[ovs-discuss] OVS-DPDK - Very poor performance when connected to namespace/container

Mooney, Sean K sean.k.mooney at intel.com
Fri Jun 16 17:01:50 UTC 2017


> -----Original Message-----
> From: Darrell Ball [mailto:dball at vmware.com]
> Sent: Friday, June 16, 2017 5:53 PM
> To: Gray, Mark D <mark.d.gray at intel.com>; Mooney, Sean K
> <sean.k.mooney at intel.com>; Avi Cohen (A) <avi.cohen at huawei.com>;
> users at dpdk.org; ovs-discuss at openvswitch.org
> Subject: Re: [ovs-discuss] OVS-DPDK - Very poor performance when
> connected to namespace/container
> 
> This should be quite a bit better than the AF_PACKET PMD.
> This becomes available in 17.08 and is important, it would be nice to
> get into the next OVS release.
[Mooney, Sean K] 
Virtio user will work only if you have dpdk in the container/namespce correct?
The vhsot frontend is being provisioned by isided the dpdk vhost driver in the application.

I agree that is the way to go if your application support dpdk, if not you would need
To use one of the other vdevs.

> 
> Also, any existing data on the performance advantage of AF_PACKET PMD
> with single queue ?
[Mooney, Sean K] I would be interested in seeing this also if anyone has data to share.
> 
> Darrell
> 
> 
> On 6/16/17, 1:56 AM, "ovs-discuss-bounces at openvswitch.org on behalf of
> Gray, Mark D" <ovs-discuss-bounces at openvswitch.org on behalf of
> mark.d.gray at intel.com> wrote:
> 
>     Hi Avi,
> 
>     The other option is to use virtio-use
> (https://urldefense.proofpoint.com/v2/url?u=http-
> 3A__dpdk.org_doc_guides_howto_virtio-5Fuser-5Ffor-5Fcontainer-
> 5Fnetworking.html&d=DwICAg&c=uilaK90D4TOVoH58JNXRgQ&r=BVhFA09CGX7JQ5Ih-
> uZnsw&m=_7l_cdKorhow4zRqAu5lnTmzv9Etgn5TX7D6P0pqP8c&s=ThmUVGZC2M1LBAIhn
> vs-5OiSZz7ywpez2Qj70BrQjoM&e= ) which gives dpdk-like performance to a
> dpdk application running in a container. The configuration for ovs-dpdk
> has not been documented but it is possible to use (as a vdev).
> 
>     Also, I have dropped the dpdk-ovs at lists.01.org mail address as this
> is for the discontinued ovdk project.
> 
>     Mark
> 
>     > -----Original Message-----
>     > From: Dpdk-ovs [mailto:dpdk-ovs-bounces at lists.01.org] On Behalf
> Of
>     > Mooney, Sean K
>     > Sent: Thursday, June 15, 2017 12:33 PM
>     > To: Avi Cohen (A) <avi.cohen at huawei.com>; dpdk-ovs at lists.01.org;
>     > users at dpdk.org; ovs-discuss at openvswitch.org
>     > Subject: Re: [Dpdk-ovs] OVS-DPDK - Very poor performance when
>     > connected to namespace/container
>     >
>     >
>     >
>     > > -----Original Message-----
>     > > From: Avi Cohen (A) [mailto:avi.cohen at huawei.com]
>     > > Sent: Thursday, June 15, 2017 9:50 AM
>     > > To: Mooney, Sean K <sean.k.mooney at intel.com>; dpdk-
> ovs at lists.01.org;
>     > > users at dpdk.org; ovs-discuss at openvswitch.org
>     > > Subject: RE: OVS-DPDK - Very poor performance when connected to
>     > > namespace/container
>     > >
>     > >
>     > >
>     > > > -----Original Message-----
>     > > > From: Mooney, Sean K [mailto:sean.k.mooney at intel.com]
>     > > > Sent: Thursday, 15 June, 2017 11:24 AM
>     > > > To: Avi Cohen (A); dpdk-ovs at lists.01.org; users at dpdk.org;
> ovs-
