But if you receive a 9000 MTU frame on an "input" interface that results 
sending it out on an interface of a 1500 MTU, then if you set DF bit the frame 
will just be dropped by the router. If you want your data to "cross" your frame 
over a different MTU path, then you can not set DF to 1. This is a quite simple 
and easy thing to demonstrate. Just create a simple virtual lab with 3 Linux 
doing routing and test it. So, if your goal is to communicate over paths that 
may have a MTU lower than 9000 you better make sure your server sends out a 
frame that the path can support.


From: Fabrice Bacchella <fabrice.bacche...@orange.fr>
Sent: Tuesday, August 8, 2017 1:37 PM
To: Moacir Ferreira
Cc: users@ovirt.org
Subject: Re: [ovirt-users] Users Digest, Vol 71, Issue 37

The border router will do like any other router on the world. If the DF bit is 
set (common case) or if it's IPv6, it will not fragment but send an ICMP.

Le 8 août 2017 à 13:34, Moacir Ferreira 
<moacirferre...@hotmail.com<mailto:moacirferre...@hotmail.com>> a écrit :

True! But in some point of the network it may be necessary to make the MTU 
1500. For example, if your data need to cross the Internet. The border router 
in between your LAN and the Internet will have to fragment a large frame back 
to a normal one to send it over the Internet. This router will just "die" if 
you have a heavy load.


From: Fabrice Bacchella 
Sent: Tuesday, August 8, 2017 12:23 PM
To: Moacir Ferreira
Cc: users@ovirt.org<mailto:users@ovirt.org>
Subject: Re: [ovirt-users] Users Digest, Vol 71, Issue 37

Le 8 août 2017 à 11:49, Moacir Ferreira 
<moacirferre...@hotmail.com<mailto:moacirferre...@hotmail.com>> a écrit :

This is by far more complex. A good NIC will have an offload engine (LSO - 
Large Segment Offload) and, if so, the NIC driver will report a MTU of 64K to 
the IP stack. The IP stack will then send data to the NIC as if the MTU were 
64K and the NIC will fragment it to the size of the "declared" MTU on the 
interface so PMTUD will not be efficient in such scenario. If all this takes 
place in the server, then you get no problem. But if a standard router is 
configured to support 9K jumbo frame in one interface (i.e.: LAN connection) 
and 1500 in another (i.e.: WAN connection) then the router will be responsible 
for the fragmentation.

That's happen only if the bit don't fragment is not set, otherwise router are 
not allowed to do that and send back a "packet to big" ICMP, it's called path 
mtu discovery. To my knowledge, it's usually set, and even mandatory on IPv6.

Users mailing list

Reply via email to