Re: [GIT PULL] Re: REGRESSION: Performance regressions fromswitching anon_vma->lock to mutex

[Ingo Molnar]

* Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> wrote:

> 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, ...)

There's a crazy solution for that: the idle thread could process RCU 
callbacks carefully, as if it was running user-space code.

/me runs

Ok, joke aside: this is simply a special case where the idle thread 
generates RCU work via hardirqs. The idle thread is arguably special 
and could be handled in a special way: a helper thread that executes 
only in this case?

Thanks,

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/