};
/**
+ * Different FID Format
+ * http://arch.lustre.org/index.php?title=Interoperability_fids_zfs#NEW.0
+ *
+ * FID:
+ * File IDentifier generated by client from range allocated by the seq service.
+ * First 0x400 sequences [2^33, 2^33 + 0x400] are reserved for system use. Note
+ * that on ldiskfs MDTs that IGIF FIDs can use inode numbers starting at 12,
+ * but this is in the IGIF SEQ rangeand does not conflict with assigned FIDs.
+ *
+ * IGIF:
+ * Inode and Generation In FID, a surrogate FID used to globally identify an
+ * existing object on OLD formatted MDT file system. This would only be used on
+ * MDT0 in a DNE filesystem, because there are not expected to be any OLD
+ * formatted DNE filesystems. Belongs to a sequence in [12, 2^32 - 1] range,
+ * where sequence number is inode number, and inode generation is used as OID.
+ * NOTE: This assumes no more than 2^32-1 inodes exist in the MDT filesystem,
+ * which is the maximum possible for an ldiskfs backend. NOTE: This assumes
+ * that the reserved ext3/ext4/ldiskfs inode numbers [0-11] are never visible
+ * to clients, which has always been true.
+ *
+ * IDIF:
+ * Object ID in FID, a surrogate FID used to globally identify an existing
+ * object on OLD formatted OST file system. Belongs to a sequence in
+ * [2^32, 2^33 - 1]. Sequence number is calculated as:
+ * 1 << 32 | (ost_index << 16) | ((objid >> 32) & 0xffff)
+ * that is, SEQ consists of 16-bit OST index, and higher 16 bits of object ID.
+ * The generation of unique SEQ values per OST allows the IDIF FIDs to be
+ * identified in the FLD correctly. The OID field is calculated as:
+ * objid & 0xffffffff
+ * that is, it consists of lower 32 bits of object ID. NOTE This assumes that
+ * no more than 2^48-1 objects have ever been created on an OST, and that no
+ * more than 65535 OSTs are in use. Both are very reasonable assumptions (can
+ * uniquely map all objects on an OST that created 1M objects per second for 9
+ * years, or combinations thereof).
+ *
+ * OST_MDT0:
+ * Surrogate FID used to identify an existing object on OLD formatted OST
+ * filesystem. Belongs to the reserved sequence 0, and is used internally prior
+ * to the introduction of FID-on-OST, at which point IDIF will be used to
+ * identify objects as residing on a specific OST.
+ *
+ * LLOG:
+ * For Lustre Log objects the object sequence 1 is used. This is compatible with
+ * both OLD and NEW.1 namespaces, as this SEQ number is in the ext3/ldiskfs
+ * reserved inode range and does not conflict with IGIF sequence numbers.
+ *
+ * ECHO:
+ * For testing OST IO performance the object sequence 2 is used. This is
+ * compatible with both OLD and NEW.1 namespaces, as this SEQ number is in the
+ * ext3/ldiskfs reserved inode range and does not conflict with IGIF sequence
+ * numbers.
+ *
+ * OST_MDT1 .. OST_MAX:
+ * For testing with multiple MDTs the object sequence 3 through 9 is used,
+ * allowing direct mapping of MDTs 1 through 7 respectively, for a total of 8
+ * MDTs including OST_MDT0. This matches the legacy CMD project "group"
+ * mappings. However, this SEQ range is only for testing prior to any production
+ * DNE release, as the objects in this range conflict across all OSTs, as the
+ * OST index is not part of the FID.
+ *
+ *
+ * For compatibility with existing OLD OST network protocol structures, the FID
+ * must map onto the o_id and o_gr in a manner that ensures existing objects are
+ * identified consistently for IO, as well as onto the lock namespace to ensure
+ * both IDIFs map onto the same objects for IO as well as resources in the DLM.
+ *
+ * DLM OLD OBIF/IDIF:
+ * resource[] = {o_id, o_seq, 0, 0}; // o_seq == 0 for production releases
+ *
+ * DLM NEW.1 FID (this is the same for both the MDT and OST):
+ * resource[] = {SEQ, OID, VER, HASH};
+ *
+ * Note that for mapping IDIF values to DLM resource names the o_id may be
+ * larger than the 2^33 reserved sequence numbers for IDIF, so it is possible
+ * for the o_id numbers to overlap FID SEQ numbers in the resource. However, in
+ * all production releases the OLD o_seq field is always zero, and all valid FID
+ * OID values are non-zero, so the lock resources will not collide.
+ *
+ * For objects within the IDIF range, group extraction (non-CMD) will be:
+ * o_id = (fid->f_seq & 0x7fff) << 16 | fid->f_oid;
+ * o_seq = 0; // formerly group number
+ */
+
+/**
* Note that reserved SEQ numbers below 12 will conflict with ldiskfs
* inodes in the IGIF namespace, so these reserved SEQ numbers can be
* used for other purposes and not risk collisions with existing inodes.
