Thread (8 messages) 8 messages, 4 authors, 2008-08-30

Re: [NET_NEXT PATCH 1/2] pkt_sched: Add multiqueue scheduler support

From: Alexander Duyck <hidden>
Date: 2008-08-28 16:07:22

It looks mostly fine.

But I wonder how useful this "bands" parameter is.
It behaves as follows:

1) "1" is always allowed, essentially non-multiqueue
2) ->real_num_tx_queues is always allowed
3) 0 means auto detect, which is also ->real_num_tx_queues

Everything else is rejected.
Actually you give me too much credit.  I don't think bands even works
as a boolean, or at least it wasn't meant to.  It was supposed to be 0
or the number of queues which either way ends up the number of queues.
 It was a bit of leftover interface from the rr/prio configuration.  I
realized I left that in there when I was driving home last night but
by then it was too late.

I will probably just have it always default the number of bands to
always be real_num_tx_queues and save the user from having to enter
bands in the tc command line.

Thanks,

Alex
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help