Messages in this thread | | | Date | Sun, 23 Nov 2008 14:36:04 +0100 | From | Ingo Molnar <> | Subject | Re: [PATCH 2/2 v3] SGI RTC: add generic timer system interrupt |
| |
* H. Peter Anvin <hpa@zytor.com> wrote:
> Dimitri Sivanich wrote: > > > > There are basically two issues with using 'normal IRQs' in cases like this: > > > > - Using normal IRQs would mean we would have an IRQ per cpu. The current > > hard coded maximum, NR_IRQS, is 4352 (NR_VECTORS + (32 * MAX_IO_APICS)). > > On machines with large numbers of cpus and an irq per cpu for each desired > > interrupt, that's a lot of IRQs. In addition, the GRU, will need 2 such > > IRQs per cpu. On 4096 cpu systems, you've already used up more than the > > limit just for that. Until some sort of infrastructure change takes place > > that would potentially allow this to be dynamically increased, such as > > Yinghai Lu's "sparse_irq aka dyn_irq v14" patch, this problem will exist. > > > > Furthermore, the actual runtime limit, nr_irqs, is set to 96 by > > probe_nr_irqs for our configuration. This is because that code assumes all > > vectors are io-apic vectors, not cpu centric vectors like the ones I'm > > talking about. With the current, scheme, even on a 128 cpu system, I'm out > > of IRQs immediately. > > > > - The current infrastructure for requesting vector/IRQ combinations doesn't > > allow one to request an interrupt priority higher than i/o device interrupt > > priorities. Clock event (high resolution timer) code should run at higher > > interrupt priority. > > Okay, so it is a hack pending us taking care of issues in the > current code. #1 we're obviously working on, #2 I need to think > some more about but shouldn't be too hard to fix -- if real, it also > affects other interrupt-driven clock sources. > > I'm OK with this being a temporary hack, but I want it to be > recognized as such and cleaned up as soon as possible.
okay.
Dimitri, looks like there are no blocker issues - John's clocksource comments need to be addressed and then we should be green to go for having this applied.
Ingo
| |