diff options
| -rw-r--r-- | include/linux/sched.h | 13 | ||||
| -rw-r--r-- | kernel/sched/core.c | 1 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 16 |
3 files changed, 27 insertions, 3 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index b1fc75e7187b..a463bc3ad437 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1343,7 +1343,20 @@ struct task_struct { u64 node_stamp; /* migration stamp */ struct callback_head numa_work; + /* + * Exponential decaying average of faults on a per-node basis. + * Scheduling placement decisions are made based on the these counts. + * The values remain static for the duration of a PTE scan + */ unsigned long *numa_faults; + + /* + * numa_faults_buffer records faults per node during the current + * scan window. When the scan completes, the counts in numa_faults + * decay and these values are copied. + */ + unsigned long *numa_faults_buffer; + int numa_preferred_nid; #endif /* CONFIG_NUMA_BALANCING */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d15cd70f85b5..064a0af44540 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1636,6 +1636,7 @@ static void __sched_fork(struct task_struct *p) p->numa_preferred_nid = -1; p->numa_work.next = &p->numa_work; p->numa_faults = NULL; + p->numa_faults_buffer = NULL; #endif /* CONFIG_NUMA_BALANCING */ } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9efd34f63e81..3abc651bc38a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -892,8 +892,14 @@ static void task_numa_placement(struct task_struct *p) /* Find the node with the highest number of faults */ for_each_online_node(nid) { - unsigned long faults = p->numa_faults[nid]; + unsigned long faults; + + /* Decay existing window and copy faults since last scan */ p->numa_faults[nid] >>= 1; + p->numa_faults[nid] += p->numa_faults_buffer[nid]; + p->numa_faults_buffer[nid] = 0; + + faults = p->numa_faults[nid]; if (faults > max_faults) { max_faults = faults; max_nid = nid; @@ -919,9 +925,13 @@ void task_numa_fault(int node, int pages, bool migrated) if (unlikely(!p->numa_faults)) { int size = sizeof(*p->numa_faults) * 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 + nr_node_ids; } /* @@ -939,7 +949,7 @@ void task_numa_fault(int node, int pages, bool migrated) task_numa_placement(p); - p->numa_faults[node] += pages; + p->numa_faults_buffer[node] += pages; } static void reset_ptenuma_scan(struct task_struct *p) |