On Mon, Oct 30, 2017 at 7:10 PM, David Miller <da...@davemloft.net> wrote: > From: Tom Herbert <t...@quantonium.net> > Date: Mon, 30 Oct 2017 14:16:00 -0700 > >> I wrote a quick test program that floods a whole bunch of these >> packets to a host and sure enough there is substantial time spent >> in ip6_parse_tlv. > ... >> 25.38% [kernel] [k] __fib6_clean_all >> 21.63% [kernel] [k] ip6_parse_tlv > > Yet the routing code still dominates the cost.
I wouldn't read too much into that. This was unconnected UDP on VMs and the only purpose here was to demonstrate that ip6_parse_tlv does get a lot of work with a lot of TLVs. Martin's results listed in the tested section are probably a more accurate gauge of the impact and potential to mitigate DOS. Tom