aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLee Schermerhorn <lee.schermerhorn@hp.com>2009-12-14 17:58:21 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-15 08:53:12 -0800
commit06808b0827e1cd14eedc96bac2655d5b37ac246c (patch)
tree8f7b52a4af1532ed414631f68b99a059e299d83f /include
parentc1e6c8d074ea3621106548654cc244d2edc12ead (diff)
hugetlb: derive huge pages nodes allowed from task mempolicy
This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/hugetlb.h6
-rw-r--r--include/linux/mempolicy.h3
2 files changed, 9 insertions, 0 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 41a59afc70f..78b4bc64c00 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -23,6 +23,12 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
+
+#ifdef CONFIG_NUMA
+int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
+ void __user *, size_t *, loff_t *);
+#endif
+
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 085c903fe0f..1cc966cd3e5 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -201,6 +201,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p);
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
unsigned long addr, gfp_t gfp_flags,
struct mempolicy **mpol, nodemask_t **nodemask);
+extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
extern unsigned slab_node(struct mempolicy *policy);
extern enum zone_type policy_zone;
@@ -328,6 +329,8 @@ static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
return node_zonelist(0, gfp_flags);
}
+static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; }
+
static inline int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes,
const nodemask_t *to_nodes, int flags)