Hi, As we know, in order to control the guest OS's TX rate limit, we can apply rate limit on ingress Qdisc of host's tap device. But I think skb will be dropped on host's tap ingress Qdisc, which means that for those protocol lacking of congestion control such as UDP, it will cost a lot of meaningless time to produce dropped packet .
What about introducing rate limit on qemu's emulated net device? I think guest's UDP transaction will be blocked at wait_for_wmem. Thanks and regards, pingfan
