per-zone and reclaim enhancements for memory controller: calculate...

per-zone and reclaim enhancements for memory controller: calculate active/inactive imbalance per cgroup
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Paul Menage <menage@google.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memcontrol.h

@@ -68,6 +68,8 @@ extern void mem_cgroup_page_migration(struct page *page, struct page *newpage);
  * For memory reclaim.
  */
 extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
+extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
+
 
 
 #else /* CONFIG_CGROUP_MEM_CONT */
@@ -145,6 +147,12 @@ static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 {
 	return 0;
 }
+
+static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
+{
+	return 0;
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */

mm/memcontrol.c

@@ -436,6 +436,20 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
 	return (int)((rss * 100L) / total);
 }
+/*
+ * This function is called from vmscan.c. In page reclaiming loop. balance
+ * between active and inactive list is calculated. For memory controller
+ * page reclaiming, we should use using mem_cgroup's imbalance rather than
+ * zone's global lru imbalance.
+ */
+long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
+{
+	unsigned long active, inactive;
+	/* active and inactive are the number of pages. 'long' is ok.*/
+	active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);
+	inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);
+	return (long) (active / (inactive + 1));
+}
 
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,