Re: [PATCH v2] mm/mempolicy: track page allocations per mempolicy

[Usama Arif]

On Fri,  6 Mar 2026 20:55:20 -0800 "JP Kobryn (Meta)" <jp.kobryn@xxxxxxxxx> wrote:

> When investigating pressure on a NUMA node, there is no straightforward way
> to determine which policies are driving allocations to it.
> 
> Add per-policy page allocation counters as new node stat items. These
> counters track allocations to nodes and also whether the allocations were
> intentional or fallbacks.
> 
> The new stats follow the existing numa hit/miss/foreign style and have the
> following meanings:
> 
>   hit
>     - for BIND and PREFERRED_MANY, allocation succeeded on node in nodemask
>     - for other policies, allocation succeeded on intended node
>     - counted on the node of the allocation
>   miss
>     - allocation intended for other node, but happened on this one
>     - counted on other node
>   foreign
>     - allocation intended on this node, but happened on other node
>     - counted on this node
> 
> Counters are exposed per-memcg, per-node in memory.numa_stat and globally
> in /proc/vmstat.
> 
> Signed-off-by: JP Kobryn (Meta) <jp.kobryn@xxxxxxxxx>
> ---
> v2:
>   - Replaced single per-policy total counter (PGALLOC_MPOL_*) with
>     hit/miss/foreign triplet per policy
>   - Changed from global node stats to per-memcg per-node tracking
> 
> v1:
> https://lore.kernel.org/linux-mm/20260212045109.255391-2-inwardvessel@xxxxxxxxx/
> 
>  include/linux/mmzone.h | 20 ++++++++++
>  mm/memcontrol.c        | 60 ++++++++++++++++++++++++++++
>  mm/mempolicy.c         | 90 ++++++++++++++++++++++++++++++++++++++++--
>  mm/vmstat.c            | 20 ++++++++++
>  4 files changed, 187 insertions(+), 3 deletions(-)
> 
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 7bd0134c241c..c0517cbcb0e2 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -323,6 +323,26 @@ enum node_stat_item {
>  	PGSCAN_ANON,
>  	PGSCAN_FILE,
>  	PGREFILL,
> +#ifdef CONFIG_NUMA
> +	NUMA_MPOL_LOCAL_HIT,
> +	NUMA_MPOL_LOCAL_MISS,
> +	NUMA_MPOL_LOCAL_FOREIGN,
> +	NUMA_MPOL_PREFERRED_HIT,
> +	NUMA_MPOL_PREFERRED_MISS,
> +	NUMA_MPOL_PREFERRED_FOREIGN,
> +	NUMA_MPOL_PREFERRED_MANY_HIT,
> +	NUMA_MPOL_PREFERRED_MANY_MISS,
> +	NUMA_MPOL_PREFERRED_MANY_FOREIGN,
> +	NUMA_MPOL_BIND_HIT,
> +	NUMA_MPOL_BIND_MISS,
> +	NUMA_MPOL_BIND_FOREIGN,
> +	NUMA_MPOL_INTERLEAVE_HIT,
> +	NUMA_MPOL_INTERLEAVE_MISS,
> +	NUMA_MPOL_INTERLEAVE_FOREIGN,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_HIT,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_MISS,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_FOREIGN,
> +#endif
>  #ifdef CONFIG_HUGETLB_PAGE
>  	NR_HUGETLB,
>  #endif
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 982231a078f2..4d29f723a2de 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -420,6 +420,26 @@ static const unsigned int memcg_node_stat_items[] = {
>  	PGSCAN_ANON,
>  	PGSCAN_FILE,
>  	PGREFILL,
> +#ifdef CONFIG_NUMA
> +	NUMA_MPOL_LOCAL_HIT,
> +	NUMA_MPOL_LOCAL_MISS,
> +	NUMA_MPOL_LOCAL_FOREIGN,
> +	NUMA_MPOL_PREFERRED_HIT,
> +	NUMA_MPOL_PREFERRED_MISS,
> +	NUMA_MPOL_PREFERRED_FOREIGN,
> +	NUMA_MPOL_PREFERRED_MANY_HIT,
> +	NUMA_MPOL_PREFERRED_MANY_MISS,
> +	NUMA_MPOL_PREFERRED_MANY_FOREIGN,
> +	NUMA_MPOL_BIND_HIT,
> +	NUMA_MPOL_BIND_MISS,
> +	NUMA_MPOL_BIND_FOREIGN,
> +	NUMA_MPOL_INTERLEAVE_HIT,
> +	NUMA_MPOL_INTERLEAVE_MISS,
> +	NUMA_MPOL_INTERLEAVE_FOREIGN,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_HIT,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_MISS,
> +	NUMA_MPOL_WEIGHTED_INTERLEAVE_FOREIGN,
> +#endif
>  #ifdef CONFIG_HUGETLB_PAGE
>  	NR_HUGETLB,
>  #endif
> @@ -1591,6 +1611,26 @@ static const struct memory_stat memory_stats[] = {
>  #ifdef CONFIG_NUMA_BALANCING
>  	{ "pgpromote_success",		PGPROMOTE_SUCCESS	},
>  #endif
> +#ifdef CONFIG_NUMA
> +	{ "numa_mpol_local_hit",		NUMA_MPOL_LOCAL_HIT		},
> +	{ "numa_mpol_local_miss",		NUMA_MPOL_LOCAL_MISS		},
> +	{ "numa_mpol_local_foreign",		NUMA_MPOL_LOCAL_FOREIGN		},
> +	{ "numa_mpol_preferred_hit",		NUMA_MPOL_PREFERRED_HIT		},
> +	{ "numa_mpol_preferred_miss",		NUMA_MPOL_PREFERRED_MISS	},
> +	{ "numa_mpol_preferred_foreign",	NUMA_MPOL_PREFERRED_FOREIGN	},
> +	{ "numa_mpol_preferred_many_hit",	NUMA_MPOL_PREFERRED_MANY_HIT	},
> +	{ "numa_mpol_preferred_many_miss",	NUMA_MPOL_PREFERRED_MANY_MISS	},
> +	{ "numa_mpol_preferred_many_foreign",	NUMA_MPOL_PREFERRED_MANY_FOREIGN },
> +	{ "numa_mpol_bind_hit",			NUMA_MPOL_BIND_HIT		},
> +	{ "numa_mpol_bind_miss",		NUMA_MPOL_BIND_MISS		},
> +	{ "numa_mpol_bind_foreign",		NUMA_MPOL_BIND_FOREIGN		},
> +	{ "numa_mpol_interleave_hit",		NUMA_MPOL_INTERLEAVE_HIT	},
> +	{ "numa_mpol_interleave_miss",		NUMA_MPOL_INTERLEAVE_MISS	},
> +	{ "numa_mpol_interleave_foreign",	NUMA_MPOL_INTERLEAVE_FOREIGN	},
> +	{ "numa_mpol_weighted_interleave_hit",	NUMA_MPOL_WEIGHTED_INTERLEAVE_HIT },
> +	{ "numa_mpol_weighted_interleave_miss",	NUMA_MPOL_WEIGHTED_INTERLEAVE_MISS },
> +	{ "numa_mpol_weighted_interleave_foreign", NUMA_MPOL_WEIGHTED_INTERLEAVE_FOREIGN },
> +#endif
>  };
>  
>  /* The actual unit of the state item, not the same as the output unit */
> @@ -1642,6 +1682,26 @@ static int memcg_page_state_output_unit(int item)
>  	case PGREFILL:
>  #ifdef CONFIG_NUMA_BALANCING
>  	case PGPROMOTE_SUCCESS:
> +#endif
> +#ifdef CONFIG_NUMA
> +	case NUMA_MPOL_LOCAL_HIT:
> +	case NUMA_MPOL_LOCAL_MISS:
> +	case NUMA_MPOL_LOCAL_FOREIGN:
> +	case NUMA_MPOL_PREFERRED_HIT:
> +	case NUMA_MPOL_PREFERRED_MISS:
> +	case NUMA_MPOL_PREFERRED_FOREIGN:
> +	case NUMA_MPOL_PREFERRED_MANY_HIT:
> +	case NUMA_MPOL_PREFERRED_MANY_MISS:
> +	case NUMA_MPOL_PREFERRED_MANY_FOREIGN:
> +	case NUMA_MPOL_BIND_HIT:
> +	case NUMA_MPOL_BIND_MISS:
> +	case NUMA_MPOL_BIND_FOREIGN:
> +	case NUMA_MPOL_INTERLEAVE_HIT:
> +	case NUMA_MPOL_INTERLEAVE_MISS:
> +	case NUMA_MPOL_INTERLEAVE_FOREIGN:
> +	case NUMA_MPOL_WEIGHTED_INTERLEAVE_HIT:
> +	case NUMA_MPOL_WEIGHTED_INTERLEAVE_MISS:
> +	case NUMA_MPOL_WEIGHTED_INTERLEAVE_FOREIGN:
>  #endif
>  		return 1;
>  	default:
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 0e5175f1c767..2417de75098d 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -117,6 +117,7 @@
>  #include <asm/tlb.h>
>  #include <linux/uaccess.h>
>  #include <linux/memory.h>
> +#include <linux/memcontrol.h>
>  
>  #include "internal.h"
>  
> @@ -2426,6 +2427,83 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
>  	return page;
>  }
>  
> +/*
> + * Count a mempolicy allocation. Stats are tracked per-node and per-cgroup.
> + * The following numa_{hit/miss/foreign} pattern is used:
> + *
> + *   hit
> + *     - for BIND and PREFERRED_MANY, allocation succeeded on node in nodemask
> + *     - for other policies, allocation succeeded on intended node
> + *     - counted on the node of the allocation
> + *   miss
> + *     - allocation intended for other node, but happened on this one
> + *     - counted on other node
> + *   foreign
> + *     - allocation intended on this node, but happened on other node
> + *     - counted on this node
> + */
> +static void mpol_count_numa_alloc(struct mempolicy *pol, int intended_nid,
> +				  struct page *page, unsigned int order)
> +{
> +	int actual_nid = page_to_nid(page);
> +	long nr_pages = 1L << order;
> +	enum node_stat_item hit_idx;
> +	struct mem_cgroup *memcg;
> +	struct lruvec *lruvec;
> +	bool is_hit;
> +
> +	if (!root_mem_cgroup || mem_cgroup_disabled())
> +		return;

Hello JP!

The stats are exposed via /proc/vmstat and are guarded by CONFIG_NUMA, not
CONFIG_MEMCG. Early returning overhere would make it inaccuate. Does
it make sense to use mod_node_page_state if memcg is not available,
so that these global counters work regardless of cgroup configuration.

> +
> +	/*
> +	 * Start with hit then use +1 or +2 later on to change to miss or
> +	 * foreign respectively if needed.
> +	 */
> +	switch (pol->mode) {
> +	case MPOL_PREFERRED:
> +		hit_idx = NUMA_MPOL_PREFERRED_HIT;
> +		break;
> +	case MPOL_PREFERRED_MANY:
> +		hit_idx = NUMA_MPOL_PREFERRED_MANY_HIT;
> +		break;
> +	case MPOL_BIND:
> +		hit_idx = NUMA_MPOL_BIND_HIT;
> +		break;
> +	case MPOL_INTERLEAVE:
> +		hit_idx = NUMA_MPOL_INTERLEAVE_HIT;
> +		break;
> +	case MPOL_WEIGHTED_INTERLEAVE:
> +		hit_idx = NUMA_MPOL_WEIGHTED_INTERLEAVE_HIT;
> +		break;
> +	default:
> +		hit_idx = NUMA_MPOL_LOCAL_HIT;
> +		break;
> +	}
> +
> +	if (pol->mode == MPOL_BIND || pol->mode == MPOL_PREFERRED_MANY)
> +		is_hit = node_isset(actual_nid, pol->nodes);
> +	else
> +		is_hit = (actual_nid == intended_nid);
> +
> +	rcu_read_lock();
> +	memcg = mem_cgroup_from_task(current);
> +
> +	if (is_hit) {
> +		lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(actual_nid));
> +		mod_lruvec_state(lruvec, hit_idx, nr_pages);
> +	} else {
> +		/* account for miss on the fallback node */
> +		lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(actual_nid));
> +		mod_lruvec_state(lruvec, hit_idx + 1, nr_pages);
> +
> +		/* account for foreign on the intended node */
> +		lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(intended_nid));
> +		mod_lruvec_state(lruvec, hit_idx + 2, nr_pages);
> +	}
> +
> +	rcu_read_unlock();
> +}
> +
>  /**
>   * alloc_pages_mpol - Allocate pages according to NUMA mempolicy.
>   * @gfp: GFP flags.