* Re: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup [not found] <OF9062862D.67700483-ON65257F4A.004D1715-65257F4A.004D1738@LocalDomain> @ 2016-02-04 14:54 ` Abhijeet Karve 2016-02-04 17:37 ` Chandran, Sugesh 0 siblings, 1 reply; 3+ messages in thread From: Abhijeet Karve @ 2016-02-04 14:54 UTC (permalink / raw) To: przemyslaw.czesnowicz; +Cc: dev, discuss Hi All, The issue which we are facing as described in previous threads thats beccause of seting up ovs+dpdk with igb_uio driver instead of vfio_pci? Would appriciate if get any suggestions on this. Thanks & Regards Abhijeet Karve To: przemyslaw.czesnowicz@intel.com From: Abhijeet Karve Date: 01/30/2016 07:32PM Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Subject: Fw: RE: [dpdk-dev] DPDK vhostuser with vxlan Hi przemek, We have setup vxlan tunnel between our two compute nodes, Can see the traafic in vxlan port on br-tun of source instance's compute node. We are in same situation which is being described in below thread, i looked dev mailing archieves for it but seems no one has responded it. http://comments.gmane.org/gmane.linux.network.openvswitch.general/9878 Would be really appriciate if provide us any suggestions on it. Thanks & Regards Abhijeet Karve -----Forwarded by on 01/30/2016 07:24PM ----- ======================= To: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> From: Abhijeet Karve/AHD/TCS@TCS Date: 01/27/2016 09:52PM Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Inter-VM communication & IP allocation through DHCP issue ======================= Hi Przemek, Thanks for the quick response. Now able to get the DHCP ip's for 2 vhostuser instances and able to ping each other. Isssue was a bug in cirros 0.3.0 images which we were using in openstack after using 0.3.1 image as given in the URL(https://www.redhat.com/archives/rhos-list/2013-August/msg00032.html), able to get the IP's in vhostuser VM instances. As per our understanding, Packet flow across DPDK datapath will be like vhostuser ports are connected to the br-int bridge & same is being patched to the br-dpdk bridge where in our physical network (NIC) is connected with dpdk0 port. So for testing the flow we have to connect that physical network(NIC) with external packet generator (e.g - ixia, iperf) & run the testpmd application in the vhostuser VM, right? Does it required to add any flows/efforts in bridge configurations(either br-int or br-dpdk)? Thanks & Regards Abhijeet Karve From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Date: 01/27/2016 05:11 PM Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Inter-VM communication & IP allocation through DHCP issue Hi Abhijeet, It seems you are almost there! When booting the VM’s do you request hugepage memory for them (by setting hw:mem_page_size=large in flavor extra_spec)? If not then please do, if yes then please look into libvirt logfiles for the VM’s (in /var/log/libvirt/qemu/instance-xxx), I think there could be a clue. Regards Przemek From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] Sent: Monday, January 25, 2016 6:13 PM To: Czesnowicz, Przemyslaw Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Inter-VM communication & IP allocation through DHCP issue Hi Przemek, Thank you for your response, It really provided us breakthrough. After setting up DPDK on compute node for stable/kilo, We are trying to set up Openstack stable/liberty all-in-one setup, At present we are not able to get the IP allocation for the vhost type instances through DHCP. Also we tried assigning IP's manually to them but the inter-VM communication also not happening, #neutron agent-list root@nfv-dpdk-devstack:/etc/neutron# neutron agent-list +--------------------------------------+--------------------+-------------------+-------+----------------+---------------------------+ | id | agent_type | host | alive | admin_state_up | binary | +--------------------------------------+--------------------+-------------------+-------+----------------+---------------------------+ | 3b29e93c-3a25-4f7d-bf6c-6bb309db5ec0 | DPDK OVS Agent | nfv-dpdk-devstack | :-) | True | neutron-openvswitch-agent | | 62593b2c-c10f-4d93-8551-c46ce24895a6 | L3 agent | nfv-dpdk-devstack | :-) | True | neutron-l3-agent | | 7cb97af9-cc20-41f8-90fb-aba97d39dfbd | DHCP agent | nfv-dpdk-devstack | :-) | True | neutron-dhcp-agent | | b613c654-99b7-437e-9317-20fa651a1310 | Linux bridge agent | nfv-dpdk-devstack | :-) | True | neutron-linuxbridge-agent | | c2dd0384-6517-4b44-9c25-0d2825d23f57 | Metadata agent | nfv-dpdk-devstack | :-) | True | neutron-metadata-agent | | f23dde40-7dc0-4f20-8b3e-eb90ddb15e49 | Open vSwitch agent | nfv-dpdk-devstack | xxx | True | neutron-openvswitch-agent | +--------------------------------------+--------------------+-------------------+-------+----------------+---------------------------+ ovs-vsctl show output# -------------------------------------------------------- Bridge br-dpdk Port br-dpdk Interface br-dpdk type: internal Port phy-br-dpdk Interface phy-br-dpdk type: patch options: {peer=int-br-dpdk} Bridge br-int fail_mode: secure Port "vhufa41e799-f2" tag: 5 Interface "vhufa41e799-f2" type: dpdkvhostuser Port int-br-dpdk Interface int-br-dpdk type: patch options: {peer=phy-br-dpdk} Port "tap4e19f8e1-59" tag: 5 Interface "tap4e19f8e1-59" type: internal Port "vhu05734c49-3b" tag: 5 Interface "vhu05734c49-3b" type: dpdkvhostuser Port "vhu10c06b4d-84" tag: 5 Interface "vhu10c06b4d-84" type: dpdkvhostuser Port patch-tun Interface patch-tun type: patch options: {peer=patch-int} Port "vhue169c581-ef" tag: 5 Interface "vhue169c581-ef" type: dpdkvhostuser Port br-int Interface br-int type: internal Bridge br-tun fail_mode: secure Port br-tun Interface br-tun type: internal error: "could not open network device br-tun (Invalid argument)" Port patch-int Interface patch-int type: patch options: {peer=patch-tun} ovs_version: "2.4.0" -------------------------------------------------------- ovs-ofctl dump-flows br-int# -------------------------------------------------------- root@nfv-dpdk-devstack:/etc/neutron# ovs-ofctl dump-flows br-int NXST_FLOW reply (xid=0x4): cookie=0xaaa002bb2bcf827b, duration=2410.012s, table=0, n_packets=0, n_bytes=0, idle_age=2410, priority=10,icmp6,in_port=43,icmp_type=136 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2409.480s, table=0, n_packets=0, n_bytes=0, idle_age=2409, priority=10,icmp6,in_port=44,icmp_type=136 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.704s, table=0, n_packets=0, n_bytes=0, idle_age=2408, priority=10,icmp6,in_port=45,icmp_type=136 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.155s, table=0, n_packets=0, n_bytes=0, idle_age=2408, priority=10,icmp6,in_port=42,icmp_type=136 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2409.858s, table=0, n_packets=0, n_bytes=0, idle_age=2409, priority=10,arp,in_port=43 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2409.314s, table=0, n_packets=0, n_bytes=0, idle_age=2409, priority=10,arp,in_port=44 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.564s, table=0, n_packets=0, n_bytes=0, idle_age=2408, priority=10,arp,in_port=45 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.019s, table=0, n_packets=0, n_bytes=0, idle_age=2408, priority=10,arp,in_port=42 actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2411.538s, table=0, n_packets=0, n_bytes=0, idle_age=2411, priority=3,in_port=1,dl_vlan=346 actions=mod_vlan_vid:5,NORMAL cookie=0xaaa002bb2bcf827b, duration=2415.038s, table=0, n_packets=0, n_bytes=0, idle_age=2415, priority=2,in_port=1 actions=drop cookie=0xaaa002bb2bcf827b, duration=2416.148s, table=0, n_packets=0, n_bytes=0, idle_age=2416, priority=0 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2416.059s, table=23, n_packets=0, n_bytes=0, idle_age=2416, priority=0 actions=drop cookie=0xaaa002bb2bcf827b, duration=2410.101s, table=24, n_packets=0, n_bytes=0, idle_age=2410, priority=2,icmp6,in_port=43,icmp_type=136,nd_target=fe80::f816:3eff:fe81:da61 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.571s, table=24, n_packets=0, n_bytes=0, idle_age=2409, priority=2,icmp6,in_port=44,icmp_type=136,nd_target=fe80::f816:3eff:fe73:254 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.775s, table=24, n_packets=0, n_bytes=0, idle_age=2408, priority=2,icmp6,in_port=45,icmp_type=136,nd_target=fe80::f816:3eff:fe88:5cc actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.231s, table=24, n_packets=0, n_bytes=0, idle_age=2408, priority=2,icmp6,in_port=42,icmp_type=136,nd_target=fe80::f816:3eff:fe86:f5f7 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.930s, table=24, n_packets=0, n_bytes=0, idle_age=2409, priority=2,arp,in_port=43,arp_spa=20.20.20.14 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.389s, table=24, n_packets=0, n_bytes=0, idle_age=2409, priority=2,arp,in_port=44,arp_spa=20.20.20.16 