Messages in this thread | | | Date | Fri, 3 Mar 2000 16:16:16 +0100 (CET) | From | Ingo Molnar <> | Subject | Re: new IRQ scalability changes in 2.3.48 |
| |
On Fri, 3 Mar 2000 yodaiken@fsmlabs.com wrote:
> Since we need a spin lock anyways in doIRQ, I still don't get how > this makes things any better.
if different IRQs are delivered to different CPUs, then there is no global spinlock connection between them. Also see /proc/irq/*/smp_affinity. Eg. if we localize a given IRQ to a single CPU, another IRQ source to another CPU then they will no more interact with each other. But the effect is there even in the generic case where APIC IRQs typically come in groups. (ie. the same CPU is used as a target for several IRQs, then another CPU is picked.)
-- mingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |