DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Rao, Ravi" <Ravi.Rao@us.fujitsu.com>
To: "Traynor, Kevin" <kevin.traynor@intel.com>,
	"therbert@redhat.com" <therbert@redhat.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] performance issue with ovs + dpdk2.0 with vhost
Date: Fri, 15 May 2015 17:27:32 +0000	[thread overview]
Message-ID: <4E5A07CF014F73489C60025F5BCB7834EBC16866@RCHEXMBP1.fnc.net.local> (raw)
In-Reply-To: <BC0FEEC7D7650749874CEC11314A88F730753022@IRSMSX104.ger.corp.intel.com>

Hi ,
   If do not enable dpdk, plian ovs can pass about 120,000 pps but once I make ovs to use dpdk the main reason in doing this is to get more performance I am seeing that it is passing only 1000 pps.
So I guess the drop from 120,000 to just 1000 means I am missing something.
Regards,
Ravi

-----Original Message-----
From: Traynor, Kevin [mailto:kevin.traynor@intel.com] 
Sent: Friday, May 15, 2015 12:02 PM
To: Rao, Ravi; therbert@redhat.com; dev@dpdk.org
Subject: RE: [dpdk-dev] performance issue with ovs + dpdk2.0 with vhost


> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Ravi Rao
> Sent: Friday, May 15, 2015 5:12 PM
> To: therbert@redhat.com; dev@dpdk.org
> Subject: Re: [dpdk-dev] performance issue with ovs + dpdk2.0 with 
> vhost
> 
> Hi,
>     This is what I am trying to Do.
> Below is the setup..
> 
> |                   +----------------------+   |
>                    | guest                |   |
>                    |                      |   |
>                    |                      |   |  guest
>                    |  eth0   L3fwd  eth1  |   |
>                    |   |              |   |   |
>                    +---+--------------+---+ __|
>                            ^      :
>                            |      |
>                            :      v                       __
>      +-----------------+--------------+-----------------+   |
>      |                 | ovs-br0      |                 |
>      |                 +--------------+                 |   |
>      |                     ^      :                     |   |
>      |          +----------+      +---------+           |   |  host
>      |          :                           v           |   |
>      |   +--------------+            +--------------+   |   |
>      |   |   dpdk0      |  ovs-dpdk  |   dpdk1      |   |   |
>      +---+--------------+------------+--------------+---+ __|
>                 ^                           :
>                 |                           |
>                 :                           v
>      +--------------------------------------------------+
>      |                                                  |
>      |                traffic generator                 |
>      |                                                  |
>      +--------------------------------------------------+|
> 
> 
> Step1: Use the latest ovs and dpdk2.0 to get the ovs running with 2 
> dpdk interfaces that are bound to 2 10GB physical interfaces
> #** Inser the required Modules
> cd /root/dpdk-2.0.0
> modprobe uio
> modprobe cuse
> rmmod igb_uio
> rmmod rte_kni
> insmod x86_64-native-linuxapp-gcc/kmod/igb_uio.ko
> 
> #**** Assign the dpdk capable interfaces to igb_uio driver 
> tools/dpdk_nic_bind.py --status tools/dpdk_nic_bind.py -b igb_uio 
> 0000:02:00.0 tools/dpdk_nic_bind.py -b igb_uio 0000:02:00.1 
> tools/dpdk_nic_bind.py --status
> 
> #--- Setup the openVswitch
> cd /root/ovs
> pkill -9 ovs
> mkdir -p /usr/local/etc/openvswitch
> mkdir -p /usr/local/var/run/openvswitch rm -rf 
> /usr/local/etc/openvswitch/conf.db
> ovsdb/ovsdb-tool create /usr/local/etc/openvswitch/conf.db
> vswitchd/vswitch.ovsschema
> 
> #Start ovsdb-server
> ovsdb/ovsdb-server 
> --remote=punix:/usr/local/var/run/openvswitch/db.sock
> --remote=db:Open_vSwitch,Open_vSwitch,manager_options --pidfile 
> --detach utilities/ovs-vsctl --no-wait init
> 
> #Start vswitchd:
> export DB_SOCK=/usr/local/var/run/openvswitch/db.sock
> rm /dev/vhost-net
> vswitchd/ovs-vswitchd --dpdk -c 0x3 -n 4 --socket-mem 1024,0 -- 
> unix:$DB_SOCK --pidfile --detach
> 
> #Add bridge & ports
> utilities/ovs-vsctl add-br ovs-br0 -- set bridge ovs-br0 
> datapath_type=netdev utilities/ovs-vsctl add-port ovs-br0 dpdk0 -- set 
> Interface dpdk0 type=dpdk utilities/ovs-vsctl add-port ovs-br0 dpdk1 
> -- set Interface dpdk1 type=dpdk
> 
> Step2: Create the dpdkvhost interfaces and bring up the guestVM using 
> QEMU export DPDK_DIR=/root/dpdk-2.0.0 insmod 
> $DPDK_DIR/lib/librte_vhost/eventfd_link/eventfd_link.ko
> cd /root/ovs
> utilities/ovs-vsctl add-port ovs-br0 dpdkvhost0 -- set Interface
> dpdkvhost0 type=dpdkvhost
> utilities/ovs-vsctl add-port ovs-br0 dpdkvhost1 -- set Interface
> dpdkvhost1 type=dpdkvhost
> 
> #**** Start the guest ubuntu VM1 from a terminal that is logged in as 
> root
> qemu-system-x86_64 --enable-kvm -k fr -m 1G \
>          -cpu host -smp cores=2,threads=1,sockets=1 \
>          -serial telnet::4444,server,nowait -monitor 
> telnet::5555,server,nowait \
>          -hda /root/VMs/images/ubuntu-14.04-template.qcow2 \
>          -object
> memory-backend-file,id=mem,size=1G,mem-path=/mnt/huge_1GB,share=on \
>          -numa node,memdev=mem \
>          -netdev
> type=tap,id=dpdkvhost0,script=no,downscript=no,ifname=dpdkvhost0,vhost=on \
>          -device
> virtio-net-
> pci,netdev=dpdkvhost0,mac=52:54:00:12:34:56,csum=off,gso=off,guest_tso
> 4=off,g
> uest_tso6=off,guest_ecn=off
> \
>          -netdev
> type=tap,id=dpdkvhost1,script=no,downscript=no,ifname=dpdkvhost1,vhost=on \
>          -device
> virtio-net-
> pci,netdev=dpdkvhost1,mac=52:54:00:12:34:57,csum=off,gso=off,guest_tso
> 4=off,g
> uest_tso6=off,guest_ecn=off
> \
>          -device ne2k_pci,mac=DE:AD:DE:01:02:03,netdev=user.0 -netdev
> user,id=user.0,hostfwd=tcp::2222-:22 &
> 
> # **** Add flows between ports
> utilities/ovs-ofctl del-flows ovs-br0
> utilities/ovs-ofctl add-flow ovs-br0 in_port=1,action=output:3 
> utilities/ovs-ofctl add-flow ovs-br0 in_port=2,action=output:4 
> utilities/ovs-ofctl add-flow ovs-br0 in_port=3,action=output:1 
> utilities/ovs-ofctl add-flow ovs-br0 in_port=4,action=output:2
> 
> Once I complete the above settings. I log into the VM and enable ipv4 
> forwarding so that it could do l3 fwd between eth0 and eth1
> 
> The issue I am seeing is when I start pumping packets on IXIA port 
> connected to physical port dpdk0 I see lots of tx_errors on dpdk0.
> I can only pass about 1000 pps without getting any errors. Is there 
> anything I am doing wrong or missing in the above setup.

