Messages in this thread | | | Date | Thu, 28 Nov 2013 15:57:55 +0100 | From | Peter Zijlstra <> | Subject | Re: [PATCH]: exec: avoid propagating PF_NO_SETAFFINITY into userspace child |
| |
On Thu, Nov 28, 2013 at 09:53:25AM -0500, Tejun Heo wrote: > On Thu, Nov 28, 2013 at 03:43:59PM +0100, Peter Zijlstra wrote: > > On Thu, Nov 28, 2013 at 03:31:45PM +0100, Peter Zijlstra wrote: > > > Sure, we absolutely must set it for per-cpu workqueues (and their > > > workers) otherwise we cannot guarantee correctness. Same for per-node if > > > we have that. > > > > On that, the per-node thing is debatable. There's no correctness issues > > with per-node stuff as we have with per-cpu storage. > > > > And if there's no correctness implications we should not force things. > > That's true iff you confine the "correctness" to not crashing. That's > an extremely narrow definition tho and most will argue against that.
Do you have a better definition that doesn't get in the way of people wanting to do actual work?
So far I just see you breaking existing setups because you don't want to support things that work perfectly well.
| |