AQL and the ath10k is lovely

amteza · September 3, 2022, 11:03pm

Here you go (click to download flent data files, rrul_be and tcpndown 2-threaded and its tcpdump -s 128 .cap file):

Permanently a separate server, the AP is just a dumb AP.

Offloading is disabled.

It is running cubic.

Did capture with -s 128.

I can't install tc to check. Is there another way? Sorry for my naïve query.

On a side note, reviewing the source code, should we keep the contents of the else's statement like below?

@@ -2697,15 +2697,6 @@ static void sta_update_codel_params(struct sta_info *sta, u32 thr)
 	if (!sta->sdata->local->ops->wake_tx_queue)
 		return;
 
-	if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) {
-		sta->cparams.target = MS2TIME(50);
-		sta->cparams.interval = MS2TIME(300);
-		sta->cparams.ecn = false;
-	} else {
-		sta->cparams.target = MS2TIME(20);
+		sta->cparams.target = MS2TIME(8);
		sta->cparams.interval = MS2TIME(100);
		sta->cparams.ecn = true;
-	}
 }

dtaht · September 3, 2022, 11:07pm

thx. you aint naive, at this point yer the most highly qualified tester fq_codel has had since @tohojo graduated.

cat /sys/kernel/debug/iee*/phy*/aqm

amteza · September 3, 2022, 11:09pm

Okay, see below for my quantum values:

access name value
R fq_flows_cnt 4096
R fq_backlog 0
R fq_overlimit 0
R fq_overmemory 0
R fq_collisions 235
R fq_memory_usage 0
RW fq_memory_limit 4194304
RW fq_limit 8192
RW fq_quantum 300
access name value
R fq_flows_cnt 4096
R fq_backlog 0
R fq_overlimit 0
R fq_overmemory 0
R fq_collisions 1272751
R fq_memory_usage 0
RW fq_memory_limit 16777216
RW fq_limit 8192
RW fq_quantum 300

I think 300 should be find as I'm not "CPU bounded", don't think we need to increase it to 1514. Second set is the one we are testing on (phy1).

dtaht · September 3, 2022, 11:10pm

just to be utterly certain you are testing the server... "openwrt.lan" is usually the name of the AP not a device connected to it...

amteza · September 3, 2022, 11:12pm

Fair query:

openwrt.lan -> OpenWrt RPi4 acting as router (no wireless interface)
nanohd-downstairs.lan -> dump AP connected to openwrt.lan via 1 Gbps Ethernet
Macbook pro -> connected to nanohd-downstairs.lan wirelessly

dtaht · September 3, 2022, 11:19pm

ok, thx, and thx especially for the caps. From which vantage point are you getting those from?

amteza · September 3, 2022, 11:22pm

I'm capturing them on the macOS computer.

dtaht · September 3, 2022, 11:29pm

theres a pretty version (in java I think) of xplot.org for osx, that and tcptrace -G, don't require a working matplotlib.

I am told these are coming along.

https://gitlab.quatermass.co.uk/jgh/tcptrace
https://gitlab.quatermass.co.uk/jgh/xplot

dtaht · September 3, 2022, 11:35pm

on osx:

sudo netstat -l your_device -qq

and I'm calling it a day. New theory - the rpi (openwrt.lan) has something rate limiting the performance of it's stack.

amteza · September 3, 2022, 11:42pm

Before calling it a day -see below. May I ask what you expect to find with the output of that command?

netstat output (too long to paste directly)

Going to enjoy Father's day for a little while.

dtaht · September 3, 2022, 11:44pm

heh. I gave you the wrong command. -qq -I (thats an I not an L) should show the native fq_codel stats on the osx box. and even that might be the wrong command... gimmee sec

amteza · September 3, 2022, 11:46pm

It makes more sense now, I should realise; here you go:

@reaper$ ➜  ~ sudo netstat -I en0 -qq
en0:
     [ sched:  FQ_CODEL  qlength:    0/128 ]
     [ pkts:  124486499  bytes: 170983491083  dropped pkts:  44041 bytes: 65229549 ]
=====================================================
     [ pri: VO (1)	srv_cl: 0x400180	quantum: 605	drr_max: 8 ]
     [ queued pkts: 0	bytes: 0 ]
     [ dequeued pkts: 33377	bytes: 6044211 ]
     [ budget: 0	target qdelay: 10.00 msec	update interval:100.00 msec ]
     [ flow control: 0	feedback: 0	stalls: 0	failed: 0 	overwhelming: 0 ]
     [ drop overflow: 0	early: 0	memfail: 0	duprexmt:0 ]
     [ flows total: 0	new: 0	old: 0 ]
     [ throttle on: 0	off: 0	drop: 0 ]
     [ compressible pkts: 0 compressed pkts: 0]
=====================================================
     [ pri: VI (2)	srv_cl: 0x380100	quantum: 3028	drr_max: 6 ]
     [ queued pkts: 0	bytes: 0 ]
     [ dequeued pkts: 5842684	bytes: 8182467304 ]
     [ budget: 0	target qdelay: 10.00 msec	update interval:100.00 msec ]
     [ flow control: 355	feedback: 355	stalls: 12	failed: 0 	overwhelming: 0 ]
     [ drop overflow: 0	early: 0	memfail: 0	duprexmt:0 ]
     [ flows total: 0	new: 0	old: 0 ]
     [ throttle on: 0	off: 0	drop: 0 ]
     [ compressible pkts: 0 compressed pkts: 0]
=====================================================
     [ pri: BE (7)	srv_cl: 0x0	quantum: 1514	drr_max: 4 ]
     [ queued pkts: 0	bytes: 0 ]
     [ dequeued pkts: 118254467	bytes: 162519175698 ]
     [ budget: 0	target qdelay: 10.00 msec	update interval:100.00 msec ]
     [ flow control: 9243	feedback: 9243	stalls: 40	failed: 0 	overwhelming: 0 ]
     [ drop overflow: 0	early: 43041	memfail: 0	duprexmt:0 ]
     [ flows total: 0	new: 0	old: 0 ]
     [ throttle on: 0	off: 0	drop: 0 ]
     [ compressible pkts: 0 compressed pkts: 0]
=====================================================
     [ pri: BK (8)	srv_cl: 0x100080	quantum: 1514	drr_max: 2 ]
     [ queued pkts: 0	bytes: 0 ]
     [ dequeued pkts: 355971	bytes: 275803870 ]
     [ budget: 0	target qdelay: 10.00 msec	update interval:100.00 msec ]
     [ flow control: 3	feedback: 3	stalls: 0	failed: 0 	overwhelming: 0 ]
     [ drop overflow: 0	early: 0	memfail: 0	duprexmt:0 ]
     [ flows total: 0	new: 0	old: 0 ]
     [ throttle on: 0	off: 0	drop: 0 ]
     [ compressible pkts: 83604 compressed pkts: 34500]

dtaht · September 3, 2022, 11:52pm

enjoy your fathers day. It is labor day here... and we have labored mightily.

did you patch the kernel or the mac80211 package?

wmm_ac_be_txop_limit=32 you see on the osx box?

dtaht · September 4, 2022, 12:01am

this was a good result from aug 4:

dtaht · September 4, 2022, 12:29am

a tcpdump of 2 flows up woul be useful also.

amteza · September 4, 2022, 12:59am

I patched package/kernel/mac80211.
Update: 1:38 AEDT - I just realised my mistake, recompiling and letting it ready for re-testing tomorrow in the early morning.

Yes, Sir, see below:

But I didn't use today the below parameters, I only modified txop=32, and I used burst=0.

tx_queue_data2_aifs=1
tx_queue_data2_cwmin=7
tx_queue_data2_cwmax=15
tx_queue_data2_burst=3.0

I will do it tomorrow.

amteza · September 4, 2022, 7:58pm

Another round.
WMM test parameters:

tx_queue_data2_aifs=3
tx_queue_data2_cwmin=15
tx_queue_data2_cwmax=63
tx_queue_data2_burst=0

wmm_ac_be_txop_limit=0

AQL test parameters:

root@nanohd-downstairs:~# cat /sys/kernel/debug/ieee80211/phy1/aql_txq_limit
AC	AQL limit low	AQL limit high
VO	5000		12000
VI	5000		12000
BE	5000		12000
BK	5000		12000
root@nanohd-downstairs:~# cat /sys/kernel/debug/ieee80211/phy1/aql_threshold
24000
root@nanohd-downstairs:~# cat /sys/kernel/debug/ieee80211/phy1/aql_enable
1

flent rrul_be test:

flent tcpn[up,down] 2-threaded test:

flent data files (ms2time=8ms txburst=0 aql=on)

dtaht · September 4, 2022, 8:06pm

yuck.

w/aql disabled?

amteza · September 4, 2022, 8:07pm

Sadly, nope. You can see this in the parameters list I posted before the graphs.

dtaht · September 4, 2022, 9:31pm

Where were we in july?

"At least it doesn't crash."

AQL and the ath10k is *lovely*

AQL and the ath10k is lovely