@@ -210,6 +210,9 @@ enum node_stat_item {
NR_PAGETABLE, /* used for pagetables */
#ifdef CONFIG_SWAP
NR_SWAPCACHE,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+ PGPROMOTE_SUCCESS, /* promote successfully */
#endif
NR_VM_NODE_STAT_ITEMS
};
@@ -181,4 +181,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
#define to_node(device) container_of(device, struct node, dev)
+static inline bool node_is_toptier(int node)
+{
+ return node_state(node, N_CPU);
+}
+
#endif /* _LINUX_NODE_H_ */
@@ -2072,6 +2072,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
pg_data_t *pgdat = NODE_DATA(node);
int isolated;
int nr_remaining;
+ unsigned int nr_succeeded;
LIST_HEAD(migratepages);
new_page_t *new;
bool compound;
@@ -2110,7 +2111,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
list_add(&page->lru, &migratepages);
nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
- MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL);
+ MIGRATE_ASYNC, MR_NUMA_MISPLACED,
+ &nr_succeeded);
if (nr_remaining) {
if (!list_empty(&migratepages)) {
list_del(&page->lru);
@@ -2119,8 +2121,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
putback_lru_page(page);
}
isolated = 0;
- } else
- count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
+ }
+ if (nr_succeeded) {
+ count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
+ if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node))
+ mod_node_page_state(pgdat, PGPROMOTE_SUCCESS,
+ nr_succeeded);
+ }
BUG_ON(!list_empty(&migratepages));
return isolated;
@@ -1242,6 +1242,9 @@ const char * const vmstat_text[] = {
#ifdef CONFIG_SWAP
"nr_swapcached",
#endif
+#ifdef CONFIG_NUMA_BALANCING
+ "pgpromote_success",
+#endif
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
In a system with multiple memory types, e.g. DRAM and PMEM, the CPU and DRAM in one socket will be put in one NUMA node as before, while the PMEM will be put in another NUMA node as described in the description of the commit c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM"). So, the NUMA balancing mechanism will identify all PMEM accesses as remote access and try to promote the PMEM pages to DRAM. To distinguish the number of the inter-type promoted pages from that of the inter-socket migrated pages. A new vmstat count is added. The counter is per-node (count in the target node). So this can be used to identify promotion imbalance among the NUMA nodes. Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Rik van Riel <riel@surriel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Wei Xu <weixugc@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: zhongjiang-ali <zhongjiang-ali@linux.alibaba.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org --- include/linux/mmzone.h | 3 +++ include/linux/node.h | 5 +++++ mm/migrate.c | 13 ++++++++++--- mm/vmstat.c | 3 +++ 4 files changed, 21 insertions(+), 3 deletions(-)