From: "Chen, Kenneth W" This could be part of the unknown 2% performance regression with db transaction processing benchmark. The four functions in the following patch use to be inline. They are un-inlined since 2.6.7. We measured that by re-inline them back on 2.6.9, it improves performance for db transaction processing benchmark, +0.2% (on real hardware :-) The cost is certainly larger kernel size, cost 928 bytes on x86, and 2728 bytes on ia64. But certainly worth the money for enterprise customer since they improve performance on enterprise workload. # size vmlinux.* text data bss dec hex filename 3261844 717184 262020 4241048 40b698 vmlinux.x86.orig 3262772 717488 262020 4242280 40bb68 vmlinux.x86.inline text data bss dec hex filename 5836933 903828 201940 6942701 69efed vmlinux.ia64.orig 5839661 903460 201940 6945061 69f925 vmlinux.ia64.inline Possible we can introduce them back? Signed-off-by: Ken Chen Signed-off-by: Andrew Morton --- 25-akpm/kernel/sched.c | 8 ++++---- 1 files changed, 4 insertions(+), 4 deletions(-) diff -puN kernel/sched.c~sched-re-inline-sched-functions kernel/sched.c --- 25/kernel/sched.c~sched-re-inline-sched-functions 2005-03-11 12:32:16.000000000 -0800 +++ 25-akpm/kernel/sched.c 2005-03-11 12:32:16.000000000 -0800 @@ -166,7 +166,7 @@ #define SCALE_PRIO(x, prio) \ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE) -static unsigned int task_timeslice(task_t *p) +static inline unsigned int task_timeslice(task_t *p) { if (p->static_prio < NICE_TO_PRIO(0)) return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio); @@ -282,7 +282,7 @@ static DEFINE_PER_CPU(struct runqueue, r * interrupts. Note the ordering: we can safely lookup the task_rq without * explicitly disabling preemption. */ -static runqueue_t *task_rq_lock(task_t *p, unsigned long *flags) +static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags) __acquires(rq->lock) { struct runqueue *rq; @@ -402,7 +402,7 @@ struct file_operations proc_schedstat_op /* * rq_lock - lock a given runqueue and disable interrupts. */ -static runqueue_t *this_rq_lock(void) +static inline runqueue_t *this_rq_lock(void) __acquires(rq->lock) { runqueue_t *rq; @@ -1308,7 +1308,7 @@ void fastcall sched_exit(task_t * p) * with the lock held can cause deadlocks; see schedule() for * details.) */ -static void finish_task_switch(task_t *prev) +static inline void finish_task_switch(task_t *prev) __releases(rq->lock) { runqueue_t *rq = this_rq(); _