[net] protecting interfaces from races between control and data ?

[Adrian Chadd]

On 7 August 2013 13:08, Scott Long <scott4long at yahoo.com> wrote:

> An even rore relevant difference is that taskqueues have a much stronger
> management API.  Ithreads can only be scheduled by generating a hardware interrupt,
> can only be drained by calling bus_teardown_intr(), and cannot be paused.  Taskqueues
> give you direct access to this control.

It would be really nice if we had a software method to trigger an
ithread to run, like a software interrupt.

It would also be nice to pin taskqueues to CPUs, we can do with
ithreads at the moment.



-adrian