>From what you are saying, I take it that it is functionally working but the rates are low. In that case I would check/set core affinities with top -H and taskset to see if there's contention occurring. You could also test with multiple PMDs (hence cores) in OVS to spread the switching workload - if you wanted to test with 4 PMDs you could use ovs-vsctl --timeout 10 set Open_vSwitch . other_config:pmd-cpu-mask=3c

> 
> Thanks & Regards,
> Ravi..
> 
> On 05/15/15 09:41, Thomas F Herbert wrote:
> > On 5/15/15 9:55 AM, Rao, Ravi wrote:
> >> Hi All,
> >>     I am trying to get a Guest VM connected to the dpdkvhost 
> >> interface on a host which has the ovs running from the latest ovs 
> >> git and dpdk2.0. Looks like I am missing something as 95% of 
> >> traffic is not getting to the VM. Can one of you please let me know 
> >> which mailing list I should be posting the details for getting a 
> >> resolution. Is it this dpdk list OR would it be the openvswitch list?
> > You could also try the openvswitch discuss list but this list is a 
> > good starting point. I am working with vhost/dpdk2.0 and ovs and 
> > others are too.
> > Could you please send more details about what you are seeing? Are 
> > you using the Linux stack in the guest? Do you see packets on the 
> > input IF in the guest?
> >> Regards,
> >> Ravi..
> >
> >

      reply	other threads:[~2015-05-15 17:27 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-15 13:55 Rao, Ravi
2015-05-15 14:01 ` Thomas F Herbert
2015-05-15 14:41 ` Thomas F Herbert
2015-05-15 16:11   ` Ravi Rao
2015-05-15 17:02     ` Traynor, Kevin
2015-05-15 17:27       ` Rao, Ravi [this message]

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=4E5A07CF014F73489C60025F5BCB7834EBC16866@RCHEXMBP1.fnc.net.local \
    --to=ravi.rao@us.fujitsu.com \
    --cc=dev@dpdk.org \
    --cc=kevin.traynor@intel.com \
    --cc=therbert@redhat.com \
    /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).