summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorPaul Jackson <pj@sgi.com>2006-03-24 03:16:08 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-24 07:33:23 -0800
commitc61afb181c649754ea221f104e268cbacfc993e3 (patch)
tree870917b3f9175cf1663a2620d989856913cfb5f8 /mm
parent101a50019ae5e370d73984ee05d56dd3b08f330a (diff)
downloadop-kernel-dev-c61afb181c649754ea221f104e268cbacfc993e3.zip
op-kernel-dev-c61afb181c649754ea221f104e268cbacfc993e3.tar.gz
[PATCH] cpuset memory spread slab cache optimizations
The hooks in the slab cache allocator code path for support of NUMA mempolicies and cpuset memory spreading are in an important code path. Many systems will use neither feature. This patch optimizes those hooks down to a single check of some bits in the current tasks task_struct flags. For non NUMA systems, this hook and related code is already ifdef'd out. The optimization is done by using another task flag, set if the task is using a non-default NUMA mempolicy. Taking this flag bit along with the PF_SPREAD_PAGE and PF_SPREAD_SLAB flag bits added earlier in this 'cpuset memory spreading' patch set, one can check for the combination of any of these special case memory placement mechanisms with a single test of the current tasks task_struct flags. This patch also tightens up the code, to save a few bytes of kernel text space, and moves some of it out of line. Due to the nested inlines called from multiple places, we were ending up with three copies of this code, which once we get off the main code path (for local node allocation) seems a bit wasteful of instruction memory. Signed-off-by: Paul Jackson <pj@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.c32
-rw-r--r--mm/slab.c41
2 files changed, 60 insertions, 13 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e93cc74..4f71cfd 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -422,6 +422,37 @@ static int contextualize_policy(int mode, nodemask_t *nodes)
return mpol_check_policy(mode, nodes);
}
+
+/*
+ * Update task->flags PF_MEMPOLICY bit: set iff non-default
+ * mempolicy. Allows more rapid checking of this (combined perhaps
+ * with other PF_* flag bits) on memory allocation hot code paths.
+ *
+ * If called from outside this file, the task 'p' should -only- be
+ * a newly forked child not yet visible on the task list, because
+ * manipulating the task flags of a visible task is not safe.
+ *
+ * The above limitation is why this routine has the funny name
+ * mpol_fix_fork_child_flag().
+ *
+ * It is also safe to call this with a task pointer of current,
+ * which the static wrapper mpol_set_task_struct_flag() does,
+ * for use within this file.
+ */
+
+void mpol_fix_fork_child_flag(struct task_struct *p)
+{
+ if (p->mempolicy)
+ p->flags |= PF_MEMPOLICY;
+ else
+ p->flags &= ~PF_MEMPOLICY;
+}
+
+static void mpol_set_task_struct_flag(void)
+{
+ mpol_fix_fork_child_flag(current);
+}
+
/* Set the process memory policy */
long do_set_mempolicy(int mode, nodemask_t *nodes)
{
@@ -434,6 +465,7 @@ long do_set_mempolicy(int mode, nodemask_t *nodes)
return PTR_ERR(new);
mpol_free(current->mempolicy);
current->mempolicy = new;
+ mpol_set_task_struct_flag();
if (new && new->policy == MPOL_INTERLEAVE)
current->il_next = first_node(new->v.nodes);
return 0;
diff --git a/mm/slab.c b/mm/slab.c
index de51665..f80b523 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -899,6 +899,7 @@ static struct array_cache *alloc_arraycache(int node, int entries,
#ifdef CONFIG_NUMA
static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
static struct array_cache **alloc_alien_cache(int node, int limit)
{
@@ -2808,19 +2809,11 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
struct array_cache *ac;
#ifdef CONFIG_NUMA
- if (unlikely(current->mempolicy && !in_interrupt())) {
- int nid = slab_node(current->mempolicy);
-
- if (nid != numa_node_id())
- return __cache_alloc_node(cachep, flags, nid);
- }
- if (unlikely(cpuset_do_slab_mem_spread() &&
- (cachep->flags & SLAB_MEM_SPREAD) &&
- !in_interrupt())) {
- int nid = cpuset_mem_spread_node();
-
- if (nid != numa_node_id())
- return __cache_alloc_node(cachep, flags, nid);
+ if (unlikely(current->flags & (PF_SPREAD_PAGE | PF_SPREAD_SLAB |
+ PF_MEMPOLICY))) {
+ objp = alternate_node_alloc(cachep, flags);
+ if (objp != NULL)
+ return objp;
}
#endif
@@ -2856,6 +2849,28 @@ static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
#ifdef CONFIG_NUMA
/*
+ * Try allocating on another node if PF_SPREAD_PAGE|PF_SPREAD_SLAB|PF_MEMPOLICY.
+ *
+ * If we are in_interrupt, then process context, including cpusets and
+ * mempolicy, may not apply and should not be used for allocation policy.
+ */
+static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+ int nid_alloc, nid_here;
+
+ if (in_interrupt())
+ return NULL;
+ nid_alloc = nid_here = numa_node_id();
+ if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
+ nid_alloc = cpuset_mem_spread_node();
+ else if (current->mempolicy)
+ nid_alloc = slab_node(current->mempolicy);
+ if (nid_alloc != nid_here)
+ return __cache_alloc_node(cachep, flags, nid_alloc);
+ return NULL;
+}
+
+/*
* A interface to enable slab creation on nodeid
*/
static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
OpenPOWER on IntegriCloud