04-26  4:36 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-25 21:30 Yinan [this message]
2020-04-27  7:51 ` 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=20200425213044.100379-1-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).