On Sun, 2018-01-28 at 19:12 -0500, Michael Richardson wrote: > Laurent GUERBY <laur...@guerby.net> wrote: > > On Sun, 2018-01-28 at 17:09 -0500, Michael Richardson wrote: > >> Laurent GUERBY <laur...@guerby.net> wrote: > >> > I tested today a few things on a brand new TP-Link > Archer C7 > >> v4.0, > >> > LAN client Dell Latitude 7480 (eth I219-LM, wifi 8265 / > 8275) > >> > WAN server NUC5i3RYB (eth I218-V), NAT between them, <1 > ms > >> latency > >> > (everything on the same table), IPv4 unless specified, > >> > using iperf3 LAN=>WAN and -R for WAN=>LAN (both TCP). > >> > >> > With the TP-Link firmware: > >> > - wired 930+ Mbit/s both ways > >> > - wireless 5G 560+ Mbit/s down 440+ Mbit/s up > >> > - wireless 2.4G 100+ Mbit/s both ways > >> > >> > With OpenWRT/LEDE trunk 20180128 4.4 kernel: > >> > - wired 350-400 Mbit/s both ways > >> > - wired with firewall deactivated 550 Mbit/s > >> > (just "iptables -t nat -A POSTROUTING -j MASQUERADE") > >> > >> That still means you have conn-tracking loaded. > >> Have you tried without that? > > > What should I do to enable NAT without conn-tracking? > > (I see a few nf_conntrack* modules in lsmod) > > Unfortunately, you don't. > > It's also hard to get rid of the conntrack modules, other than > clearing > everything and then rmmod'ing them. Sometimes I've had to rename the > .ko > files and reboot to get rid of them. > > So that means that you have to do the performance testing for routing > between two subnets.
Hi, With wired, firewall off and using routing (no MASQUERADE, explicit LAN route added on the NUC via WAN IP): - IPv4 590+ Mbit/s up and 690+ Mbit/s down - IPv6 270+ Mbit/s same both ways So without NAT/conntrack we gain about 50% on IPv4 and we're closer to line rate. For the record I tested without the router to check iperf3 my setup and IPv4 and IPv6 are 910+ Mbit/s both ways. Sincerely, Laurent PS: kernel is 4.9.77 on the archer (not 4.4, thinko in my first mail) NUC and laptop are running 4.9 debian stretch too. _______________________________________________ Lede-dev mailing list Lede-dev@lists.infradead.org http://lists.infradead.org/mailman/listinfo/lede-dev
