问题原文
原帖链接 · Zlatko Mesaros · CC BY-SA 3.0
I am trying to figure out how to interpret the attached image. First two hops are on our LAN, hops 3-5 belong to our WAN provider, while hop 6 is at our hosting provider and the hop 7 is a Windows server at that same hosting provider.
What I don't understand is how the latency on hop 7 can be lower than the latency on hop 6 or to that effect lower than the latency on hops 5 and 6. Also - the hop 6 shows significant packet loss, while hop 7 looks fine. I understand that the figures are not cumulative, but if the packet traverses all the hops, shouldn't every next hop take longer to reach than the previous one?
I read through quite a few documents, tutorials on Internet explaining the traceroute command but I still haven't found the explanation to this. I would highly appreciate a clear explanation or at least a pointer as what to read.
已采纳解答
原帖链接 · pQd · CC BY-SA 3.0
just a theory: some core routers can have overloaded management plane - hence delayed / lost responses, yet their packet forwarding plane will perform well so traffic passing via them will not be affected.
i suggest you also test using iperf for the available bandwidth. if your end-to-end performance is acceptable then you don't need to worry.
摘自公开归档,保留原文语言,版式经整理,外部媒体与邮箱地址已移除。
