On the same network, all host shall have the same MTU Packets truncating can only happen on routers Let say you have an OSD with mtu 9000, and a mon with mtu 1500 Communications from mon to osd will works, because the mon will send 1500 bytes-sized packets, and this is < 9000 However, communications from osd to mon will be drop, because the osd will send 9000 bytes-sized packets, which will be dropped by the switch I do not know if there is osd -> mon traffic Yet such configuration will clearly be bug-prone On 08/16/2018 05:53 PM, Satish Patel wrote: > Folks, > > I am changing all my OSD node MTU to 9000 and just wonder does > ceph-mon node need MTU 9000 ? I know that are not going to deal with > high volume data but just curious does that impact functionality if > ceph-mon running on MTU 1500 and all OSD data node run on MTU 9000 > (FYI: they all are on same LAN ) > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |