return max(smin, smax);
}
+/*
+ * Once a preferred node is selected the scheduler balancer will prefer moving
+ * a task to that node for sysctl_numa_balancing_settle_count number of PTE
+ * scans. This will give the process the chance to accumulate more faults on
+ * the preferred node but still allow the scheduler to move the task again if
+ * the nodes CPUs are overloaded.
+ */
+unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3;
+
+static inline int task_faults_idx(int nid, int priv)
+{
+ return 2 * nid + priv;
+}
+
+static inline unsigned long task_faults(struct task_struct *p, int nid)
+{
+ if (!p->numa_faults)
+ return 0;
+
+ return p->numa_faults[task_faults_idx(nid, 0)] +
+ p->numa_faults[task_faults_idx(nid, 1)];
+}
+
+static unsigned long weighted_cpuload(const int cpu);
+
+
+static int
+find_idlest_cpu_node(int this_cpu, int nid)
+{
+ unsigned long load, min_load = ULONG_MAX;
+ int i, idlest_cpu = this_cpu;
+
+ BUG_ON(cpu_to_node(this_cpu) == nid);
+
+ rcu_read_lock();
+ for_each_cpu(i, cpumask_of_node(nid)) {
+ load = weighted_cpuload(i);
+
+ if (load < min_load) {
+ min_load = load;
+ idlest_cpu = i;
+ }
+ }
+ rcu_read_unlock();
+
+ return idlest_cpu;
+}
+
static void task_numa_placement(struct task_struct *p)
{
- int seq;
+ int seq, nid, max_nid = -1;
+ unsigned long max_faults = 0;
- if (!p->mm) /* for example, ksmd faulting in a user's mm */
- return;
seq = ACCESS_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
+ p->numa_migrate_seq++;
p->numa_scan_period_max = task_scan_max(p);
- /* FIXME: Scheduling placement policy hints go here */
+ /* Find the node with the highest number of faults */
+ for_each_online_node(nid) {
+ unsigned long faults;
+ int priv, i;
+
+ for (priv = 0; priv < 2; priv++) {
+ i = task_faults_idx(nid, priv);
+
+ /* Decay existing window, copy faults since last scan */
+ p->numa_faults[i] >>= 1;
+ p->numa_faults[i] += p->numa_faults_buffer[i];
+ p->numa_faults_buffer[i] = 0;
+ }
+
+ /* Find maximum private faults */
+ faults = p->numa_faults[task_faults_idx(nid, 1)];
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+ }
+
+ /*
+ * Record the preferred node as the node with the most faults,
+ * requeue the task to be running on the idlest CPU on the
+ * preferred node and reset the scanning rate to recheck
+ * the working set placement.
+ */
+ if (max_faults && max_nid != p->numa_preferred_nid) {
+ int preferred_cpu;
+
+ /*
+ * If the task is not on the preferred node then find the most
+ * idle CPU to migrate to.
+ */
+ preferred_cpu = task_cpu(p);
+ if (cpu_to_node(preferred_cpu) != max_nid) {
+ preferred_cpu = find_idlest_cpu_node(preferred_cpu,
+ max_nid);
+ }
+
+ /* Update the preferred nid and migrate task if possible */
+ p->numa_preferred_nid = max_nid;
+ p->numa_migrate_seq = 0;
+ migrate_task_to(p, preferred_cpu);
+ }
}
/*
* Got a PROT_NONE fault for a page on @node.
*/
-void task_numa_fault(int node, int pages, bool migrated)
+void task_numa_fault(int last_nid, int node, int pages, bool migrated)
{
struct task_struct *p = current;
+ int priv;
if (!numabalancing_enabled)
return;
+ /* for example, ksmd faulting in a user's mm */
+ if (!p->mm)
+ return;
+
+ /* For now, do not attempt to detect private/shared accesses */
+ priv = 1;
+
/* Allocate buffer to track faults on a per-node basis */
if (unlikely(!p->numa_faults)) {
- int size = sizeof(*p->numa_faults) * nr_node_ids;
+ int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
- p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ /* numa_faults and numa_faults_buffer share the allocation */
+ p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
if (!p->numa_faults)
return;
+
+ BUG_ON(p->numa_faults_buffer);
+ p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
}
/*
task_numa_placement(p);
- p->numa_faults[node] += pages;
+ p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
}
static void reset_ptenuma_scan(struct task_struct *p)
return delta < (s64)sysctl_sched_migration_cost;
}
+#ifdef CONFIG_NUMA_BALANCING
+/* Returns true if the destination node has incurred more faults */
+static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
+{
+ int src_nid, dst_nid;
+
+ if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+ !(env->sd->flags & SD_NUMA)) {
+ return false;
+ }
+
+ src_nid = cpu_to_node(env->src_cpu);
+ dst_nid = cpu_to_node(env->dst_cpu);
+
+ if (src_nid == dst_nid ||
+ p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
+ return false;
+
+ if (dst_nid == p->numa_preferred_nid ||
+ task_faults(p, dst_nid) > task_faults(p, src_nid))
+ return true;
+
+ return false;
+}
+
+
+static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
+{
+ int src_nid, dst_nid;
+
+ if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
+ return false;
+
+ if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ return false;
+
+ src_nid = cpu_to_node(env->src_cpu);
+ dst_nid = cpu_to_node(env->dst_cpu);
+
+ if (src_nid == dst_nid ||
+ p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
+ return false;
+
+ if (task_faults(p, dst_nid) < task_faults(p, src_nid))
+ return true;
+
+ return false;
+}
+
+#else
+static inline bool migrate_improves_locality(struct task_struct *p,
+ struct lb_env *env)
+{
+ return false;
+}
+
+static inline bool migrate_degrades_locality(struct task_struct *p,
+ struct lb_env *env)
+{
+ return false;
+}
+#endif
+
/*
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
/*
* Aggressive migration if:
- * 1) task is cache cold, or
- * 2) too many balance attempts have failed.
+ * 1) destination numa is preferred
+ * 2) task is cache cold, or
+ * 3) too many balance attempts have failed.
*/
-
tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+ if (!tsk_cache_hot)
+ tsk_cache_hot = migrate_degrades_locality(p, env);
+
+ if (migrate_improves_locality(p, env)) {
+#ifdef CONFIG_SCHEDSTATS
+ if (tsk_cache_hot) {
+ schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+ schedstat_inc(p, se.statistics.nr_forced_migrations);
+ }
+#endif
+ return 1;
+ }
+
if (!tsk_cache_hot ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {