libceph: crush_location infrastructure

Allow expressing client's location in terms of CRUSH hierarchy as
a set of (bucket type name, bucket name) pairs.  The userspace syntax
"crush_location = key1=value1 key2=value2" is incompatible with mount
options and needed adaptation.  Key-value pairs are separated by '|'
and we use ':' instead of '=' to separate keys from values.  So for:

  crush_location = host=foo rack=bar

one would write:

  crush_location=host:foo|rack:bar

As in userspace, "multipath" locations are supported, so indicating
locality for parallel hierarchies is possible:

  crush_location=rack:foo1|rack:foo2|datacenter:bar

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
This commit is contained in:
Ilya Dryomov
2020-05-22 15:24:53 +02:00
parent 86403a92c3
commit 45e6aa9f55
4 changed files with 168 additions and 1 deletions

View File

@@ -302,9 +302,23 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
const struct ceph_pg *raw_pgid);
struct crush_loc {
char *cl_type_name;
char *cl_name;
};
struct crush_loc_node {
struct rb_node cl_node;
struct crush_loc cl_loc; /* pointers into cl_data */
char cl_data[];
};
int ceph_parse_crush_location(char *crush_location, struct rb_root *locs);
int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2);
void ceph_clear_crush_locs(struct rb_root *locs);
extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
u64 id);
extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id);