Re: [RFC 1/2] softirq: Defer net rx/tx processing to ksoftirqd context

From: Linus Torvalds
Date: Thu Jan 11 2018 - 15:22:47 EST


On Thu, Jan 11, 2018 at 12:16 PM, Eric Dumazet <edumazet@xxxxxxxxxx> wrote:
>
> Note that when I implemented TCP Small queues, I did experiments between
> using a work queue or a tasklet, and workqueues added unacceptable P99
> latencies, when many user threads are competing with kernel threads.

Yes.

So I think one solution might be to have a hybrid system, where we do
the softirq's synchronously normally (which is what you really want
for good latency).

But then fall down on a threaded model - but that fallback case should
be per-softirq, not global. So if one softirq uses a lot of CPU time,
that shouldn't affect the latency of other softirqs.

So maybe we could get rid of the per-cpu ksoftirqd entirely, and
replace it with with per-cpu and per-softirq workqueues?

Would something like that sound sane?

Just a SMOP/SMOT (small matter of programming/testing).

Linus