From: Nick Piggin Avoid expensive integer divide 3 times per CPU per tick. A userspace test of this loop went from 26ns, down to 19ns on a G5; and from 123ns down to 28ns on a P3. (Also avoid a variable bit shift, as suggested by Alan. The effect of this wasn't noticable on the CPUs I tested with). Signed-off-by: Nick Piggin Cc: Ingo Molnar Cc: Alan Cox Signed-off-by: Andrew Morton --- kernel/sched.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff -puN kernel/sched.c~sched-avoid-div-in-rebalance_tick kernel/sched.c --- a/kernel/sched.c~sched-avoid-div-in-rebalance_tick +++ a/kernel/sched.c @@ -2905,14 +2905,16 @@ static void active_load_balance(struct r static void update_load(struct rq *this_rq) { unsigned long this_load; - int i, scale; + unsigned int i, scale; this_load = this_rq->raw_weighted_load; /* Update our load: */ - for (i = 0, scale = 1; i < 3; i++, scale <<= 1) { + for (i = 0, scale = 1; i < 3; i++, scale += scale) { unsigned long old_load, new_load; + /* scale is effectively 1 << i now, and >> i divides by scale */ + old_load = this_rq->cpu_load[i]; new_load = this_load; /* @@ -2922,7 +2924,7 @@ static void update_load(struct rq *this_ */ if (new_load > old_load) new_load += scale-1; - this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale; + this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; } } _