Commit 60e24239 authored by Jeremy Kerr's avatar Jeremy Kerr Committed by Paul Mackerras

[POWERPC] spusched: Fix timeslice calculations

The current timeslice code mixes 'jiffies' up with 'spesched ticks'. This
change correctly defines the number of time slices each SPE contexts is
given, and clarifies the comment.

This brings the default timeslice for SPE contexts into a reasonable
range.
Signed-off-by: default avatarJeremy Kerr <jk@ozlabs.org>
Signed-off-by: default avatarPaul Mackerras <paulus@samba.org>
parent fe443ef2
...@@ -70,11 +70,11 @@ static struct timer_list spusched_timer; ...@@ -70,11 +70,11 @@ static struct timer_list spusched_timer;
/* /*
* These are the 'tuning knobs' of the scheduler: * These are the 'tuning knobs' of the scheduler:
* *
* Minimum timeslice is 5 msecs (or 10 jiffies, whichever is larger), * Minimum timeslice is 5 msecs (or 1 spu scheduler tick, whichever is
* default timeslice is 100 msecs, maximum timeslice is 800 msecs. * larger), default timeslice is 100 msecs, maximum timeslice is 800 msecs.
*/ */
#define MIN_SPU_TIMESLICE max(5 * HZ / 100, 10) #define MIN_SPU_TIMESLICE max(5 * HZ / (1000 * SPUSCHED_TICK), 1)
#define DEF_SPU_TIMESLICE (100 * HZ / 100) #define DEF_SPU_TIMESLICE (100 * HZ / (1000 * SPUSCHED_TICK))
#define MAX_USER_PRIO (MAX_PRIO - MAX_RT_PRIO) #define MAX_USER_PRIO (MAX_PRIO - MAX_RT_PRIO)
#define SCALE_PRIO(x, prio) \ #define SCALE_PRIO(x, prio) \
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment