@@ -919,6 +919,7 @@ This is value ORed together of
1 = Zone reclaim on
2 = Zone reclaim writes dirty pages out
4 = Zone reclaim swaps pages
+8 = Zone reclaim migrate pages
zone_reclaim_mode is disabled by default. For file servers or workloads
that benefit from having their data cached, zone_reclaim_mode should be
@@ -943,4 +944,9 @@ Allowing regular swap effectively restricts allocations to the local
node unless explicitly overridden by memory policies or cpuset
configurations.
+Allowing zone reclaim to migrate pages to the migration target nodes, which
+are typically cheaper and slower than DRAM, but have larger capacity, i.e.
+NVDIMM nodes, if such nodes are present in the system. The migrate mode
+is not compatible with cpuset and mempolicy settings.
+
============ End of Document =================================
@@ -285,6 +285,14 @@
* available and will not wake kswapd/kcompactd on failure. The _LIGHT
* version does not attempt reclaim/compaction at all and is by default used
* in page fault path, while the non-light is used by khugepaged.
+ *
+ * %GFP_DEMOTE is for migration on memory reclaim (a.k.a demotion) allocations.
+ * The allocation might happen in kswapd or direct reclaim, so assuming
+ * __GFP_IO and __GFP_FS are not allowed looks safer. Demotion happens for
+ * user pages (on LRU) only and on specific node. Generally it will fail
+ * quickly if memory is not available, but may wake up kswapd on failure.
+ *
+ * %GFP_TRANSHUGE_DEMOTE is used for THP demotion allocation.
*/
#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
@@ -300,6 +308,10 @@
#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
__GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
+#define GFP_DEMOTE (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_NORETRY | \
+ __GFP_NOMEMALLOC | __GFP_NOWARN | __GFP_THISNODE | \
+ GFP_NOWAIT)
+#define GFP_TRANSHUGE_DEMOTE (GFP_DEMOTE | __GFP_COMP)
/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -25,6 +25,7 @@ enum migrate_reason {
MR_MEMPOLICY_MBIND,
MR_NUMA_MISPLACED,
MR_CONTIG_RANGE,
+ MR_DEMOTE,
MR_TYPES
};
@@ -20,7 +20,8 @@
EM( MR_SYSCALL, "syscall_or_cpuset") \
EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \
EM( MR_NUMA_MISPLACED, "numa_misplaced") \
- EMe(MR_CONTIG_RANGE, "contig_range")
+ EM( MR_CONTIG_RANGE, "contig_range") \
+ EMe(MR_DEMOTE, "demote")
/*
* First define the enums in the above macros to be exported to userspace
@@ -25,6 +25,7 @@
"mempolicy_mbind",
"numa_misplaced",
"cma",
+ "demote",
};
const struct trace_print_flags pageflag_names[] = {
@@ -303,6 +303,18 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask,
}
#endif
+static inline bool has_migration_target_node_online(void)
+{
+ int nid;
+
+ for_each_online_node(nid) {
+ if (node_state(nid, N_MIGRATE_TARGET))
+ return true;
+ }
+
+ return false;
+}
+
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent);
@@ -1006,7 +1006,8 @@ static int move_to_new_page(struct page *newpage, struct page *page,
}
static int __unmap_and_move(struct page *page, struct page *newpage,
- int force, enum migrate_mode mode)
+ int force, enum migrate_mode mode,
+ enum migrate_reason reason)
{
int rc = -EAGAIN;
int page_was_mapped = 0;
@@ -1143,8 +1144,16 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
if (rc == MIGRATEPAGE_SUCCESS) {
if (unlikely(!is_lru))
put_page(newpage);
- else
+ else {
+ /*
+ * Put demoted pages on the target node's
+ * active LRU.
