Messages in this thread | | | Date | Fri, 12 Jan 2018 15:58:21 +0100 | From | Frederic Weisbecker <> | Subject | Re: [RFC 1/2] softirq: Defer net rx/tx processing to ksoftirqd context |
| |
On Fri, Jan 12, 2018 at 06:23:08AM +0100, Mike Galbraith wrote: > On Thu, 2018-01-11 at 12:22 -0800, Linus Torvalds wrote: > > On Thu, Jan 11, 2018 at 12:16 PM, Eric Dumazet <edumazet@google.com> 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? > > How would that be better than what RT used to do, and I still do for my > RT kernels via boot option, namely split ksoftirqd into per-softirq > threads.
Workqueue are probably more simple. Unless you need to set specific prios to your ksoftirqds? Not sure if that's tunable on workqueues.
| |