[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20260108033248.2791579-3-bingjiao@google.com>
Date: Thu, 8 Jan 2026 03:32:47 +0000
From: Bing Jiao <bingjiao@...gle.com>
To: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org, akpm@...ux-foundation.org, gourry@...rry.net,
longman@...hat.com, hannes@...xchg.org, mhocko@...nel.org,
roman.gushchin@...ux.dev, shakeel.butt@...ux.dev, muchun.song@...ux.dev,
tj@...nel.org, mkoutny@...e.com, david@...nel.org, zhengqi.arch@...edance.com,
lorenzo.stoakes@...cle.com, axelrasmussen@...gle.com,
chenridong@...weicloud.com, yuanchu@...gle.com, weixugc@...gle.com,
cgroups@...r.kernel.org, joshua.hahnjy@...il.com, bingjiao@...gle.com
Subject: [PATCH v7 2/2] mm/vmscan: select the closest preferred node in demote_folio_list()
The preferred demotion node (migration_target_control.nid) should be
the one closest to the source node to minimize migration latency.
Currently, a discrepancy exists where demote_folio_list() randomly
selects an allowed node if the preferred node from next_demotion_node()
is not set in mems_allowed.
To address it, update next_demotion_node() to return preferred nodes,
allowing the caller to select the preferred one.
Also update demote_folio_list() to traverse the demotion targets
hierarchically until a preferred node within mems_allowed is found.
It ensures that the selected demotion target is consistently
the closest available node.
Signed-off-by: Bing Jiao <bingjiao@...gle.com>
---
include/linux/memory-tiers.h | 6 +++---
mm/memory-tiers.c | 11 +++++++----
mm/vmscan.c | 25 ++++++++++++++++++++++---
3 files changed, 32 insertions(+), 10 deletions(-)
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 7a805796fcfd..87652042f2c2 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -53,11 +53,11 @@ struct memory_dev_type *mt_find_alloc_memory_type(int adist,
struct list_head *memory_types);
void mt_put_memory_types(struct list_head *memory_types);
#ifdef CONFIG_MIGRATION
-int next_demotion_node(int node);
+int next_demotion_node(int node, nodemask_t *preferred_nodes);
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
bool node_is_toptier(int node);
#else
-static inline int next_demotion_node(int node)
+static inline int next_demotion_node(int node, nodemask_t *preferred_nodes)
{
return NUMA_NO_NODE;
}
@@ -101,7 +101,7 @@ static inline void clear_node_memory_type(int node, struct memory_dev_type *memt
}
-static inline int next_demotion_node(int node)
+static inline int next_demotion_node(int node, nodemask_t *preferred_nodes)
{
return NUMA_NO_NODE;
}
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 864811fff409..286e4b5fa0e5 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -320,13 +320,14 @@ void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
/**
* next_demotion_node() - Get the next node in the demotion path
* @node: The starting node to lookup the next node
+ * @preferred_nodes: The pointer to nodemask of all preferred nodes to return
*
* Return: node id for next memory node in the demotion path hierarchy
- * from @node; NUMA_NO_NODE if @node is terminal. This does not keep
- * @node online or guarantee that it *continues* to be the next demotion
- * target.
+ * from @node; NUMA_NO_NODE if @node is terminal. Also returns all preferred
+ * nodes in @preferred_nodes. This does not keep @node online or guarantee
+ * that it *continues* to be the next demotion target.
*/
-int next_demotion_node(int node)
+int next_demotion_node(int node, nodemask_t *preferred_nodes)
{
struct demotion_nodes *nd;
int target;
@@ -357,6 +358,8 @@ int next_demotion_node(int node)
* target node randomly seems better until now.
*/
target = node_random(&nd->preferred);
+ if (preferred_nodes)
+ nodes_copy(*preferred_nodes, nd->preferred);
rcu_read_unlock();
return target;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 94ff5aa7c4fb..213ee75b3306 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1024,9 +1024,10 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
struct pglist_data *pgdat,
struct mem_cgroup *memcg)
{
- int target_nid = next_demotion_node(pgdat->node_id);
+ int target_nid;
unsigned int nr_succeeded;
nodemask_t allowed_mask;
+ nodemask_t preferred;
struct migration_target_control mtc = {
/*
@@ -1052,8 +1053,26 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
if (nodes_empty(allowed_mask))
return 0;
- if (!node_isset(target_nid, allowed_mask))
- target_nid = node_random(&allowed_mask);
+ target_nid = next_demotion_node(pgdat->node_id, &preferred);
+ while (target_nid != NUMA_NO_NODE &&
+ !node_isset(target_nid, allowed_mask)) {
+ /* Filter out preferred nodes that are not in allowed. */
+ nodes_and(preferred, preferred, allowed_mask);
+ if (!nodes_empty(preferred)) {
+ /* Randomly select one node from preferred. */
+ target_nid = node_random(&preferred);
+ break;
+ }
+ /*
+ * Preferred nodes in the lower tier are not set in allowed.
+ * Recursively get preferred from the next lower tier.
+ */
+ target_nid = next_demotion_node(target_nid, &preferred);
+ }
+
+ if (target_nid == NUMA_NO_NODE)
+ /* Nodes are gone (e.g., hot-unplugged). */
+ return 0;
mtc.nid = target_nid;
/* Demotion ignores all cpuset and mempolicy settings */
--
2.52.0.457.g6b5491de43-goog
Powered by blists - more mailing lists