ceph: CRUSH mapping algorithm

CRUSH is a pseudorandom data distribution function designed to map
inputs onto a dynamic hierarchy of devices, while minimizing the
extent to which inputs are remapped when the devices are added or
removed.  It includes some features that are specifically useful for
storage, most notably the ability to map each input onto a set of N
devices that are separated across administrator-defined failure
domains.  CRUSH is used to distribute data across the cluster of Ceph
storage nodes.

More information about CRUSH can be found in this paper:

    http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf

Signed-off-by: Sage Weil <sage@newdream.net>

1 files changed, 140 insertions, 0 deletions

diff --git a/fs/ceph/crush/crush.c b/fs/ceph/crush/crush.c
new file mode 100644
index 000000000000..13755cdc4fb3
--- /dev/null
+++ b/fs/ceph/crush/crush.c
@@ -0,0 +1,140 @@
+
+#ifdef __KERNEL__
+# include <linux/slab.h>
+#else
+# include <stdlib.h>
+# include <assert.h>
+# define kfree(x) do { if (x) free(x); } while (0)
+# define BUG_ON(x) assert(!(x))
+#endif
+
+#include "crush.h"
+
+/**
+ * crush_get_bucket_item_weight - Get weight of an item in given bucket
+ * @b: bucket pointer
+ * @p: item index in bucket
+ */
+int crush_get_bucket_item_weight(struct crush_bucket *b, int p)
+{
+        if (p >= b->size)
+                return 0;
+
+        switch (b->alg) {
+        case CRUSH_BUCKET_UNIFORM:
+                return ((struct crush_bucket_uniform *)b)->item_weight;
+        case CRUSH_BUCKET_LIST:
+                return ((struct crush_bucket_list *)b)->item_weights[p];
+        case CRUSH_BUCKET_TREE:
+                if (p & 1)
+                        return ((struct crush_bucket_tree *)b)->node_weights[p];
+                return 0;
+        case CRUSH_BUCKET_STRAW:
+                return ((struct crush_bucket_straw *)b)->item_weights[p];
+        }
+        return 0;
+}
+
+/**
+ * crush_calc_parents - Calculate parent vectors for the given crush map.
+ * @map: crush_map pointer
+ */
+void crush_calc_parents(struct crush_map *map)
+{
+        int i, b, c;
+
+        for (b = 0; b < map->max_buckets; b++) {
+                if (map->buckets[b] == NULL)
+                        continue;
+                for (i = 0; i < map->buckets[b]->size; i++) {
+                        c = map->buckets[b]->items[i];
+                        BUG_ON(c >= map->max_devices ||
+                               c < -map->max_buckets);
+                        if (c >= 0)
+                                map->device_parents[c] = map->buckets[b]->id;
+                        else
+                                map->bucket_parents[-1-c] = map->buckets[b]->id;
+                }
+        }
+}
+
+void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b)
+{
+        kfree(b->h.perm);
+        kfree(b->h.items);
+        kfree(b);
+}
+
+void crush_destroy_bucket_list(struct crush_bucket_list *b)
+{
+        kfree(b->item_weights);
+        kfree(b->sum_weights);
+        kfree(b->h.perm);
+        kfree(b->h.items);
+        kfree(b);
+}
+
+void crush_destroy_bucket_tree(struct crush_bucket_tree *b)
+{
+        kfree(b->node_weights);
+        kfree(b);
+}
+
+void crush_destroy_bucket_straw(struct crush_bucket_straw *b)
+{
+        kfree(b->straws);
+        kfree(b->item_weights);
+        kfree(b->h.perm);
+        kfree(b->h.items);
+        kfree(b);
+}
+
+void crush_destroy_bucket(struct crush_bucket *b)
+{
+        switch (b->alg) {
+        case CRUSH_BUCKET_UNIFORM:
+                crush_destroy_bucket_uniform((struct crush_bucket_uniform *)b);
+                break;
+        case CRUSH_BUCKET_LIST:
+                crush_destroy_bucket_list((struct crush_bucket_list *)b);
+                break;
+        case CRUSH_BUCKET_TREE:
+                crush_destroy_bucket_tree((struct crush_bucket_tree *)b);
+                break;
+        case CRUSH_BUCKET_STRAW:
+                crush_destroy_bucket_straw((struct crush_bucket_straw *)b);
+                break;
+        }
+}
+
+/**
+ * crush_destroy - Destroy a crush_map
+ * @map: crush_map pointer
+ */
+void crush_destroy(struct crush_map *map)
+{
+        int b;
+
+        /* buckets */
+        if (map->buckets) {
+                for (b = 0; b < map->max_buckets; b++) {
+                        if (map->buckets[b] == NULL)
+                                continue;
+                        crush_destroy_bucket(map->buckets[b]);
+                }
+                kfree(map->buckets);
+        }
+
+        /* rules */
+        if (map->rules) {
+                for (b = 0; b < map->max_rules; b++)
+                        kfree(map->rules[b]);
+                kfree(map->rules);
+        }
+
+        kfree(map->bucket_parents);
+        kfree(map->device_parents);
+        kfree(map);
+}
+
+