prio qdisc broken?

[Joerg Pommnitz]

Hello all,
I might make a fool out of me, but I think the prio qdisc doesn't work as
advertised in any document I could lay my hands on.

The following tests and observations were made with Linux kernel 2.6.20.21.
This makes it up-to-date in the 2.6.20.x kernel family.

My problem was that the link quality reported by the olsr.org olsrd degraded
depending on the amount of payload traffic was transferred through an
adhoc/mesh interface. The LQ is calculated from the packet loss of LQ Hello
packets sent through this interface. To make sure normal traffic does not
interfere with this value, olsrd sets the TOS field to 0x10 (Minimize-Delay)
by default. In theory this should give olsr traffic the highest priority on the link.

Investigating this issue I replaced the default Pfifo_fast with a prio qdisc and
attached a pfifo on each of the bands:

INTERFACE=wifi0
tc qdisc add dev $INTERFACE root handle 1: prio
tc qdisc add dev $INTERFACE parent 1:1 handle 10: pfifo
tc qdisc add dev $INTERFACE parent 1:2 handle 20: pfifo
tc qdisc add dev $INTERFACE parent 1:3 handle 30: pfifo

Then I used "ping -Q TOSVALUE target" to send packets with different TOS
values through the interface. "tcpdump -vvv" confirmed the correct TOS values
in the outgoing packets.

With "tc -s qdisc ls dev wifi0" I could observe the effects of the different TOS
values. The result: no effect at all! Every single packet used the band indicated
by the first value in the priomap (e.g. band 1 by default, in my case the pfifo
with handle 20:). I can't square this observation with the available documentation.

Looking at the source code, it seems that sched_prio uses the skb->priority
value to select the outgoing band. According to some documentation I found,
an application can set this value.

The following is more speculation than an educated guess: Could it be that
skb->priority used to be set according to the TOS field by default and that this
changed after the implementation of prio?

So, can somebody confirm or deny that the problem I see is real? Is there a fix?

Thanks in advance
Joerg



Heute schon einen Blick in die Zukunft von E-Mails wagen? Versuchen Sie´s mit dem neuen Yahoo! Mail. www.yahoo.de/mail

[Andy Furniss]

Post by Joerg Pommnitz
Hello all,
I might make a fool out of me, but I think the prio qdisc doesn't work as
advertised in any document I could lay my hands on.
The following tests and observations were made with Linux kernel 2.6.20.21.
This makes it up-to-date in the 2.6.20.x kernel family.

If it's kernel version you are unlucky - I just tested with a 2.6.19-rc6
and a 2.6.21.1 and it seems OK.

Echo replies don't work, and they haven't on others versions as well,
but this could be deliberate anti dos plus I am not testing forwarded
traffic.

Post by Joerg Pommnitz
My problem was that the link quality reported by the olsr.org olsrd degraded
depending on the amount of payload traffic was transferred through an
adhoc/mesh interface. The LQ is calculated from the packet loss of LQ Hello
packets sent through this interface. To make sure normal traffic does not
interfere with this value, olsrd sets the TOS field to 0x10 (Minimize-Delay)
by default. In theory this should give olsr traffic the highest priority on the link.

Even if you fix it I don't think it will help wireless using just prio.

There are/will be extensions to prio AIUI - multiqueue which if the
wireless driver supports it, prio bands will map to hardware/link layer
prio bands on the device.

Andy.