Re: [PATCH net-next 09/10] sctp: introduce priority based stream scheduler

[Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>]

On Fri, Sep 29, 2017 at 12:54:58PM -0400, Neil Horman wrote:
> On Thu, Sep 28, 2017 at 05:25:22PM -0300, Marcelo Ricardo Leitner wrote:
> > This patch introduces RFC Draft ndata section 3.4 Priority Based
> > Scheduler (SCTP_SS_PRIO).
> > 
> > It works by having a struct sctp_stream_priority for each priority
> > configured. This struct is then enlisted on a queue ordered per priority
> > if, and only if, there is a stream with data queued, so that dequeueing
> > is very straightforward: either finish current datamsg or simply dequeue
> > from the highest priority queued, which is the next stream pointed, and
> > that's it.
> > 
> > If there are multiple streams assigned with the same priority and with
> > data queued, it will do round robin amongst them while respecting
> > datamsgs boundaries (when not using idata chunks), to be reasonably
> > fair.
> > 
> > We intentionally don't maintain a list of priorities nor a list of all
> > streams with the same priority to save memory. The first would mean at
> > least 2 other pointers per priority (which, for 1000 priorities, that
> > can mean 16kB) and the second would also mean 2 other pointers but per
> > stream. As SCTP supports up to 65535 streams on a given asoc, that's
> > 1MB. This impacts when giving a priority to some stream, as we have to
> > find out if the new priority is already being used and if we can free
> > the old one, and also when tearing down.
> > 
> > The new fields in struct sctp_stream_out_ext and sctp_stream are added
> > under a union because that memory is to be shared with other schedulers.
> > It could be defined as an opaque area like skb->cb, but that would make
> > the list handling a nightmare.
> > 
> > See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
> > Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
> I presume here that it will be up to the application to rate limit its own
> throughput so as to prevent starvation of lower priority streams within an
> association?

That's my expection as well. If it cannot manage its own throughput,
then it should use another scheduler.

  Marcelo