On Thu, Sep 11, 2008 at 09:54:49PM +1000, Herbert Xu wrote:

On Thu, Sep 11, 2008 at 11:51:32AM +0000, Jarek Poplawski wrote:

quoted

IMHO, the most reasonable test here is for all tx_queues of a qdisc
beeing stopped, but since this is quite heavy, probably we need an
additional qdisc flag for such an occasion.

Yes we could do that too.  Although the head-of-qdisc approach
will eventually lead to the same result.  That is, as you pop
things off the head eventually you'll hit a packet that belongs
to the stopped queue and that'll then block the whole qdisc.

So I don't think there's anything inherently advantageous in
checking all the queues.

Yes, but this is only because this current behaviour of blocking all
transmit by one stopped tx_queue is wrong (IMHO), and with sch_multiq
there should be a real advantage.

Cheers,
Jarek P.