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.633s, table=24, n_packets=0, n_bytes=0, idle_age=2408, priority=2,arp,in_port=45,arp_spa=20.20.20.17 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.085s, table=24, n_packets=0, n_bytes=0, idle_age=2408, priority=2,arp,in_port=42,arp_spa=20.20.20.13 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2415.974s, table=24, n_packets=0, n_bytes=0, idle_age=2415, priority=0 actions=drop root@nfv-dpdk-devstack:/etc/neutron# -------------------------------------------------------- Also attaching Neutron-server, nova-compute & nova-scheduler logs. It will be really great for us if get any hint to overcome out of this Inter-VM & DHCP communication issue, Thanks & Regards Abhijeet Karve From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Date: 01/04/2016 07:54 PM Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Getting memory backing issues with qemu parameter passing You should be able to clone networking-ovs-dpdk, switch to kilo branch, and run python setup.py install in the root of networking-ovs-dpdk, that should install agent and mech driver. Then you would need to enable mech driver (ovsdpdk) on the controller in the /etc/neutron/plugins/ml2/ml2_conf.ini And run the right agent on the computes (networking-ovs-dpdk-agent). There should be pip packeges of networking-ovs-dpdk available shortly, I\x0f’ll let you know when that happens. Przemek From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] Sent: Thursday, December 24, 2015 6:42 PM To: Czesnowicz, Przemyslaw Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Getting memory backing issues with qemu parameter passing Hi Przemek, Thank you so much for your quick response. The guide(https://github.com/openstack/networking-ovs-dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst) which you have suggested that is for openstack vhost user installations with devstack. Can't we have any reference for including ovs-dpdk mechanisam driver for openstack Ubuntu distribution which we are following for compute+controller node setup?" We are facing below listed issues With the current approach of setting up openstack kilo interactively + replacing ovs with ovs-dpdk enabled and Instance creation in openstack with passing that instance id to QEMU command line which further passes the vhost-user sockets to instances for enabling the DPDK libraries in it. 1. Created a flavor m1.hugepages which is backed by hugepage memory, unable to spawn instance with this flavor \x0f– Getting a issue like: No matching hugetlbfs for the number of hugepages assigned to the flavor. 2. Passing socket info to instances via qemu manually and instnaces created are not persistent. Now as you suggested, we are looking in enabling ovsdpdk ml2 mechanism driver and agent all of that in our openstack ubuntu distribution. Would be really appriciate if get any help or ref with explanation. We are using compute + controller node setup and we are using following software platform on compute node: _____________ Openstack: Kilo Distribution: Ubuntu 14.04 OVS Version: 2.4.0 DPDK 2.0.0 _____________ Thanks, Abhijeet Karve From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Date: 12/17/2015 06:32 PM Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Successfully setup DPDK OVS with vhostuser I haven\x0f’t tried that approach not sure if that would work, it seems clunky. If you enable ovsdpdk ml2 mechanism driver and agent all of that (add ports to ovs with the right type, pass the sockets to qemu) would be done by OpenStack. Przemek From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] Sent: Thursday, December 17, 2015 12:41 PM To: Czesnowicz, Przemyslaw Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Successfully setup DPDK OVS with vhostuser Hi Przemek, Thank you so much for sharing the ref guide. Would be appreciate if clear one doubt. At present we are setting up openstack kilo interactively and further replacing ovs with ovs-dpdk enabled. Once the above setup done, We are creating instance in openstack and passing that instance id to QEMU command line which further passes the vhost-user sockets to instances, enabling the DPDK libraries in it. Isn't this the correct way of integrating ovs-dpdk with openstack? Thanks & Regards Abhijeet Karve From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> Date: 12/17/2015 05:27 PM Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Successfully setup DPDK OVS with vhostuser HI Abhijeet, For Kilo you need to use ovsdpdk mechanism driver and a matching agent to integrate ovs-dpdk with OpenStack. The guide you are following only talks about running ovs-dpdk not how it should be integrated with OpenStack. Please follow this guide: https://github.com/openstack/networking-ovs-dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst Best regards Przemek From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] Sent: Wednesday, December 16, 2015 9:37 AM To: Czesnowicz, Przemyslaw Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Successfully setup DPDK OVS with vhostuser Hi Przemek, We have configured the accelerated data path between a physical interface to the VM using openvswitch netdev-dpdk with vhost-user support. The VM created with this special data path and vhost library, I am calling as DPDK instance. If assigning ip manually to the newly created Cirros VM instance, We are able to make 2 VM's to communicate on the same compute node. Else it's not associating any ip through DHCP though DHCP is in compute node only. Yes it's a compute + controller node setup and we are using following software platform on compute node: _____________ Openstack: Kilo Distribution: Ubuntu 14.04 OVS Version: 2.4.0 DPDK 2.0.0 _____________ We are following the intel guide https://software.intel.com/en-us/blogs/2015/06/09/building-vhost-user-for-ovs-today-using-dpdk-200 When doing "ovs-vsctl show" in compute node, it shows below output: _____________________________________________ ovs-vsctl show c2ec29a5-992d-4875-8adc-1265c23e0304 Bridge br-ex Port phy-br-ex Interface phy-br-ex type: patch options: {peer=int-br-ex} Port br-ex Interface br-ex type: internal Bridge br-tun fail_mode: secure Port br-tun Interface br-tun type: internal Port patch-int Interface patch-int type: patch options: {peer=patch-tun} Bridge br-int fail_mode: secure Port "qvo0ae19a43-b6" tag: 2 Interface "qvo0ae19a43-b6" Port br-int Interface br-int type: internal Port "qvo31c89856-a2" tag: 1 Interface "qvo31c89856-a2" Port patch-tun Interface patch-tun type: patch options: {peer=patch-int} Port int-br-ex Interface int-br-ex type: patch options: {peer=phy-br-ex} Port "qvo97fef28a-ec" tag: 2 Interface "qvo97fef28a-ec" Bridge br-dpdk Port br-dpdk Interface br-dpdk type: internal Bridge "br0" Port "br0" Interface "br0" type: internal Port "dpdk0" Interface "dpdk0" type: dpdk Port "vhost-user-2" Interface "vhost-user-2" type: dpdkvhostuser Port "vhost-user-0" Interface "vhost-user-0" type: dpdkvhostuser Port "vhost-user-1" Interface "vhost-user-1" type: dpdkvhostuser ovs_version: "2.4.0" root@dpdk:~# _____________________________________________ Open flows output in bridge in compute node are as below: _____________________________________________ root@dpdk:~# ovs-ofctl dump-flows br-tun NXST_FLOW reply (xid=0x4): cookie=0x0, duration=71796.741s, table=0, n_packets=519, n_bytes=33794, idle_age=19982, hard_age=65534, priority=1,in_port=1 actions=resubmit(,2) cookie=0x0, duration=71796.700s, table=0, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0 actions=drop cookie=0x0, duration=71796.649s, table=2, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0,dl_dst=00:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,20) cookie=0x0, duration=71796.610s, table=2, n_packets=519, n_bytes=33794, idle_age=19982, hard_age=65534, priority=0,dl_dst=01:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,22) cookie=0x0, duration=71794.631s, table=3, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=1,tun_id=0x5c actions=mod_vlan_vid:2,resubmit(,10) cookie=0x0, duration=71794.316s, table=3, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=1,tun_id=0x57 actions=mod_vlan_vid:1,resubmit(,10) cookie=0x0, duration=71796.565s, table=3, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0 actions=drop cookie=0x0, duration=71796.522s, table=4, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0 actions=drop cookie=0x0, duration=71796.481s, table=10, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=1 actions=learn(table=20,hard_timeout=300,priority=1,NXM_OF_VLAN_TCI[0..11],NXM_OF_ETH_DST[]=NXM_OF_ETH_SRC[],load:0->NXM_OF_VLAN_TCI[],load:NXM_NX_TUN_ID[]->NXM_NX_TUN_ID[],output:NXM_OF_IN_PORT[]),output:1 cookie=0x0, duration=71796.439s, table=20, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0 actions=resubmit(,22) cookie=0x0, duration=71796.398s, table=22, n_packets=519, n_bytes=33794, idle_age=19982, hard_age=65534, priority=0 actions=drop root@dpdk:~# root@dpdk:~# root@dpdk:~# root@dpdk:~# ovs-ofctl dump-flows br-tun int NXST_FLOW reply (xid=0x4): cookie=0x0, duration=71801.275s, table=0, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=2,in_port=10 actions=drop cookie=0x0, duration=71801.862s, table=0, n_packets=661, n_bytes=48912, idle_age=19981, hard_age=65534, priority=1 actions=NORMAL cookie=0x0, duration=71801.817s, table=23, n_packets=0, n_bytes=0, idle_age=65534, hard_age=65534, priority=0 actions=drop root@dpdk:~# _____________________________________________ Further we don't know what all the network changes(Packet Flow addition) if required for associating IP address through the DHCP. Would be really appreciate if have clarity on DHCP flow establishment. Thanks & Regards Abhijeet Karve From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com>, "Gray, Mark D" <mark.d.gray@intel.