- *
- * Different FID Format
- * http://arch.lustre.org/index.php?title=Interoperability_fids_zfs#NEW.0
*/
enum fid_seq {
FID_SEQ_OST_MDT0 = 0,
#define OBD_CONNECT_TRUNCLOCK 0x400ULL /*locks on server for punch */
#define OBD_CONNECT_TRANSNO 0x800ULL /*replay sends init transno */
#define OBD_CONNECT_IBITS 0x1000ULL /*support for inodebits locks*/
-#define OBD_CONNECT_JOIN 0x2000ULL /*files can be concatenated.
- *We do not support JOIN FILE
- *anymore, reserve this flags
- *just for preventing such bit
- *to be reused.*/
+#define OBD_CONNECT_BARRIER 0x2000ULL /* write barrier */
#define OBD_CONNECT_ATTRFID 0x4000ULL /*Server can GetAttr By Fid*/
#define OBD_CONNECT_NODEVOH 0x8000ULL /*No open hndl on specl nodes*/
#define OBD_CONNECT_RMT_CLIENT 0x10000ULL /* Remote client, never used
#define MGS_CONNECT_SUPPORTED (OBD_CONNECT_VERSION | OBD_CONNECT_AT | \
OBD_CONNECT_FULL20 | OBD_CONNECT_IMP_RECOV | \
OBD_CONNECT_MNE_SWAB | OBD_CONNECT_PINGLESS |\
- OBD_CONNECT_BULK_MBITS)
+ OBD_CONNECT_BULK_MBITS | OBD_CONNECT_BARRIER)
#define MGS_CONNECT_SUPPORTED2 0
* Please update DECLARE_CKSUM_NAME/OBD_CKSUM_ALL in obd.h when adding a new
* algorithm and also the OBD_FL_CKSUM* flags.
*/
-typedef enum {
+typedef enum cksum_types {
OBD_CKSUM_CRC32 = 0x00000001,
OBD_CKSUM_ADLER = 0x00000002,
OBD_CKSUM_CRC32C= 0x00000004,
/* reserved for specifying OSTs */
#define LOV_MAGIC_SPECIFIC (0x0BD50000 | LOV_MAGIC_MAGIC)
#define LOV_MAGIC LOV_MAGIC_V1
+#define LOV_MAGIC_COMP_V1 (0x0BD60000 | LOV_MAGIC_MAGIC)
/*
* magic for fully defined striping
* depending on the case (replay uses ready striping, non-replay req uses
* hints), so MDT replaces magic with appropriate one and now LOD can
* easily understand what's inside -bzzz
+ *
+ * those *_DEF magics are only used on server side internally, they
+ * won't be put on wire or disk.
*/
-#define LOV_MAGIC_V1_DEF 0x0CD10BD0
-#define LOV_MAGIC_V3_DEF 0x0CD30BD0
+#define LOV_MAGIC_DEF 0x10000000
+#define LOV_MAGIC_V1_DEF (LOV_MAGIC_DEF | LOV_MAGIC_V1)
+#define LOV_MAGIC_V3_DEF (LOV_MAGIC_DEF | LOV_MAGIC_V3)
+#define LOV_MAGIC_COMP_V1_DEF (LOV_MAGIC_DEF | LOV_MAGIC_COMP_V1)
#define lov_pattern(pattern) (pattern & ~LOV_PATTERN_F_MASK)
#define lov_pattern_flags(pattern) (pattern & LOV_PATTERN_F_MASK)
struct ldlm_inodebits l_inodebits;
} ldlm_wire_policy_data_t;
+struct barrier_lvb {
+ __u32 lvb_status;
+ __u32 lvb_index;
+ __u64 lvb_padding;
+};
+
+struct ldlm_gl_barrier_desc {
+ __u32 lgbd_status;
+ __u32 lgbd_timeout;
+ __u64 lgbd_padding;
+};
+
union ldlm_gl_desc {
struct ldlm_gl_lquota_desc lquota_desc;
+ struct ldlm_gl_barrier_desc barrier_desc;
};
enum ldlm_intent_flags {
} u;
};
+enum {
+ CONFIG_T_CONFIG = 0,
+ CONFIG_T_SPTLRPC = 1,
+ CONFIG_T_RECOVER = 2,
+ CONFIG_T_PARAMS = 3,
+ CONFIG_T_NODEMAP = 4,
+ CONFIG_T_BARRIER = 5,
+ CONFIG_T_MAX
+};
+
struct mgs_config_body {
char mcb_name[MTI_NAME_MAXLEN]; /* logname */
__u64 mcb_offset; /* next index of config log to request */
struct lustre_handle o_handle; /* brw: lock handle to prolong
* locks */
struct llog_cookie o_lcookie; /* destroy: unlink cookie from
- * MDS, obsolete in 2.8, reused
- * in OSP */
+ * MDS, obsolete in 2.8 */
__u32 o_uid_h;
__u32 o_gid_h;
*/
struct mdc_swap_layouts {
__u64 msl_flags;
-} __packed;
+} __attribute__((packed));
struct close_data {
struct lustre_handle cd_handle;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff