mempolicy: Rename MPOL_F_MORON to MPOL_F_MOPRON
Subsystems (3)
PATCH 1/2 mempolicy: Rename MPOL_F_MORON to MPOL_F_MOPRON
To follow code-of-conduct better.
--- include/uapi/linux/mempolicy.h | 2 +- kernel/sched/debug.c | 2 +- mm/mempolicy.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-)
include/uapi/linux/mempolicy.h +1 -1
@@ -60,7 +60,7 @@ enum {#define MPOL_F_SHARED (1 << 0)/* identify shared policies */ #define MPOL_F_LOCAL (1 << 1)/* preferred local allocation */ #define MPOL_F_MOF (1 << 3)/* this policy wants migrate on fault */ -#define MPOL_F_MORON (1 << 4)/* Migrate On protnone Reference On Node */ +#define MPOL_F_MOPRON (1 << 4)/* Migrate On Protnone Reference On Node */ #endif /* _UAPI_LINUX_MEMPOLICY_H */
kernel/sched/debug.c +1 -1
@@ -844,7 +844,7 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)task_lock (p); pol = p->mempolicy; -if (pol && !(pol->flags &MPOL_F_MORON )) +if (pol && !(pol->flags &MPOL_F_MOPRON )) pol =NULL ;mpol_get (pol);task_unlock (p);
mm/mempolicy.c +3 -3
@@ -2515,7 +2515,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long }/* Migrate the page towards the node whose CPU is referencing it */ -if (pol->flags &MPOL_F_MORON ) { +if (pol->flags &MPOL_F_MOPRON ) { polnid = thisnid;if (!should_numa_migrate_memory (current, page, curnid, thiscpu))
@@ -2806,7 +2806,7 @@ void __init numa_policy_init(void) preferred_node_policy[nid] = (struct mempolicy ) { .refcnt =ATOMIC_INIT (1 ), .mode =MPOL_PREFERRED , - .flags =MPOL_F_MOF |MPOL_F_MORON , + .flags =MPOL_F_MOF |MPOL_F_MOPRON , .v = { .preferred_node = nid, }, }; }
@@ -3014,7 +3014,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)unsigned short mode =MPOL_DEFAULT ;unsigned short flags =0 ; -if (pol && pol != &default_policy && !(pol->flags &MPOL_F_MORON )) { +if (pol && pol != &default_policy && !(pol->flags &MPOL_F_MOPRON )) { mode = pol->mode; flags = pol->flags; }
Signature · 1 line
2.28.0
PATCH 2/2 autonuma: Migrate on fault among multiple bound nodes
Now, AutoNUMA can only optimize the page placement among the NUMA nodes if the default memory policy is used. Because the memory policy specified explicitly should take precedence. But this seems too strict in some situations. For example, on a system with 4 NUMA nodes, if the memory of an application is bound to the node 0 and 1, AutoNUMA can potentially migrate the pages between the node 0 and 1 to reduce cross-node accessing without breaking the explicit memory binding policy.
So in this patch, if mbind(.mode=MPOL_BIND, .flags=MPOL_MF_LAZY) is used to bind the memory of the application to multiple nodes, and in the hint page fault handler both the faulting page node and the accessing node are in the policy nodemask, the page will be tried to be migrated to the accessing node to reduce the cross-node accessing.
[Peter Zijlstra: provided the simplified implementation method.]
Questions:
Sysctl knob kernel.numa_balancing can enable/disable AutoNUMA optimizing globally. But for the memory areas that are bound to multiple NUMA nodes, even if the AutoNUMA is enabled globally via the sysctl knob, we still need to enable AutoNUMA again with a special flag. Why not just optimize the page placement if possible as long as AutoNUMA is enabled globally? The interface would look simpler with that.
--- mm/mempolicy.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)
mm/mempolicy.c +11 -6
@@ -2494,15 +2494,19 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned longbreak ;case MPOL_BIND : -/* -* allows binding to multiple nodes. -* use current page if in policy nodemask, -* else select nearest allowed node, if any. -* If no allowed nodes, use current [!misplaced]. +* Allows binding to multiple nodes. If both current and +* accessing nodes are in policy nodemask, migrate to +* accessing node to optimize page placement. Otherwise, +* use current page if in policy nodemask, else select +* nearest allowed node, if any. If no allowed nodes, use +* current [!misplaced]. */ -if (node_isset (curnid, pol->v.nodes)) +if (node_isset (curnid, pol->v.nodes)) { +if (node_isset (thisnid, pol->v.nodes)) + goto mopron; goto out; + } z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER),
@@ -2516,6 +2520,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long/* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags &MPOL_F_MOPRON ) { +mopron: polnid = thisnid;if (!should_numa_migrate_memory (current, page, curnid, thiscpu))
Signature · 1 line
2.28.0
Quoted 80 lines · Huang Ying
To follow code-of-conduct better.
Signed-off-by "Huang, Ying" <[email protected]>Suggested-by "Matthew Wilcox (Oracle)" <[email protected]>Cc Andrew Morton <[email protected]>Cc Ingo Molnar <[email protected]>Cc Mel Gorman <[email protected]>Cc Rik van Riel <[email protected]>Cc Johannes Weiner <[email protected]>Cc Dave Hansen <[email protected]>Cc Andi Kleen <[email protected]>Cc Michal Hocko <[email protected]>Cc David Rientjes <[email protected]>--- include/uapi/linux/mempolicy.h | 2 +- kernel/sched/debug.c | 2 +- mm/mempolicy.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-)include/uapi/linux/mempolicy.h +1
-1@@ -60,7 +60,7 @@ enum {#define MPOL_F_SHARED (1 << 0)/* identify shared policies */ #define MPOL_F_LOCAL (1 << 1)/* preferred local allocation */ #define MPOL_F_MOF (1 << 3)/* this policy wants migrate on fault */ -#define MPOL_F_MORON (1 << 4)/* Migrate On protnone Reference On Node */ +#define MPOL_F_MOPRON (1 << 4)/* Migrate On Protnone Reference On Node */ #endif /* _UAPI_LINUX_MEMPOLICY_H */ kernel/sched/debug.c +1
-1@@ -844,7 +844,7 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)task_lock (p); pol = p->mempolicy; -if (pol && !(pol->flags &MPOL_F_MORON )) +if (pol && !(pol->flags &MPOL_F_MOPRON )) pol =NULL ;mpol_get (pol);task_unlock (p);mm/mempolicy.c +3
-3@@ -2515,7 +2515,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long }/* Migrate the page towards the node whose CPU is referencing it */ -if (pol->flags &MPOL_F_MORON ) { +if (pol->flags &MPOL_F_MOPRON ) { polnid = thisnid;if (!should_numa_migrate_memory (current, page, curnid, thiscpu))@@ -2806,7 +2806,7 @@ void __init numa_policy_init(void) preferred_node_policy[nid] = (struct mempolicy ) { .refcnt =ATOMIC_INIT (1 ), .mode =MPOL_PREFERRED , - .flags =MPOL_F_MOF |MPOL_F_MORON , + .flags =MPOL_F_MOF |MPOL_F_MOPRON , .v = { .preferred_node = nid, }, }; }@@ -3014,7 +3014,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)unsigned short mode =MPOL_DEFAULT ;unsigned short flags =0 ; -if (pol && pol != &default_policy && !(pol->flags &MPOL_F_MORON )) { +if (pol && pol != &default_policy && !(pol->flags &MPOL_F_MOPRON )) { mode = pol->mode; flags = pol->flags; }Signature · 1 line
2.28.0