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org> Date: 12/15/2015 09:13 PM Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# Successfully setup DPDK OVS with vhostuser Hi Abhijeet, If you answer below questions it will help me understand your problem. What do you mean by DPDK instance? Are you able to communicate with other VM's on the same compute node? Can you check if the DHCP requests arrive on the controller node? (I'm assuming this is at least compute+ controller setup) Best regards Przemek > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Abhijeet Karve > Sent: Tuesday, December 15, 2015 5:56 AM > To: Gray, Mark D > Cc: dev@dpdk.org; discuss@openvswitch.org > Subject: Re: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > Dear All, > > After seting up system boot parameters as shown below, the issue is > resolved now & we are able to successfully setup openvswitch netdev-dpdk > with vhostuser support. > > __________________________________________________________ > _______________________________________________________ > Setup 2 sets of huge pages with different sizes. One for Vhost and another > for Guest VM. > Edit /etc/default/grub. > GRUB_CMDLINE_LINUX="iommu=pt intel_iommu=on hugepagesz=1G > hugepages=10 hugepagesz=2M hugepages=4096" > # update-grub > - Mount the huge pages into different directory. > # sudo mount -t hugetlbfs nodev /mnt/huge_2M -o pagesize=2M > # sudo mount -t hugetlbfs nodev /mnt/huge_1G -o pagesize=1G > __________________________________________________________ > _______________________________________________________ > > At present we are facing an issue in Testing DPDK application on setup. In our > scenario, We have DPDK instance launched on top of the Openstack Kilo > compute node. Not able to assign DHCP IP from controller. > > > Thanks & Regards > Abhijeet Karve > > =====-----=====-----===== > Notice: The information contained in this e-mail message and/or > attachments to it may contain confidential or privileged information. If you > are not the intended recipient, any dissemination, use, review, distribution, > printing or copying of the information contained in this e-mail message > and/or attachments to it are strictly prohibited. If you have received this > communication in error, please notify us by reply e-mail or telephone and > immediately and permanently delete the message and any attachments. > Thank you > From olivier.matz@6wind.com Thu Feb 4 16:03:00 2016 Return-Path: <olivier.matz@6wind.com> Received: from proxy.6wind.com (host.76.145.23.62.rev.coltfrance.com [62.23.145.76]) by dpdk.org (Postfix) with ESMTP id 2B0D62A5F for <dev@dpdk.org>; Thu, 4 Feb 2016 16:03:00 +0100 (CET) Received: from [10.16.0.195] (unknown [10.16.0.195]) by proxy.6wind.com (Postfix) with ESMTP id 7DF612A350; Thu, 4 Feb 2016 16:02:16 +0100 (CET) Message-ID: <56B36815.6030001@6wind.com> Date: Thu, 04 Feb 2016 16:02:45 +0100 From: Olivier MATZ <olivier.matz@6wind.com> User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Icedove/31.7.0 MIME-Version: 1.0 To: David Hunt <david.hunt@intel.com>, dev@dpdk.org References: <1453829155-1366-1-git-send-email-david.hunt@intel.com> <1453829155-1366-3-git-send-email-david.hunt@intel.com> In-Reply-To: <1453829155-1366-3-git-send-email-david.hunt@intel.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [dpdk-dev] [PATCH 2/5] memool: add stack (lifo) based external mempool handler X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK <dev.dpdk.org> List-Unsubscribe: <http://dpdk.org/ml/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://dpdk.org/ml/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <http://dpdk.org/ml/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> X-List-Received-Date: Thu, 04 Feb 2016 15:03:00 -0000 Hi, > [PATCH 2/5] memool: add stack (lifo) based external mempool handler typo in the patch title: memool -> mempool On 01/26/2016 06:25 PM, David Hunt wrote: > adds a simple stack based mempool handler > > Signed-off-by: David Hunt <david.hunt@intel.com> What is the purpose of this mempool handler? Is it an example or is it something that could be useful for dpdk applications? If it's just an example, I think we could move this code in app/test. > --- a/app/test/test_mempool_perf.c > +++ b/app/test/test_mempool_perf.c > @@ -52,7 +52,6 @@ > #include <rte_lcore.h> > #include <rte_atomic.h> > #include <rte_branch_prediction.h> > -#include <rte_ring.h> > #include <rte_mempool.h> > #include <rte_spinlock.h> > #include <rte_malloc.h> Is this change related? > +struct rte_mempool_common_stack { > + /* Spinlock to protect access */ > + rte_spinlock_t sl; > + > + uint32_t size; > + uint32_t len; > + void *objs[]; > + > +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG > +#endif There is nothing inside the #ifdef > +static void * > +common_stack_alloc(struct rte_mempool *mp, > + const char *name, unsigned n, int socket_id, unsigned flags) > +{ > + struct rte_mempool_common_stack *s; > + char stack_name[RTE_RING_NAMESIZE]; > + > + int size = sizeof(*s) + (n+16)*sizeof(void *); > + > + flags = flags; > + > + /* Allocate our local memory structure */ > + snprintf(stack_name, sizeof(stack_name), "%s-common-stack", name); > + s = rte_zmalloc_socket(stack_name, > + size, RTE_CACHE_LINE_SIZE, socket_id); > + if (s == NULL) { > + RTE_LOG(ERR, MEMPOOL, "Cannot allocate stack!\n"); > + return NULL; > + } > + > + /* And the spinlock we use to protect access */ > + rte_spinlock_init(&s->sl); > + > + s->size = n; > + mp->rt_pool = (void *) s; > + mp->handler_idx = rte_get_mempool_handler("stack"); > + > + return (void *) s; > +} The explicit casts could be removed I think. > + > +static int common_stack_put(void *p, void * const *obj_table, > + unsigned n) > +{ > + struct rte_mempool_common_stack *s > + (struct rte_mempool_common_stack *)p; indent issue (same in get() and count()) > + void **cache_objs; > + unsigned index; > + > + /* Acquire lock */ > + rte_spinlock_lock(&s->sl); > + cache_objs = &s->objs[s->len]; > + > + /* Is there sufficient space in the stack ? */ > + if ((s->len + n) > s->size) { > + rte_spinlock_unlock(&s->sl); > + return -ENOENT; > + } I think this cannot happen as there is a check in the get(). I wonder if a rte_panic() wouldn't be better here. Regards, Olivier ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup 2016-02-04 14:54 ` [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup Abhijeet Karve @ 2016-02-04 17:37 ` Chandran, Sugesh 2016-02-05 15:16 ` Abhijeet Karve 0 siblings, 1 reply; 3+ messages in thread From: Chandran, Sugesh @ 2016-02-04 17:37 UTC (permalink / raw) To: Abhijeet Karve, Czesnowicz, Przemyslaw; +Cc: dev, discuss Hi Abhijeet, It looks to me that the arp entries may not populated right for the VxLAN ports in OVS. Can you please refer the debug section in http://openvswitch.org/support/config-cookbooks/userspace-tunneling/ to verify and insert right arp entries in case they are missing ?? Regards _Sugesh > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Abhijeet Karve > Sent: Thursday, February 4, 2016 2:55 PM > To: Czesnowicz, Przemyslaw <przemyslaw.czesnowicz@intel.com> > Cc: dev@dpdk.org; discuss@openvswitch.org > Subject: Re: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with > igb_uio in ovs+dpdk setup > > Hi All, > > The issue which we are facing as described in previous threads thats > beccause of seting up ovs+dpdk with igb_uio driver instead of vfio_pci? > > Would appriciate if get any suggestions on this. > > Thanks & Regards > Abhijeet Karve > > > To: przemyslaw.czesnowicz@intel.com > From: Abhijeet Karve > Date: 01/30/2016 07:32PM > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Subject: Fw: RE: [dpdk-dev] DPDK vhostuser with vxlan > > > Hi przemek, > > > We have setup vxlan tunnel between our two compute nodes, Can see the > traafic in vxlan port on br-tun of source instance's compute node. > > We are in same situation which is being described in below thread, i looked > dev mailing archieves for it but seems no one has responded it. > > > http://comments.gmane.org/gmane.linux.network.openvswitch.general/98 > 78 > > Would be really appriciate if provide us any suggestions on it. > > > > Thanks & Regards > Abhijeet Karve > > -----Forwarded by on 01/30/2016 07:24PM ----- > > ======================= > To: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > From: Abhijeet Karve/AHD/TCS@TCS > Date: 01/27/2016 09:52PM > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > ======================= > Hi Przemek, > > Thanks for the quick response. Now able to get the DHCP ip's for 2 vhostuser > instances and able to ping each other. Isssue was a bug in cirros 0.3.0 images > which we were using in openstack after using 0.3.1 image as given in the > URL(https://www.redhat.com/archives/rhos-list/2013- > August/msg00032.html), able to get the IP's in vhostuser VM instances. > > As per our understanding, Packet flow across DPDK datapath will be like > vhostuser ports are connected to the br-int bridge & same is being patched > to the br-dpdk bridge where in our physical network (NIC) is connected with > dpdk0 port. > > So for testing the flow we have to connect that physical network(NIC) with > external packet generator (e.g - ixia, iperf) & run the testpmd application in > the vhostuser VM, right? > > Does it required to add any flows/efforts in bridge configurations(either br- > int or br-dpdk)? > > > Thanks & Regards > Abhijeet Karve > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 01/27/2016 05:11 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > > > > Hi Abhijeet, > > > It seems you are almost there! > When booting the VM’s do you request hugepage memory for them > (by setting hw:mem_page_size=large in flavor extra_spec)? > If not then please do, if yes then please look into libvirt logfiles for the > VM’s (in /var/log/libvirt/qemu/instance-xxx), I think there could be a > clue. > > > Regards > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Monday, January 25, 2016 6:13 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > > Hi Przemek, > > Thank you for your response, It really provided us breakthrough. > > After setting up DPDK on compute node for stable/kilo, We are trying to set > up Openstack stable/liberty all-in-one setup, At present we are not able to > get the IP allocation for the vhost type instances through DHCP. Also we tried > assigning IP's manually to them but the inter-VM communication also not > happening, > > #neutron agent-list > root@nfv-dpdk-devstack:/etc/neutron# neutron agent-list > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > | id | agent_type | host | alive | admin_state_up > | binary | > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > | 3b29e93c-3a25-4f7d-bf6c-6bb309db5ec0 | DPDK OVS Agent | nfv-dpdk- > devstack | :-) | True | neutron-openvswitch-agent | > | 62593b2c-c10f-4d93-8551-c46ce24895a6 | L3 agent | nfv-dpdk- > devstack | :-) | True | neutron-l3-agent | > | 7cb97af9-cc20-41f8-90fb-aba97d39dfbd | DHCP agent | nfv-dpdk- > devstack | :-) | True | neutron-dhcp-agent | > | b613c654-99b7-437e-9317-20fa651a1310 | Linux bridge agent | nfv-dpdk- > devstack | :-) | True | neutron-linuxbridge-agent | > | c2dd0384-6517-4b44-9c25-0d2825d23f57 | Metadata agent | nfv-dpdk- > devstack | :-) | True | neutron-metadata-agent | > | f23dde40-7dc0-4f20-8b3e-eb90ddb15e49 | Open vSwitch agent | nfv-dpdk- > devstack | xxx | True | neutron-openvswitch-agent | > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > > > ovs-vsctl show output# > -------------------------------------------------------- > Bridge br-dpdk > Port br-dpdk > Interface br-dpdk > type: internal > Port phy-br-dpdk > Interface phy-br-dpdk > type: patch > options: {peer=int-br-dpdk} > Bridge br-int > fail_mode: secure > Port "vhufa41e799-f2" > tag: 5 > Interface "vhufa41e799-f2" > type: dpdkvhostuser > Port int-br-dpdk > Interface int-br-dpdk > type: patch > options: {peer=phy-br-dpdk} > Port "tap4e19f8e1-59" > tag: 5 > Interface "tap4e19f8e1-59" > type: internal > Port "vhu05734c49-3b" > tag: 5 > Interface "vhu05734c49-3b" > type: dpdkvhostuser > Port "vhu10c06b4d-84" > tag: 5 > Interface "vhu10c06b4d-84" > type: dpdkvhostuser > Port patch-tun > Interface patch-tun > type: patch > options: {peer=patch-int} > Port "vhue169c581-ef" > tag: 5 > Interface "vhue169c581-ef" > type: dpdkvhostuser > Port br-int > Interface br-int > type: internal > Bridge br-tun > fail_mode: secure > Port br-tun > Interface br-tun > type: internal > error: "could not open network device br-tun (Invalid argument)" > Port patch-int > Interface patch-int > type: patch > options: {peer=patch-tun} > ovs_version: "2.4.0" > -------------------------------------------------------- > > > ovs-ofctl dump-flows br-int# > -------------------------------------------------------- > root@nfv-dpdk-devstack:/etc/neutron# ovs-ofctl dump-flows br-int > NXST_FLOW reply (xid=0x4): > cookie=0xaaa002bb2bcf827b, duration=2410.012s, table=0, n_packets=0, > n_bytes=0, idle_age=2410, priority=10,icmp6,in_port=43,icmp_type=136 > actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2409.480s, > table=0, n_packets=0, n_bytes=0, idle_age=2409, > priority=10,icmp6,in_port=44,icmp_type=136 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.704s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,icmp6,in_port=45,icmp_type=136 > actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.155s, > table=0, n_packets=0, n_bytes=0, idle_age=2408, > priority=10,icmp6,in_port=42,icmp_type=136 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2409.858s, table=0, n_packets=0, > n_bytes=0, idle_age=2409, priority=10,arp,in_port=43 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2409.314s, table=0, n_packets=0, > n_bytes=0, idle_age=2409, priority=10,arp,in_port=44 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.564s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,arp,in_port=45 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.019s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,arp,in_port=42 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2411.538s, table=0, n_packets=0, > n_bytes=0, idle_age=2411, priority=3,in_port=1,dl_vlan=346 > actions=mod_vlan_vid:5,NORMAL cookie=0xaaa002bb2bcf827b, > duration=2415.038s, table=0, n_packets=0, n_bytes=0, idle_age=2415, > priority=2,in_port=1 actions=drop cookie=0xaaa002bb2bcf827b, > duration=2416.148s, table=0, n_packets=0, n_bytes=0, idle_age=2416, > priority=0 actions=NORMAL cookie=0xaaa002bb2bcf827b, > duration=2416.059s, table=23, n_packets=0, n_bytes=0, idle_age=2416, > priority=0 actions=drop cookie=0xaaa002bb2bcf827b, duration=2410.101s, > table=24, n_packets=0, n_bytes=0, idle_age=2410, > priority=2,icmp6,in_port=43,icmp_type=136,nd_target=fe80::f816:3eff:fe81: > da61 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.571s, > table=24, n_packets=0, n_bytes=0, idle_age=2409, > priority=2,icmp6,in_port=44,icmp_type=136,nd_target=fe80::f816:3eff:fe73: > 254 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.775s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,icmp6,in_port=45,icmp_type=136,nd_target=fe80::f816:3eff:fe88: > 5cc actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.231s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,icmp6,in_port=42,icmp_type=136,nd_target=fe80::f816:3eff:fe86: > f5f7 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.930s, > table=24, n_packets=0, n_bytes=0, idle_age=2409, > priority=2,arp,in_port=43,arp_spa=20.20.20.14 actions=NORMAL > cookie=0xaaa002bb2bcf827b, duration=2409.389s, table=24, n_packets=0, > n_bytes=0, idle_age=2409, priority=2,arp,in_port=44,arp_spa=20.20.20.16 > actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.633s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,arp,in_port=45,arp_spa=20.20.20.17 actions=NORMAL > cookie=0xaaa002bb2bcf827b, duration=2408.085s, table=24, n_packets=0, > n_bytes=0, idle_age=2408, priority=2,arp,in_port=42,arp_spa=20.20.20.13 > actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2415.974s, > table=24, n_packets=0, n_bytes=0, idle_age=2415, priority=0 actions=drop > root@nfv-dpdk-devstack:/etc/neutron# > -------------------------------------------------------- > > > > > > Also attaching Neutron-server, nova-compute & nova-scheduler logs. > > It will be really great for us if get any hint to overcome out of this Inter-VM & > DHCP communication issue, > > > > > Thanks & Regards > Abhijeet Karve > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 01/04/2016 07:54 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Getting memory backing issues with qemu parameter passing > > > > > You should be able to clone networking-ovs-dpdk, switch to kilo branch, and > run python setup.py install in the root of networking-ovs-dpdk, that should > install agent and mech driver. > Then you would need to enable mech driver (ovsdpdk) on the controller in > the /etc/neutron/plugins/ml2/ml2_conf.ini > And run the right agent on the computes (networking-ovs-dpdk-agent). > > > There should be pip packeges of networking-ovs-dpdk available shortly, > I\x0f’ll let you know when that happens. > > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Thursday, December 24, 2015 6:42 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Getting memory backing issues with qemu parameter passing > > Hi Przemek, > > Thank you so much for your quick response. > > The guide(https://github.com/openstack/networking-ovs- > dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst) which you have > suggested that is for openstack vhost user installations with devstack. > Can't we have any reference for including ovs-dpdk mechanisam driver for > openstack Ubuntu distribution which we are following for > compute+controller node setup?" > > We are facing below listed issues With the current approach of setting up > openstack kilo interactively + replacing ovs with ovs-dpdk enabled and > Instance creation in openstack with > passing that instance id to QEMU command line which further passes the > vhost-user sockets to instances for enabling the DPDK libraries in it. > > > 1. Created a flavor m1.hugepages which is backed by hugepage memory, > unable to spawn instance with this flavor \x0f– Getting a issue like: No > matching hugetlbfs for the number of hugepages assigned to the flavor. > 2. Passing socket info to instances via qemu manually and instnaces created > are not persistent. > > Now as you suggested, we are looking in enabling ovsdpdk ml2 mechanism > driver and agent all of that in our openstack ubuntu distribution. > > Would be really appriciate if get any help or ref with explanation. > > We are using compute + controller node setup and we are using following > software platform on compute node: > _____________ > Openstack: Kilo > Distribution: Ubuntu 14.04 > OVS Version: 2.4.0 > DPDK 2.0.0 > _____________ > > Thanks, > Abhijeet Karve > > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 12/17/2015 06:32 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > I haven\x0f’t tried that approach not sure if that would work, it seems > clunky. > > If you enable ovsdpdk ml2 mechanism driver and agent all of that (add ports > to ovs with the right type, pass the sockets to qemu) would be done by > OpenStack. > > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Thursday, December 17, 2015 12:41 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > Hi Przemek, > > Thank you so much for sharing the ref guide. > > Would be appreciate if clear one doubt. > > At present we are setting up openstack kilo interactively and further > replacing ovs with ovs-dpdk enabled. > Once the above setup done, We are creating instance in openstack and > passing that instance id to QEMU command line which further passes the > vhost-user sockets to instances, enabling the DPDK libraries in it. > > Isn't this the correct way of integrating ovs-dpdk with openstack? > > > Thanks & Regards > Abhijeet Karve > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 12/17/2015 05:27 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > > HI Abhijeet, > > For Kilo you need to use ovsdpdk mechanism driver and a matching agent to > integrate ovs-dpdk with OpenStack. > > The guide you are following only talks about running ovs-dpdk not how it > should be integrated with OpenStack. > > Please follow this guide: > https://github.com/openstack/networking-ovs- > dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst > > Best regards > Przemek > > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Wednesday, December 16, 2015 9:37 AM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > Hi Przemek, > > > We have configured the accelerated data path between a physical interface > to the VM using openvswitch netdev-dpdk with vhost-user support. The VM > created with this special data path and vhost library, I am calling as DPDK > instance. > > If assigning ip manually to the newly created Cirros VM instance, We are able > to make 2 VM's to communicate on the same compute node. Else it's not > associating any ip through DHCP though DHCP is in compute node only. > > Yes it's a compute + controller node setup and we are using following > software platform on compute node: > _____________ > Openstack: Kilo > Distribution: Ubuntu 14.04 > OVS Version: 2.4.0 > DPDK 2.0.0 > _____________ > > We are following the intel guide https://software.intel.com/en- > us/blogs/2015/06/09/building-vhost-user-for-ovs-today-using-dpdk-200 > > When doing "ovs-vsctl show" in compute node, it shows below output: > _____________________________________________ > ovs-vsctl show > c2ec29a5-992d-4875-8adc-1265c23e0304 > Bridge br-ex > Port phy-br-ex > Interface phy-br-ex > type: patch > options: {peer=int-br-ex} > Port br-ex > Interface br-ex > type: internal > Bridge br-tun > fail_mode: secure > Port br-tun > Interface br-tun > type: internal > Port patch-int > Interface patch-int > type: patch > options: {peer=patch-tun} > Bridge br-int > fail_mode: secure > Port "qvo0ae19a43-b6" > tag: 2 > Interface "qvo0ae19a43-b6" > Port br-int > Interface br-int > type: internal > Port "qvo31c89856-a2" > tag: 1 > Interface "qvo31c89856-a2" > Port patch-tun > Interface patch-tun > type: patch > options: {peer=patch-int} > Port int-br-ex > Interface int-br-ex > type: patch > options: {peer=phy-br-ex} > Port "qvo97fef28a-ec" > tag: 2 > Interface "qvo97fef28a-ec" > Bridge br-dpdk > Port br-dpdk > Interface br-dpdk > type: internal > Bridge "br0" > Port "br0" > Interface "br0" > type: internal > Port "dpdk0" > Interface "dpdk0" > type: dpdk > Port "vhost-user-2" > Interface "vhost-user-2" > type: dpdkvhostuser > Port "vhost-user-0" > Interface "vhost-user-0" > type: dpdkvhostuser > Port "vhost-user-1" > Interface "vhost-user-1" > type: dpdkvhostuser > ovs_version: "2.4.0" > root@dpdk:~# > _____________________________________________ > > Open flows output in bridge in compute node are as below: > _____________________________________________ > root@dpdk:~# ovs-ofctl dump-flows br-tun > NXST_FLOW reply (xid=0x4): > cookie=0x0, duration=71796.741s, table=0, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, priority=1,in_port=1 actions=resubmit(,2) > cookie=0x0, duration=71796.700s, table=0, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.649s, table=2, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, > priority=0,dl_dst=00:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,20) > cookie=0x0, duration=71796.610s, table=2, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, > priority=0,dl_dst=01:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,22) > cookie=0x0, duration=71794.631s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1,tun_id=0x5c > actions=mod_vlan_vid:2,resubmit(,10) > cookie=0x0, duration=71794.316s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1,tun_id=0x57 > actions=mod_vlan_vid:1,resubmit(,10) > cookie=0x0, duration=71796.565s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.522s, table=4, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.481s, table=10, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1 > actions=learn(table=20,hard_timeout=300,priority=1,NXM_OF_VLAN_TCI[0.. > 11],NXM_OF_ETH_DST[]=NXM_OF_ETH_SRC[],load:0- > >NXM_OF_VLAN_TCI[],load:NXM_NX_TUN_ID[]- > >NXM_NX_TUN_ID[],output:NXM_OF_IN_PORT[]),output:1 > cookie=0x0, duration=71796.439s, table=20, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=resubmit(,22) > cookie=0x0, duration=71796.398s, table=22, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, priority=0 actions=drop > root@dpdk:~# > root@dpdk:~# > root@dpdk:~# > root@dpdk:~# ovs-ofctl dump-flows br-tun > int NXST_FLOW reply (xid=0x4): > cookie=0x0, duration=71801.275s, table=0, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=2,in_port=10 actions=drop > cookie=0x0, duration=71801.862s, table=0, n_packets=661, n_bytes=48912, > idle_age=19981, hard_age=65534, priority=1 actions=NORMAL > cookie=0x0, duration=71801.817s, table=23, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > root@dpdk:~# > _____________________________________________ > > > Further we don't know what all the network changes(Packet Flow addition) if > required for associating IP address through the DHCP. > > Would be really appreciate if have clarity on DHCP flow establishment. > > > > Thanks & Regards > Abhijeet Karve > > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com>, "Gray, Mark D" > <mark.d.gray@intel.