>     > > > discuss at openvswitch.org
>     > > > Cc: Mooney, Sean K
>     > > > Subject: RE: OVS-DPDK - Very poor performance when connected
> to
>     > > > namespace/container
>     > > >
>     > > >
>     > > >
>     > > > > -----Original Message-----
>     > > > > From: Dpdk-ovs [mailto:dpdk-ovs-bounces at lists.01.org] On
> Behalf Of
>     > > > > Avi Cohen (A)
>     > > > > Sent: Thursday, June 15, 2017 8:14 AM
>     > > > > To: dpdk-ovs at lists.01.org; users at dpdk.org;
>     > > > > ovs-discuss at openvswitch.org
>     > > > > Subject: [Dpdk-ovs] OVS-DPDK - Very poor performance when
>     > > > > connected to namespace/container
>     > > > >
>     > > > > Hello   All,
>     > > > > I have OVS-DPDK connected to a namespace via veth pair
> device.
>     > > > >
>     > > > > I've got a very poor performance - compared to normal OVS
> (i.e. no
>     > > > > DPDK).
>     > > > > For example - TCP jumbo pkts throughput: normal OVS  ~
> 10Gbps ,
>     > > OVS-
>     > > > > DPDK 1.7 Gbps.
>     > > > >
>     > > > > This can be explained as follows:
>     > > > > veth is implemented in kernel - in OVS-DPDK data is
> transferred
>     > > from
>     > > > > veth to user space while in normal OVS we save this
> transfer
>     > > > [Mooney, Sean K] that is part of the reason, the other reson
> this is
>     > > > slow and The main limiter to scalling adding veth pairs or
> ovs
>     > > > internal port to ovs with dpdk is That these linux kernel
> ports are
>     > > > not processed by the dpdk pmds. They are server by the Ovs-
> vswitchd
>     > > > main thread via a fall back to the non dpdk acclarated netdev
>     > > implementation.
>     > > > >
>     > > > > Is there any other device to connect to namespace ?
> something like
>     > > > > vhost-user ? I understand that vhost-user cannot be used
> for
>     > > > > namespace
>     > > > [Mooney, Sean K] I have been doing some experiments in this
> regard.
>     > > > You should be able to use the tap, pcap or afpacket pmd to
> add a
>     > > > vedv that will improve Performance. I have seen some strange
> issue
>     > > > with
>     > > the
>     > > > tap pmd that cause packet to be drop By the kernel on tx on
> some
>     > > ports
>     > > > but not others so there may be issues with that dirver.
>     > > >
>     > > > Previous experiment with libpcap seemed to work well with ovs
> 2.5
>     > > > but I have not tried it With ovs 2.7/master since the
> introduction
>     > > > of generic vdev support at runtime. Previously vdevs And to
> be
>     > > > allocated
>     > > using the dpdk args.
>     > > >
>     > > > I would try following the af_packet example here
>     > > >
>     > >
>     > https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__github.com_openvswitch_ovs_blob_b132189d8456f38f3ee139f126d68&d=DwI
> CAg&c=uilaK90D4TOVoH58JNXRgQ&r=BVhFA09CGX7JQ5Ih-
> uZnsw&m=_7l_cdKorhow4zRqAu5lnTmzv9Etgn5TX7D6P0pqP8c&s=REyqxTB8Gd9BnEtet
> H_Aul0OgyyGK0DFhKl3tFGzOGI&e=
>     > 0
>     > > > 9 01a9ee9a8/Documentation/howto/dpdk.rst#vdev-support
>     > > >
>     > > [Avi Cohen (A)]
>     > > Thank you Mooney, Sean K
>     > > I already tried to connect the namespace with a tap device (see
> 1 & 2
>     > > below)  - and got the worst performance  for some reason the
