Messages in this thread | | | Subject | Re: [patch] sched: fix scheduling latencies for !PREEMPT kernels | From | Lee Revell <> | Date | Tue, 14 Sep 2004 20:35:15 -0400 |
| |
On Tue, 2004-09-14 at 10:54, Ingo Molnar wrote: > * Nick Piggin <nickpiggin@yahoo.com.au> wrote: > > > Another thing, I don't mean this to sound like a rhetorical question, > > but if we have a preemptible kernel, why is it a good idea to sprinkle > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > > cond_rescheds everywhere? Isn't this now the worst of both worlds? Why > > would someone who really cares about latency not enable preempt? > > two things: > > 1) none of the big distros enables CONFIG_PREEMPT in their kernels - not > even SuSE. This is pretty telling. >
I am not sure this means preemption is a bad idea, it just means there's no point in enabling CONFIG_PREEMPT with the current kernel because it's not enough of an improvement to make a difference for low latency applications.
Lee
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |