Duplicate Address Detection misfire?

Zaphod Beeblebrox zbeeble at gmail.com
Fri Jul 19 01:21:13 UTC 2013


On Sun, Jun 30, 2013 at 10:39 PM, Kevin Day <kevin at your.org> wrote:

>
> On Jun 30, 2013, at 6:48 PM, Zaphod Beeblebrox <zbeeble at gmail.com> wrote:
>
> > I have a FreeBSD 9.1-RELEASE vmware guest running. It is using the
> > "bridged" type of networking with VMWare.  It gets it's IPv4 address from
> > DHCP (successfully) and then fails to initialize IPv6.  The relevant
> > rc.conf is:
> >
> > ipv6_activate_all_interfaces="YES"
> > ifconfig_em0_ipv6="inet6 accept_rtadv"
> > ip6addrctl_verbose="YES"
> >
> > The console output says:
> >
> > em0: DAD detected duplicate IPv6 address fe80:2::20c:29ff:fe0a:3989: NS
> > in/out=2/1, NA in=0
> > em0: DAD complete for fe80:2::20c:29ff:fe0a:3989 - duplicate found
> > em0: manual intervention required
> > em0: possible hardware address duplication deteted, disable IPv6
> >
> > And subsequently, em0's nd6 has "IFDISABLED" in it.
> >
> > With wireshark, I see two ICMPv6 neighbor solicitations that are
> identical
> > --- is this the problem?
> >
> > How do I fix this?
>
> Did you copy this VM and have both copies running at once? If so, it
> assigned the same MAC address to each VM.
>
> VMware is suppose to detect this and ask if you "copied" or "moved" the
> VM, and if you say "copied" it will randomly assign a new MAC to the VM. If
> this didn't happen or if you said "moved" when you actually copied it, just
> go in and delete/re-create the network interface in the VM's settings to
> create a new MAC for it.
>
> If that's not the issue, we'd probably need more details about your
> configuration.
>

To further diagnose, there is only one VM running.  To ensure that there
were no duplicates, I reassigned the MAC address in the VMWare
configuration dialogue.  Additionally, I tried stopping rtadvd on my router
(no effect) and I tried putting the guest on a "host-only network"
(basically isolated it) --- this clears the problem --- both the link-local
and the static address are assigned.

Frustrated, I dumped the windows interface that is bridged to the VMWare
guest.  When it boots, I see the following:

2461    19:24:16.376027000    Vmware_2e:46:fd    Broadcast    ARP    42
Gratuitous ARP for 66.96.20.42 (Request)
2462    19:24:16.388241000    ::    ff02::1:ff00:42    ICMPv6    78
Neighbor Solicitation for 2001:1928:1::42
2463    19:24:16.389065000    ::    ff02::1:ff00:42    ICMPv6    78
Neighbor Solicitation for 2001:1928:1::42
2464    19:24:16.444130000    ::    ff02::16    ICMPv6    130    Multicast
Listener Report Message v2
2465    19:24:16.444605000    ::    ff02::16    ICMPv6    130    Multicast
Listener Report Message v2
2466    19:24:16.594663000    ::    ff02::1:ff2e:46fd    ICMPv6    78
Neighbor Solicitation for fe80::250:56ff:fe2e:46fd
2467    19:24:16.595179000    ::    ff02::1:ff2e:46fd    ICMPv6    78
Neighbor Solicitation for fe80::250:56ff:fe2e:46fd
2753    19:24:22.274728000    Vmware_2e:46:fd    Broadcast    ARP    42
Who has 66.96.20.33?  Tell 66.96.20.42
2754    19:24:22.274902000    Intel_bc:6f:87    Vmware_2e:46:fd    ARP
60    66.96.20.33 is at 00:0e:0c:bc:6f:87

... and then it goes on to chatter ipv4-wise as expected.  Note that there
are two of each packet.  Is that normal?  The ethernet source of all these
packets is my vmware guest (save the who-has reply that I copied in).


More information about the freebsd-net mailing list