[PATCHv2, RFC 04/30] radix-tree: implement preload for multiple contiguous elements

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

Currently radix_tree_preload() only guarantees enough nodes to insert
one element. It's a hard limit. You cannot batch a number insert under
one tree_lock.

This patch introduces radix_tree_preload_count(). It allows to
preallocate nodes enough to insert a number of *contiguous* elements.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@xxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
 include/linux/radix-tree.h |    3 +++
 lib/radix-tree.c           |   32 +++++++++++++++++++++++++-------
 2 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index ffc444c..81318cb 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -83,6 +83,8 @@ do {									\
 	(root)->rnode = NULL;						\
 } while (0)
 
+#define RADIX_TREE_PRELOAD_NR		512 /* For THP's benefit */
+
 /**
  * Radix-tree synchronization
  *
@@ -231,6 +233,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root,
 unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
+int radix_tree_preload_count(unsigned size, gfp_t gfp_mask);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index e796429..9bef0ac 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -81,16 +81,24 @@ static struct kmem_cache *radix_tree_node_cachep;
  * The worst case is a zero height tree with just a single item at index 0,
  * and then inserting an item at index ULONG_MAX. This requires 2 new branches
  * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared.
+ *
+ * Worst case for adding N contiguous items is adding entries at indexes
+ * (ULONG_MAX - N) to ULONG_MAX. It requires nodes to insert single worst-case
+ * item plus extra nodes if you cross the boundary from one node to the next.
+ *
  * Hence:
  */
-#define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1)
+#define RADIX_TREE_PRELOAD_MIN (RADIX_TREE_MAX_PATH * 2 - 1)
+#define RADIX_TREE_PRELOAD_MAX \
+	(RADIX_TREE_PRELOAD_MIN + \
+	 DIV_ROUND_UP(RADIX_TREE_PRELOAD_NR - 1, RADIX_TREE_MAP_SIZE))
 
 /*
  * Per-cpu pool of preloaded nodes
  */
 struct radix_tree_preload {
 	int nr;
-	struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE];
+	struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_MAX];
 };
 static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
@@ -257,29 +265,34 @@ radix_tree_node_free(struct radix_tree_node *node)
 
 /*
  * Load up this CPU's radix_tree_node buffer with sufficient objects to
- * ensure that the addition of a single element in the tree cannot fail.  On
- * success, return zero, with preemption disabled.  On error, return -ENOMEM
+ * ensure that the addition of *contiguous* elements in the tree cannot fail.
+ * On success, return zero, with preemption disabled.  On error, return -ENOMEM
  * with preemption not disabled.
  *
  * To make use of this facility, the radix tree must be initialised without
  * __GFP_WAIT being passed to INIT_RADIX_TREE().
  */
-int radix_tree_preload(gfp_t gfp_mask)
+int radix_tree_preload_count(unsigned size, gfp_t gfp_mask)
 {
 	struct radix_tree_preload *rtp;
 	struct radix_tree_node *node;
 	int ret = -ENOMEM;
+	int alloc = RADIX_TREE_PRELOAD_MIN +
+		DIV_ROUND_UP(size - 1, RADIX_TREE_MAP_SIZE);
+
+	if (size > RADIX_TREE_PRELOAD_NR)
+		return -ENOMEM;
 
 	preempt_disable();
 	rtp = &__get_cpu_var(radix_tree_preloads);
-	while (rtp->nr < ARRAY_SIZE(rtp->nodes)) {
+	while (rtp->nr < alloc) {
 		preempt_enable();
 		node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 		if (node == NULL)
 			goto out;
 		preempt_disable();
 		rtp = &__get_cpu_var(radix_tree_preloads);
-		if (rtp->nr < ARRAY_SIZE(rtp->nodes))
+		if (rtp->nr < alloc)
 			rtp->nodes[rtp->nr++] = node;
 		else
 			kmem_cache_free(radix_tree_node_cachep, node);
@@ -288,6 +301,11 @@ int radix_tree_preload(gfp_t gfp_mask)
 out:
 	return ret;
 }
+
+int radix_tree_preload(gfp_t gfp_mask)
+{
+	return radix_tree_preload_count(1, gfp_mask);
+}
 EXPORT_SYMBOL(radix_tree_preload);
 
 /*
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux