The guest TCP stack is the connection endpoint and sets the MSS of the
packets. As a result, if you want it to use a different MSS it must
know about the underlying MTU. You might see larger packets at various
points in the stack but this is simply an optimization and the MSS
that the guest request
Hi
AFAIK all tcp implementations in common OS set the DF (dont frag) flag.
Instead of IP fragment, TCP use MSS to auto negotiate and discover the
network MTU. IP frag has several issues, IP frag wastes more header space
and CPU, and fragmented packet can't be fragmented twice.
On Mon, Dec 16, 20
Hi all,
I do that tests with a recent kernel (3.11.0) and I still can not use
Jumbo frame without change the guest MTU. I made that test because I
though that Linux patch [1] pshed by Nicira can solve my problem.
On thing change, when I use a veth between the Linux bridge (qbr) and
the OVS bridge
Hi,
I use OpenStack Neutron with OVS and VXLAN encapsulation.
# ovs-vsctl -V
ovs-vsctl (Open vSwitch) 2.0.0
# uname -r
3.2.0-41-generic
I've got Cisco Nexus fabric and I like to be able to use it with the
maximum frame size (9216 octets) without impact the MTU configuration
of the guest VM.
Co