+ */
+ if (!PageUnevictable(newpage) &&
+ reason == MR_DEMOTE)
+ SetPageActive(newpage);
putback_lru_page(newpage);
+ }
}
return rc;
@@ -1198,7 +1207,7 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
goto out;
}
- rc = __unmap_and_move(page, newpage, force, mode);
+ rc = __unmap_and_move(page, newpage, force, mode, reason);
if (rc == MIGRATEPAGE_SUCCESS)
set_page_owner_migrate_reason(newpage, reason);
@@ -1094,6 +1094,55 @@ static void page_check_dirty_writeback(struct page *page,
mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
}
+#ifdef CONFIG_NUMA
+#define RECLAIM_OFF 0
+#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
+#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
+#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
+#define RECLAIM_MIGRATE (1<<3) /* Migrate pages to migration target
+ * node during reclaim */
+static struct page *alloc_demote_page(struct page *page, unsigned long node)
+{
+ if (unlikely(PageHuge(page)))
+ /* HugeTLB demotion is not supported for now */
+ BUG();
+ else if (PageTransHuge(page)) {
+ struct page *thp;
+
+ thp = alloc_pages_node(node, GFP_TRANSHUGE_DEMOTE,
+ HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
+ } else
+ return __alloc_pages_node(node, GFP_DEMOTE, 0);
+}
+#else
+static inline struct page *alloc_demote_page(struct page *page,
+ unsigned long node)
+{
+ return NULL;
+}
+#endif
+
+static inline bool is_demote_ok(int nid)
+{
+ /* Just do demotion with migrate mode of node reclaim */
+ if (!(node_reclaim_mode & RECLAIM_MIGRATE))
+ return false;
+
+ /* Current node is cpuless node */
+ if (!node_state(nid, N_CPU_MEM))
+ return false;
+
+ /* No online migration target node */
+ if (!has_migration_target_node_online())
+ return false;
+
+ return true;
+}
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
@@ -1106,6 +1155,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
{
LIST_HEAD(ret_pages);
LIST_HEAD(free_pages);
+ LIST_HEAD(demote_pages);
unsigned nr_reclaimed = 0;
unsigned pgactivate = 0;
@@ -1269,6 +1319,18 @@ static unsigned long shrink_page_list(struct list_head *page_list,
*/
if (PageAnon(page) && PageSwapBacked(page)) {
if (!PageSwapCache(page)) {
+ /*
+ * Demote anonymous pages only for now and
+ * skip MADV_FREE pages.
+ *
+ * Demotion only happen from primary nodes
+ * to cpuless nodes.
+ */
+ if (is_demote_ok(page_to_nid(page))) {
+ list_add(&page->lru, &demote_pages);
+ unlock_page(page);
+ continue;
+ }
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (PageTransHuge(page)) {
@@ -1480,6 +1542,30 @@ static unsigned long shrink_page_list(struct list_head *page_list,
VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
+ /* Demote pages to migration target */
+ if (!list_empty(&demote_pages)) {
+ int err, target_nid;
+ unsigned int nr_succeeded = 0;
+ nodemask_t used_mask;
+
+ nodes_clear(used_mask);
+ target_nid = find_next_best_node(pgdat->node_id, &used_mask,
+ true);
+
+ /* Demotion would ignore all cpuset and mempolicy settings */
+ err = migrate_pages(&demote_pages, alloc_demote_page, NULL,
+ target_nid, MIGRATE_ASYNC, MR_DEMOTE,
+ &nr_succeeded);
+
+ nr_reclaimed += nr_succeeded;
+
+ if (err) {
+ putback_movable_pages(&demote_pages);
+
+ list_splice(&ret_pages, &demote_pages);
+ }
+ }
+
mem_cgroup_uncharge_list(&free_pages);
try_to_unmap_flush();
free_unref_page_list(&free_pages);
@@ -2136,10 +2222,11 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
unsigned long gb;
/*
- * If we don't have swap space, anonymous page deactivation
- * is pointless.
+ * If we don't have swap space or migtation target node online,
+ * anonymous page deactivation is pointless.
*/
- if (!file && !total_swap_pages)
+ if (!file && !total_swap_pages &&
+ !is_demote_ok(pgdat->node_id))
return false;
inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
@@ -2213,22 +2300,34 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
unsigned long ap, fp;
enum lru_list lru;
- /* If we have no swap space, do not bother scanning anon pages. */
- if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
- scan_balance = SCAN_FILE;
- goto out;
- }
-
/*
- * Global reclaim will swap to prevent OOM even with no
- * swappiness, but memcg users want to use this knob to
- * disable swapping for individual groups completely when
- * using the memory controller's swap limit feature would be
- * too expensive.
+ * Anon pages can be demoted to PMEM. If there is PMEM node online,
+ * still scan anonymous LRU even though the systme is swapless or
+ * swapping is disabled by memcg.
+ *
+ * If current node is already PMEM node, demotion is not applicable.
*/
- if (!global_reclaim(sc) && !swappiness) {
- scan_balance = SCAN_FILE;
- goto out;
+ if (!is_demote_ok(pgdat->node_id)) {
+ /*
+ * If we have no swap space, do not bother scanning
+ * anon pages.
+ */
+ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
+ scan_balance = SCAN_FILE;
+ goto out;
+ }
+
+ /*
+ * Global reclaim will swap to prevent OOM even with no
+ * swappiness, but memcg users want to use this knob to
+ * disable swapping for individual groups completely when
+ * using the memory controller's swap limit feature would be
+ * too expensive.
+ */
+ if (!global_reclaim(sc) && !swappiness) {
+ scan_balance = SCAN_FILE;
+ goto out;
+ }
}
/*
@@ -2577,7 +2676,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
*/
pages_for_compaction = compact_gap(sc->order);
inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
- if (get_nr_swap_pages() > 0)
+ if (get_nr_swap_pages() > 0 || is_demote_ok(pgdat->node_id))
inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
if (sc->nr_reclaimed < pages_for_compaction &&
inactive_lru_pages > pages_for_compaction)
@@ -3262,7 +3361,8 @@ static void age_active_anon(struct pglist_data *pgdat,
{
struct mem_cgroup *memcg;
- if (!total_swap_pages)
+ /* Aging anon page as long as demotion is fine */
+ if (!total_swap_pages && !is_demote_ok(pgdat->node_id))
return;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
@@ -4003,11 +4103,6 @@ static int __init kswapd_init(void)
*/
int node_reclaim_mode __read_mostly;
-#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
-#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
-
/*
* Priority for NODE_RECLAIM. This determines the fraction of pages
* of a node considered for each zone_reclaim. 4 scans 1/16th of
@@ -4084,8 +4179,10 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
.gfp_mask = current_gfp_context(gfp_mask),
.order = order,
.priority = NODE_RECLAIM_PRIORITY,
- .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
- .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
+ .may_writepage = !!((node_reclaim_mode & RECLAIM_WRITE) ||
+ (node_reclaim_mode & RECLAIM_MIGRATE)),
+ .may_unmap = !!((node_reclaim_mode & RECLAIM_UNMAP) ||
+ (node_reclaim_mode & RECLAIM_MIGRATE)),
.may_swap = 1,
.reclaim_idx = gfp_zone(gfp_mask),
};
@@ -4105,7 +4202,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
+ if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages ||
+ (node_reclaim_mode & RECLAIM_MIGRATE)) {
/*
* Free memory by calling shrink node with increasing
* priorities until we have enough memory freed.
@@ -4138,9 +4236,12 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
* thrown out if the node is overallocated. So we do not reclaim
* if less than a specified percentage of the node is used by
* unmapped file backed pages.
+ *
+ * Migrate mode doesn't care the above restrictions.
*/
if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
- node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+ node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages &&
+ !(node_reclaim_mode & RECLAIM_MIGRATE))
return NODE_RECLAIM_FULL;
/*
Since migration target node (i.e. PMEM) typically provides larger capacity than DRAM and has much lower access latency than disk, so it is a good choice to use as a middle tier between DRAM and disk in page reclaim path. With migration target nodes, the demotion path of anonymous pages could be: DRAM -> PMEM -> swap device This patch demotes anonymous pages only for the time being and demote THP to the migration target node in a whole. To avoid expensive page reclaim and/or compaction on the target node if there is memory pressure on it, the most conservative gfp flag is used, which would fail quickly if there is memory pressure and just wakeup kswapd on failure. The migrate_pages() would split THP to migrate one by one as base page upon THP allocation failure. Demote pages to the cloest migration target node even though the system is swapless. The current logic of page reclaim just scan anon LRU when swap is on and swappiness is set properly. Demoting to the migration target doesn't need care whether swap is available or not. But, reclaiming from the migration target node still skip anon LRU if swap is not available. The demotion just happens from DRAM node to its cloest migration target node. Demoting to a remote migration target node or migrating from the target node to DRAM on reclaim path is not allowed. And, define a new migration reason for demotion, called MR_DEMOTE. Demote page via async migration to avoid blocking. The migration is just allowed via node reclaim. Introduce a new node reclaim mode: migrate mode. The migrate mode is not compatible with cpuset and mempolicy settings. Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> --- Documentation/sysctl/vm.txt | 6 ++ include/linux/gfp.h | 12 ++++ include/linux/migrate.h | 1 + include/trace/events/migrate.h | 3 +- mm/debug.c | 1 + mm/internal.h | 12 ++++ mm/migrate.c | 15 +++- mm/vmscan.c | 157 +++++++++++++++++++++++++++++++++-------- 8 files changed, 175 insertions(+), 32 deletions(-)