From 57f0f512b273f60d52568b8c6b77e17f5636edc0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Wed, 5 Aug 2015 17:04:01 -0300 Subject: Initial import --- include/linux/crush/crush.h | 209 +++++++++++++++++++++++++++++++++++++++++++ include/linux/crush/hash.h | 17 ++++ include/linux/crush/mapper.h | 20 +++++ 3 files changed, 246 insertions(+) create mode 100644 include/linux/crush/crush.h create mode 100644 include/linux/crush/hash.h create mode 100644 include/linux/crush/mapper.h (limited to 'include/linux/crush') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h new file mode 100644 index 000000000..48a1a7d10 --- /dev/null +++ b/include/linux/crush/crush.h @@ -0,0 +1,209 @@ +#ifndef CEPH_CRUSH_CRUSH_H +#define CEPH_CRUSH_CRUSH_H + +#include + +/* + * CRUSH is a pseudo-random data distribution algorithm that + * efficiently distributes input values (typically, data objects) + * across a heterogeneous, structured storage cluster. + * + * The algorithm was originally described in detail in this paper + * (although the algorithm has evolved somewhat since then): + * + * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf + * + * LGPL2 + */ + + +#define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ + +#define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ + + +#define CRUSH_ITEM_UNDEF 0x7ffffffe /* undefined result (internal use only) */ +#define CRUSH_ITEM_NONE 0x7fffffff /* no result */ + +/* + * CRUSH uses user-defined "rules" to describe how inputs should be + * mapped to devices. A rule consists of sequence of steps to perform + * to generate the set of output devices. + */ +struct crush_rule_step { + __u32 op; + __s32 arg1; + __s32 arg2; +}; + +/* step op codes */ +enum { + CRUSH_RULE_NOOP = 0, + CRUSH_RULE_TAKE = 1, /* arg1 = value to start with */ + CRUSH_RULE_CHOOSE_FIRSTN = 2, /* arg1 = num items to pick */ + /* arg2 = type */ + CRUSH_RULE_CHOOSE_INDEP = 3, /* same */ + CRUSH_RULE_EMIT = 4, /* no args */ + CRUSH_RULE_CHOOSELEAF_FIRSTN = 6, + CRUSH_RULE_CHOOSELEAF_INDEP = 7, + + CRUSH_RULE_SET_CHOOSE_TRIES = 8, /* override choose_total_tries */ + CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */ + CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10, + CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11, + CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12 +}; + +/* + * for specifying choose num (arg1) relative to the max parameter + * passed to do_rule + */ +#define CRUSH_CHOOSE_N 0 +#define CRUSH_CHOOSE_N_MINUS(x) (-(x)) + +/* + * The rule mask is used to describe what the rule is intended for. + * Given a ruleset and size of output set, we search through the + * rule list for a matching rule_mask. + */ +struct crush_rule_mask { + __u8 ruleset; + __u8 type; + __u8 min_size; + __u8 max_size; +}; + +struct crush_rule { + __u32 len; + struct crush_rule_mask mask; + struct crush_rule_step steps[0]; +}; + +#define crush_rule_size(len) (sizeof(struct crush_rule) + \ + (len)*sizeof(struct crush_rule_step)) + + + +/* + * A bucket is a named container of other items (either devices or + * other buckets). Items within a bucket are chosen using one of a + * few different algorithms. The table summarizes how the speed of + * each option measures up against mapping stability when items are + * added or removed. + * + * Bucket Alg Speed Additions Removals + * ------------------------------------------------ + * uniform O(1) poor poor + * list O(n) optimal poor + * tree O(log n) good good + * straw O(n) better better + * straw2 O(n) optimal optimal + */ +enum { + CRUSH_BUCKET_UNIFORM = 1, + CRUSH_BUCKET_LIST = 2, + CRUSH_BUCKET_TREE = 3, + CRUSH_BUCKET_STRAW = 4, + CRUSH_BUCKET_STRAW2 = 5, +}; +extern const char *crush_bucket_alg_name(int alg); + +struct crush_bucket { + __s32 id; /* this'll be negative */ + __u16 type; /* non-zero; type=0 is reserved for devices */ + __u8 alg; /* one of CRUSH_BUCKET_* */ + __u8 hash; /* which hash function to use, CRUSH_HASH_* */ + __u32 weight; /* 16-bit fixed point */ + __u32 size; /* num items */ + __s32 *items; + + /* + * cached random permutation: used for uniform bucket and for + * the linear search fallback for the other bucket types. + */ + __u32 perm_x; /* @x for which *perm is defined */ + __u32 perm_n; /* num elements of *perm that are permuted/defined */ + __u32 *perm; +}; + +struct crush_bucket_uniform { + struct crush_bucket h; + __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ +}; + +struct crush_bucket_list { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *sum_weights; /* 16-bit fixed point. element i is sum + of weights 0..i, inclusive */ +}; + +struct crush_bucket_tree { + struct crush_bucket h; /* note: h.size is _tree_ size, not number of + actual items */ + __u8 num_nodes; + __u32 *node_weights; +}; + +struct crush_bucket_straw { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ + __u32 *straws; /* 16-bit fixed point */ +}; + +struct crush_bucket_straw2 { + struct crush_bucket h; + __u32 *item_weights; /* 16-bit fixed point */ +}; + + + +/* + * CRUSH map includes all buckets, rules, etc. + */ +struct crush_map { + struct crush_bucket **buckets; + struct crush_rule **rules; + + __s32 max_buckets; + __u32 max_rules; + __s32 max_devices; + + /* choose local retries before re-descent */ + __u32 choose_local_tries; + /* choose local attempts using a fallback permutation before + * re-descent */ + __u32 choose_local_fallback_tries; + /* choose attempts before giving up */ + __u32 choose_total_tries; + /* attempt chooseleaf inner descent once for firstn mode; on + * reject retry outer descent. Note that this does *not* + * apply to a collision: in that case we will retry as we used + * to. */ + __u32 chooseleaf_descend_once; + + /* if non-zero, feed r into chooseleaf, bit-shifted right by (r-1) + * bits. a value of 1 is best for new clusters. for legacy clusters + * that want to limit reshuffling, a value of 3 or 4 will make the + * mappings line up a bit better with previous mappings. */ + __u8 chooseleaf_vary_r; +}; + + +/* crush.c */ +extern int crush_get_bucket_item_weight(const struct crush_bucket *b, int pos); +extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b); +extern void crush_destroy_bucket_list(struct crush_bucket_list *b); +extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b); +extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b); +extern void crush_destroy_bucket_straw2(struct crush_bucket_straw2 *b); +extern void crush_destroy_bucket(struct crush_bucket *b); +extern void crush_destroy_rule(struct crush_rule *r); +extern void crush_destroy(struct crush_map *map); + +static inline int crush_calc_tree_node(int i) +{ + return ((i+1) << 1)-1; +} + +#endif diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h new file mode 100644 index 000000000..91e884230 --- /dev/null +++ b/include/linux/crush/hash.h @@ -0,0 +1,17 @@ +#ifndef CEPH_CRUSH_HASH_H +#define CEPH_CRUSH_HASH_H + +#define CRUSH_HASH_RJENKINS1 0 + +#define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 + +extern const char *crush_hash_name(int type); + +extern __u32 crush_hash32(int type, __u32 a); +extern __u32 crush_hash32_2(int type, __u32 a, __u32 b); +extern __u32 crush_hash32_3(int type, __u32 a, __u32 b, __u32 c); +extern __u32 crush_hash32_4(int type, __u32 a, __u32 b, __u32 c, __u32 d); +extern __u32 crush_hash32_5(int type, __u32 a, __u32 b, __u32 c, __u32 d, + __u32 e); + +#endif diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h new file mode 100644 index 000000000..eab367446 --- /dev/null +++ b/include/linux/crush/mapper.h @@ -0,0 +1,20 @@ +#ifndef CEPH_CRUSH_MAPPER_H +#define CEPH_CRUSH_MAPPER_H + +/* + * CRUSH functions for find rules and then mapping an input to an + * output set. + * + * LGPL2 + */ + +#include + +extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); +extern int crush_do_rule(const struct crush_map *map, + int ruleno, + int x, int *result, int result_max, + const __u32 *weights, int weight_max, + int *scratch); + +#endif -- cgit v1.2.3-54-g00ecf