Re: [B.A.T.M.A.N.] batctl bw performance

["Gabriel Tolón" <gtolon@inti.gob.ar>]

El 07/06/13 11:40, Antonio Quartulli escribió:
> On Fri, Jun 07, 2013 at 11:38:26AM -0300, Gabriel Tolón wrote:
>> Hi,
>>
>>
>> El 07/06/13 10:57, Antonio Quartulli escribió:
>>> Hi Gabriel,
>>>
>>> thank you for your logs
>>>
>>> On Fri, Jun 07, 2013 at 10:49:10AM -0300, Gabriel Tolón wrote:
>>>>>
>>>>> Hello Gabriel,
>>>>> there is a lot of noise because you are also generating traffic on the network.
>>>>> However I can see the ICMP Echo Request and then an Echo Reply, therefore the
>>>>> two nodes seem to be exchanging ICMP packets correctly.
>>>>>
>>>>> I'm checking again to try to understand what went wrong.
>>>>>
>>>>> Meanwhile, can you please report the output of
>>>>> "batctl l"
>>>>> during a bw test after having set the bw_meter log level by running
>>>>> "batctl ll bwm" ?
>>>>>
>>>>> To get the exact log of one test, you can first run batctl l (this will print
>>>>> all the past log), then you run the test and then you run batctl l again to
>>>>> obtain the interesting log. Please upload it on pastebin too.
>>>>>
>>>>> Thanks a lot!
>>>>>
>>>>
>>>> Sure, here they are:
>>>>
>>>> http://pastebin.com/fLu9hsyt
>>>>
>>>
>>>
>>>   From this log I can see that the protocol is entering Fast Retransmit many times
>>> and this happens due to reordering or small losses (the latter option is more
>>> realistic on a single hop network - but is it really one hop? I never asked).
>>
>> Yes, it's one hop. Just two routers at a distance of 2 meters. They have
>> two radios, but in the last tests I've unloaded one of them (the 5 Ghz
>> one) to make it simpler, so they see each other just by one radio interface.
>>
>>>
>>> The other strange thing I see is the final SRTT value which is 260ms and looks
>>> pretty high. Is there anything else going on the network (other traffic or..)?
>>
>> Mmm, I don't know what's that SRTT, but no, there shouldn't be anything
>> else in the air, at least not from me. But If there were interference or
>> something like that, normal iperf would be slower I guess.
>>
>> Besides, now I've tested connecting my PC via Ethernet to log avoiding
>> interference from myself, also unloading the 2GHz, and loading the 5GHz
>> in the routers (the 5GHz band should be cleaner), and the batctl bw
>> keeps with slower values than iperf, 5Mbps this time.
>>
>> If you want I could sniff the air with wireshark or something.
>>
>> Maybe other possibility could be testing the bw meter connecting the
>> routers by etnernet and not wirelessly?
>
> Yes, you can try ethernet too. it works the same way.
>
>>
>> Just for curiosity, you have already tested this on other scenarios and
>> worked OK?
>
> yeah, I tested it using my routers (OM2Ps) and it worked good.
>
> You can try to sniff one or two seconds of traffic with "batctl td"
> on the nodes. This will give us what is exactly going in the air.
>
> Cheers,
>
>

This time, I logged just from Equipo 1, to generate less traffic.

I noticed something weird. When I run batctl bw I get this time 
something like 12 Mbps. If I wait for about 10 seconds and repeat the 
command, I get something similar, but, if I run the command inmediatly 
after the bw test finishes, the result improves a lot, here you can see 
the commands with the seconds between them:


root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:09 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 3064500 Bytes.
Throughput: 1.46 MB/s (12.26 Mbps)
root@Equipo 1:~#
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:15 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 3201000 Bytes.
Throughput: 1.53 MB/s (12.80 Mbps)
root@Equipo 1:~#
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:18 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 14545500 Bytes.
Throughput: 6.94 MB/s (58.18 Mbps)
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:20 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 18729000 Bytes.
Throughput: 8.93 MB/s (74.91 Mbps)
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:23 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 21067500 Bytes.
Throughput: 10.05 MB/s (84.26 Mbps)
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:26 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 22351500 Bytes.
Throughput: 10.66 MB/s (89.40 Mbps)
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:37 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 13281000 Bytes.
Throughput: 6.33 MB/s (53.12 Mbps)
root@Equipo 1:~#
root@Equipo 1:~#
root@Equipo 1:~#
root@Equipo 1:~# date; batctl bw -t 2000 E3-5GHz
Fri Jun  7 16:40:49 UTC 2013
Bandwidth meter called towards 64:70:02:4e:d9:d7
Test over in 2000ms.
Sent 3204000 Bytes.
Throughput: 1.53 MB/s (12.82 Mbps)
root@Equipo 1:~#


Maybe something in the time calculation is wrong?

The logs are too heavy for pastebin, so here it's just the part 
corresponding to the first batctl bw in Equipo1:

http://pastebin.com/THEr2Cq3

If you want to watch the whole log I can send you, or paste it in parts.

Regards