linux-sg2042/include/linux/crush/crush.h

246 lines
7.0 KiB
C
Raw Normal View History

#ifndef CEPH_CRUSH_CRUSH_H
#define CEPH_CRUSH_CRUSH_H
#ifdef __KERNEL__
# include <linux/types.h>
#else
# include "crush_compat.h"
#endif
/*
* 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_MAX_RULESET (1<<8) /* max crush ruleset number */
#define CRUSH_MAX_RULES CRUSH_MAX_RULESET /* should be the same as max rulesets */
#define CRUSH_MAX_DEVICE_WEIGHT (100u * 0x10000u)
#define CRUSH_MAX_BUCKET_WEIGHT (65535u * 0x10000u)
#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);
/*
* although tree was a legacy algorithm, it has been buggy, so
* exclude it.
*/
#define CRUSH_LEGACY_ALLOWED_BUCKET_ALGS ( \
(1 << CRUSH_BUCKET_UNIFORM) | \
(1 << CRUSH_BUCKET_LIST) | \
(1 << CRUSH_BUCKET_STRAW))
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. */
libceph: for chooseleaf rules, retry CRUSH map descent from root if leaf is failed Add libceph support for a new CRUSH tunable recently added to Ceph servers. Consider the CRUSH rule step chooseleaf firstn 0 type <node_type> This rule means that <n> replicas will be chosen in a manner such that each chosen leaf's branch will contain a unique instance of <node_type>. When an object is re-replicated after a leaf failure, if the CRUSH map uses a chooseleaf rule the remapped replica ends up under the <node_type> bucket that held the failed leaf. This causes uneven data distribution across the storage cluster, to the point that when all the leaves but one fail under a particular <node_type> bucket, that remaining leaf holds all the data from its failed peers. This behavior also limits the number of peers that can participate in the re-replication of the data held by the failed leaf, which increases the time required to re-replicate after a failure. For a chooseleaf CRUSH rule, the tree descent has two steps: call them the inner and outer descents. If the tree descent down to <node_type> is the outer descent, and the descent from <node_type> down to a leaf is the inner descent, the issue is that a down leaf is detected on the inner descent, so only the inner descent is retried. In order to disperse re-replicated data as widely as possible across a storage cluster after a failure, we want to retry the outer descent. So, fix up crush_choose() to allow the inner descent to return immediately on choosing a failed leaf. Wire this up as a new CRUSH tunable. Note that after this change, for a chooseleaf rule, if the primary OSD in a placement group has failed, choosing a replacement may result in one of the other OSDs in the PG colliding with the new primary. This requires that OSD's data for that PG to need moving as well. This seems unavoidable but should be relatively rare. This corresponds to ceph.git commit 88f218181a9e6d2292e2697fc93797d0f6d6e5dc. Signed-off-by: Jim Schutt <jaschut@sandia.gov> Reviewed-by: Sage Weil <sage@inktank.com>
2012-12-01 00:15:25 +08:00
__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;
#ifndef __KERNEL__
/*
* version 0 (original) of straw_calc has various flaws. version 1
* fixes a few of them.
*/
__u8 straw_calc_version;
/*
* allowed bucket algs is a bitmask, here the bit positions
* are CRUSH_BUCKET_*. note that these are *bits* and
* CRUSH_BUCKET_* values are not, so we need to or together (1
* << CRUSH_BUCKET_WHATEVER). The 0th bit is not used to
* minimize confusion (bucket type values start at 1).
*/
__u32 allowed_bucket_algs;
__u32 *choose_tries;
#endif
};
/* 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