Duplicate Address Detection misfire?

[Zaphod Beeblebrox]

Ironically, the win 7 host is using an "em" series card.  Specifically, an
Intel "Gigabit CT".  It is configured in vlan mode and the VMWare bridged
connection is connected to a VLAN.

Regardless, tho, Intel's own drivers are usually not this bad --- and the
driver is up-to-date.


On Tue, Jul 23, 2013 at 10:22 AM, Kevin Day <kevin at your.org> wrote:

> Sorry for the slow reply.
>
> We run mainly ESXi (the bare metal version of VMware, not the desktop
> versions) but I do remember seeing something sort of similar on a desktop
> version ages ago. Basically we narrowed it down to a Windows driver bug on
> the host system's ethernet card. It was basically reflecting back
> everything it transmitted into the receive queue. This was before IPv6 was
> in use here, but I remember it breaking a file sharing protocol (SMB? AFP?)
> that also didn't like seeing its own multicasts/broadcasts echoed back to
> itself.
>
> By any chance is this on a system using WiFi rather than wired ethernet?
> Many routers/access points/wifi adapters have problems with the idea of
> VMware's "bridged mode" networking - they expect only one MAC per station
> and do not do the right thing in some places.
>
> I don't have an answer for you, but I'd look at the physical networking
> card/adapter on the host OS first if I were troubleshooting this. Updated
> driver/replace with something else/etc.
>
> -- Kevin
>
> On Jul 23, 2013, at 12:44 AM, Zaphod Beeblebrox <zbeeble at gmail.com> wrote:
>
> > What to do when you don't trust the interface?  VMWare is obviously
> emulating the hardware and their interpretation of what the hardware "is"
> is possibly different from ours.
> >
> > If I boot single-user and tcpdump the interface, I see two transmitted
> solicitations.  The kernel claims to have sent one.
> >
> > My concern: is the vmware interface reflecting the solicitation packet
> because it is a broadcast packet?
> >
> > To determine this, I've gone over the tcpdump and pcap-filter man pages
> to look for a way to only dump packets leaving from or arriving at an
> interface.  Can this be done?
> >
> > If VMWare is reflecting the packet back, I'm curious as to how we can
> fix this.
> >
>
>