Messages in this thread | | | Subject | Re: [GIT PULL] Re: REGRESSION: Performance regressions from switching anon_vma->lock to mutex | From | Benjamin Herrenschmidt <> | Date | Fri, 17 Jun 2011 08:21:23 +1000 |
| |
On Thu, 2011-06-16 at 22:25 +0200, Ingo Molnar wrote:
> > Whatever does the boosting will need to have process context and > > can be subject to delays, so that pretty much needs to be a > > kthread. But it will context-switch quite rarely, so should not be > > a problem. > > So user-return notifiers ought to be the ideal platform for that, > right? We don't even have to touch the scheduler: anything that > schedules will eventually return to user-space, at which point the > RCU GC magic can run. > > And user-return-notifiers can be triggered from IRQs as well. > > That allows us to get rid of softirqs altogether and maybe even speed > the whole thing up and allow it to be isolated better.
I'm a little worried of relying on things returning to userspace.
One could imagine something like a router appliance where userspace is essentially asleep forever and everything happens in the kernel (networking via softirq, maybe NFS kernel server, ...)
Cheers, Ben.
| |