* [Cake] bringing up a new router/connection
@ 2021-02-03 21:24 David Lang
2021-02-04 0:03 ` Jonathan Morton
` (2 more replies)
0 siblings, 3 replies; 8+ messages in thread
From: David Lang @ 2021-02-03 21:24 UTC (permalink / raw)
To: cake
I finally got a decent speed connection (cablemodem 600/35) to supplement my dsl
(8/1) and am trying to test it's current performance before I install/configure
cake and am running into some grief. I am hoping to get some pointers to find
the bottleneck.
the ISP devices have bad bufferbloat, ping times go from ~20ms to 8.8.8.8 to t
least 120ms, and I saw one time when they went to 1200ms
I'm using a c2600 router running the current openwrt
https://openwrt.org/toh/tp-link/tp-link_archer_c2600_v1 and have mwan3
configured to provide failover between my wan connections.
I have a block of static addresses for the router with the ISP router in bridge
mode
when plugged directly into the ISP router, I am getting the advertised speeds,
when going through the c2600 I top out at 200-300Mb download and 10-15mb upload
eth0.2 is the high speed cablemodem
# tc qdisc
qdisc noqueue 0: dev lo root refcnt 2
qdisc mq 0: dev eth0 root
qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc mq 0: dev eth1 root
qdisc fq_codel 0: dev eth1 parent :1 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc noqueue 0: dev br-lan root refcnt 2
qdisc noqueue 0: dev eth1.1 root refcnt 2
qdisc noqueue 0: dev eth0.4 root refcnt 2
qdisc noqueue 0: dev wlan0 root refcnt 2
qdisc noqueue 0: dev eth0.2 root refcnt 2
David Lang
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-03 21:24 [Cake] bringing up a new router/connection David Lang
@ 2021-02-04 0:03 ` Jonathan Morton
2021-02-04 0:15 ` David Lang
2021-02-04 5:51 ` Pete Heist
2021-02-04 1:11 ` xnor
2021-02-04 4:53 ` Y
2 siblings, 2 replies; 8+ messages in thread
From: Jonathan Morton @ 2021-02-04 0:03 UTC (permalink / raw)
To: David Lang; +Cc: cake
> On 3 Feb, 2021, at 11:24 pm, David Lang <david@lang.hm> wrote:
>
> when plugged directly into the ISP router, I am getting the advertised speeds, when going through the c2600 I top out at 200-300Mb download and 10-15mb upload
That sounds about right for a consumer CPE router. I believe there is usually a hardware bottleneck between the SoC and the Ethernet complex that is significantly narrower than the Ethernet ports and switch fabric. Once the downstream gets saturated there is also no room for upstream traffic.
You could set it up for 100Mbit down, 25Mbit up using Cake, and see how that works. It'll be a major improvement over 8/1 DSL, even if it isn't using the full advertised capacity of the cable.
One device that should be able to keep up is a Raspberry Pi 4 (not the earlier versions) supplemented with a USB3-attached GigE dongle. Pete Heist has established that it can sustain 600Mbit through Cake without much CPU load or added latency. Above that level the characteristics do degrade a bit.
- Jonathan Morton
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-04 0:03 ` Jonathan Morton
@ 2021-02-04 0:15 ` David Lang
2021-02-04 5:51 ` Pete Heist
1 sibling, 0 replies; 8+ messages in thread
From: David Lang @ 2021-02-04 0:15 UTC (permalink / raw)
To: Jonathan Morton; +Cc: David Lang, cake
On Thu, 4 Feb 2021, Jonathan Morton wrote:
>> On 3 Feb, 2021, at 11:24 pm, David Lang <david@lang.hm> wrote:
>>
>> when plugged directly into the ISP router, I am getting the advertised speeds, when going through the c2600 I top out at 200-300Mb download and 10-15mb upload
>
> That sounds about right for a consumer CPE router. I believe there is usually a hardware bottleneck between the SoC and the Ethernet complex that is significantly narrower than the Ethernet ports and switch fabric. Once the downstream gets saturated there is also no room for upstream traffic.
note this is still without cake, and neither core seems to be saturated yet.
I do have a Turris Omni that I plan to move this to, but I was expecting this
one to give me reasonable speeds on just a raw connection.
I will need a device with at least 3 ethernet ports (DSL, cablmodem, LAN)
David Lang
> You could set it up for 100Mbit down, 25Mbit up using Cake, and see how that works. It'll be a major improvement over 8/1 DSL, even if it isn't using the full advertised capacity of the cable.
>
> One device that should be able to keep up is a Raspberry Pi 4 (not the earlier versions) supplemented with a USB3-attached GigE dongle. Pete Heist has established that it can sustain 600Mbit through Cake without much CPU load or added latency. Above that level the characteristics do degrade a bit.
>
> - Jonathan Morton
>
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-03 21:24 [Cake] bringing up a new router/connection David Lang
2021-02-04 0:03 ` Jonathan Morton
@ 2021-02-04 1:11 ` xnor
2021-02-04 5:24 ` David Lang
2021-02-04 4:53 ` Y
2 siblings, 1 reply; 8+ messages in thread
From: xnor @ 2021-02-04 1:11 UTC (permalink / raw)
To: David Lang, cake
Hello David,
connect to the router over ssh and run top. What's the top load line(s)
with usr, sys, ... softirq look like during a download speedtest?
Anyway, according to some review it should be able to route about
700-800 Mbps WAN->LAN, with the original firmware. This is probably only
possible with hardware offloading.
Even if there was no bottleneck I wouldn't expect getting even remotely
close to that with cake also on ingress.
The only device I have to compare to yours is a smaller TP-Link router
with the same routing performance but a QCA9563 (750 MHz single core)
and I wouldn't use that for anything above 100 Mbps.
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-03 21:24 [Cake] bringing up a new router/connection David Lang
2021-02-04 0:03 ` Jonathan Morton
2021-02-04 1:11 ` xnor
@ 2021-02-04 4:53 ` Y
2021-02-04 5:14 ` David Lang
2 siblings, 1 reply; 8+ messages in thread
From: Y @ 2021-02-04 4:53 UTC (permalink / raw)
To: cake
Did you test with traffic shaping like this?
Yutaka
pi@raspberrypi:~$ tc -s qdisc show dev eth0
qdisc cake 8033: root refcnt 2 bandwidth 809Kbit besteffort dual-srchost
nonat nowash ack-filter-aggressive no-split-gso rtt 100.0ms atm overhead 10
> # tc qdisc
> qdisc noqueue 0: dev lo root refcnt 2
> qdisc mq 0: dev eth0 root
> qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum
> 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
> qdisc mq 0: dev eth1 root
> qdisc fq_codel 0: dev eth1 parent :1 limit 10240p flows 1024 quantum
> 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
> qdisc noqueue 0: dev br-lan root refcnt 2
> qdisc noqueue 0: dev eth1.1 root refcnt 2
> qdisc noqueue 0: dev eth0.4 root refcnt 2
> qdisc noqueue 0: dev wlan0 root refcnt 2
> qdisc noqueue 0: dev eth0.2 root refcnt 2
>
> David Lang
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-04 4:53 ` Y
@ 2021-02-04 5:14 ` David Lang
0 siblings, 0 replies; 8+ messages in thread
From: David Lang @ 2021-02-04 5:14 UTC (permalink / raw)
To: Y; +Cc: cake
I replaced the c2600 with the Turris Omni (one of the kickstarter ones) and
setup cake on it. This is running the Turris version 5 OS, which is supposed to
closely track upstream openwrt (let me know what I can do to check versions as
needed)
download wise I get good performance at 300000 download, but upload is still
having problems, mostly just getting 10-15Mb even with the rate set to 0 to
bypass cake entirely
eth2 is the DSL, lan4 is the cablemodem (lan4 is a switch port, probably
accessed via eth1)
root@sun:~# tc -s qdisc show dev eth1
qdisc mq 0: root
Sent 11872252393 bytes 8358655 pkt (dropped 0, overlimits 0 requeues 2496)
backlog 0b 0p requeues 2496
qdisc fq_codel 0: parent :8 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :7 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :6 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :5 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :4 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :3 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :2 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :1 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 11872252393 bytes 8358655 pkt (dropped 0, overlimits 0 requeues 2496)
backlog 0b 0p requeues 2496
maxpacket 2272 drop_overlimit 0 new_flow_count 1483 ecn_mark 0
new_flows_len 0 old_flows_len 0
root@sun:~# tc -s qdisc show dev eth2
qdisc mq 0: root
Sent 3957079 bytes 29531 pkt (dropped 0, overlimits 0 requeues 1)
backlog 0b 0p requeues 1
qdisc fq_codel 0: parent :8 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :7 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :6 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :5 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :4 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :3 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :2 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: parent :1 limit 10240p flows 1024 quantum 1514 target 5.0ms
interval 100.0ms memory_limit 4Mb ecn
Sent 3957079 bytes 29531 pkt (dropped 0, overlimits 0 requeues 1)
backlog 0b 0p requeues 1
maxpacket 336 drop_overlimit 0 new_flow_count 2 ecn_mark 0
new_flows_len 0 old_flows_len 0
root@sun:~# tc -s qdisc show dev lan4
qdisc noqueue 0: root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc ingress ffff: parent ffff:fff1 ----------------
Sent 3190516525 bytes 2312113 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
root@sun:~# tc qdisc
qdisc noqueue 0: dev lo root refcnt 2
qdisc mq 0: dev eth0 root
qdisc fq_codel 0: dev eth0 parent :8 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :7 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :6 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :5 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :4 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :3 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :2 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc mq 0: dev eth1 root
qdisc fq_codel 0: dev eth1 parent :8 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :7 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :6 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :5 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :4 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :3 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :2 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth1 parent :1 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc mq 0: dev eth2 root
qdisc fq_codel 0: dev eth2 parent :8 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :7 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :6 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :5 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :4 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :3 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :2 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc fq_codel 0: dev eth2 parent :1 limit 10240p flows 1024 quantum 1514 target
5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc noqueue 0: dev lan0 root refcnt 2
qdisc noqueue 0: dev lan1 root refcnt 2
qdisc noqueue 0: dev lan2 root refcnt 2
qdisc noqueue 0: dev lan3 root refcnt 2
qdisc noqueue 0: dev lan4 root refcnt 2
qdisc ingress ffff: dev lan4 parent ffff:fff1 ----------------
qdisc noqueue 0: dev br-lan root refcnt 2
qdisc noqueue 0: dev wlan1 root refcnt 2
qdisc noqueue 0: dev wlan1-1 root refcnt 2
qdisc fq_codel 0: dev tap0 root refcnt 2 limit 10240p flows 1024 quantum 1514
target 5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc noqueue 0: dev wlan0 root refcnt 2
qdisc cake 8013: dev ifb4lan4 root refcnt 2 bandwidth 300Mbit besteffort
triple-isolate nonat wash no-ack-filter split-gso rtt 100.0ms raw overhead 0
On Thu, 4 Feb 2021, Y via Cake wrote:
> Date: Thu, 4 Feb 2021 13:53:59 +0900
> From: Y via Cake <cake@lists.bufferbloat.net>
> Reply-To: Y <intruder_tkyf@yahoo.fr>
> To: cake@lists.bufferbloat.net
> Subject: Re: [Cake] bringing up a new router/connection
>
> Did you test with traffic shaping like this?
>
> Yutaka
>
> pi@raspberrypi:~$ tc -s qdisc show dev eth0
> qdisc cake 8033: root refcnt 2 bandwidth 809Kbit besteffort dual-srchost
> nonat nowash ack-filter-aggressive no-split-gso rtt 100.0ms atm overhead 10
>
>> # tc qdisc
>> qdisc noqueue 0: dev lo root refcnt 2
>> qdisc mq 0: dev eth0 root
>> qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum
>> 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
>> qdisc mq 0: dev eth1 root
>> qdisc fq_codel 0: dev eth1 parent :1 limit 10240p flows 1024 quantum
>> 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
>> qdisc noqueue 0: dev br-lan root refcnt 2
>> qdisc noqueue 0: dev eth1.1 root refcnt 2
>> qdisc noqueue 0: dev eth0.4 root refcnt 2
>> qdisc noqueue 0: dev wlan0 root refcnt 2
>> qdisc noqueue 0: dev eth0.2 root refcnt 2
>>
>> David Lang
>> _______________________________________________
>> Cake mailing list
>> Cake@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/cake
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-04 1:11 ` xnor
@ 2021-02-04 5:24 ` David Lang
0 siblings, 0 replies; 8+ messages in thread
From: David Lang @ 2021-02-04 5:24 UTC (permalink / raw)
To: xnor; +Cc: David Lang, cake
I made the mistake of installing htop and now even after uninstalling the htop
package, still have the htop display :-(
I've moved on to the turris omni, hich is supposed to be pretty good
performance. Download is still on the slow side, but I'm now throttling it with
cake to around 300M, but I'm still getting horrible upload performance (10M-15M
instead of 35M), processing power doesn't explain the upload issue.
David Lang
On Thu, 4 Feb 2021, xnor wrote:
> Date: Thu, 4 Feb 2021 02:11:32 +0100
> From: xnor <xnoreq@gmail.com>
> To: David Lang <david@lang.hm>, cake@lists.bufferbloat.net
> Subject: Re: [Cake] bringing up a new router/connection
>
> Hello David,
>
> connect to the router over ssh and run top. What's the top load line(s) with
> usr, sys, ... softirq look like during a download speedtest?
>
> Anyway, according to some review it should be able to route about 700-800
> Mbps WAN->LAN, with the original firmware. This is probably only possible
> with hardware offloading.
> Even if there was no bottleneck I wouldn't expect getting even remotely close
> to that with cake also on ingress.
>
> The only device I have to compare to yours is a smaller TP-Link router with
> the same routing performance but a QCA9563 (750 MHz single core) and I
> wouldn't use that for anything above 100 Mbps.
>
>
>
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Cake] bringing up a new router/connection
2021-02-04 0:03 ` Jonathan Morton
2021-02-04 0:15 ` David Lang
@ 2021-02-04 5:51 ` Pete Heist
1 sibling, 0 replies; 8+ messages in thread
From: Pete Heist @ 2021-02-04 5:51 UTC (permalink / raw)
To: cake
On Thu, 2021-02-04 at 02:03 +0200, Jonathan Morton wrote:
>
>
> One device that should be able to keep up is a Raspberry Pi 4 (not
> the earlier versions) supplemented with a USB3-attached GigE dongle.
> Pete Heist has established that it can sustain 600Mbit through Cake
> without much CPU load or added latency. Above that level the
> characteristics do degrade a bit.
Fwiw, here's what I saw on the RasPi4 and APU2. The RasPi4 was tested
with one-armed routing as that's what I was after at the time, but the
APU2 was tested through two interfaces also.
https://docs.google.com/spreadsheets/d/1SAm4Vi9jo7VG7cJVndMdaWjrgfqL6EBx3FYDjkP_HIY/edit?usp=sharing
>
> - Jonathan Morton
>
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2021-02-04 5:51 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-02-03 21:24 [Cake] bringing up a new router/connection David Lang
2021-02-04 0:03 ` Jonathan Morton
2021-02-04 0:15 ` David Lang
2021-02-04 5:51 ` Pete Heist
2021-02-04 1:11 ` xnor
2021-02-04 5:24 ` David Lang
2021-02-04 4:53 ` Y
2021-02-04 5:14 ` David Lang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox