Re: TCP data throughput for BCM43362

From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: 2016-10-12 19:08:44

Possibly related (same subject, not in this thread)

2016-10-12 · Re: TCP data throughput for BCM43362 · Jörg Krause <hidden>
2016-10-12 · Re: TCP data throughput for BCM43362 · Jörg Krause <hidden>
2016-09-22 · Re: TCP data throughput for BCM43362 · Jörg Krause <hidden>
2016-09-22 · Re: TCP data throughput for BCM43362 · Arend Van Spriel <arend.vanspriel@broadcom.com>
2016-09-21 · Re: TCP data throughput for BCM43362 · Arend van Spriel <arend.vanspriel@broadcom.com>

On 12-10-16 16:27, Jörg Krause wrote:

On Mi, 2016-10-12 at 10:11 +0200, Arend Van Spriel wrote:

quoted

On 11-10-2016 8:14, Jörg Krause wrote:

quoted



Hi Arend,

Am 22. September 2016 16:00:36 MESZ, schrieb Arend Van Spriel <aren
d.vanspriel@broadcom.com>:

quoted

Op 22 sep. 2016 14:52 schreef "Jörg Krause"
[off-list ref]:

quoted


On Do, 2016-09-22 at 10:09 +0200, Arend Van Spriel wrote:

quoted

On 19-9-2016 8:36, Jörg Krause wrote:

quoted


Hi Arend,

On Wed, 2016-09-14 at 20:13 +0200, Arend Van Spriel wrote:

quoted


On 14-9-2016 15:41, Jörg Krause wrote:

quoted



Hi,

On Mon, 2016-08-29 at 23:15 +0200, Jörg Krause wrote:

quoted



On Mi, 2016-08-24 at 20:35 +0200, Arend Van Spriel
wrote:

quoted




On 22-8-2016 15:37, Jörg Krause wrote:

quoted





Hi all,

I am back from vacation and I'd like to do more
investigations
about
this issue. Please see my comments below...

On Sun, 2016-08-07 at 13:41 +0200, Arend van
Spriel
wrote:

quoted





On 06-08-16 16:12, Jörg Krause wrote:

quoted






Hi all,

A bit weird email format making it a bit hard
to
determine
where
your
last reply starts...

quoted






On Fr, 2016-08-05 at 17:56 -0700, Franky Lin
wrote:

On Fri, Aug 5, 2016 at 2:29 PM, Jörg Krause
<joerg.krause
@emb
ed
ded.
ro
cks>
wrote:





Am 5. August 2016 23:01:10 MESZ, schrieb
Arend Van
Spriel
<
arend.vanspriel@broadcom.com>:


Op 5 aug. 2016 22:46 schreef "Jörg Krause"
[off-list ref]:



Hi,

I'm using a custom ARM board with an BCM43362
wifi
chip
from

Broadcom.


The wifi chip is attached via SDIO to the

controller

quoted

with
a
clock of
48MHz. Linux kernel version is 4.7.

When measuring the network bandwidth with
iperf3 I
get a
bandwith of
only around 5 Mbps. I found a similar thread
at the
Broadcom

community


[1] where the test was done with a M4 CPU +

BCM43362

quoted

and
an
average
result of 3.3 Mbps.

Interestingly, a BCM43362 Wi-Fi Dev Kit [2]
notes a
TCP
data

throughput


greater than 20 Mbps.

Why is the throughput I measured much lower?
Note
that I
measured
several times with almost no neighbor devices
or
networks.

This is a test sample measured with iperf3:

    $ iperf3 -c 192.168.2.1 -i 1 -t 10
    Connecting to host 192.168.2.1, port 5201
    [  4] local 192.168.2.155 port 36442
connected

to

quoted

quoted
quoted
quoted
quoted
quoted
quoted
quoted
quoted
quoted
192.168.2.1

port


    5201
    [ ID]
Interval           Transfer     Bandwidth    
  

Retr

quoted

 Cwn
d
    [  4]   0.00-1.00   sec   615
KBytes  5.04
Mbits/sec    0   56.6
    KBytes
    [  4]   1.00-2.00   sec   622
KBytes  5.10
Mbits/sec    0   84.8
    KBytes
    [  4]   2.00-3.00   sec   625
KBytes  5.12
Mbits/sec    0    113
    KBytes
    [  4]   3.00-4.00   sec   571
KBytes  4.68
Mbits/sec    0    140
    KBytes
    [  4]   4.00-5.00   sec   594
KBytes  4.87
Mbits/sec    0    167
    KBytes
    [  4]   5.00-6.00   sec   628
KBytes  5.14
Mbits/sec    0    195
    KBytes
    [  4]   6.00-7.00   sec   619
KBytes  5.07
Mbits/sec    0    202
    KBytes
    [  4]   7.00-8.00   sec   608
KBytes  4.98
Mbits/sec    0    202
    KBytes
    [  4]   8.00-9.00   sec   602
KBytes  4.93
Mbits/sec    0    202
    KBytes
    [  4]   9.00-10.00  sec   537
KBytes  4.40
Mbits/sec    0    202
    KBytes
    - - - - - - - - - - - - - - - - - - - - -
- - -

quoted

quoted
quoted
quoted
quoted
quoted
quoted
quoted
quoted
quoted
    [ ID]
Interval           Transfer     Bandwidth    
  

Retr

quoted

    [  4]   0.00-10.00  sec  5.88
MBytes  4.93
    Mbits/sec    0             sender
    [  4]   0.00-10.00  sec  5.68
MBytes  4.76
    Mbits/sec                  receiver


Not overly familiar with iperf3. Do these
lines

mean

quoted

you
are
doing
bidirectional test, ie. upstream and
downstream at
the
same
time.
Another
thing affecting tput could be power-save.


No, iperf3 does not support bidrectional
test.

Power-

quoted

save
is
turned
off.

What does iw link say?

but I guess it starts here!

quoted






I compared the results with a Cubietruck I
have:

# iperf3 -s
-------------------------------------------
--------
----
----
Server listening on 5201
-------------------------------------------
--------
----
----
Accepted connection from 192.168.178.46, port
42906
[  5] local 192.168.178.38 port 5201
connected to
192.168.178.46
port
42908
[ ID]
Interval           Transfer     Bandwidth
[  5]   0.00-1.00   sec  2.29 MBytes  19.2
Mbits/sec
[  5]   1.00-2.00   sec  2.21 MBytes  18.5
Mbits/sec
[  5]   2.00-3.00   sec  2.17 MBytes  18.2
Mbits/sec
[  5]   3.00-4.00   sec  2.09 MBytes  17.6
Mbits/sec
[  5]   4.00-5.00   sec  2.20 MBytes  18.5
Mbits/sec
[  5]   5.00-6.00   sec  2.64 MBytes  22.1
Mbits/sec
[  5]   6.00-7.00   sec  2.67 MBytes  22.4
Mbits/sec
[  5]   7.00-8.00   sec  2.62 MBytes  22.0
Mbits/sec
[  5]   8.00-9.00   sec  2.35 MBytes  19.8
Mbits/sec
[  5]   9.00-10.00  sec  2.30 MBytes  19.3
Mbits/sec
[  5]  10.00-10.03  sec  83.4 KBytes  23.5
Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - -
- -
[ ID]
Interval           Transfer     Bandwidth

Retr

quoted

[  5]   0.00-10.03  sec  23.9 MBytes  20.0
Mbits/sec    0             sender
[  5]   0.00-10.03  sec  23.6 MBytes  19.8
Mbits/sec                  receiver

# iw dev wlan0 link
Connected to xx:xx:xx:xx:xx (on wlan0)
      SSID: xxx
      freq: 2437
      tx bitrate: 65.0 MBit/s

      bss flags:      short-preamble short-
slot-
time
      dtim period:    1
      beacon int:     100

Too bad RSSI is not in the output above. That
may be
due to
a
regression
in our driver which has been fixed by commit
94abd778a7bb
("brcmfmac:
add fallback for devices that do not report
per-chain
values").
However,
the tx bitrate seems within the same range as
the

other

quoted

platform.

quoted






The Cubietruck works also with the brcmfmac
driver.

May it depend on the NVRAM file?

Not sure. Can you tell me a bit more about the
custom
ARM
board.
Does
it
use the same wifi module as Cubietruck, ie. the
AMPAK
AP6210?
If
you
can
make a wireshark sniff we can check the actual

bitrate

quoted

and
medium
density in terms of packets. Another thing to
look at
is
the
SDIO
host
controller. In brcmf_sdiod_sgtable_alloc() some
key
values
are
used
from
the host controller. It only logs the number of

entries

quoted

of
the
scatter-gather table, but could you add the
other
values in
this
function that are used to determine the number
of
entries.

My board uses the BCM43362 chip solely (no
Bluetooth)
attached to
the
SDIO interface of a NXP i.MX28 processor.

I added some additional printk() to
brcmf_sdiod_sgtable_alloc().
These
are the values printed after modprobe brcmfmac:

[    8.926657] sg_support=1
[    8.929440] max_blocks=511
[    8.932213] max_request_size=261632
[    8.935741] max_segment_count=52
[    8.939005] max_segment_size=65280
[    8.946095] nents=35

Thanks. That looks good.

quoted





Additionally I attached a xz compresses wireshark
sniff
while
running
iper3 between the BCM43362 running as in AP mode
with
iperf3
as a
server and a PC in station mode running iperf3 as
a
client.

Looking at the sniff it seems you captured on the

ethernet

quoted

side.
That
does not give me any 802.11 specific info. Can you
make a
wireless
capture preferably without encryption.

You,re right! Sorry for this mistake. I did a re-
capture on
the
wireless side now.

Anything new about this? Anything I can do to help?

I missed your previous email. Was already wondering
whether to
ping
you.
Digging around in my email folders I found it so will
take a

look

quoted

at
it.

Did you had some time to look at this?

Ehm. I still only see TCP stuff. To capture 802.11 management

frames

quoted

you
need preferably a dedicated device using monitor mode [1].

Stupid me! Now I used a monitor interface on a desktop to
monitor the
traffic between the BCM43362 operating in soft-AP mode and a
notebook
operating in managed mode.

The BCM43362 runs the iperf server, the notebook the iperf
client.

Thanks.

Week almost through so might next week.

Did you had some time to look at this?

So the bcm43362 is your AP and running iperf server.

It is running the iperf server. It is running in station mode as well
as in AP mode, depending on the use case. The wireshark dump was taken
when the bcm43362 is operating in AP mode.

quoted

What specs does the ARM on your custom board have?

Which specs do you mean?

quoted

The trace shows that it does not do
aggregation. What it does not show is whether A-MPDU was setup, ie.
ADDBA message exchange. So could you create a similar capture
including
connection setup, ie. AUTH/ASSOC, etc.

Yes, I can do that. Note, that I am using wpa_supplicant 2.5 for AP
mode operation (not hostapd).

ok. unchartered territory for me. In the beacon frame I see

.... ..01 = Maximum Rx A-MPDU Length: 0x1 (16383[Bytes])
...1 10.. = MPDU Density: 8 [usec] (0x6)

In the trace it is only ~1500 bytes so no A-MPDU. What device is in the
notebook? Can you use 'iw list' there to obtain info.

quoted

Just to confirm. You are using the firmware from linux-firmware,
right?

Right.

quoted

Or are you using firmware from the wiced dev kit?

No. I guess you mean bcmdhd?

You referred to 20 Mbps claim on wiced dev kit page at mouser so I
assumed you were using that and it includes firmware. As you confirmed
using firmware from linux-firmware repo this question does not matter.

Regards,
Arend

Best regards
Jörg Krause

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help