diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-03-19 09:43:06 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-03-19 09:43:06 -0700 |
commit | fc7f99cf36ebae853639dabb43bc2f0098c59aef (patch) | |
tree | 3ca7050397f515f91ef98f8b6293f9f7fd84ef02 /fs/ceph/osdmap.h | |
parent | 0a492fdef8aa241f6139e6455e852cc710ae8ed1 (diff) | |
parent | f1a3d57213fe264b4cf584e78bac36aaf9998729 (diff) | |
download | op-kernel-dev-fc7f99cf36ebae853639dabb43bc2f0098c59aef.zip op-kernel-dev-fc7f99cf36ebae853639dabb43bc2f0098c59aef.tar.gz |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (205 commits)
ceph: update for write_inode API change
ceph: reset osd after relevant messages timed out
ceph: fix flush_dirty_caps race with caps migration
ceph: include migrating caps in issued set
ceph: fix osdmap decoding when pools include (removed) snaps
ceph: return EBADF if waiting for caps on closed file
ceph: set osd request message front length correctly
ceph: reset front len on return to msgpool; BUG on mismatched front iov
ceph: fix snaptrace decoding on cap migration between mds
ceph: use single osd op reply msg
ceph: reset bits on connection close
ceph: remove bogus mds forward warning
ceph: remove fragile __map_osds optimization
ceph: fix connection fault STANDBY check
ceph: invalidate_authorizer without con->mutex held
ceph: don't clobber write return value when using O_SYNC
ceph: fix client_request_forward decoding
ceph: drop messages on unregistered mds sessions; cleanup
ceph: fix comments, locking in destroy_inode
ceph: move dereference after NULL test
...
Fix trivial conflicts in Documentation/ioctl/ioctl-number.txt
Diffstat (limited to 'fs/ceph/osdmap.h')
-rw-r--r-- | fs/ceph/osdmap.h | 125 |
1 files changed, 125 insertions, 0 deletions
diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h new file mode 100644 index 0000000..1fb55af --- /dev/null +++ b/fs/ceph/osdmap.h @@ -0,0 +1,125 @@ +#ifndef _FS_CEPH_OSDMAP_H +#define _FS_CEPH_OSDMAP_H + +#include <linux/rbtree.h> +#include "types.h" +#include "ceph_fs.h" +#include "crush/crush.h" + +/* + * The osd map describes the current membership of the osd cluster and + * specifies the mapping of objects to placement groups and placement + * groups to (sets of) osds. That is, it completely specifies the + * (desired) distribution of all data objects in the system at some + * point in time. + * + * Each map version is identified by an epoch, which increases monotonically. + * + * The map can be updated either via an incremental map (diff) describing + * the change between two successive epochs, or as a fully encoded map. + */ +struct ceph_pg_pool_info { + struct rb_node node; + int id; + struct ceph_pg_pool v; + int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; +}; + +struct ceph_pg_mapping { + struct rb_node node; + struct ceph_pg pgid; + int len; + int osds[]; +}; + +struct ceph_osdmap { + struct ceph_fsid fsid; + u32 epoch; + u32 mkfs_epoch; + struct ceph_timespec created, modified; + + u32 flags; /* CEPH_OSDMAP_* */ + + u32 max_osd; /* size of osd_state, _offload, _addr arrays */ + u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ + struct ceph_entity_addr *osd_addr; + + struct rb_root pg_temp; + struct rb_root pg_pools; + u32 pool_max; + + /* the CRUSH map specifies the mapping of placement groups to + * the list of osds that store+replicate them. */ + struct crush_map *crush; +}; + +/* + * file layout helpers + */ +#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) +#define ceph_file_layout_stripe_count(l) \ + ((__s32)le32_to_cpu((l).fl_stripe_count)) +#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) +#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) +#define ceph_file_layout_object_su(l) \ + ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) +#define ceph_file_layout_pg_preferred(l) \ + ((__s32)le32_to_cpu((l).fl_pg_preferred)) +#define ceph_file_layout_pg_pool(l) \ + ((__s32)le32_to_cpu((l).fl_pg_pool)) + +static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_stripe_unit) * + le32_to_cpu(l->fl_stripe_count); +} + +/* "period" == bytes before i start on a new set of objects */ +static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_object_size) * + le32_to_cpu(l->fl_stripe_count); +} + + +static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) +{ + return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); +} + +static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag) +{ + return map && (map->flags & flag); +} + +extern char *ceph_osdmap_state_str(char *str, int len, int state); + +static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, + int osd) +{ + if (osd >= map->max_osd) + return NULL; + return &map->osd_addr[osd]; +} + +extern struct ceph_osdmap *osdmap_decode(void **p, void *end); +extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, + struct ceph_osdmap *map, + struct ceph_messenger *msgr); +extern void ceph_osdmap_destroy(struct ceph_osdmap *map); + +/* calculate mapping of a file extent to an object */ +extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout, + u64 off, u64 *plen, + u64 *bno, u64 *oxoff, u64 *oxlen); + +/* calculate mapping of object to a placement group */ +extern int ceph_calc_object_layout(struct ceph_object_layout *ol, + const char *oid, + struct ceph_file_layout *fl, + struct ceph_osdmap *osdmap); +extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, + struct ceph_pg pgid); + +#endif |