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org> > Date: 12/15/2015 09:13 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > > > Hi Abhijeet, > > If you answer below questions it will help me understand your problem. > > What do you mean by DPDK instance? > Are you able to communicate with other VM's on the same compute node? > Can you check if the DHCP requests arrive on the controller node? (I'm > assuming this is at least compute+ controller setup) > > Best regards > Przemek > > > -----Original Message----- > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Abhijeet Karve > > Sent: Tuesday, December 15, 2015 5:56 AM > > To: Gray, Mark D > > Cc: dev@dpdk.org; discuss@openvswitch.org > > Subject: Re: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > > Successfully setup DPDK OVS with vhostuser > > > > Dear All, > > > > After seting up system boot parameters as shown below, the issue is > > resolved now & we are able to successfully setup openvswitch netdev- > dpdk > > with vhostuser support. > > > > > __________________________________________________________ > > _______________________________________________________ > > Setup 2 sets of huge pages with different sizes. One for Vhost and another > > for Guest VM. > > Edit /etc/default/grub. > > GRUB_CMDLINE_LINUX="iommu=pt intel_iommu=on > hugepagesz=1G > > hugepages=10 hugepagesz=2M hugepages=4096" > > # update-grub > > - Mount the huge pages into different directory. > > # sudo mount -t hugetlbfs nodev /mnt/huge_2M -o pagesize=2M > > # sudo mount -t hugetlbfs nodev /mnt/huge_1G -o pagesize=1G > > > __________________________________________________________ > > _______________________________________________________ > > > > At present we are facing an issue in Testing DPDK application on setup. In > our > > scenario, We have DPDK instance launched on top of the Openstack Kilo > > compute node. Not able to assign DHCP IP from controller. > > > > > > Thanks & Regards > > Abhijeet Karve > > > > =====-----=====-----===== > > Notice: The information contained in this e-mail message and/or > > attachments to it may contain confidential or privileged information. If you > > are not the intended recipient, any dissemination, use, review, > distribution, > > printing or copying of the information contained in this e-mail message > > and/or attachments to it are strictly prohibited. If you have received this > > communication in error, please notify us by reply e-mail or telephone and > > immediately and permanently delete the message and any attachments. > > Thank you > > > ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup 2016-02-04 17:37 ` Chandran, Sugesh @ 2016-02-05 15:16 ` Abhijeet Karve 0 siblings, 0 replies; 3+ messages in thread From: Abhijeet Karve @ 2016-02-05 15:16 UTC (permalink / raw) To: Chandran, Sugesh, Czesnowicz, Przemyslaw; +Cc: dev, discuss Dear Sugesh, Przemek, Thanks for your extended support. We are done with setting up Open-vSwitch netdev-dpdk with vhost-user in openstack environment. Following changes what we made in our infrastructure. 1. As Vxlan was not been supported in our external bare metal equipment(Gateways), So we replaced vxlan network with vlan network type in our openstack setup. 2. Added arp entries for br-dpdk bridge for entertaining any arp requests. 3. MTU size settings done in our external N/w equipment.. Thank you once again everyone. Thanks & Regards Abhijeet Karve From: "Chandran, Sugesh" <sugesh.chandran@intel.com> To: Abhijeet Karve <abhijeet.karve@tcs.com>, "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" <discuss@openvswitch.org> Date: 02/04/2016 11:08 PM Subject: RE: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup Hi Abhijeet, It looks to me that the arp entries may not populated right for the VxLAN ports in OVS. Can you please refer the debug section in http://openvswitch.org/support/config-cookbooks/userspace-tunneling/ to verify and insert right arp entries in case they are missing ?? Regards _Sugesh > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Abhijeet Karve > Sent: Thursday, February 4, 2016 2:55 PM > To: Czesnowicz, Przemyslaw <przemyslaw.czesnowicz@intel.com> > Cc: dev@dpdk.org; discuss@openvswitch.org > Subject: Re: [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with > igb_uio in ovs+dpdk setup > > Hi All, > > The issue which we are facing as described in previous threads thats > beccause of seting up ovs+dpdk with igb_uio driver instead of vfio_pci? > > Would appriciate if get any suggestions on this. > > Thanks & Regards > Abhijeet Karve > > > To: przemyslaw.czesnowicz@intel.com > From: Abhijeet Karve > Date: 01/30/2016 07:32PM > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Subject: Fw: RE: [dpdk-dev] DPDK vhostuser with vxlan > > > Hi przemek, > > > We have setup vxlan tunnel between our two compute nodes, Can see the > traafic in vxlan port on br-tun of source instance's compute node. > > We are in same situation which is being described in below thread, i looked > dev mailing archieves for it but seems no one has responded it. > > > http://comments.gmane.org/gmane.linux.network.openvswitch.general/98 > 78 > > Would be really appriciate if provide us any suggestions on it. > > > > Thanks & Regards > Abhijeet Karve > > -----Forwarded by on 01/30/2016 07:24PM ----- > > ======================= > To: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > From: Abhijeet Karve/AHD/TCS@TCS > Date: 01/27/2016 09:52PM > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > ======================= > Hi Przemek, > > Thanks for the quick response. Now able to get the DHCP ip's for 2 vhostuser > instances and able to ping each other. Isssue was a bug in cirros 0.3.0 images > which we were using in openstack after using 0.3.1 image as given in the > URL(https://www.redhat.com/archives/rhos-list/2013- > August/msg00032.html), able to get the IP's in vhostuser VM instances. > > As per our understanding, Packet flow across DPDK datapath will be like > vhostuser ports are connected to the br-int bridge & same is being patched > to the br-dpdk bridge where in our physical network (NIC) is connected with > dpdk0 port. > > So for testing the flow we have to connect that physical network(NIC) with > external packet generator (e.g - ixia, iperf) & run the testpmd application in > the vhostuser VM, right? > > Does it required to add any flows/efforts in bridge configurations(either br- > int or br-dpdk)? > > > Thanks & Regards > Abhijeet Karve > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 01/27/2016 05:11 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > > > > Hi Abhijeet, > > > It seems you are almost there! > When booting the VM’s do you request hugepage memory for them > (by setting hw:mem_page_size=large in flavor extra_spec)? > If not then please do, if yes then please look into libvirt logfiles for the > VM’s (in /var/log/libvirt/qemu/instance-xxx), I think there could be a > clue. > > > Regards > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Monday, January 25, 2016 6:13 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Inter-VM communication & IP allocation through DHCP issue > > Hi Przemek, > > Thank you for your response, It really provided us breakthrough. > > After setting up DPDK on compute node for stable/kilo, We are trying to set > up Openstack stable/liberty all-in-one setup, At present we are not able to > get the IP allocation for the vhost type instances through DHCP. Also we tried > assigning IP's manually to them but the inter-VM communication also not > happening, > > #neutron agent-list > root@nfv-dpdk-devstack:/etc/neutron# neutron agent-list > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > | id | agent_type | host | alive | admin_state_up > | binary | > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > | 3b29e93c-3a25-4f7d-bf6c-6bb309db5ec0 | DPDK OVS Agent | nfv-dpdk- > devstack | :-) | True | neutron-openvswitch-agent | > | 62593b2c-c10f-4d93-8551-c46ce24895a6 | L3 agent | nfv-dpdk- > devstack | :-) | True | neutron-l3-agent | > | 7cb97af9-cc20-41f8-90fb-aba97d39dfbd | DHCP agent | nfv-dpdk- > devstack | :-) | True | neutron-dhcp-agent | > | b613c654-99b7-437e-9317-20fa651a1310 | Linux bridge agent | nfv-dpdk- > devstack | :-) | True | neutron-linuxbridge-agent | > | c2dd0384-6517-4b44-9c25-0d2825d23f57 | Metadata agent | nfv-dpdk- > devstack | :-) | True | neutron-metadata-agent | > | f23dde40-7dc0-4f20-8b3e-eb90ddb15e49 | Open vSwitch agent | nfv-dpdk- > devstack | xxx | True | neutron-openvswitch-agent | > +--------------------------------------+--------------------+-------------------+-------+-- > --------------+---------------------------+ > > > ovs-vsctl show output# > -------------------------------------------------------- > Bridge br-dpdk > Port br-dpdk > Interface br-dpdk > type: internal > Port phy-br-dpdk > Interface phy-br-dpdk > type: patch > options: {peer=int-br-dpdk} > Bridge br-int > fail_mode: secure > Port "vhufa41e799-f2" > tag: 5 > Interface "vhufa41e799-f2" > type: dpdkvhostuser > Port int-br-dpdk > Interface int-br-dpdk > type: patch > options: {peer=phy-br-dpdk} > Port "tap4e19f8e1-59" > tag: 5 > Interface "tap4e19f8e1-59" > type: internal > Port "vhu05734c49-3b" > tag: 5 > Interface "vhu05734c49-3b" > type: dpdkvhostuser > Port "vhu10c06b4d-84" > tag: 5 > Interface "vhu10c06b4d-84" > type: dpdkvhostuser > Port patch-tun > Interface patch-tun > type: patch > options: {peer=patch-int} > Port "vhue169c581-ef" > tag: 5 > Interface "vhue169c581-ef" > type: dpdkvhostuser > Port br-int > Interface br-int > type: internal > Bridge br-tun > fail_mode: secure > Port br-tun > Interface br-tun > type: internal > error: "could not open network device br-tun (Invalid argument)" > Port patch-int > Interface patch-int > type: patch > options: {peer=patch-tun} > ovs_version: "2.4.0" > -------------------------------------------------------- > > > ovs-ofctl dump-flows br-int# > -------------------------------------------------------- > root@nfv-dpdk-devstack:/etc/neutron# ovs-ofctl dump-flows br-int > NXST_FLOW reply (xid=0x4): > cookie=0xaaa002bb2bcf827b, duration=2410.012s, table=0, n_packets=0, > n_bytes=0, idle_age=2410, priority=10,icmp6,in_port=43,icmp_type=136 > actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2409.480s, > table=0, n_packets=0, n_bytes=0, idle_age=2409, > priority=10,icmp6,in_port=44,icmp_type=136 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.704s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,icmp6,in_port=45,icmp_type=136 > actions=resubmit(,24) cookie=0xaaa002bb2bcf827b, duration=2408.155s, > table=0, n_packets=0, n_bytes=0, idle_age=2408, > priority=10,icmp6,in_port=42,icmp_type=136 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2409.858s, table=0, n_packets=0, > n_bytes=0, idle_age=2409, priority=10,arp,in_port=43 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2409.314s, table=0, n_packets=0, > n_bytes=0, idle_age=2409, priority=10,arp,in_port=44 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.564s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,arp,in_port=45 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2408.019s, table=0, n_packets=0, > n_bytes=0, idle_age=2408, priority=10,arp,in_port=42 actions=resubmit(,24) > cookie=0xaaa002bb2bcf827b, duration=2411.538s, table=0, n_packets=0, > n_bytes=0, idle_age=2411, priority=3,in_port=1,dl_vlan=346 > actions=mod_vlan_vid:5,NORMAL cookie=0xaaa002bb2bcf827b, > duration=2415.038s, table=0, n_packets=0, n_bytes=0, idle_age=2415, > priority=2,in_port=1 actions=drop cookie=0xaaa002bb2bcf827b, > duration=2416.148s, table=0, n_packets=0, n_bytes=0, idle_age=2416, > priority=0 actions=NORMAL cookie=0xaaa002bb2bcf827b, > duration=2416.059s, table=23, n_packets=0, n_bytes=0, idle_age=2416, > priority=0 actions=drop cookie=0xaaa002bb2bcf827b, duration=2410.101s, > table=24, n_packets=0, n_bytes=0, idle_age=2410, > priority=2,icmp6,in_port=43,icmp_type=136,nd_target=fe80::f816:3eff:fe81: > da61 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.571s, > table=24, n_packets=0, n_bytes=0, idle_age=2409, > priority=2,icmp6,in_port=44,icmp_type=136,nd_target=fe80::f816:3eff:fe73: > 254 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.775s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,icmp6,in_port=45,icmp_type=136,nd_target=fe80::f816:3eff:fe88: > 5cc actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.231s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,icmp6,in_port=42,icmp_type=136,nd_target=fe80::f816:3eff:fe86: > f5f7 actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2409.930s, > table=24, n_packets=0, n_bytes=0, idle_age=2409, > priority=2,arp,in_port=43,arp_spa=20.20.20.14 actions=NORMAL > cookie=0xaaa002bb2bcf827b, duration=2409.389s, table=24, n_packets=0, > n_bytes=0, idle_age=2409, priority=2,arp,in_port=44,arp_spa=20.20.20.16 > actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2408.633s, > table=24, n_packets=0, n_bytes=0, idle_age=2408, > priority=2,arp,in_port=45,arp_spa=20.20.20.17 actions=NORMAL > cookie=0xaaa002bb2bcf827b, duration=2408.085s, table=24, n_packets=0, > n_bytes=0, idle_age=2408, priority=2,arp,in_port=42,arp_spa=20.20.20.13 > actions=NORMAL cookie=0xaaa002bb2bcf827b, duration=2415.974s, > table=24, n_packets=0, n_bytes=0, idle_age=2415, priority=0 actions=drop > root@nfv-dpdk-devstack:/etc/neutron# > -------------------------------------------------------- > > > > > > Also attaching Neutron-server, nova-compute & nova-scheduler logs. > > It will be really great for us if get any hint to overcome out of this Inter-VM & > DHCP communication issue, > > > > > Thanks & Regards > Abhijeet Karve > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 01/04/2016 07:54 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Getting memory backing issues with qemu parameter passing > > > > > You should be able to clone networking-ovs-dpdk, switch to kilo branch, and > run python setup.py install in the root of networking-ovs-dpdk, that should > install agent and mech driver. > Then you would need to enable mech driver (ovsdpdk) on the controller in > the /etc/neutron/plugins/ml2/ml2_conf.ini > And run the right agent on the computes (networking-ovs-dpdk-agent). > > > There should be pip packeges of networking-ovs-dpdk available shortly, > I\x0f’ll let you know when that happens. > > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Thursday, December 24, 2015 6:42 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Getting memory backing issues with qemu parameter passing > > Hi Przemek, > > Thank you so much for your quick response. > > The guide(https://github.com/openstack/networking-ovs- > dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst) which you have > suggested that is for openstack vhost user installations with devstack. > Can't we have any reference for including ovs-dpdk mechanisam driver for > openstack Ubuntu distribution which we are following for > compute+controller node setup?" > > We are facing below listed issues With the current approach of setting up > openstack kilo interactively + replacing ovs with ovs-dpdk enabled and > Instance creation in openstack with > passing that instance id to QEMU command line which further passes the > vhost-user sockets to instances for enabling the DPDK libraries in it. > > > 1. Created a flavor m1.hugepages which is backed by hugepage memory, > unable to spawn instance with this flavor \x0f– Getting a issue like: No > matching hugetlbfs for the number of hugepages assigned to the flavor. > 2. Passing socket info to instances via qemu manually and instnaces created > are not persistent. > > Now as you suggested, we are looking in enabling ovsdpdk ml2 mechanism > driver and agent all of that in our openstack ubuntu distribution. > > Would be really appriciate if get any help or ref with explanation. > > We are using compute + controller node setup and we are using following > software platform on compute node: > _____________ > Openstack: Kilo > Distribution: Ubuntu 14.04 > OVS Version: 2.4.0 > DPDK 2.0.0 > _____________ > > Thanks, > Abhijeet Karve > > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 12/17/2015 06:32 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > I haven\x0f’t tried that approach not sure if that would work, it seems > clunky. > > If you enable ovsdpdk ml2 mechanism driver and agent all of that (add ports > to ovs with the right type, pass the sockets to qemu) would be done by > OpenStack. > > Przemek > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Thursday, December 17, 2015 12:41 PM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > Hi Przemek, > > Thank you so much for sharing the ref guide. > > Would be appreciate if clear one doubt. > > At present we are setting up openstack kilo interactively and further > replacing ovs with ovs-dpdk enabled. > Once the above setup done, We are creating instance in openstack and > passing that instance id to QEMU command line which further passes the > vhost-user sockets to instances, enabling the DPDK libraries in it. > > Isn't this the correct way of integrating ovs-dpdk with openstack? > > > Thanks & Regards > Abhijeet Karve > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org>, "Gray, Mark D" <mark.d.gray@intel.com> > Date: 12/17/2015 05:27 