On Tue, Aug 16, 2022 at 4:07 PM Jakub Kicinski [off-list ref] wrote:

On Tue, 16 Aug 2022 07:02:33 +0000 Bobby Eshleman wrote:

quoted

quoted

From a cursory look (and Documentation/ would be nice..) it feels
very wrong to me. Do you know of any uses of a netdev which would
be semantically similar to what you're doing? Treating netdevs as
buildings blocks for arbitrary message passing solutions is something
I dislike quite strongly.

The big difference between vsock and "arbitrary message passing" is that
vsock is actually constrained by the virtio device that backs it (made
up of virtqueues and the underlying protocol). That virtqueue pair is
acting like the queues on a physical NIC, so it actually makes sense to
manage the queuing of vsock's device like we would manage the queueing
of a real device.

Still, I concede that ignoring the netdev state is a probably bad idea.

That said, I also think that using packet scheduling in vsock is a good
idea, and that ideally we can reuse Linux's already robust library of
packet scheduling algorithms by introducing qdisc somehow.

We've been burnt in the past by people doing the "let me just pick
these useful pieces out of netdev" thing. Makes life hard both for
maintainers and users trying to make sense of the interfaces.

I interpret this in a different way: we just believe "one size does
not fit all",
as most Linux kernel developers do. I am very surprised you don't.

Feel free to suggest any other ways, eventually you will need to
reimplement TC one way or the other.

If you think about it in another way, vsock is networking too, its name
contains a "sock", do I need to say more? :)

What comes to mind if you're just after queuing is that we already
bastardized the CoDel implementation (include/net/codel_impl.h).
If CoDel is good enough for you maybe that's the easiest way?
Although I suspect that you're after fairness not early drops.
Wireless folks use CoDel as a second layer queuing. (CC: Toke)

What makes you believe CoDel fits all cases? If it really does, you
probably have to convince Toke to give up his idea on XDP map
as it would no longer make any sense. I don't see you raise such
an argument there... What makes you treat this differently with XDP
map? I am very curious about your thought process here. ;-)

Thanks.