summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorChristoph Lameter <clameter@engr.sgi.com>2006-01-18 17:42:36 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-18 19:20:18 -0800
commitdc85da15d42b0efc792b0f5eab774dc5dbc1ceec (patch)
tree4b347b10dadf3cc7bdbff36709e8cee2bc673996 /mm
parentfc0abb1451c64c79ac80665d5ba74450ce274e4d (diff)
downloadop-kernel-dev-dc85da15d42b0efc792b0f5eab774dc5dbc1ceec.zip
op-kernel-dev-dc85da15d42b0efc792b0f5eab774dc5dbc1ceec.tar.gz
[PATCH] NUMA policies in the slab allocator V2
This patch fixes a regression in 2.6.14 against 2.6.13 that causes an imbalance in memory allocation during bootup. The slab allocator in 2.6.13 is not numa aware and simply calls alloc_pages(). This means that memory policies may control the behavior of alloc_pages(). During bootup the memory policy is set to MPOL_INTERLEAVE resulting in the spreading out of allocations during bootup over all available nodes. The slab allocator in 2.6.13 has only a single list of slab pages. As a result the per cpu slab cache and the spinlock controlled page lists may contain slab entries from off node memory. The slab allocator in 2.6.13 makes no effort to discern the locality of an entry on its lists. The NUMA aware slab allocator in 2.6.14 controls locality of the slab pages explicitly by calling alloc_pages_node(). The NUMA slab allocator manages slab entries by having lists of available slab pages for each node. The per cpu slab cache can only contain slab entries associated with the node local to the processor. This guarantees that the default allocation mode of the slab allocator always assigns local memory if available. Setting MPOL_INTERLEAVE as a default policy during bootup has no effect anymore. In 2.6.14 all node unspecific slab allocations are performed on the boot processor. This means that most of key data structures are allocated on one node. Most processors will have to refer to these structures making the boot node a potential bottleneck. This may reduce performance and cause unnecessary memory pressure on the boot node. This patch implements NUMA policies in the slab layer. There is the need of explicit application of NUMA memory policies by the slab allcator itself since the NUMA slab allocator does no longer let the page_allocator control locality. The check for policies is made directly at the beginning of __cache_alloc using current->mempolicy. The memory policy is already frequently checked by the page allocator (alloc_page_vma() and alloc_page_current()). So it is highly likely that the cacheline is present. For MPOL_INTERLEAVE kmalloc() will spread out each request to one node after another so that an equal distribution of allocations can be obtained during bootup. It is not possible to push the policy check to lower layers of the NUMA slab allocator since the per cpu caches are now only containing slab entries from the current node. If the policy says that the local node is not to be preferred or forbidden then there is no point in checking the slab cache or local list of slab pages. The allocation better be directed immediately to the lists containing slab entries for the allowed set of nodes. This way of applying policy also fixes another strange behavior in 2.6.13. alloc_pages() is controlled by the memory allocation policy of the current process. It could therefore be that one process is running with MPOL_INTERLEAVE and would f.e. obtain a new page following that policy since no slab entries are in the lists anymore. A page can typically be used for multiple slab entries but lets say that the current process is only using one. The other entries are then added to the slab lists. These are now non local entries in the slab lists despite of the possible availability of local pages that would provide faster access and increase the performance of the application. Another process without MPOL_INTERLEAVE may now run and expect a local slab entry from kmalloc(). However, there are still these free slab entries from the off node page obtained from the other process via MPOL_INTERLEAVE in the cache. The process will then get an off node slab entry although other slab entries may be available that are local to that process. This means that the policy if one process may contaminate the locality of the slab caches for other processes. This patch in effect insures that a per process policy is followed for the allocation of slab entries and that there cannot be a memory policy influence from one process to another. A process with default policy will always get a local slab entry if one is available. And the process using memory policies will get its memory arranged as requested. Off-node slab allocation will require the use of spinlocks and will make the use of per cpu caches not possible. A process using memory policies to redirect allocations offnode will have to cope with additional lock overhead in addition to the latency added by the need to access a remote slab entry. Changes V1->V2 - Remove #ifdef CONFIG_NUMA by moving forward declaration into prior #ifdef CONFIG_NUMA section. - Give the function determining the node number to use a saner name. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/mempolicy.c30
-rw-r--r--mm/slab.c12
2 files changed, 42 insertions, 0 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a683a66..71430d4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -976,6 +976,36 @@ static unsigned interleave_nodes(struct mempolicy *policy)
return nid;
}
+/*
+ * Depending on the memory policy provide a node from which to allocate the
+ * next slab entry.
+ */
+unsigned slab_node(struct mempolicy *policy)
+{
+ if (in_interrupt())
+ return numa_node_id();
+
+ switch (policy->policy) {
+ case MPOL_INTERLEAVE:
+ return interleave_nodes(policy);
+
+ case MPOL_BIND:
+ /*
+ * Follow bind policy behavior and start allocation at the
+ * first node.
+ */
+ return policy->v.zonelist->zones[0]->zone_pgdat->node_id;
+
+ case MPOL_PREFERRED:
+ if (policy->v.preferred_node >= 0)
+ return policy->v.preferred_node;
+ /* Fall through */
+
+ default:
+ return numa_node_id();
+ }
+}
+
/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
struct vm_area_struct *vma, unsigned long off)
diff --git a/mm/slab.c b/mm/slab.c
index bd0317f..9025608 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -103,6 +103,7 @@
#include <linux/rcupdate.h>
#include <linux/string.h>
#include <linux/nodemask.h>
+#include <linux/mempolicy.h>
#include <linux/mutex.h>
#include <asm/uaccess.h>
@@ -773,6 +774,8 @@ static struct array_cache *alloc_arraycache(int node, int entries,
}
#ifdef CONFIG_NUMA
+static void *__cache_alloc_node(kmem_cache_t *, gfp_t, int);
+
static inline struct array_cache **alloc_alien_cache(int node, int limit)
{
struct array_cache **ac_ptr;
@@ -2570,6 +2573,15 @@ static inline void *____cache_alloc(kmem_cache_t *cachep, gfp_t flags)
void *objp;
struct array_cache *ac;
+#ifdef CONFIG_NUMA
+ if (current->mempolicy) {
+ int nid = slab_node(current->mempolicy);
+
+ if (nid != numa_node_id())
+ return __cache_alloc_node(cachep, flags, nid);
+ }
+#endif
+
check_irq_off();
ac = ac_data(cachep);
if (likely(ac->avail)) {
OpenPOWER on IntegriCloud