Messages in this thread | | | Subject | Re: [RFC PATCH 0/2] net: threadable napi poll loop | From | Rik van Riel <> | Date | Wed, 11 May 2016 11:01:43 -0400 |
| |
On Wed, 2016-05-11 at 07:40 -0700, Eric Dumazet wrote: > On Wed, May 11, 2016 at 6:13 AM, Hannes Frederic Sowa > <hannes@stressinduktion.org> wrote: > > > This looks racy to me as the ksoftirqd could be in the progress to > > stop > > and we would miss another softirq invocation. > > Looking at smpboot_thread_fn(), it looks fine : >
Additionally, we are talking about waking up ksoftirqd on the same CPU.
That means the wakeup code could interrupt ksoftirqd almost going to sleep, but the two code paths could not run simultaneously.
That does narrow the scope considerably.
-- All rights reversed [unhandled content-type:application/pgp-signature] | |