Messages in this thread Patch in this message | | | Subject | Re: Measuring tools - top and interrupts | From | Mike Galbraith <> | Date | Sat, 24 Jun 2006 08:26:23 +0200 |
| |
On Sat, 2006-06-24 at 07:59 +0200, Mike Galbraith wrote: > On Thu, 2006-06-22 at 09:58 -0700, Danial Thom wrote: > > > And 75K pps may not be "much", but its still at > > least 10% of what the system can handle, so it > > should measure around a 10% load. 2.4 measures > > about 12% load. So the only conclusion is that > > load accounting is broken in 2.6. > > For UP, yes. SMP kernel accounts irq processing time properly.
For my little box, the below cures it.
--- linux-2.6.17x/arch/i386/kernel/apic.c.org 2006-06-24 08:08:46.000000000 +0200 +++ linux-2.6.17x/arch/i386/kernel/apic.c 2006-06-24 08:09:16.000000000 +0200 @@ -1175,9 +1175,7 @@ EXPORT_SYMBOL(switch_ipi_to_APIC_timer); inline void smp_local_timer_interrupt(struct pt_regs * regs) { profile_tick(CPU_PROFILING, regs); -#ifdef CONFIG_SMP update_process_times(user_mode_vm(regs)); -#endif /* * We take the 'long' return path, and there every subsystem
- 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/
| |