[ovirt-users] OVN Provider setup issues

[Lance Richardson]

> From: "Andrea Fagiani" <andrea.fagiani at immobiliare.it>
> To: "Dan Kenigsberg" <danken at redhat.com>
> Cc: users at ovirt.org, "Lance Richardson" <lrichard at redhat.com>, mmirecki at redhat.com
> Sent: Wednesday, November 16, 2016 12:24:15 PM
> Subject: Re: [ovirt-users] OVN Provider setup issues
> 
> On 16/11/2016 17:23, Dan Kenigsberg wrote:
> > On Tue, Nov 08, 2016 at 09:21:13AM +0100, Andrea Fagiani wrote:
> >> Hi all,
> >>
> >> I've been messing around with the ovirt-ovn-provider [1] and I've run into
> >> some issues during the initial setup.
> >>
> >> I have a 5-node cluster (running the hosted-engine VA), LEGACY virtual
> >> switch; this test was done on a single host. Following the instructions
> >> from
> >> the aforementioned blog post, I have downloaded the ovirt-provider-ovn and
> >> ovirt-provider-ovn-driver rpms, and built the rpm packages for:
> >>
> >> - openvswitch (2.6.90)
> >> - openvswitch-ovn-common
> >> - openvswitch-ovn-host
> >> - openvswitch-ovn-central
> >> - python-openvswitch
> >>
> >> I set up a dedicated VM for the OVN controller, installed ovs and
> >> ovn-central, started the ovn-northd and ovirt-provider-ovn services. So
> >> far
> >> so good. I then moved on to the oVirt host and installed the above
> >> packages
> >> (minus ovn-central) as well as the ovirt-provider-ovn-driver provided,
> >> started the ovn-controller service and ran
> >>
> >> # vdsm-tool ovn-config <ovn controller IP> <host management IP>
> >>
> >> Executing the suggested checks I noticed that something didn't quite go as
> >> planned. Below is the /var/log/openvswitch/ovn-controller.log from the
> >> host
> >> machine. There are no firewalls involved (not even on the servers) and I
> >> also tried disabling SELinux but to no avail.
> >>
> >> Any ideas?
> >>
> >> Thanks,
> >> Andrea
> >>
> >> [1] http://www.ovirt.org/blog/2016/11/ovirt-provider-ovn/
> >>
> >>
> >> 2016-11-07T14:22:09.552Z|00001|vlog|INFO|opened log file
> >> /var/log/openvswitch/ovn-controller.log
> >> 2016-11-07T14:22:09.553Z|00002|reconnect|INFO|unix:/var/run/openvswitch/db.sock:
> >> connecting...
> >> 2016-11-07T14:22:09.553Z|00003|reconnect|INFO|unix:/var/run/openvswitch/db.sock:
> >> connected
> >> 2016-11-07T14:22:09.555Z|00004|reconnect|INFO|tcp:10.100.248.11:6642:
> >> connecting...
> >> 2016-11-07T14:22:09.555Z|00005|reconnect|INFO|tcp:10.100.248.11:6642:
> >> connected
> >> 2016-11-07T14:22:09.556Z|00006|ofctrl|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connecting to switch
> >> 2016-11-07T14:22:09.556Z|00007|rconn|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connecting...
> >> 2016-11-07T14:22:09.557Z|00008|pinctrl|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connecting to switch
> >> 2016-11-07T14:22:09.557Z|00009|rconn|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connecting...
> >> 2016-11-07T14:22:09.557Z|00010|rconn|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connected
> >> 2016-11-07T14:22:09.557Z|00011|rconn|INFO|unix:/var/run/openvswitch/br-int.mgmt:
> >> connected
> >> 2016-11-07T14:22:09.558Z|00012|ofctrl|INFO|OpenFlow error: OFPT_ERROR
> >> (OF1.3) (xid=0x9): OFPBMC_BAD_FIELD
> >> OFPT_FLOW_MOD (OF1.3) (xid=0x9):
> >> (***truncated to 64 bytes from 240***)
> >> 00000000  04 0e 00 f0 00 00 00 09-00 00 00 00 00 00 00 00
> >> |................|
> >> 00000010  00 00 00 00 00 00 00 00-22 00 00 00 00 00 00 00
> >> |........".......|
> >> 00000020  ff ff ff ff ff ff ff ff-ff ff ff ff 00 00 00 00
> >> |................|
> >> 00000030  00 01 00 04 00 00 00 00-00 04 00 b8 00 00 00 00
> >> |................|
> > Andrea, could you tell (mostly Lance) which kernel version are you
> > using?
> Here is the yum info output for the kernel package on the offending host:
> 
> Installed Packages
> Name      : kernel
> Arch        : x86_64
> Version   : 3.10.0
> Release   : 327.36.3.el7
> 
> Andrea
> 

OK, the 327 kernel did not support conntrack and cannot be used for OVN.

RHEL 7.3 or newer is the minimum requirement for OVN.

   Lance