mm: make lru_add_drain_all() selective

make lru_add_drain_all() only selectively interrupt the cpus that have
per-cpu free pages that can be drained.

This is important in nohz mode where calling mlockall(), for example,
otherwise will interrupt every core unnecessarily.

This is important on workloads where nohz cores are handling 10 Gb traffic
in userspace.  Those CPUs do not enter the kernel and place pages into LRU
pagevecs and they really, really don't want to be interrupted, or they
drop packets on the floor.

Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index c03c139219c9f7bd04b64c3a3c09e6c281478827..46ba0c6c219fbb64523741a316efcdd3d909a742 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -280,7 +280,7 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
-extern int lru_add_drain_all(void);
+extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_page(struct page *page);
 extern void swap_setup(void);

diff --git a/mm/swap.c b/mm/swap.c
index c899502d3e3698222026d81e05e5873d7d95f128..759c3caf44bd21bef216c6a011981f150615646b 100644 (file)
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -432,6 +432,11 @@ static void activate_page_drain(int cpu)
                pagevec_lru_move_fn(pvec, __activate_page, NULL);
 }
 
+static bool need_activate_page_drain(int cpu)
+{
+       return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+}
+
 void activate_page(struct page *page)
 {
        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -449,6 +454,11 @@ static inline void activate_page_drain(int cpu)
 {
 }
 
+static bool need_activate_page_drain(int cpu)
+{
+       return false;
+}
+
 void activate_page(struct page *page)
 {
        struct zone *zone = page_zone(page);
@@ -701,12 +711,36 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
        lru_add_drain();
 }
 
-/*
- * Returns 0 for success
- */
-int lru_add_drain_all(void)
+static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
+
+void lru_add_drain_all(void)
 {
-       return schedule_on_each_cpu(lru_add_drain_per_cpu);
+       static DEFINE_MUTEX(lock);
+       static struct cpumask has_work;
+       int cpu;
+
+       mutex_lock(&lock);
+       get_online_cpus();
+       cpumask_clear(&has_work);
+
+       for_each_online_cpu(cpu) {
+               struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
+
+               if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
+                   pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
+                   pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
+                   need_activate_page_drain(cpu)) {
+                       INIT_WORK(work, lru_add_drain_per_cpu);
+                       schedule_work_on(cpu, work);
+                       cpumask_set_cpu(cpu, &has_work);
+               }
+       }
+
+       for_each_cpu(cpu, &has_work)
+               flush_work(&per_cpu(lru_add_drain_work, cpu));
+
+       put_online_cpus();
+       mutex_unlock(&lock);
 }
 
 /*