Re: MSEC_TO_JIFFIES is messed up...
From: William Lee Irwin III <hidden>
Date: 2004-05-12 22:20:41
Also in:
lkml
On Wed, May 12, 2004 at 11:17:48PM +0200, Ingo Molnar wrote:
ok. -A3 attached, it does the roundup in the msec->jiffies conversion. (not the other way around though, and that's fine.)
I'm assuming -A3 is current, then: Optimize the cases where HZ is a divisor of 1000 or vice-versa in JIFFIES_TO_MSECS() and MSECS_TO_JIFFIES() by allowing the nonvanishing(!) integral ratios to appear as a parenthesized expressions eligible for constant folding optimizations. -- wli Index: linux-2.5/include/linux/time.h ===================================================================
--- linux-2.5.orig/include/linux/time.h 2004-05-12 15:04:10.000000000 -0700
+++ linux-2.5/include/linux/time.h 2004-05-12 15:12:49.000000000 -0700@@ -184,12 +184,12 @@ * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ -#if HZ == 1000 -# define JIFFIES_TO_MSECS(x) (x) -# define MSECS_TO_JIFFIES(x) (x) -#elif HZ == 100 -# define JIFFIES_TO_MSECS(x) ((x) * 10) -# define MSECS_TO_JIFFIES(x) (((x) + 9) / 10) +#if HZ <= 1000 && !(1000 % HZ) +# define JIFFIES_TO_MSECS(j) ((1000/HZ)*(j)) +# define MSECS_TO_JIFFIES(m) (((m) + (1000/HZ) - 1)/(1000/HZ)) +#elif HZ > 1000 && !(HZ % 1000) +# define JIFFIES_TO_MSECS(j) (((j) + (HZ/1000) - 1)/(HZ/1000)) +# define MSECS_TO_JIFFIES(m) ((m)*(HZ/1000)) #else # define JIFFIES_TO_MSECS(x) (((x) * 1000) / HZ) # define MSECS_TO_JIFFIES(x) (((x) * HZ + 999) / 1000)