Y l=J 2BP@n1h߿ 0+ l4( (  fB- }_I|+? /* SPDX-License-Identifier: GPL-2.0 */ #ifndef CEPH_RADOS_H #define CEPH_RADOS_H /* * Data types for the Ceph distributed object storage layer RADOS * (Reliable Autonomic Distributed Object Store). */ #include /* * fs id */ struct ceph_fsid { unsigned char fsid[16]; }; static inline int ceph_fsid_compare(const struct ceph_fsid *a, const struct ceph_fsid *b) { return memcmp(a, b, sizeof(*a)); } /* * ino, object, etc. */ typedef __le64 ceph_snapid_t; #define CEPH_SNAPDIR ((__u64)(-1)) /* reserved for hidden .snap dir */ #define CEPH_NOSNAP ((__u64)(-2)) /* "head", "live" revision */ #define CEPH_MAXSNAP ((__u64)(-3)) /* largest valid snapid */ struct ceph_timespec { __le32 tv_sec; __le32 tv_nsec; } __attribute__ ((packed)); /* * object layout - how objects are mapped into PGs */ #define CEPH_OBJECT_LAYOUT_HASH 1 #define CEPH_OBJECT_LAYOUT_LINEAR 2 #define CEPH_OBJECT_LAYOUT_HASHINO 3 /* * pg layout -- how PGs are mapped onto (sets of) OSDs */ #define CEPH_PG_LAYOUT_CRUSH 0 #define CEPH_PG_LAYOUT_HASH 1 #define CEPH_PG_LAYOUT_LINEAR 2 #define CEPH_PG_LAYOUT_HYBRID 3 #define CEPH_PG_MAX_SIZE 32 /* max # osds in a single pg */ /* * placement group. * we encode this into one __le64. */ struct ceph_pg_v1 { __le16 preferred; /* preferred primary osd */ __le16 ps; /* placement seed */ __le32 pool; /* object pool */ } __attribute__ ((packed)); /* * pg_pool is a set of pgs storing a pool of objects * * pg_num -- base number of pseudorandomly placed pgs * * pgp_num -- effective number when calculating pg placement. this * is used for pg_num increases. new pgs result in data being "split" * into new pgs. for this to proceed smoothly, new pgs are intiially * colocated with their parents; that is, pgp_num doesn't increase * until the new pgs have successfully split. only _then_ are the new * pgs placed independently. * * lpg_num -- localized pg count (per device). replicas are randomly * selected. * * lpgp_num -- as above. */ #define CEPH_NOPOOL ((__u64) (-1)) /* pool id not defined */ #define CEPH_POOL_TYPE_REP 1 #define CEPH_POOL_TYPE_RAID4 2 /* never implemented */ #define CEPH_POOL_TYPE_EC 3 /* * stable_mod func is used to control number of placement groups. * similar to straight-up modulo, but produces a stable mapping as b * increases over time. b is the number of bins, and bmask is the * containing power of 2 minus 1. * * b <= bmask and bmask=(2**n)-1 * e.g., b=12 -> bmask=15, b=123 -> bmask=127 */ static inline int ceph_stable_mod(int x, int b, int bmask) { if ((x & bmask) < b) return x & bmask; else return x & (bmask >> 1); } /* * object layout - how a given object should be stored. */ struct ceph_object_layout { struct ceph_pg_v1 ol_pgid; /* raw pg, with _full_ ps precision. */ __le32 ol_stripe_unit; /* for per-object parity, if any */ } __attribute__ ((packed)); /* * compound epoch+version, used by storage layer to serialize mutations */ struct ceph_eversion { __le64 version; __le32 epoch; } __attribute__ ((packed)); /* * osd map bits */ /* status bits */ #define CEPH_OSD_EXISTS (1<<0) #define CEPH_OSD_UP (1<<1) #define CEPH_OSD_AUTOOUT (1<<2) /* osd was automatically marked out */ #define CEPH_OSD_NEW (1<<3) /* osd is new, never marked in */ extern const char *ceph_osd_state_name(int s); /* osd weights. fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */ #define CEPH_OSD_IN 0x10000 #define CEPH_OSD_OUT 0 /* osd primary-affinity. fixed point value: 0x10000 == baseline */ #define CEPH_OSD_MAX_PRIMARY_AFFINITY 0x10000 #define CEPH_OSD_DEFAULT_PRIMARY_AFFINITY 0x10000 /* * osd map flag bits */ #define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC), not set since ~luminous */ #define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC), not set since ~luminous */ #define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all r