Over the weekend I upgraded my 4040 to 23.05.0 and cleaned up a bit of the config; however, the settings for SQM have been preserved, both the speed and the discipline.
Which is why I cannot really understand how my Samknows Whitebox is reporting such a huge improvement:
Any idea what could be behind that?
Maybe post the output of cat /etc/config/sqm, tc -s qdisc, and tc -d qdisc` so we can see whether the old rate was too low or whether the new rate is too high?
/etc/config/sqm (after the upgrade)
config queue 'eth1'
option debug_logging '0'
option download '111000'
option enabled '1'
option interface 'pppoe-wan'
option linklayer 'ethernet'
option overhead '38'
option qdisc 'cake'
option script 'piece_of_cake.qos'
option upload '27500'
option verbosity '5'
and before the upgrade (different sorting):
config queue 'eth1'
option debug_logging '0'
option verbosity '5'
option qdisc 'cake'
option script 'piece_of_cake.qos'
option linklayer 'ethernet'
option overhead '38'
option interface 'pppoe-wan'
option upload '27500'
option enabled '1'
option download '111000'
Apart from the sorting, it is unchanged.... one possibly relevant change is that I removed the vlans in my setup, since I was using them just to split the bridge and apparentl with DSA you can do that without vlans.
tc -s qdisc output:
qdisc noqueue 0: dev lo root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc mq 0: dev eth0 root
Sent 4897042196 bytes 6493382 pkt (dropped 0, overlimits 0 requeues 49)
backlog 0b 0p requeues 49
qdisc fq_codel 0: dev eth0 parent :4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
Sent 1169641025 bytes 1685969 pkt (dropped 0, overlimits 0 requeues 15)
backlog 0b 0p requeues 15
maxpacket 1506 drop_overlimit 0 new_flow_count 5032 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: dev eth0 parent :3 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
Sent 1290260353 bytes 1491602 pkt (dropped 0, overlimits 0 requeues 10)
backlog 0b 0p requeues 10
maxpacket 1506 drop_overlimit 0 new_flow_count 3599 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: dev eth0 parent :2 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
Sent 1352906264 bytes 1783223 pkt (dropped 0, overlimits 0 requeues 16)
backlog 0b 0p requeues 16
maxpacket 1506 drop_overlimit 0 new_flow_count 3441 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
Sent 1084234554 bytes 1532588 pkt (dropped 0, overlimits 0 requeues 8)
backlog 0b 0p requeues 8
maxpacket 1506 drop_overlimit 0 new_flow_count 4305 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc noqueue 0: dev lan1 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev lan2 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev lan3 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev lan4 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev wan root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev phy0-ap0 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev phy1-ap0 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev phy0-ap1 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev phy1-ap1 root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc cake 800d: dev pppoe-wan root refcnt 2 bandwidth 27500Kbit besteffort triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms noatm overhead 38
Sent 433845324 bytes 1434478 pkt (dropped 4504, overlimits 315395 requeues 0)
backlog 0b 0p requeues 0
memory used: 403136b of 4Mb
capacity estimate: 27500Kbit
min/max network layer size: 21 / 1492
min/max overhead-adjusted size: 59 / 1530
average network hdr offset: 0
Tin 0
thresh 27500Kbit
target 5ms
interval 100ms
pk_delay 499us
av_delay 109us
sp_delay 44us
backlog 0b
pkts 1438982
bytes 440371100
way_inds 103649
way_miss 55250
way_cols 0
drops 4504
marks 0
ack_drop 0
sp_flows 1
bk_flows 1
un_flows 0
max_len 17280
quantum 839
qdisc ingress ffff: dev pppoe-wan parent ffff:fff1 ----------------
Sent 2737999934 bytes 2482049 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev 6in4-he_2_fra root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc cake 800e: dev ifb4pppoe-wan root refcnt 2 bandwidth 111Mbit besteffort triple-isolate nonat wash no-ack-filter split-gso rtt 100ms noatm overhead 38
Sent 2732251571 bytes 2478179 pkt (dropped 3870, overlimits 2184307 requeues 0)
backlog 0b 0p requeues 0
memory used: 1031424b of 5550000b
capacity estimate: 111Mbit
min/max network layer size: 28 / 1492
min/max overhead-adjusted size: 66 / 1530
average network hdr offset: 0
Tin 0
thresh 111Mbit
target 5ms
interval 100ms
pk_delay 193us
av_delay 100us
sp_delay 38us
backlog 0b
pkts 2482049
bytes 2737999934
way_inds 97506
way_miss 51006
way_cols 0
drops 3870
marks 0
ack_drop 0
sp_flows 2
bk_flows 1
un_flows 0
max_len 1492
quantum 1514
qdisc fq_codel 0: dev tun0 root refcnt 2 limit 10240p flows 1024 quantum 1500 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
Sent 9538765 bytes 11998 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
maxpacket 1403 drop_overlimit 0 new_flow_count 22 ecn_mark 0
new_flows_len 0 old_flows_len 0
qdisc noqueue 0: dev br-guest root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
qdisc noqueue 0: dev br-casa root refcnt 2
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
tc -d qdisc output:
qdisc noqueue 0: dev lo root refcnt 2
qdisc mq 0: dev eth0 root
qdisc fq_codel 0: dev eth0 parent :4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
qdisc fq_codel 0: dev eth0 parent :3 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
qdisc fq_codel 0: dev eth0 parent :2 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
qdisc fq_codel 0: dev eth0 parent :1 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
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 noqueue 0: dev wan root refcnt 2
qdisc noqueue 0: dev phy0-ap0 root refcnt 2
qdisc noqueue 0: dev phy1-ap0 root refcnt 2
qdisc noqueue 0: dev phy0-ap1 root refcnt 2
qdisc noqueue 0: dev phy1-ap1 root refcnt 2
qdisc cake 800d: dev pppoe-wan root refcnt 2 bandwidth 27500Kbit besteffort triple-isolate nonat nowash no-ack-filter split-gso rtt 100ms noatm overhead 38
qdisc ingress ffff: dev pppoe-wan parent ffff:fff1 ----------------
qdisc noqueue 0: dev 6in4-he_2_fra root refcnt 2
qdisc cake 800e: dev ifb4pppoe-wan root refcnt 2 bandwidth 111Mbit besteffort triple-isolate nonat wash no-ack-filter split-gso rtt 100ms noatm overhead 38
qdisc fq_codel 0: dev tun0 root refcnt 2 limit 10240p flows 1024 quantum 1500 target 5ms interval 100ms memory_limit 4Mb ecn drop_batch 64
qdisc noqueue 0: dev br-guest root refcnt 2
qdisc noqueue 0: dev br-casa root refcnt 2
Thanks!
With 111Mbps 38bytes overhead PPPoE, IPv4 TCP the theoretical upper limit would be around:
111 * ((1500-8-20-20)/(1500-8+38)) = 105.34 Mbps
so it seems your router freed up some CPU cycles somewhere (maybe by offloading some software VLAN handling?) and can invest them into cake?
thank you for the check, I guess the router is running at capacity, CPU-wise, if an update brings the speed close to the theoretical limit.
I think this frequent calculation of expected goodput should be built into luci-app-sqm so people know what to expect when they enter their bandwidth numbers.
The calculation is not all that complicated, but you need to know a few things that are generally not easy to deduce. But I will mull your proposal...
This topic was automatically closed 10 days after the last reply. New replies are no longer allowed.