summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/scheduler/sched-domains.txt32
-rw-r--r--kernel/sched.c11
-rw-r--r--kernel/sched_fair.c5
3 files changed, 37 insertions, 11 deletions
diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt
index 373ceacc367e..b7ee379b651b 100644
--- a/Documentation/scheduler/sched-domains.txt
+++ b/Documentation/scheduler/sched-domains.txt
@@ -1,8 +1,7 @@
-Each CPU has a "base" scheduling domain (struct sched_domain). These are
-accessed via cpu_sched_domain(i) and this_sched_domain() macros. The domain
+Each CPU has a "base" scheduling domain (struct sched_domain). The domain
hierarchy is built from these base domains via the ->parent pointer. ->parent
-MUST be NULL terminated, and domain structures should be per-CPU as they
-are locklessly updated.
+MUST be NULL terminated, and domain structures should be per-CPU as they are
+locklessly updated.
Each scheduling domain spans a number of CPUs (stored in the ->span field).
A domain's span MUST be a superset of it child's span (this restriction could
@@ -26,11 +25,26 @@ is treated as one entity. The load of a group is defined as the sum of the
load of each of its member CPUs, and only when the load of a group becomes
out of balance are tasks moved between groups.
-In kernel/sched.c, rebalance_tick is run periodically on each CPU. This
-function takes its CPU's base sched domain and checks to see if has reached
-its rebalance interval. If so, then it will run load_balance on that domain.
-rebalance_tick then checks the parent sched_domain (if it exists), and the
-parent of the parent and so forth.
+In kernel/sched.c, trigger_load_balance() is run periodically on each CPU
+through scheduler_tick(). It raises a softirq after the next regularly scheduled
+rebalancing event for the current runqueue has arrived. The actual load
+balancing workhorse, run_rebalance_domains()->rebalance_domains(), is then run
+in softirq context (SCHED_SOFTIRQ).
+
+The latter function takes two arguments: the current CPU and whether it was idle
+at the time the scheduler_tick() happened and iterates over all sched domains
+our CPU is on, starting from its base domain and going up the ->parent chain.
+While doing that, it checks to see if the current domain has exhausted its
+rebalance interval. If so, it runs load_balance() on that domain. It then checks
+the parent sched_domain (if it exists), and the parent of the parent and so
+forth.
+
+Initially, load_balance() finds the busiest group in the current sched domain.
+If it succeeds, it looks for the busiest runqueue of all the CPUs' runqueues in
+that group. If it manages to find such a runqueue, it locks both our initial
+CPU's runqueue and the newly found busiest one and starts moving tasks from it
+to our runqueue. The exact number of tasks amounts to an imbalance previously
+computed while iterating over this sched domain's groups.
*** Implementing sched domains ***
The "base" domain will "span" the first level of the hierarchy. In the case
diff --git a/kernel/sched.c b/kernel/sched.c
index f592ce6f8616..a8845516ace6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5011,6 +5011,17 @@ recheck:
return -EINVAL;
}
+ /*
+ * If not changing anything there's no need to proceed further:
+ */
+ if (unlikely(policy == p->policy && (!rt_policy(policy) ||
+ param->sched_priority == p->rt_priority))) {
+
+ __task_rq_unlock(rq);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ return 0;
+ }
+
#ifdef CONFIG_RT_GROUP_SCHED
if (user) {
/*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3f7ec9e27ee1..c7ec5c8e7b44 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -22,6 +22,7 @@
#include <linux/latencytop.h>
#include <linux/sched.h>
+#include <linux/cpumask.h>
/*
* Targeted preemption latency for CPU-bound tasks:
@@ -3850,8 +3851,8 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
interval = msecs_to_jiffies(interval);
if (unlikely(!interval))
interval = 1;
- if (interval > HZ*NR_CPUS/10)
- interval = HZ*NR_CPUS/10;
+ if (interval > HZ*num_online_cpus()/10)
+ interval = HZ*num_online_cpus()/10;
need_serialize = sd->flags & SD_SERIALIZE;