cpuset sched_load_balance flag

Add a new per-cpuset flag called 'sched_load_balance'.

When enabled in a cpuset (the default value) it tells the kernel scheduler
that the scheduler should provide the normal load balancing on the CPUs in
that cpuset, sometimes moving tasks from one CPU to a second CPU if the
second CPU is less loaded and if that task is allowed to run there.

When disabled (write "0" to the file) then it tells the kernel scheduler
that load balancing is not required for the CPUs in that cpuset.

Now even if this flag is disabled for some cpuset, the kernel may still
have to load balance some or all the CPUs in that cpuset, if some
overlapping cpuset has its sched_load_balance flag enabled.

If there are some CPUs that are not in any cpuset whose sched_load_balance
flag is enabled, the kernel scheduler will not load balance tasks to those
CPUs.

Moreover the kernel will partition the 'sched domains' (non-overlapping
sets of CPUs over which load balancing is attempted) into the finest
granularity partition that it can find, while still keeping any two CPUs
that are in the same shed_load_balance enabled cpuset in the same element
of the partition.

This serves two purposes:
 1) It provides a mechanism for real time isolation of some CPUs, and
 2) it can be used to improve performance on systems with many CPUs
    by supporting configurations in which load balancing is not done
    across all CPUs at once, but rather only done in several smaller
    disjoint sets of CPUs.

This mechanism replaces the earlier overloading of the per-cpuset
flag 'cpu_exclusive', which overloading was removed in an earlier
patch: cpuset-remove-sched-domain-hooks-from-cpusets

See further the Documentation and comments in the code itself.

[akpm@linux-foundation.org: don't be weird]
Signed-off-by: Paul Jackson <pj@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 81 insertions, 14 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 5d5e107ebc4e..39d6354af489 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6376,26 +6376,31 @@ error:
 	return -ENOMEM;
 #endif
 }
+
+static cpumask_t *doms_cur;	/* current sched domains */
+static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
+
+/*
+ * Special case: If a kmalloc of a doms_cur partition (array of
+ * cpumask_t) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask_t fallback_doms.
+ */
+static cpumask_t fallback_doms;
+
 /*
  * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
+ * For now this just excludes isolated cpus, but could be used to
+ * exclude other special cases in the future.
  */
 static int arch_init_sched_domains(const cpumask_t *cpu_map)
 {
-	cpumask_t cpu_default_map;
-	int err;
-
-	/*
-	 * Setup mask for cpus without special case scheduling requirements.
-	 * For now this just excludes isolated cpus, but could be used to
-	 * exclude other special cases in the future.
-	 */
-	cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
-
-	err = build_sched_domains(&cpu_default_map);
-
+	ndoms_cur = 1;
+	doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+	if (!doms_cur)
+		doms_cur = &fallback_doms;
+	cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
 	register_sched_domain_sysctl();
-
-	return err;
+	return build_sched_domains(doms_cur);
 }
 
 static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
@@ -6419,6 +6424,68 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
 	arch_destroy_sched_domains(cpu_map);
 }
 
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks.  This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.)  We should setup one
+ * sched domain for each mask.  CPUs not in any of the cpumasks will
+ * not be load balanced.  If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be kmalloc'd.  This routine takes
+ * ownership of it and will kfree it when done with it.  If the caller
+ * failed the kmalloc call, then it can pass in doms_new == NULL,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms'.
+ *
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
+{
+	int i, j;
+
+	if (doms_new == NULL) {
+		ndoms_new = 1;
+		doms_new = &fallback_doms;
+		cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+	}
+
+	/* Destroy deleted domains */
+	for (i = 0; i < ndoms_cur; i++) {
+		for (j = 0; j < ndoms_new; j++) {
+			if (cpus_equal(doms_cur[i], doms_new[j]))
+				goto match1;
+		}
+		/* no match - a current sched domain not in new doms_new[] */
+		detach_destroy_domains(doms_cur + i);
+match1:
+		;
+	}
+
+	/* Build new domains */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < ndoms_cur; j++) {
+			if (cpus_equal(doms_new[i], doms_cur[j]))
+				goto match2;
+		}
+		/* no match - add a new doms_new */
+		build_sched_domains(doms_new + i);
+match2:
+		;
+	}
+
+	/* Remember the new sched domains */
+	if (doms_cur != &fallback_doms)
+		kfree(doms_cur);
+	doms_cur = doms_new;
+	ndoms_cur = ndoms_new;
+}
+
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
 static int arch_reinit_sched_domains(void)
 {