New router test for bufferbloat Belkin RT3200 Linksys E8450 AX

yes thanks

this is my result with and witouth irq balance on my vdsl2 :wink:


irq work well :slight_smile:

Well, given that your router is way overkill for a VDSL line, it only makes sense to test this (again) on a faster/ ftth line.

1 Like

hello , i have playing with irq balance and my gameplay lag , i has search the problem

then down to the forum

The link is for PC not routers, i use irq balance on my wrt3200acm and my games run good

hello everyone today i connected via two belkin rt3200 e8450 and iperf3 router and two computers

I carried out tests and I get these results

that would mean that the router shapes the gigabit with sqm ??

I first did iperf3 -s

and secondly do iperf3 - c that would be great news for me having gigabit soon

@dlakelan @psherman
@anon50098793 @slh

So expected maximal TCP/IPv4 goodput for your configured rates would be approximately (since I need to guess your per-packet-overhead setting, I assume true ethernet with a VLAN tag, to be on the safe side):

900 * ((1500-20-20)/(1500+38+4)) = 852.140077821
800 * ((1500-20-20)/(1500+38+4)) = 757.457846952
200 * ((1500-20-20)/(1500+38+4)) = 189.364461738

Which is close to what you actually measure, so it seems this router shapes ~1500 byte packets at gigabit rates. It would be interesting to repeat the test with smaller packet/MSS/MTU size to see how the router performes with considerably higher packet-rates with smaller packets.

2 Likes

or even better from many client addresses ( thanks @rhester72 )

1 Like

ok i will make a test i change to the interface lan mtu is right ?

to luci what values i put

Please leave the MTU alone, but rather configure appropriate MSS clamping (assuming you test via TCP in iperf). For example you could add the following to /etc/firewall.user:

# special rules to allow MSS clamping for in and outbound traffic                                                                   
# use ip6tables -t mangle -S ; iptables -t mangle -S to check                                                                       
forced_MSS=216                                                                                                                      
                                                                                                                                    
# affects both down- and upstream, egress seems to require at least 216                                                             
iptables -t mangle -A FORWARD -p tcp -m tcp --tcp-flags SYN,RST SYN -m comment --comment "custom: Zone wan MTU fixing" -j TCPMSS --set-mss ${forced_MSS}                                                                                                               
ip6tables -t mangle -A FORWARD -p tcp -m tcp --tcp-flags SYN,RST SYN -m comment --comment "custom6: Zone wan MTU fixing" -j TCPMSS  --set-mss ${forced_MSS}     

then get a packet capture on the router ot confirm that both in and out TCP-traffic uses a reduced MSS.

1 Like

thank you very much for this information

i will test now

so after many test this is the result :wink:

i have test with 216 512 and 1024 :wink:



the last test is 216

and here a test of speedguide

what should we conclude from this? I did some fiber test in the past and sqm did not exceed 500 mbits on a 1/1 line however the line was in mtu 1500 in the orange settings

@Gruntruck

Expected throughput (with same assumptions as before)
MTU = MSS + 20 (TCP header) + 20 (IPv4 header)

1000.000 * ((1460))/(1460 + 40 + 38 + 4)) = 946.82 Mbps
1000.000 * ((1024))/(1024 + 40 + 38 + 4)) = 925.86 Mbps
1000.000 * ((512))/(512 + 40 + 38 + 4)) = 861.95 Mbps
1000.000 * ((216))/(216 + 40 + 38 + 4)) = 724.83 Mbps

So you are getting noticeably less throughput than expected, this might indicate that the router hits a CPU limit. Let's look at the packet rates you did achieve in your tests:

thoughput [bit/s] / packetsize [bit/packet] = packet-rate [packet/s]
908 * 1000^2 / ((1024 + 40 + 38 + 4) * 8) = 102622.1 packets/s
482 * 1000^2 / ((512 + 40 + 38 + 4) * 8) = 101431.0 packets/s
235* 1000^2 / ((216 + 40 + 38 + 4) * 8) = 98573.8 packets/s

So it seems that you are limited to roughly 100000 Packets per second on this router, not bad, and probably good enough for most uses of a gigabit link (since most connections will use relative large packet sizes, especially for bulk data transfer). If push comes to shove however and lots of small packets are in the traffic mix the router will hit limits.

Question, the speedguide results were with which forced _MSS setting?

1 Like

Yes thanks for clarification, i have make a speedguide test withouth mss just my official router after recabled

No mss just my habituel settings..

I found this site for 1gbps co :wink:

https://kb.juniper.net/InfoCenter/index?page=content&id=KB14737

1 Like

Okay, that fits what the site reported as MSS :wink:

Decent reference :wink:

1 Like

Hello everyone, I'm going to test the rt3200 on a 2.5 gigabit downlink and 1 upstream connection this Thursday (switzerland)

Would you have any questions or commands to suggest to me as a htop during the irq balance packet steering test etc, I can test gladly :slight_smile: thank you

hi everybody !! new test with steering enabled and irq balance

just result amazing on fiber optic

Capture d’écran 2021-08-22 à 22.46.53
Capture d’écran 2021-08-22 à 22.47.33


have a nice day ! :slight_smile:

2 Likes

Are you using SQM cake?

ok i'm use cake with piece of cake i will modified i'm use cake only on upload not download because my bufferbloat on download is vry good

1 Like

hello everyone after several fiber optic and vdsl2 tests on my side we noticed, in video games that bad gameplay in call of duty was felt when activating packet steering, no problem with irq balance,

we therefore concluded that in optical fiber and also vdsl2 only irq balance should be activated,

1 Like

hello everybody test with script hfsc of dlakelan

i have enabled packet steering and software offloading

2 Likes