X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=mm%2Fvmstat.c;h=c64d169537bfcfe65fc963b009779de85c9b051a;hb=50ef295119645215c076700e7ddf4869df5f56ce;hp=9d824643a22f167800864a5f24b86645a25cfcdb;hpb=d1187ed21026fd512b87851d0ca26d9ae16f9059;p=linux-2.6

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9d824643a2..c64d169537 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -10,8 +10,10 @@
  */
 
 #include <linux/mm.h>
+#include <linux/err.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -281,6 +283,17 @@ EXPORT_SYMBOL(dec_zone_page_state);
 
 /*
  * Update the zone counters for one cpu.
+ *
+ * Note that refresh_cpu_vm_stats strives to only access
+ * node local memory. The per cpu pagesets on remote zones are placed
+ * in the memory local to the processor using that pageset. So the
+ * loop over all zones will access a series of cachelines local to
+ * the processor.
+ *
+ * The call to zone_page_state_add updates the cachelines with the
+ * statistics in the remote zone struct as well as the global cachelines
+ * with the global counters. These could cause remote node cache line
+ * bouncing and will have to be only done when necessary.
  */
 void refresh_cpu_vm_stats(int cpu)
 {
@@ -289,21 +302,54 @@ void refresh_cpu_vm_stats(int cpu)
 	unsigned long flags;
 
 	for_each_zone(zone) {
-		struct per_cpu_pageset *pcp;
+		struct per_cpu_pageset *p;
 
 		if (!populated_zone(zone))
 			continue;
 
-		pcp = zone_pcp(zone, cpu);
+		p = zone_pcp(zone, cpu);
 
 		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-			if (pcp->vm_stat_diff[i]) {
+			if (p->vm_stat_diff[i]) {
 				local_irq_save(flags);
-				zone_page_state_add(pcp->vm_stat_diff[i],
+				zone_page_state_add(p->vm_stat_diff[i],
 					zone, i);
-				pcp->vm_stat_diff[i] = 0;
+				p->vm_stat_diff[i] = 0;
+#ifdef CONFIG_NUMA
+				/* 3 seconds idle till flush */
+				p->expire = 3;
+#endif
 				local_irq_restore(flags);
 			}
+#ifdef CONFIG_NUMA
+		/*
+		 * Deal with draining the remote pageset of this
+		 * processor
+		 *
+		 * Check if there are pages remaining in this pageset
+		 * if not then there is nothing to expire.
+		 */
+		if (!p->expire || (!p->pcp[0].count && !p->pcp[1].count))
+			continue;
+
+		/*
+		 * We never drain zones local to this processor.
+		 */
+		if (zone_to_nid(zone) == numa_node_id()) {
+			p->expire = 0;
+			continue;
+		}
+
+		p->expire--;
+		if (p->expire)
+			continue;
+
+		if (p->pcp[0].count)
+			drain_zone_pages(zone, p->pcp + 0);
+
+		if (p->pcp[1].count)
+			drain_zone_pages(zone, p->pcp + 1);
+#endif
 	}
 }
 
@@ -427,13 +473,13 @@ const struct seq_operations fragmentation_op = {
 #endif
 
 #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
-					TEXT_FOR_HIGHMEM(xx)
+					TEXT_FOR_HIGHMEM(xx) xx "_movable",
 
 static const char * const vmstat_text[] = {
 	/* Zoned VM counters */
 	"nr_free_pages",
-	"nr_active",
 	"nr_inactive",
+	"nr_active",
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
@@ -641,18 +687,20 @@ const struct seq_operations vmstat_op = {
 
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
+int sysctl_stat_interval __read_mostly = HZ;
 
 static void vmstat_update(struct work_struct *w)
 {
 	refresh_cpu_vm_stats(smp_processor_id());
-	schedule_delayed_work(&__get_cpu_var(vmstat_work), HZ);
+	schedule_delayed_work(&__get_cpu_var(vmstat_work),
+		sysctl_stat_interval);
 }
 
 static void __devinit start_cpu_timer(int cpu)
 {
 	struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
 
-	INIT_DELAYED_WORK(vmstat_work, vmstat_update);
+	INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
 	schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
 }