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" <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: osalvador <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: [email protected]
Cc: [email protected]
---
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(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 58e744b78c2c..eda6d2f09d77 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -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
};
diff --git a/include/linux/node.h b/include/linux/node.h
index bb21fd631b16..81bbf1c0afd3 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -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_ */
diff --git a/mm/migrate.c b/mm/migrate.c
index cf25b00f03c8..b7c27abb0e5c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2141,6 +2141,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
pg_data_t *pgdat = NODE_DATA(node);
int isolated;
int nr_remaining;
+ int nr_succeeded;
LIST_HEAD(migratepages);
new_page_t *new;
bool compound;
@@ -2179,7 +2180,8 @@ 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);
@@ -2188,8 +2190,13 @@ 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(NODE_DATA(node), PGPROMOTE_SUCCESS,
+ nr_succeeded);
+ }
BUG_ON(!list_empty(&migratepages));
return isolated;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d701c335628c..53a6e92b1efb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -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",
--
2.30.2
On Mon, Nov 15, 2021 at 5:36 PM Huang Ying <[email protected]> wrote:
>
> 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.
Reviewed-by: Yang Shi <[email protected]>
>
> Signed-off-by: "Huang, Ying" <[email protected]>
> Cc: Andrew Morton <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: Rik van Riel <[email protected]>
> Cc: Mel Gorman <[email protected]>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Dave Hansen <[email protected]>
> Cc: Yang Shi <[email protected]>
> Cc: Zi Yan <[email protected]>
> Cc: Wei Xu <[email protected]>
> Cc: osalvador <[email protected]>
> Cc: Shakeel Butt <[email protected]>
> Cc: [email protected]
> Cc: [email protected]
> ---
> 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(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 58e744b78c2c..eda6d2f09d77 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -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
> };
> diff --git a/include/linux/node.h b/include/linux/node.h
> index bb21fd631b16..81bbf1c0afd3 100644
> --- a/include/linux/node.h
> +++ b/include/linux/node.h
> @@ -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_ */
> diff --git a/mm/migrate.c b/mm/migrate.c
> index cf25b00f03c8..b7c27abb0e5c 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -2141,6 +2141,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
> pg_data_t *pgdat = NODE_DATA(node);
> int isolated;
> int nr_remaining;
> + int nr_succeeded;
> LIST_HEAD(migratepages);
> new_page_t *new;
> bool compound;
> @@ -2179,7 +2180,8 @@ 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);
> @@ -2188,8 +2190,13 @@ 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(NODE_DATA(node), PGPROMOTE_SUCCESS,
> + nr_succeeded);
> + }
> BUG_ON(!list_empty(&migratepages));
> return isolated;
>
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index d701c335628c..53a6e92b1efb 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -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",
> --
> 2.30.2
>