From 758b2cdc6f6a22c702bd8f2344382fb1270b2161 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 25 Nov 2008 02:35:04 +1030 Subject: sched: wrap sched_group and sched_domain cpumask accesses. Impact: trivial wrap of member accesses This eases the transition in the next patch. We also get rid of a temporary cpumask in find_idlest_cpu() thanks to for_each_cpu_and, and sched_balance_self() due to getting weight before setting sd to NULL. Signed-off-by: Rusty Russell Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel/sched_fair.c') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 98345e4..bba0040 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1024,7 +1024,6 @@ static void yield_task_fair(struct rq *rq) #if defined(ARCH_HAS_SCHED_WAKE_IDLE) static int wake_idle(int cpu, struct task_struct *p) { - cpumask_t tmp; struct sched_domain *sd; int i; @@ -1044,10 +1043,9 @@ static int wake_idle(int cpu, struct task_struct *p) if ((sd->flags & SD_WAKE_IDLE) || ((sd->flags & SD_WAKE_IDLE_FAR) && !task_hot(p, task_rq(p)->clock, sd))) { - cpus_and(tmp, sd->span, p->cpus_allowed); - cpus_and(tmp, tmp, cpu_active_map); - for_each_cpu_mask_nr(i, tmp) { - if (idle_cpu(i)) { + for_each_cpu_and(i, sched_domain_span(sd), + &p->cpus_allowed) { + if (cpu_active(i) && idle_cpu(i)) { if (i != task_cpu(p)) { schedstat_inc(p, se.nr_wakeups_idle); @@ -1240,7 +1238,7 @@ static int select_task_rq_fair(struct task_struct *p, int sync) * this_cpu and prev_cpu are present in: */ for_each_domain(this_cpu, sd) { - if (cpu_isset(prev_cpu, sd->span)) { + if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) { this_sd = sd; break; } -- cgit v1.1 From 96f874e26428ab5d2db681c100210c254775e154 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 25 Nov 2008 02:35:14 +1030 Subject: sched: convert remaining old-style cpumask operators Impact: Trivial API conversion NR_CPUS -> nr_cpu_ids cpumask_t -> struct cpumask sizeof(cpumask_t) -> cpumask_size() cpumask_a = cpumask_b -> cpumask_copy(&cpumask_a, &cpumask_b) cpu_set() -> cpumask_set_cpu() first_cpu() -> cpumask_first() cpumask_of_cpu() -> cpumask_of() cpus_* -> cpumask_* There are some FIXMEs where we all archs to complete infrastructure (patches have been sent): cpu_coregroup_map -> cpu_coregroup_mask node_to_cpumask* -> cpumask_of_node There is also one FIXME where we pass an array of cpumasks to partition_sched_domains(): this implies knowing the definition of 'struct cpumask' and the size of a cpumask. This will be fixed in a future patch. Signed-off-by: Rusty Russell Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched_fair.c') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index bba0040..08ffffd 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1017,7 +1017,7 @@ static void yield_task_fair(struct rq *rq) * search starts with cpus closest then further out as needed, * so we always favor a closer, idle cpu. * Domains may include CPUs that are not usable for migration, - * hence we need to mask them out (cpu_active_map) + * hence we need to mask them out (cpu_active_mask) * * Returns the CPU we should wake onto. */ @@ -1244,7 +1244,7 @@ static int select_task_rq_fair(struct task_struct *p, int sync) } } - if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) + if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed))) goto out; /* -- cgit v1.1 From 7eb52dfa70dbf5232b5b83ec4357e6bebaa8fde8 Mon Sep 17 00:00:00 2001 From: Vaidyanathan Srinivasan Date: Thu, 18 Dec 2008 23:26:29 +0530 Subject: sched: bias task wakeups to preferred semi-idle packages Impact: tweak task wakeup to save power more agressively Preferred wakeup cpu (from a semi idle package) has been nominated in find_busiest_group() in the previous patch. Use this information in sched_mc_preferred_wakeup_cpu in function wake_idle() to bias task wakeups if the following conditions are satisfied: - The present cpu that is trying to wakeup the process is idle and waking the target process on this cpu will potentially wakeup a completely idle package - The previous cpu on which the target process ran is also idle and hence selecting the previous cpu may wakeup a semi idle cpu package - The task being woken up is allowed to run in the nominated cpu (cpu affinity and restrictions) Basically if both the current cpu and the previous cpu on which the task ran is idle, select the nominated cpu from semi idle cpu package for running the new task that is waking up. Cache hotness is considered since the actual biasing happens in wake_idle() only if the application is cache cold. This technique will effectively move short running bursty jobs in a mostly idle system. Wakeup biasing for power savings gets automatically disabled if system utilisation increases due to the fact that the probability of finding both this_cpu and prev_cpu idle decreases. Signed-off-by: Vaidyanathan Srinivasan Acked-by: Balbir Singh Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'kernel/sched_fair.c') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 08ffffd..36b5e34 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1026,6 +1026,24 @@ static int wake_idle(int cpu, struct task_struct *p) { struct sched_domain *sd; int i; + unsigned int chosen_wakeup_cpu; + int this_cpu; + + /* + * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu + * are idle and this is not a kernel thread and this task's affinity + * allows it to be moved to preferred cpu, then just move! + */ + + this_cpu = smp_processor_id(); + chosen_wakeup_cpu = + cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu; + + if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP && + idle_cpu(cpu) && idle_cpu(this_cpu) && + p->mm && !(p->flags & PF_KTHREAD) && + cpu_isset(chosen_wakeup_cpu, p->cpus_allowed)) + return chosen_wakeup_cpu; /* * If it is idle, then it is the best cpu to run this task. -- cgit v1.1