Re: Changes in the network interface queueing handoff model

Robert Watson wrote this message on Mon, Jul 31, 2006 at 18:08 +0100:
I question whether you need a fallback software if_snd queue at all for
modern devices such as the Intel and Broadcom gigabit chips. The hardware
transmit descriptor rings typically have sizes of the order of 256
descriptors. I think if the ring fills up, you could simply drop the
packet with ENOBUFS. That's what happens if the if_snd queue fills up,
and its maximum size is comparable to the sizes of modern descriptor
rings. It would simplify things quite a bit to eliminate the if_snd queue
entirely for such devices.

I tend to agree, but implemented full queueing support for if_em to make
sure I understood to complexity implications of completely removing
queueing from the ifnet side dispatch. I guess an interesting question for
us is how we decide what the right threshold is to implement software
queuing. Do any if_em cards need software queueing, or do they all have
adequate in-hardware queues as is? Entirely cutting the queue code would
significantly simplify em_startmbuf.

This work tends to lead to a generic ethernet card framework that I've
been thinking about.. where instead of cards doing all the handling of
a ring buffer, the card registers a few functions to manipulate a ring
buffer (if it has one), and does the necessary work... Though encoding
all the different style of ring buffers may be interesting, per packet
instead of per segment (if_re)...

The other part is to digest the current monolithic lock structure that
the ethernet cards have, into three (or four) different locks, tx head,
tx tail, rx head & tail...

--
John-Mark Gurney Voice: +1 415 225 5579

"All that I will do, has been done, All that I have, has not."
_______________________________________________
freebsd-arch@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-arch
To unsubscribe, send any mail to "freebsd-arch-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: Changes in the network interface queueing handoff model
    ... I think if the ring fills up, ... and its maximum size is comparable to the sizes of modern descriptor ... It would simplify things quite a bit to eliminate the if_snd queue ... Do any if_em cards need software queueing, ...
    (freebsd-net)
  • Re: [PATCH take 2] Atmel MACB ethernet driver
    ... If it's a problem with the descriptor, it would probably help to dump ... in the ring to see if any of them look suspicious. ... ARM people. ...
    (Linux-Kernel)
  • -Crawl- What a temptation..-6 armor randart.. and a YACD
    ... M - 14 orcish arrows ... // Really need to wear this instead of the ring mail. ... B - a deck of cards ...
    (rec.games.roguelike.misc)
  • Re: [PATCHv8 3/3] vhost_net: a kernel-level virtio server
    ... queue in backend device: we tell backend to send it and forget. ... separate because I want to make it possible to relocate e.g. used ring ... to another address while ring is running. ...
    (Linux-Kernel)
  • Re: [PATCH] virtio_net: free transmit skbs in a timer
    ... notification when there are no more packets in xmit ring would be ... The reason I'm interested in adjustable thresholds is that you can then to tx mitigation without suffering the worst-case latency when you aren't streaming or streaming slower than what you tuned for. ... is talking about moving network tx queue into the net drivers themselves, ...
    (Linux-Kernel)