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > > HI Abhijeet, > > For Kilo you need to use ovsdpdk mechanism driver and a matching agent to > integrate ovs-dpdk with OpenStack. > > The guide you are following only talks about running ovs-dpdk not how it > should be integrated with OpenStack. > > Please follow this guide: > https://github.com/openstack/networking-ovs- > dpdk/blob/stable/kilo/doc/source/getstarted/ubuntu.rst > > Best regards > Przemek > > > From: Abhijeet Karve [mailto:abhijeet.karve@tcs.com] > Sent: Wednesday, December 16, 2015 9:37 AM > To: Czesnowicz, Przemyslaw > Cc: dev@dpdk.org; discuss@openvswitch.org; Gray, Mark D > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > Hi Przemek, > > > We have configured the accelerated data path between a physical interface > to the VM using openvswitch netdev-dpdk with vhost-user support. The VM > created with this special data path and vhost library, I am calling as DPDK > instance. > > If assigning ip manually to the newly created Cirros VM instance, We are able > to make 2 VM's to communicate on the same compute node. Else it's not > associating any ip through DHCP though DHCP is in compute node only. > > Yes it's a compute + controller node setup and we are using following > software platform on compute node: > _____________ > Openstack: Kilo > Distribution: Ubuntu 14.04 > OVS Version: 2.4.0 > DPDK 2.0.0 > _____________ > > We are following the intel guide https://software.intel.com/en- > us/blogs/2015/06/09/building-vhost-user-for-ovs-today-using-dpdk-200 > > When doing "ovs-vsctl show" in compute node, it shows below output: > _____________________________________________ > ovs-vsctl show > c2ec29a5-992d-4875-8adc-1265c23e0304 > Bridge br-ex > Port phy-br-ex > Interface phy-br-ex > type: patch > options: {peer=int-br-ex} > Port br-ex > Interface br-ex > type: internal > Bridge br-tun > fail_mode: secure > Port br-tun > Interface br-tun > type: internal > Port patch-int > Interface patch-int > type: patch > options: {peer=patch-tun} > Bridge br-int > fail_mode: secure > Port "qvo0ae19a43-b6" > tag: 2 > Interface "qvo0ae19a43-b6" > Port br-int > Interface br-int > type: internal > Port "qvo31c89856-a2" > tag: 1 > Interface "qvo31c89856-a2" > Port patch-tun > Interface patch-tun > type: patch > options: {peer=patch-int} > Port int-br-ex > Interface int-br-ex > type: patch > options: {peer=phy-br-ex} > Port "qvo97fef28a-ec" > tag: 2 > Interface "qvo97fef28a-ec" > Bridge br-dpdk > Port br-dpdk > Interface br-dpdk > type: internal > Bridge "br0" > Port "br0" > Interface "br0" > type: internal > Port "dpdk0" > Interface "dpdk0" > type: dpdk > Port "vhost-user-2" > Interface "vhost-user-2" > type: dpdkvhostuser > Port "vhost-user-0" > Interface "vhost-user-0" > type: dpdkvhostuser > Port "vhost-user-1" > Interface "vhost-user-1" > type: dpdkvhostuser > ovs_version: "2.4.0" > root@dpdk:~# > _____________________________________________ > > Open flows output in bridge in compute node are as below: > _____________________________________________ > root@dpdk:~# ovs-ofctl dump-flows br-tun > NXST_FLOW reply (xid=0x4): > cookie=0x0, duration=71796.741s, table=0, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, priority=1,in_port=1 actions=resubmit(,2) > cookie=0x0, duration=71796.700s, table=0, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.649s, table=2, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, > priority=0,dl_dst=00:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,20) > cookie=0x0, duration=71796.610s, table=2, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, > priority=0,dl_dst=01:00:00:00:00:00/01:00:00:00:00:00 actions=resubmit(,22) > cookie=0x0, duration=71794.631s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1,tun_id=0x5c > actions=mod_vlan_vid:2,resubmit(,10) > cookie=0x0, duration=71794.316s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1,tun_id=0x57 > actions=mod_vlan_vid:1,resubmit(,10) > cookie=0x0, duration=71796.565s, table=3, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.522s, table=4, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > cookie=0x0, duration=71796.481s, table=10, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=1 > actions=learn(table=20,hard_timeout=300,priority=1,NXM_OF_VLAN_TCI[0.. > 11],NXM_OF_ETH_DST[]=NXM_OF_ETH_SRC[],load:0- > >NXM_OF_VLAN_TCI[],load:NXM_NX_TUN_ID[]- > >NXM_NX_TUN_ID[],output:NXM_OF_IN_PORT[]),output:1 > cookie=0x0, duration=71796.439s, table=20, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=resubmit(,22) > cookie=0x0, duration=71796.398s, table=22, n_packets=519, n_bytes=33794, > idle_age=19982, hard_age=65534, priority=0 actions=drop > root@dpdk:~# > root@dpdk:~# > root@dpdk:~# > root@dpdk:~# ovs-ofctl dump-flows br-tun > int NXST_FLOW reply (xid=0x4): > cookie=0x0, duration=71801.275s, table=0, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=2,in_port=10 actions=drop > cookie=0x0, duration=71801.862s, table=0, n_packets=661, n_bytes=48912, > idle_age=19981, hard_age=65534, priority=1 actions=NORMAL > cookie=0x0, duration=71801.817s, table=23, n_packets=0, n_bytes=0, > idle_age=65534, hard_age=65534, priority=0 actions=drop > root@dpdk:~# > _____________________________________________ > > > Further we don't know what all the network changes(Packet Flow addition) if > required for associating IP address through the DHCP. > > Would be really appreciate if have clarity on DHCP flow establishment. > > > > Thanks & Regards > Abhijeet Karve > > > > > > From: "Czesnowicz, Przemyslaw" <przemyslaw.czesnowicz@intel.com> > To: Abhijeet Karve <abhijeet.karve@tcs.com>, "Gray, Mark D" > <mark.d.gray@intel.com> > Cc: "dev@dpdk.org" <dev@dpdk.org>, "discuss@openvswitch.org" > <discuss@openvswitch.org> > Date: 12/15/2015 09:13 PM > Subject: RE: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > Successfully setup DPDK OVS with vhostuser > > > > > > > > Hi Abhijeet, > > If you answer below questions it will help me understand your problem. > > What do you mean by DPDK instance? > Are you able to communicate with other VM's on the same compute node? > Can you check if the DHCP requests arrive on the controller node? (I'm > assuming this is at least compute+ controller setup) > > Best regards > Przemek > > > -----Original Message----- > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Abhijeet Karve > > Sent: Tuesday, December 15, 2015 5:56 AM > > To: Gray, Mark D > > Cc: dev@dpdk.org; discuss@openvswitch.org > > Subject: Re: [dpdk-dev] DPDK OVS on Ubuntu 14.04# Issue's Resolved# > > Successfully setup DPDK OVS with vhostuser > > > > Dear All, > > > > After seting up system boot parameters as shown below, the issue is > > resolved now & we are able to successfully setup openvswitch netdev- > dpdk > > with vhostuser support. > > > > > __________________________________________________________ > > _______________________________________________________ > > Setup 2 sets of huge pages with different sizes. One for Vhost and another > > for Guest VM. > > Edit /etc/default/grub. > > GRUB_CMDLINE_LINUX="iommu=pt intel_iommu=on > hugepagesz=1G > > hugepages=10 hugepagesz=2M hugepages=4096" > > # update-grub > > - Mount the huge pages into different directory. > > # sudo mount -t hugetlbfs nodev /mnt/huge_2M -o pagesize=2M > > # sudo mount -t hugetlbfs nodev /mnt/huge_1G -o pagesize=1G > > > __________________________________________________________ > > _______________________________________________________ > > > > At present we are facing an issue in Testing DPDK application on setup. In > our > > scenario, We have DPDK instance launched on top of the Openstack Kilo > > compute node. Not able to assign DHCP IP from controller. > > > > > > Thanks & Regards > > Abhijeet Karve > > > > =====-----=====-----===== > > Notice: The information contained in this e-mail message and/or > > attachments to it may contain confidential or privileged information. If you > > are not the intended recipient, any dissemination, use, review, > distribution, > > printing or copying of the information contained in this e-mail message > > and/or attachments to it are strictly prohibited. If you have received this > > communication in error, please notify us by reply e-mail or telephone and > > immediately and permanently delete the message and any attachments. > > Thank you > > > ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2016-02-05 16:20 UTC | newest] Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- [not found] <OF9062862D.67700483-ON65257F4A.004D1715-65257F4A.004D1738@LocalDomain> 2016-02-04 14:54 ` [dpdk-dev] Fw: RE: DPDK vhostuser with vxlan# Does issue with igb_uio in ovs+dpdk setup Abhijeet Karve 2016-02-04 17:37 ` Chandran, Sugesh 2016-02-05 15:16 ` Abhijeet Karve
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).