> packet
>     > > is cut to default MTU inside the  OVS-DPDK which transmit the
> packet
>     > > to its peer. - although all interfaces MTU were set to 9000.
>     > >
>     > >  1. ovs-vsctl add-port $BRIDGE tap1 -- set Interface tap1
>     > > type=internal
>     > >
>     > >  2. ip link set tap1 netns ns1 // attach it to namespace
>     > [Mooney, Sean K] this is not using the dpdk tap pmd , internal
> port and veth
>     > ports If added to ovs will not be accelerated by dpdk unless you
> use a vdev to
>     > attach them.
>     > >
>     > > I'm looking at your link to create a virtual PMD with vdev
> support - I
>     > > see there a creation of a virtual PMD device , but I'm not sure
> how
>     > > this is connected to the namespace ?  what device should I
> assign to
>     > > the namespace ?
>     > [Mooney, Sean K]
>     > You would use it as follows
>     >
>     > ip tuntap add dev tap1 mode tap
>     >
>     > ovs-vsctl add-port br0 tap1 -- set Interface tap1 type=dpdk \
>     > options:dpdk-devargs=eth_af_packet0,iface=tap1
>     >
>     > ip link set tap1 netns ns1
>     >
>     > ip netns exec ns1 ifconfig 192.168.1.1/24 up
>     >
>     > in general though if you are using ovs-dpdk you should avoid
> using network
>     > namespace and the kernel where possible but the above should
> improve
>     > you performance. One caveat, the amount of vdev+phyical
> interfaces is
>     > limited by how dpdk is compiled by default to 32 devices but it
> can be
>     > increased to 256 if required.
>     >
>     > >
>     > > Best Regards
>     > > avi
>     > >
>     > > > if you happen to be investigating this for use with openstack
>     > > > routers we Are currently working on a way to remove the use
> of
>     > > > namespace entirely for dvr when using The default neutron
> agent and
>     > > > sdn controllers such as ovn already provide that
> functionality.
>     > > > >
>     > > > > Best Regards
>     > > > > avi
>     > > > > _______________________________________________
>     > > > > Dpdk-ovs mailing list
>     > > > > Dpdk-ovs at lists.01.org
>     > > > > https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__lists.01.org_mailman_listinfo_dpdk-
> 2Dovs&d=DwICAg&c=uilaK90D4TOVoH58JNXRgQ&r=BVhFA09CGX7JQ5Ih-
> uZnsw&m=_7l_cdKorhow4zRqAu5lnTmzv9Etgn5TX7D6P0pqP8c&s=ACWRjXvbu0MKa41bi
> 9F6bBW3Srw-WghpVzyDs-5oSFc&e=
>     > _______________________________________________
>     > Dpdk-ovs mailing list
>     > Dpdk-ovs at lists.01.org
>     > https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__lists.01.org_mailman_listinfo_dpdk-
> 2Dovs&d=DwICAg&c=uilaK90D4TOVoH58JNXRgQ&r=BVhFA09CGX7JQ5Ih-
> uZnsw&m=_7l_cdKorhow4zRqAu5lnTmzv9Etgn5TX7D6P0pqP8c&s=ACWRjXvbu0MKa41bi
> 9F6bBW3Srw-WghpVzyDs-5oSFc&e=
>     _______________________________________________
>     discuss mailing list
>     discuss at openvswitch.org
>     https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__mail.openvswitch.org_mailman_listinfo_ovs-
> 2Ddiscuss&d=DwICAg&c=uilaK90D4TOVoH58JNXRgQ&r=BVhFA09CGX7JQ5Ih-
> uZnsw&m=_7l_cdKorhow4zRqAu5lnTmzv9Etgn5TX7D6P0pqP8c&s=5dbke1-
> uxXxS5IYomkpMMPVvbXG9uXZthWdONHRQapo&e=
> 



More information about the discuss mailing list