When I am reading the source of openvswitch I find the logic about fragment.
rule_dpif_lookup_in_table function:
(...skip...)
if (frag && ofproto->up.frag_handling == OFPC_FRAG_NORMAL) {
/* We must pretend that transport ports are unavailable. */
struct flow ofpc_normal_flow = *flow;
ofpc_normal_flow.tp_src = htons(0);
ofpc_normal_flow.tp_dst = htons(0);
cls_rule = classifier_lookup(cls, &ofpc_normal_flow, wc);
} else if (frag && ofproto->up.frag_handling == OFPC_FRAG_DROP) {
cls_rule = &ofproto->drop_frags_rule->up.cr;
/* Frag mask in wc already set above. */
} else {
cls_rule = classifier_lookup(cls, flow, wc);
}
(...skip...)
Is this meaning if the frag_handling flag is set to OFPC_FRAG_DROP then all
the packet with fragment IP header on will be dropped?
So the drop flow will be installed in kernel?
But I also see the default action is OFPC_FRAG_NORMAL, so I wonder in which
case the OFPC_FRAG_DROP should be used?
Looking for your reply. Thank you!
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
