On Sat, Oct 03, 2020 at 05:54:38AM +0200, Eric Dumazet wrote:
>
> Sure, a WQ is already giving nice results on appliances, because there
> you do not need strong isolation.
> Would a kthread approach also work well on appliances ? Probably...
Right. I think we're on the same page.
The only reason
On Fri, Oct 2, 2020 at 4:02 PM David Miller wrote:
>
> From: Wei Wang
> Date: Wed, 30 Sep 2020 12:21:35 -0700
>
> ...
> > And the reason we prefer 1 kthread per napi, instead of 1 workqueue
> > entity per host, is that kthread is more configurable than workqueue,
> > and we could leverage existi
From: Wei Wang
Date: Wed, 30 Sep 2020 12:21:35 -0700
...
> And the reason we prefer 1 kthread per napi, instead of 1 workqueue
> entity per host, is that kthread is more configurable than workqueue,
> and we could leverage existing tuning tools for threads, like taskset,
> chrt, etc to tune sche
On Thu, 1 Oct 2020 18:44:40 -0700 Wei Wang wrote:
> > Can you share relative performance delta of this banchmark?
> >
> > Could you explain why threads are slower than ksoftirqd if you pin the
> > application away? From your cover letter it sounded like you want the
> > scheduler to see the NAPI lo
On Fri, 2 Oct 2020 09:56:31 +0200 Eric Dumazet wrote:
> On Thu, Oct 1, 2020 at 10:26 PM Jakub Kicinski wrote:
> >
> > On Thu, 1 Oct 2020 09:52:45 +0200 Eric Dumazet wrote:
>
> > > The unique work queue is a problem on server class platforms, with
> > > NUMA placement.
> > > We now have servers
On Thu, 1 Oct 2020 15:12:20 -0700 Wei Wang wrote:
> Yes. I did a round of testing with workqueue as well. The "real
> workload" I mentioned is a google internal application benchmark which
> involves networking as well as disk ops.
> There are 2 types of tests there.
> 1 is sustained tests, where
On Thu, 1 Oct 2020 09:52:45 +0200 Eric Dumazet wrote:
> On Wed, Sep 30, 2020 at 10:08 PM Jakub Kicinski wrote:
> > On Wed, 30 Sep 2020 12:21:35 -0700 Wei Wang wrote:
> > > With napi poll moved to kthread, scheduler is in charge of scheduling both
> > > the kthreads handling network load, and the
On Wed, 30 Sep 2020 12:21:35 -0700 Wei Wang wrote:
> With napi poll moved to kthread, scheduler is in charge of scheduling both
> the kthreads handling network load, and the user threads, and is able to
> make better decisions. In the previous benchmark, if we do this and we
> pin the kthreads proc
