Re: [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.32-15

[Ingo Molnar]

* Mark_H_Johnson@xxxxxxxxxxxx <Mark_H_Johnson@xxxxxxxxxxxx> wrote:

> A comparison of PREEMPT_RT (no tracing) to PREEMPT_DESKTOP
> (with tracing) to help answer previous requests.
> 
> Comparison of .32-20RT and .32-18PK results
> 20RT has PREEMPT_RT (all tracing disabled)
> 18PK has PREEMPT_DESKTOP and no threaded IRQ's (tracing enabled)
> 2.4 has lowlat + preempt patches applied
> 
>       within 100 usec
>        CPU loop (%)   Elapsed Time (sec)    2.4
> Test   RT     PK        RT      PK   |   CPU  Elapsed
> X     99.87 100.00&     65 *    64+  |  97.20   70
> top   99.35 100.00&     31 *    31+  |  97.48   29
> neto  96.94 100.00&    113 *   184+  |  96.23   36
> neti  97.05 100.00&    119 *   170+  |  95.86   41

interesting - the PK kernel with tracing enabled performs better than
the PK kernel with tracing disabled? Sounds counter-intuitive.

	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/