On Tue, 19 Nov 2002, Ian Morgan wrote:
> # cat /proc/cpufreq
> minimum CPU frequency - maximum CPU frequency - policy
> CPU 0 2405487 kHz ( 100 %) - 2706165 kHz (112 %) - powersave
Can you try this patch?
Index: linux-2.4.20-rc1-ac4/arch/i386/kernel/p4-clockmod.c
===================================================================
RCS file: /build/cvsroot/linux-2.4.20-rc1-ac4/arch/i386/kernel/p4-clockmod.c,v
retrieving revision 1.1.1.1
diff -u -r1.1.1.1 p4-clockmod.c
--- linux-2.4.20-rc1-ac4/arch/i386/kernel/p4-clockmod.c 18 Nov 2002 01:39:49 -0000 1.1.1.1
+++ linux-2.4.20-rc1-ac4/arch/i386/kernel/p4-clockmod.c 22 Nov 2002 06:12:11 -0000
@@ -209,7 +209,7 @@
if (number_states)
return;
- policy->max = (stock_freq / 8) * (((unsigned int) ((policy->max * 8) / stock_freq)) + 1);
+ policy->max = ((stock_freq / 8) * (((unsigned int) ((policy->max * 80) / stock_freq)))/10);
return;
}
> On the other hand, some short (<1 min) cpu-bound processes for benchmarking
> each took the same amount of time to run when the clock was at 12%, 100%,
> and 112%, so I'm not sure the clock was really being changed at all.
I can look into that.
-- function.linuxpower.ca- 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/
This archive was generated by hypermail 2b29 : Sat Nov 23 2002 - 22:00:39 EST