void lmv_activate_target(struct lmv_obd *lmv, struct lmv_tgt_desc *tgt,
int activate)
{
- if (tgt->ltd_active == activate)
- return;
+ if (tgt->ltd_active == activate)
+ return;
- tgt->ltd_active = activate;
- lmv->desc.ld_active_tgt_count += (activate ? 1 : -1);
+ tgt->ltd_active = activate;
+ lmv->lmv_mdt_descs.ltd_lmv_desc.ld_active_tgt_count +=
+ (activate ? 1 : -1);
tgt->ltd_exp->exp_obd->obd_inactive = !activate;
}
tgt->ltd_active = 1;
tgt->ltd_exp = mdc_exp;
- lmv->desc.ld_active_tgt_count++;
+ lmv->lmv_mdt_descs.ltd_lmv_desc.ld_active_tgt_count++;
md_init_ea_size(tgt->ltd_exp, lmv->max_easize, lmv->max_def_easize);
- rc = lqos_add_tgt(&lmv->lmv_qos, tgt);
+ rc = lu_qos_add_tgt(&lmv->lmv_qos, tgt);
if (rc) {
obd_disconnect(mdc_exp);
RETURN(rc);
static void lmv_del_target(struct lmv_obd *lmv, struct lu_tgt_desc *tgt)
{
LASSERT(tgt);
- lqos_del_tgt(&lmv->lmv_qos, tgt);
- lu_tgt_descs_del(&lmv->lmv_mdt_descs, tgt);
+ ltd_del_tgt(&lmv->lmv_mdt_descs, tgt);
OBD_FREE_PTR(tgt);
}
struct lmv_obd *lmv = &obd->u.lmv;
struct lmv_tgt_desc *tgt;
struct lu_tgt_descs *ltd = &lmv->lmv_mdt_descs;
- int orig_tgt_count = 0;
int rc = 0;
ENTRY;
tgt->ltd_active = 0;
mutex_lock(<d->ltd_mutex);
- rc = lu_tgt_descs_add(ltd, tgt);
- if (!rc && index >= lmv->desc.ld_tgt_count) {
- orig_tgt_count = lmv->desc.ld_tgt_count;
- lmv->desc.ld_tgt_count = index + 1;
- }
+ rc = ltd_add_tgt(ltd, tgt);
mutex_unlock(<d->ltd_mutex);
if (rc)
RETURN(0);
rc = lmv_connect_mdc(obd, tgt);
- if (rc != 0) {
- mutex_lock(<d->ltd_mutex);
- lmv->desc.ld_tgt_count = orig_tgt_count;
- memset(tgt, 0, sizeof(*tgt));
- mutex_unlock(<d->ltd_mutex);
- } else {
+ if (!rc) {
int easize = sizeof(struct lmv_stripe_md) +
- lmv->desc.ld_tgt_count * sizeof(struct lu_fid);
+ lmv->lmv_mdt_count * sizeof(struct lu_fid);
+
lmv_init_ea_size(obd->obd_self_export, easize, 0);
}
if (lmv->connected)
GOTO(unlock, rc = 0);
- if (lmv->desc.ld_tgt_count == 0) {
+ if (!lmv->lmv_mdt_count) {
CERROR("%s: no targets configured: rc = -EINVAL\n",
obd->obd_name);
GOTO(unlock, rc = -EINVAL);
}
lmv->connected = 1;
- easize = lmv_mds_md_size(lmv->desc.ld_tgt_count, LMV_MAGIC);
+ easize = lmv_mds_md_size(lmv->lmv_mdt_count, LMV_MAGIC);
lmv_init_ea_size(obd->obd_self_export, easize, 0);
EXIT;
unlock:
if (!tgt->ltd_exp)
continue;
- --lmv->desc.ld_active_tgt_count;
+ --lmv->lmv_mdt_descs.ltd_lmv_desc.ld_active_tgt_count;
obd_disconnect(tgt->ltd_exp);
}
struct lmv_obd *lmv = &obddev->u.lmv;
struct lu_tgt_desc *tgt = NULL;
int set = 0;
- __u32 count = lmv->desc.ld_tgt_count;
+ __u32 count = lmv->lmv_mdt_count;
int rc = 0;
ENTRY;
__u32 index;
memcpy(&index, data->ioc_inlbuf2, sizeof(__u32));
- if (index >= count)
+
+ if (index >= lmv->lmv_mdt_descs.ltd_tgts_size)
RETURN(-ENODEV);
tgt = lmv_tgt(lmv, index);
struct obd_quotactl *oqctl;
if (qctl->qc_valid == QC_MDTIDX) {
- if (count <= qctl->qc_idx)
- RETURN(-EINVAL);
-
tgt = lmv_tgt(lmv, qctl->qc_idx);
- if (!tgt || !tgt->ltd_exp)
- RETURN(-EINVAL);
} else if (qctl->qc_valid == QC_UUID) {
lmv_foreach_tgt(lmv, tgt) {
if (!obd_uuid_equals(&tgt->ltd_uuid,
RETURN(-EINVAL);
}
- if (tgt->ltd_index >= count)
- RETURN(-EAGAIN);
+ if (!tgt || !tgt->ltd_exp)
+ RETURN(-EINVAL);
- LASSERT(tgt != NULL && tgt->ltd_exp != NULL);
OBD_ALLOC_PTR(oqctl);
if (!oqctl)
RETURN(-ENOMEM);
RETURN(rc);
}
-/**
- * This is _inode_ placement policy function (not name).
- */
-static u32 lmv_placement_policy(struct obd_device *obd,
- struct md_op_data *op_data)
+int lmv_fid_alloc(const struct lu_env *env, struct obd_export *exp,
+ struct lu_fid *fid, struct md_op_data *op_data)
{
+ struct obd_device *obd = class_exp2obd(exp);
struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_user_md *lum;
- u32 mdt;
-
- ENTRY;
-
- if (lmv->desc.ld_tgt_count == 1)
- RETURN(0);
-
- lum = op_data->op_data;
- /*
- * Choose MDT by
- * 1. See if the stripe offset is specified by lum.
- * 2. If parent has default LMV, and its hash type is "space", choose
- * MDT with QoS. (see lmv_locate_tgt_qos()).
- * 3. Then check if default LMV stripe offset is not -1.
- * 4. Finally choose MDS by name hash if the parent
- * is striped directory. (see lmv_locate_tgt()).
- *
- * presently explicit MDT location is not supported
- * for foreign dirs (as it can't be embedded into free
- * format LMV, like with lum_stripe_offset), so we only
- * rely on default stripe offset or then name hashing.
- */
- if (op_data->op_cli_flags & CLI_SET_MEA && lum != NULL &&
- le32_to_cpu(lum->lum_magic != LMV_MAGIC_FOREIGN) &&
- le32_to_cpu(lum->lum_stripe_offset) != (__u32)-1) {
- mdt = le32_to_cpu(lum->lum_stripe_offset);
- } else if (op_data->op_code == LUSTRE_OPC_MKDIR &&
- !lmv_dir_striped(op_data->op_mea1) &&
- lmv_dir_qos_mkdir(op_data->op_default_mea1)) {
- mdt = op_data->op_mds;
- } else if (op_data->op_code == LUSTRE_OPC_MKDIR &&
- op_data->op_default_mea1 &&
- op_data->op_default_mea1->lsm_md_master_mdt_index !=
- (__u32)-1) {
- mdt = op_data->op_default_mea1->lsm_md_master_mdt_index;
- op_data->op_mds = mdt;
- } else {
- mdt = op_data->op_mds;
- }
-
- RETURN(mdt);
-}
-
-int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds)
-{
struct lmv_tgt_desc *tgt;
int rc;
ENTRY;
- tgt = lmv_tgt(lmv, mds);
+ LASSERT(op_data);
+ LASSERT(fid);
+
+ tgt = lmv_tgt(lmv, op_data->op_mds);
if (!tgt)
RETURN(-ENODEV);
+ if (!tgt->ltd_active || !tgt->ltd_exp)
+ RETURN(-ENODEV);
+
/*
* New seq alloc and FLD setup should be atomic. Otherwise we may find
* on server that seq in new allocated fid is not yet known.
*/
mutex_lock(&tgt->ltd_fid_mutex);
-
- if (tgt->ltd_active == 0 || tgt->ltd_exp == NULL)
- GOTO(out, rc = -ENODEV);
-
- /*
- * Asking underlying tgt layer to allocate new fid.
- */
rc = obd_fid_alloc(NULL, tgt->ltd_exp, fid, NULL);
+ mutex_unlock(&tgt->ltd_fid_mutex);
if (rc > 0) {
LASSERT(fid_is_sane(fid));
rc = 0;
}
- EXIT;
-out:
- mutex_unlock(&tgt->ltd_fid_mutex);
- return rc;
-}
-
-int lmv_fid_alloc(const struct lu_env *env, struct obd_export *exp,
- struct lu_fid *fid, struct md_op_data *op_data)
-{
- struct obd_device *obd = class_exp2obd(exp);
- struct lmv_obd *lmv = &obd->u.lmv;
- u32 mds;
- int rc;
-
- ENTRY;
-
- LASSERT(op_data != NULL);
- LASSERT(fid != NULL);
-
- mds = lmv_placement_policy(obd, op_data);
-
- rc = __lmv_fid_alloc(lmv, fid, mds);
- if (rc)
- CERROR("Can't alloc new fid, rc %d\n", rc);
-
RETURN(rc);
}
RETURN(-EINVAL);
}
- obd_str2uuid(&lmv->desc.ld_uuid, desc->ld_uuid.uuid);
- lmv->desc.ld_tgt_count = 0;
- lmv->desc.ld_active_tgt_count = 0;
- lmv->desc.ld_qos_maxage = LMV_DESC_QOS_MAXAGE_DEFAULT;
+ obd_str2uuid(&lmv->lmv_mdt_descs.ltd_lmv_desc.ld_uuid,
+ desc->ld_uuid.uuid);
+ lmv->lmv_mdt_descs.ltd_lmv_desc.ld_tgt_count = 0;
+ lmv->lmv_mdt_descs.ltd_lmv_desc.ld_active_tgt_count = 0;
+ lmv->lmv_mdt_descs.ltd_lmv_desc.ld_qos_maxage =
+ LMV_DESC_QOS_MAXAGE_DEFAULT;
lmv->max_def_easize = 0;
lmv->max_easize = 0;
spin_lock_init(&lmv->lmv_lock);
- /* Set up allocation policy (QoS and RR) */
- INIT_LIST_HEAD(&lmv->lmv_qos.lq_svr_list);
- init_rwsem(&lmv->lmv_qos.lq_rw_sem);
- lmv->lmv_qos.lq_dirty = 1;
- lmv->lmv_qos.lq_reset = 1;
- /* Default priority is toward free space balance */
- lmv->lmv_qos.lq_prio_free = 232;
- /* Default threshold for rr (roughly 17%) */
- lmv->lmv_qos.lq_threshold_rr = 43;
-
- lu_qos_rr_init(&lmv->lmv_qos.lq_rr);
-
/*
* initialize rr_index to lower 32bit of netid, so that client
* can distribute subdirs evenly from the beginning.
if (rc)
CERROR("Can't init FLD, err %d\n", rc);
- rc = lu_tgt_descs_init(&lmv->lmv_mdt_descs);
+ rc = lu_tgt_descs_init(&lmv->lmv_mdt_descs, true);
if (rc)
CWARN("%s: error initialize target table: rc = %d\n",
obd->obd_name, rc);
if (flags & OBD_STATFS_FOR_MDT0)
return 0;
- if (lmv->lmv_statfs_start || lmv->desc.ld_tgt_count == 1)
+ if (lmv->lmv_statfs_start || lmv->lmv_mdt_count == 1)
return lmv->lmv_statfs_start;
/* choose initial MDT for this client */
/* We dont need a full 64-bit modulus, just enough
* to distribute the requests across MDTs evenly.
*/
- lmv->lmv_statfs_start =
- (u32)lnet_id.nid % lmv->desc.ld_tgt_count;
+ lmv->lmv_statfs_start = (u32)lnet_id.nid %
+ lmv->lmv_mdt_count;
break;
}
}
/* distribute statfs among MDTs */
idx = lmv_select_statfs_mdt(lmv, flags);
- for (i = 0; i < lmv->desc.ld_tgt_count; i++, idx++) {
- idx = idx % lmv->desc.ld_tgt_count;
+ for (i = 0; i < lmv->lmv_mdt_descs.ltd_tgts_size; i++, idx++) {
+ idx = idx % lmv->lmv_mdt_descs.ltd_tgts_size;
tgt = lmv_tgt(lmv, idx);
if (!tgt || !tgt->ltd_exp)
continue;
int rc;
if (ktime_get_seconds() - tgt->ltd_statfs_age <
- obd->u.lmv.desc.ld_qos_maxage)
+ obd->u.lmv.lmv_mdt_descs.ltd_lmv_desc.ld_qos_maxage)
return 0;
rc = obd_statfs_async(tgt->ltd_exp, &oinfo, 0, NULL);
RETURN(rc);
}
+static struct lu_tgt_desc *lmv_locate_tgt_qos(struct lmv_obd *lmv, __u32 *mdt)
+{
+ struct lu_tgt_desc *tgt;
+ __u64 total_weight = 0;
+ __u64 cur_weight = 0;
+ __u64 rand;
+ int rc;
+
+ ENTRY;
+
+ if (!ltd_qos_is_usable(&lmv->lmv_mdt_descs))
+ RETURN(ERR_PTR(-EAGAIN));
+
+ down_write(&lmv->lmv_qos.lq_rw_sem);
+
+ if (!ltd_qos_is_usable(&lmv->lmv_mdt_descs))
+ GOTO(unlock, tgt = ERR_PTR(-EAGAIN));
+
+ rc = ltd_qos_penalties_calc(&lmv->lmv_mdt_descs);
+ if (rc)
+ GOTO(unlock, tgt = ERR_PTR(rc));
+
+ lmv_foreach_tgt(lmv, tgt) {
+ tgt->ltd_qos.ltq_usable = 0;
+ if (!tgt->ltd_exp || !tgt->ltd_active)
+ continue;
+
+ tgt->ltd_qos.ltq_usable = 1;
+ lu_tgt_qos_weight_calc(tgt);
+ total_weight += tgt->ltd_qos.ltq_weight;
+ }
+
+ rand = lu_prandom_u64_max(total_weight);
+
+ lmv_foreach_connected_tgt(lmv, tgt) {
+ if (!tgt->ltd_qos.ltq_usable)
+ continue;
+
+ cur_weight += tgt->ltd_qos.ltq_weight;
+ if (cur_weight < rand)
+ continue;
+
+ *mdt = tgt->ltd_index;
+ ltd_qos_update(&lmv->lmv_mdt_descs, tgt, &total_weight);
+ GOTO(unlock, rc = 0);
+ }
+
+ /* no proper target found */
+ GOTO(unlock, tgt = ERR_PTR(-EAGAIN));
+unlock:
+ up_write(&lmv->lmv_qos.lq_rw_sem);
+
+ return tgt;
+}
+
+static struct lu_tgt_desc *lmv_locate_tgt_rr(struct lmv_obd *lmv, __u32 *mdt)
+{
+ struct lu_tgt_desc *tgt;
+ int i;
+ int index;
+
+ ENTRY;
+
+ spin_lock(&lmv->lmv_qos.lq_rr.lqr_alloc);
+ for (i = 0; i < lmv->lmv_mdt_descs.ltd_tgts_size; i++) {
+ index = (i + lmv->lmv_qos_rr_index) %
+ lmv->lmv_mdt_descs.ltd_tgts_size;
+ tgt = lmv_tgt(lmv, index);
+ if (!tgt || !tgt->ltd_exp || !tgt->ltd_active)
+ continue;
+
+ *mdt = tgt->ltd_index;
+ lmv->lmv_qos_rr_index = (*mdt + 1) %
+ lmv->lmv_mdt_descs.ltd_tgts_size;
+ spin_unlock(&lmv->lmv_qos.lq_rr.lqr_alloc);
+
+ RETURN(tgt);
+ }
+ spin_unlock(&lmv->lmv_qos.lq_rr.lqr_alloc);
+
+ RETURN(ERR_PTR(-ENODEV));
+}
+
static struct lmv_tgt_desc *
lmv_locate_tgt_by_name(struct lmv_obd *lmv, struct lmv_stripe_md *lsm,
const char *name, int namelen, struct lu_fid *fid,
* which is set outside, and if dir is migrating, 'op_data->op_post_migrate'
* indicates whether old or new layout is used to locate.
*
- * For plain direcotry, normally it will locate MDT by FID, but if this
- * directory has default LMV, and its hash type is "space", locate MDT with QoS.
+ * For plain direcotry, it just locate the MDT of op_data->op_fid1.
*
* \param[in] lmv LMV device
* \param[in] op_data client MD stack parameters, name, namelen
* index if the file under striped dir is being restored, see
* ct_restore(). */
if (op_data->op_bias & MDS_CREATE_VOLATILE &&
- (int)op_data->op_mds != -1) {
+ op_data->op_mds != LMV_OFFSET_DEFAULT) {
tgt = lmv_tgt(lmv, op_data->op_mds);
if (!tgt)
return ERR_PTR(-ENODEV);
op_data->op_mds = oinfo->lmo_mds;
tgt = lmv_tgt(lmv, oinfo->lmo_mds);
if (!tgt)
- tgt = ERR_PTR(-ENODEV);
- } else if (op_data->op_code == LUSTRE_OPC_MKDIR &&
- lmv_dir_qos_mkdir(op_data->op_default_mea1) &&
- !lmv_dir_striped(lsm)) {
- tgt = lmv_locate_tgt_qos(lmv, &op_data->op_mds);
- if (tgt == ERR_PTR(-EAGAIN))
- tgt = lmv_locate_tgt_rr(lmv, &op_data->op_mds);
- /*
- * only update statfs when mkdir under dir with "space" hash,
- * this means the cached statfs may be stale, and current mkdir
- * may not follow QoS accurately, but it's not serious, and it
- * avoids periodic statfs when client doesn't mkdir under
- * "space" hashed directories.
- *
- * TODO: after MDT support QoS object allocation, also update
- * statfs for 'lfs mkdir -i -1 ...", currently it's done in user
- * space.
- */
- if (!IS_ERR(tgt)) {
- struct obd_device *obd;
-
- obd = container_of(lmv, struct obd_device, u.lmv);
- lmv_statfs_check_update(obd, tgt);
- }
+ return ERR_PTR(-ENODEV);
} else {
tgt = lmv_locate_tgt_by_name(lmv, op_data->op_mea1,
op_data->op_name, op_data->op_namelen,
&op_data->op_mds, true);
}
+int lmv_migrate_existence_check(struct lmv_obd *lmv, struct md_op_data *op_data)
+{
+ struct lu_tgt_desc *tgt;
+ struct ptlrpc_request *request;
+ int rc;
+
+ LASSERT(lmv_dir_migrating(op_data->op_mea1));
+
+ tgt = lmv_locate_tgt(lmv, op_data);
+ if (IS_ERR(tgt))
+ return PTR_ERR(tgt);
+
+ rc = md_getattr_name(tgt->ltd_exp, op_data, &request);
+ if (!rc) {
+ ptlrpc_req_finished(request);
+ return -EEXIST;
+ }
+
+ return rc;
+}
+
+/* mkdir by QoS in two cases:
+ * 1. 'lfs mkdir -i -1'
+ * 2. parent default LMV master_mdt_index is -1
+ *
+ * NB, mkdir by QoS only if parent is not striped, this is to avoid remote
+ * directories under striped directory.
+ */
+static inline bool lmv_op_qos_mkdir(const struct md_op_data *op_data)
+{
+ const struct lmv_stripe_md *lsm = op_data->op_default_mea1;
+ const struct lmv_user_md *lum = op_data->op_data;
+
+ if (op_data->op_code != LUSTRE_OPC_MKDIR)
+ return false;
+
+ if (lmv_dir_striped(op_data->op_mea1))
+ return false;
+
+ if (op_data->op_cli_flags & CLI_SET_MEA && lum &&
+ (le32_to_cpu(lum->lum_magic) == LMV_USER_MAGIC ||
+ le32_to_cpu(lum->lum_magic) == LMV_USER_MAGIC_SPECIFIC) &&
+ le32_to_cpu(lum->lum_stripe_offset) == LMV_OFFSET_DEFAULT)
+ return true;
+
+ if (lsm && lsm->lsm_md_master_mdt_index == LMV_OFFSET_DEFAULT)
+ return true;
+
+ return false;
+}
+
+/* 'lfs mkdir -i <specific_MDT>' */
+static inline bool lmv_op_user_specific_mkdir(const struct md_op_data *op_data)
+{
+ const struct lmv_user_md *lum = op_data->op_data;
+
+ return op_data->op_code == LUSTRE_OPC_MKDIR &&
+ op_data->op_cli_flags & CLI_SET_MEA && lum &&
+ (le32_to_cpu(lum->lum_magic) == LMV_USER_MAGIC ||
+ le32_to_cpu(lum->lum_magic) == LMV_USER_MAGIC_SPECIFIC) &&
+ le32_to_cpu(lum->lum_stripe_offset) != LMV_OFFSET_DEFAULT;
+}
+
+/* parent default LMV master_mdt_index is not -1. */
+static inline bool
+lmv_op_default_specific_mkdir(const struct md_op_data *op_data)
+{
+ return op_data->op_code == LUSTRE_OPC_MKDIR &&
+ op_data->op_default_mea1 &&
+ op_data->op_default_mea1->lsm_md_master_mdt_index !=
+ LMV_OFFSET_DEFAULT;
+}
int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
const void *data, size_t datalen, umode_t mode, uid_t uid,
gid_t gid, cfs_cap_t cap_effective, __u64 rdev,
ENTRY;
- if (!lmv->desc.ld_active_tgt_count)
+ if (!lmv->lmv_mdt_descs.ltd_lmv_desc.ld_active_tgt_count)
RETURN(-EIO);
if (lmv_dir_bad_hash(op_data->op_mea1))
if (lmv_dir_migrating(op_data->op_mea1)) {
/*
* if parent is migrating, create() needs to lookup existing
- * name, to avoid creating new file under old layout of
- * migrating directory, check old layout here.
+ * name in both old and new layout, check old layout on client.
*/
- tgt = lmv_locate_tgt(lmv, op_data);
- if (IS_ERR(tgt))
- RETURN(PTR_ERR(tgt));
-
- rc = md_getattr_name(tgt->ltd_exp, op_data, request);
- if (!rc) {
- ptlrpc_req_finished(*request);
- *request = NULL;
- RETURN(-EEXIST);
- }
-
+ rc = lmv_migrate_existence_check(lmv, op_data);
if (rc != -ENOENT)
RETURN(rc);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
- CDEBUG(D_INODE, "CREATE name '%.*s' on "DFID" -> mds #%x\n",
- (int)op_data->op_namelen, op_data->op_name,
- PFID(&op_data->op_fid1), op_data->op_mds);
+ if (lmv_op_qos_mkdir(op_data)) {
+ tgt = lmv_locate_tgt_qos(lmv, &op_data->op_mds);
+ if (tgt == ERR_PTR(-EAGAIN))
+ tgt = lmv_locate_tgt_rr(lmv, &op_data->op_mds);
+ /*
+ * only update statfs after QoS mkdir, this means the cached
+ * statfs may be stale, and current mkdir may not follow QoS
+ * accurately, but it's not serious, and avoids periodic statfs
+ * when client doesn't mkdir by QoS.
+ */
+ if (!IS_ERR(tgt))
+ lmv_statfs_check_update(obd, tgt);
+ } else if (lmv_op_user_specific_mkdir(op_data)) {
+ struct lmv_user_md *lum = op_data->op_data;
+
+ op_data->op_mds = le32_to_cpu(lum->lum_stripe_offset);
+ tgt = lmv_tgt(lmv, op_data->op_mds);
+ if (!tgt)
+ RETURN(-ENODEV);
+ } else if (lmv_op_default_specific_mkdir(op_data)) {
+ op_data->op_mds =
+ op_data->op_default_mea1->lsm_md_master_mdt_index;
+ tgt = lmv_tgt(lmv, op_data->op_mds);
+ if (!tgt)
+ RETURN(-ENODEV);
+ }
+
+ if (IS_ERR(tgt))
+ RETURN(PTR_ERR(tgt));
rc = lmv_fid_alloc(NULL, exp, &op_data->op_fid2, op_data);
if (rc)
RETURN(rc);
- if (exp_connect_flags(exp) & OBD_CONNECT_DIR_STRIPE) {
- /* Send the create request to the MDT where the object
- * will be located */
- tgt = lmv_fid2tgt(lmv, &op_data->op_fid2);
- if (IS_ERR(tgt))
- RETURN(PTR_ERR(tgt));
-
- op_data->op_mds = tgt->ltd_index;
- }
-
- CDEBUG(D_INODE, "CREATE obj "DFID" -> mds #%x\n",
- PFID(&op_data->op_fid2), op_data->op_mds);
+ CDEBUG(D_INODE, "CREATE name '%.*s' "DFID" on "DFID" -> mds #%x\n",
+ (int)op_data->op_namelen, op_data->op_name,
+ PFID(&op_data->op_fid2), PFID(&op_data->op_fid1),
+ op_data->op_mds);
op_data->op_flags |= MF_MDC_CANCEL_FID1;
rc = md_create(tgt->ltd_exp, op_data, data, datalen, mode, uid, gid,
if (IS_ERR(child_tgt))
RETURN(PTR_ERR(child_tgt));
- if (!S_ISDIR(op_data->op_mode) && tp_tgt)
- rc = __lmv_fid_alloc(lmv, &target_fid, tp_tgt->ltd_index);
- else
- rc = lmv_fid_alloc(NULL, exp, &target_fid, op_data);
+ /* for directory, migrate to MDT specified by lum_stripe_offset;
+ * otherwise migrate to the target stripe of parent, but parent
+ * directory may have finished migration (normally current file too),
+ * allocate FID on MDT lum_stripe_offset, and server will check
+ * whether file was migrated already.
+ */
+ if (S_ISDIR(op_data->op_mode) || !tp_tgt) {
+ struct lmv_user_md *lum = op_data->op_data;
+
+ op_data->op_mds = le32_to_cpu(lum->lum_stripe_offset);
+ } else {
+ op_data->op_mds = tp_tgt->ltd_index;
+ }
+ rc = lmv_fid_alloc(NULL, exp, &target_fid, op_data);
if (rc)
RETURN(rc);
exp->exp_connect_data = *(struct obd_connect_data *)val;
RETURN(rc);
} else if (KEY_IS(KEY_TGT_COUNT)) {
- *((int *)val) = lmv->desc.ld_tgt_count;
+ *((int *)val) = lmv->lmv_mdt_descs.ltd_tgts_size;
RETURN(0);
}
struct obd_device *obddev = class_exp2obd(exp);
struct ptlrpc_request_set *set = _set;
struct lmv_obd *lmv = &obddev->u.lmv;
- int tgt_count = lmv->desc.ld_tgt_count;
+ int tgt_count = lmv->lmv_mdt_count;
struct lu_tgt_desc *tgt;
struct fid_array *fat, **fas = NULL;
int i, rc, **rcs = NULL;
* set default value -1, so lmv_locate_tgt() knows this stripe
* target is not initialized.
*/
- lsm->lsm_md_oinfo[i].lmo_mds = (u32)-1;
+ lsm->lsm_md_oinfo[i].lmo_mds = LMV_OFFSET_DEFAULT;
if (!fid_is_sane(&lsm->lsm_md_oinfo[i].lmo_fid))
continue;
* since this can be easily found, and only try others if that fails.
*/
for (i = 0, index = lmv_fid2tgt_index(lmv, fid);
- i < lmv->desc.ld_tgt_count;
- i++, index = (index + 1) % lmv->desc.ld_tgt_count) {
+ i < lmv->lmv_mdt_descs.ltd_tgts_size;
+ i++, index = (index + 1) % lmv->lmv_mdt_descs.ltd_tgts_size) {
if (index < 0) {
CDEBUG(D_HA, "%s: "DFID" is inaccessible: rc = %d\n",
obd->obd_name, PFID(fid), index);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff