*/
#define DEBUG_SUBSYSTEM S_LMV
-#include <linux/slab.h>
+
+#include <linux/file.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/user_namespace.h>
static int lmv_check_connect(struct obd_device *obd);
-static void lmv_activate_target(struct lmv_obd *lmv,
- struct lmv_tgt_desc *tgt,
- int activate)
+void lmv_activate_target(struct lmv_obd *lmv, struct lmv_tgt_desc *tgt,
+ int activate)
{
if (tgt->ltd_active == activate)
return;
lmv->connected = 0;
lmv->conn_data = *data;
+ lmv->lmv_cache = localdata;
- if (lmv->targets_proc_entry == NULL) {
- lmv->targets_proc_entry = lprocfs_register("target_obds",
- obd->obd_proc_entry,
- NULL, NULL);
- if (IS_ERR(lmv->targets_proc_entry)) {
- CERROR("%s: cannot register "
- "/proc/fs/lustre/%s/%s/target_obds\n",
- obd->obd_name, obd->obd_type->typ_name,
- obd->obd_name);
- lmv->targets_proc_entry = NULL;
- }
+ lmv->lmv_tgts_kobj = kobject_create_and_add("target_obds",
+ &obd->obd_kset.kobj);
+ if (!lmv->lmv_tgts_kobj) {
+ CERROR("%s: cannot create /sys/fs/lustre/%s/%s/target_obds\n",
+ obd->obd_name, obd->obd_type->typ_name, obd->obd_name);
}
rc = lmv_check_connect(obd);
if (rc != 0)
- GOTO(out_proc, rc);
+ GOTO(out_sysfs, rc);
*pexp = exp;
RETURN(rc);
-out_proc:
- if (lmv->targets_proc_entry != NULL)
- lprocfs_remove(&lmv->targets_proc_entry);
+out_sysfs:
+ if (lmv->lmv_tgts_kobj)
+ kobject_put(lmv->lmv_tgts_kobj);
class_disconnect(exp);
for (i = 0; i < lmv->desc.ld_tgt_count; i++) {
struct lmv_tgt_desc *tgt = lmv->tgts[i];
- if (tgt == NULL || tgt->ltd_exp == NULL || !tgt->ltd_active) {
+ if (tgt == NULL || tgt->ltd_exp == NULL) {
CWARN("%s: NULL export for %d\n", obd->obd_name, i);
continue;
}
+ if (!tgt->ltd_active)
+ continue;
rc = md_init_ea_size(tgt->ltd_exp, easize, def_easize);
if (rc) {
int rc;
ENTRY;
- mdc_obd = class_find_client_obd(&tgt->ltd_uuid, LUSTRE_MDC_NAME,
- &obd->obd_uuid);
- if (!mdc_obd) {
- CERROR("target %s not attached\n", tgt->ltd_uuid.uuid);
- RETURN(-EINVAL);
- }
+ mdc_obd = class_find_client_obd(&tgt->ltd_uuid, LUSTRE_MDC_NAME,
+ &obd->obd_uuid);
+ if (!mdc_obd) {
+ CERROR("target %s not attached\n", tgt->ltd_uuid.uuid);
+ RETURN(-EINVAL);
+ }
CDEBUG(D_CONFIG, "connect to %s(%s) - %s, %s\n",
mdc_obd->obd_name, mdc_obd->obd_uuid.uuid,
tgt->ltd_uuid.uuid, obd->obd_uuid.uuid);
- if (!mdc_obd->obd_set_up) {
- CERROR("target %s is not set up\n", tgt->ltd_uuid.uuid);
- RETURN(-EINVAL);
- }
+ if (!mdc_obd->obd_set_up) {
+ CERROR("target %s is not set up\n", tgt->ltd_uuid.uuid);
+ RETURN(-EINVAL);
+ }
rc = obd_connect(NULL, &mdc_exp, mdc_obd, &obd->obd_uuid,
- &lmv->conn_data, NULL);
+ &lmv->conn_data, lmv->lmv_cache);
if (rc) {
CERROR("target %s connect error %d\n", tgt->ltd_uuid.uuid, rc);
RETURN(rc);
if (rc)
RETURN(rc);
- target.ft_srv = NULL;
- target.ft_exp = mdc_exp;
- target.ft_idx = tgt->ltd_idx;
+ target.ft_srv = NULL;
+ target.ft_exp = mdc_exp;
+ target.ft_idx = tgt->ltd_index;
- fld_client_add_target(&lmv->lmv_fld, &target);
+ fld_client_add_target(&lmv->lmv_fld, &target);
- rc = obd_register_observer(mdc_obd, obd);
- if (rc) {
- obd_disconnect(mdc_exp);
- CERROR("target %s register_observer error %d\n",
- tgt->ltd_uuid.uuid, rc);
- RETURN(rc);
- }
+ rc = obd_register_observer(mdc_obd, obd);
+ if (rc) {
+ obd_disconnect(mdc_exp);
+ CERROR("target %s register_observer error %d\n",
+ tgt->ltd_uuid.uuid, rc);
+ RETURN(rc);
+ }
if (obd->obd_observer) {
/*
md_init_ea_size(tgt->ltd_exp, lmv->max_easize, lmv->max_def_easize);
+ rc = lqos_add_tgt(&lmv->lmv_qos, tgt);
+ if (rc) {
+ obd_disconnect(mdc_exp);
+ RETURN(rc);
+ }
+
CDEBUG(D_CONFIG, "Connected to %s(%s) successfully (%d)\n",
mdc_obd->obd_name, mdc_obd->obd_uuid.uuid,
atomic_read(&obd->obd_refcount));
- if (lmv->targets_proc_entry != NULL) {
- struct proc_dir_entry *mdc_symlink;
-
- LASSERT(mdc_obd->obd_type != NULL);
- LASSERT(mdc_obd->obd_type->typ_name != NULL);
- mdc_symlink = lprocfs_add_symlink(mdc_obd->obd_name,
- lmv->targets_proc_entry,
- "../../../%s/%s",
- mdc_obd->obd_type->typ_name,
- mdc_obd->obd_name);
- if (mdc_symlink == NULL) {
- CERROR("cannot register LMV target "
- "/proc/fs/lustre/%s/%s/target_obds/%s\n",
- obd->obd_type->typ_name, obd->obd_name,
- mdc_obd->obd_name);
- }
- }
+ lmv_statfs_check_update(obd, tgt);
+
+ if (lmv->lmv_tgts_kobj)
+ /* Even if we failed to create the link, that's fine */
+ rc = sysfs_create_link(lmv->lmv_tgts_kobj,
+ &mdc_obd->obd_kset.kobj,
+ mdc_obd->obd_name);
RETURN(0);
}
if (lmv->tgts[index] == NULL)
return;
+ lqos_del_tgt(&lmv->lmv_qos, lmv->tgts[index]);
+
OBD_FREE_PTR(lmv->tgts[index]);
lmv->tgts[index] = NULL;
return;
__u32 index, int gen)
{
struct obd_device *mdc_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_tgt_desc *tgt;
- int orig_tgt_count = 0;
- int rc = 0;
- ENTRY;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt;
+ int orig_tgt_count = 0;
+ int rc = 0;
+
+ ENTRY;
CDEBUG(D_CONFIG, "Target uuid: %s. index %d\n", uuidp->uuid, index);
mdc_obd = class_find_client_obd(uuidp, LUSTRE_MDC_NAME,
}
mutex_init(&tgt->ltd_fid_mutex);
- tgt->ltd_idx = index;
+ tgt->ltd_index = index;
tgt->ltd_uuid = *uuidp;
tgt->ltd_active = 0;
lmv->tgts[index] = tgt;
mdc_obd->obd_fail = obd->obd_fail;
mdc_obd->obd_no_recov = obd->obd_no_recov;
- if (lmv->targets_proc_entry != NULL)
- lprocfs_remove_proc_entry(mdc_obd->obd_name,
- lmv->targets_proc_entry);
+ if (lmv->lmv_tgts_kobj)
+ sysfs_remove_link(lmv->lmv_tgts_kobj,
+ mdc_obd->obd_name);
}
rc = obd_fid_fini(tgt->ltd_exp->exp_obd);
lmv_disconnect_mdc(obd, lmv->tgts[i]);
}
- if (lmv->targets_proc_entry != NULL)
- lprocfs_remove(&lmv->targets_proc_entry);
- else
- CERROR("/proc/fs/lustre/%s/%s/target_obds missing\n",
- obd->obd_type->typ_name, obd->obd_name);
+ if (lmv->lmv_tgts_kobj)
+ kobject_put(lmv->lmv_tgts_kobj);
out_local:
/*
if (remote_gf != NULL) {
struct getinfo_fid2path *ori_gf;
char *ptr;
+ int len;
ori_gf = (struct getinfo_fid2path *)karg;
if (strlen(ori_gf->gf_u.gf_path) + 1 +
ptr = ori_gf->gf_u.gf_path;
- memmove(ptr + strlen(gf->gf_u.gf_path) + 1, ptr,
- strlen(ori_gf->gf_u.gf_path));
-
- strncpy(ptr, gf->gf_u.gf_path,
- strlen(gf->gf_u.gf_path));
- ptr += strlen(gf->gf_u.gf_path);
- *ptr = '/';
+ len = strlen(gf->gf_u.gf_path);
+ /* move the current path to the right to release space
+ * for closer-to-root part */
+ memmove(ptr + len + 1, ptr, strlen(ori_gf->gf_u.gf_path));
+ memcpy(ptr, gf->gf_u.gf_path, len);
+ ptr[len] = '/';
}
CDEBUG(D_INFO, "%s: get path %s "DFID" rec: %llu ln: %u\n",
void __user *uarg)
{
struct lmv_obd *lmv = &obd->u.lmv;
- struct file *filp;
- __u32 i, j;
- int err;
- bool any_set = false;
- struct kkuc_ct_data kcd = {
- .kcd_magic = KKUC_CT_DATA_MAGIC,
- .kcd_archive = lk->lk_data,
- };
- int rc = 0;
+ struct file *filp;
+ __u32 i, j;
+ int err;
+ bool any_set = false;
+ struct kkuc_ct_data *kcd;
+ size_t kcd_size;
+ int rc = 0;
ENTRY;
filp = fget(lk->lk_wfd);
if (!filp)
RETURN(-EBADF);
+ if (lk->lk_flags & LK_FLG_DATANR)
+ kcd_size = offsetof(struct kkuc_ct_data,
+ kcd_archives[lk->lk_data_count]);
+ else
+ kcd_size = sizeof(*kcd);
+
+ OBD_ALLOC(kcd, kcd_size);
+ if (kcd == NULL)
+ GOTO(err_fput, rc = -ENOMEM);
+
+ kcd->kcd_nr_archives = lk->lk_data_count;
+ if (lk->lk_flags & LK_FLG_DATANR) {
+ kcd->kcd_magic = KKUC_CT_DATA_ARRAY_MAGIC;
+ if (lk->lk_data_count > 0)
+ memcpy(kcd->kcd_archives, lk->lk_data,
+ sizeof(*kcd->kcd_archives) * lk->lk_data_count);
+ } else {
+ kcd->kcd_magic = KKUC_CT_DATA_BITMAP_MAGIC;
+ }
+
rc = libcfs_kkuc_group_add(filp, &obd->obd_uuid, lk->lk_uid,
- lk->lk_group, &kcd, sizeof(kcd));
+ lk->lk_group, kcd, kcd_size);
+ OBD_FREE(kcd, kcd_size);
if (rc)
GOTO(err_fput, rc);
RETURN(-EFAULT);
rc = obd_statfs(NULL, tgt->ltd_exp, &stat_buf,
- cfs_time_shift_64(-OBD_STATFS_CACHE_SECONDS),
+ ktime_get_seconds() - OBD_STATFS_CACHE_SECONDS,
0);
if (rc)
RETURN(rc);
RETURN(-EINVAL);
/* only files on same MDT can have their layouts swapped */
- if (tgt1->ltd_idx != tgt2->ltd_idx)
+ if (tgt1->ltd_index != tgt2->ltd_index)
RETURN(-EPERM);
rc = obd_iocontrol(cmd, tgt1->ltd_exp, len, karg, uarg);
/**
* This is _inode_ placement policy function (not name).
*/
-static int lmv_placement_policy(struct obd_device *obd,
- struct md_op_data *op_data, u32 *mds)
+static u32 lmv_placement_policy(struct obd_device *obd,
+ struct md_op_data *op_data)
{
- struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_obd *lmv = &obd->u.lmv;
struct lmv_user_md *lum;
+ u32 mdt;
ENTRY;
- LASSERT(mds != NULL);
-
- if (lmv->desc.ld_tgt_count == 1) {
- *mds = 0;
+ if (lmv->desc.ld_tgt_count == 1)
RETURN(0);
- }
lum = op_data->op_data;
- /* Choose MDS by
+ /*
+ * Choose MDT by
* 1. See if the stripe offset is specified by lum.
- * 2. Then check if there is default stripe offset.
- * 3. Finally choose MDS by name hash if the parent
- * is striped directory. (see lmv_locate_mds()). */
+ * 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) {
- *mds = le32_to_cpu(lum->lum_stripe_offset);
- } else if (op_data->op_default_stripe_offset != (__u32)-1) {
- *mds = op_data->op_default_stripe_offset;
- op_data->op_mds = *mds;
- /* Correct the stripe offset in lum */
- if (lum != NULL)
- lum->lum_stripe_offset = cpu_to_le32(*mds);
+ 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 {
- *mds = op_data->op_mds;
+ mdt = op_data->op_mds;
}
- RETURN(0);
+ RETURN(mdt);
}
int __lmv_fid_alloc(struct lmv_obd *lmv, struct lu_fid *fid, u32 mds)
rc = 0;
}
- EXIT;
+ EXIT;
out:
mutex_unlock(&tgt->ltd_fid_mutex);
- return rc;
+ 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 = 0;
- int rc;
- ENTRY;
+ struct obd_device *obd = class_exp2obd(exp);
+ struct lmv_obd *lmv = &obd->u.lmv;
+ u32 mds;
+ int rc;
- LASSERT(op_data != NULL);
- LASSERT(fid != NULL);
+ ENTRY;
- rc = lmv_placement_policy(obd, op_data, &mds);
- if (rc) {
- CERROR("Can't get target for allocating fid, "
- "rc %d\n", rc);
- RETURN(rc);
- }
+ LASSERT(op_data != NULL);
+ LASSERT(fid != NULL);
- rc = __lmv_fid_alloc(lmv, fid, mds);
- if (rc) {
- CERROR("Can't alloc new fid, rc %d\n", rc);
- RETURN(rc);
- }
+ mds = lmv_placement_policy(obd, op_data);
- RETURN(rc);
+ rc = __lmv_fid_alloc(lmv, fid, mds);
+ if (rc)
+ CERROR("Can't alloc new fid, rc %d\n", rc);
+
+ RETURN(rc);
}
static int lmv_setup(struct obd_device *obd, struct lustre_cfg *lcfg)
{
- struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_obd *lmv = &obd->u.lmv;
struct lmv_desc *desc;
- int rc;
+ struct lnet_process_id lnet_id;
+ int i = 0;
+ int rc;
+
ENTRY;
if (LUSTRE_CFG_BUFLEN(lcfg, 1) < 1) {
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;
lmv->max_def_easize = 0;
lmv->max_easize = 0;
spin_lock_init(&lmv->lmv_lock);
mutex_init(&lmv->lmv_init_mutex);
-#ifdef CONFIG_PROC_FS
- obd->obd_vars = lprocfs_lmv_obd_vars;
- lprocfs_obd_setup(obd, true);
- lprocfs_alloc_md_stats(obd, 0);
- rc = lprocfs_seq_create(obd->obd_proc_entry, "target_obd",
- 0444, &lmv_proc_target_fops, obd);
+ /* 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.
+ */
+ while (LNetGetId(i++, &lnet_id) != -ENOENT) {
+ if (LNET_NETTYP(LNET_NIDNET(lnet_id.nid)) != LOLND) {
+ lmv->lmv_qos_rr_index = (u32)lnet_id.nid;
+ break;
+ }
+ }
+
+ rc = lmv_tunables_init(obd);
if (rc)
- CWARN("%s: error adding LMV target_obd file: rc = %d\n",
+ CWARN("%s: error adding LMV sysfs/debugfs files: rc = %d\n",
obd->obd_name, rc);
-#endif
+
rc = fld_client_init(&lmv->lmv_fld, obd->obd_name,
LUSTRE_CLI_FLD_HASH_DHT);
if (rc) {
RETURN(rc);
}
+static int lmv_select_statfs_mdt(struct lmv_obd *lmv, __u32 flags)
+{
+ int i;
+
+ if (flags & OBD_STATFS_FOR_MDT0)
+ return 0;
+
+ if (lmv->lmv_statfs_start || lmv->desc.ld_tgt_count == 1)
+ return lmv->lmv_statfs_start;
+
+ /* choose initial MDT for this client */
+ for (i = 0;; i++) {
+ struct lnet_process_id lnet_id;
+ if (LNetGetId(i, &lnet_id) == -ENOENT)
+ break;
+
+ if (LNET_NETTYP(LNET_NIDNET(lnet_id.nid)) != LOLND) {
+ /* 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;
+ break;
+ }
+ }
+
+ return lmv->lmv_statfs_start;
+}
+
static int lmv_statfs(const struct lu_env *env, struct obd_export *exp,
- struct obd_statfs *osfs, __u64 max_age, __u32 flags)
+ struct obd_statfs *osfs, time64_t max_age, __u32 flags)
{
struct obd_device *obd = class_exp2obd(exp);
struct lmv_obd *lmv = &obd->u.lmv;
struct obd_statfs *temp;
int rc = 0;
- __u32 i;
+ __u32 i, idx;
ENTRY;
OBD_ALLOC(temp, sizeof(*temp));
if (temp == NULL)
RETURN(-ENOMEM);
- for (i = 0; i < lmv->desc.ld_tgt_count; i++) {
- if (lmv->tgts[i] == NULL || lmv->tgts[i]->ltd_exp == NULL)
+ /* 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;
+ if (lmv->tgts[idx] == NULL || lmv->tgts[idx]->ltd_exp == NULL)
continue;
- rc = obd_statfs(env, lmv->tgts[i]->ltd_exp, temp,
+ rc = obd_statfs(env, lmv->tgts[idx]->ltd_exp, temp,
max_age, flags);
if (rc) {
- CERROR("can't stat MDS #%d (%s), error %d\n", i,
- lmv->tgts[i]->ltd_exp->exp_obd->obd_name,
+ CERROR("%s: can't stat MDS #%d: rc = %d\n",
+ lmv->tgts[idx]->ltd_exp->exp_obd->obd_name, i,
rc);
GOTO(out_free_temp, rc);
}
+ if (temp->os_state & OS_STATE_SUM ||
+ flags == OBD_STATFS_FOR_MDT0) {
+ /* reset to the last aggregated values
+ * and don't sum with non-aggrated data */
+ /* If the statfs is from mount, it needs to retrieve
+ * necessary information from MDT0. i.e. mount does
+ * not need the merged osfs from all of MDT. Also
+ * clients can be mounted as long as MDT0 is in
+ * service */
+ *osfs = *temp;
+ break;
+ }
+
if (i == 0) {
*osfs = *temp;
- /* If the statfs is from mount, it will needs
- * retrieve necessary information from MDT0.
- * i.e. mount does not need the merged osfs
- * from all of MDT.
- * And also clients can be mounted as long as
- * MDT0 is in service*/
- if (flags & OBD_STATFS_FOR_MDT0)
- GOTO(out_free_temp, rc);
- } else {
- osfs->os_bavail += temp->os_bavail;
- osfs->os_blocks += temp->os_blocks;
- osfs->os_ffree += temp->os_ffree;
- osfs->os_files += temp->os_files;
- }
+ } else {
+ osfs->os_bavail += temp->os_bavail;
+ osfs->os_blocks += temp->os_blocks;
+ osfs->os_ffree += temp->os_ffree;
+ osfs->os_files += temp->os_files;
+ osfs->os_granted += temp->os_granted;
+ }
}
EXIT;
return rc;
}
+static int lmv_statfs_update(void *cookie, int rc)
+{
+ struct obd_info *oinfo = cookie;
+ struct obd_device *obd = oinfo->oi_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt = oinfo->oi_tgt;
+ struct obd_statfs *osfs = oinfo->oi_osfs;
+
+ /*
+ * NB: don't deactivate TGT upon error, because we may not trigger async
+ * statfs any longer, then there is no chance to activate TGT.
+ */
+ if (!rc) {
+ spin_lock(&lmv->lmv_lock);
+ tgt->ltd_statfs = *osfs;
+ tgt->ltd_statfs_age = ktime_get_seconds();
+ spin_unlock(&lmv->lmv_lock);
+ lmv->lmv_qos.lq_dirty = 1;
+ }
+
+ return rc;
+}
+
+/* update tgt statfs async if it's ld_qos_maxage old */
+int lmv_statfs_check_update(struct obd_device *obd, struct lmv_tgt_desc *tgt)
+{
+ struct obd_info oinfo = {
+ .oi_obd = obd,
+ .oi_tgt = tgt,
+ .oi_cb_up = lmv_statfs_update,
+ };
+ int rc;
+
+ if (ktime_get_seconds() - tgt->ltd_statfs_age <
+ obd->u.lmv.desc.ld_qos_maxage)
+ return 0;
+
+ rc = obd_statfs_async(tgt->ltd_exp, &oinfo, 0, NULL);
+
+ return rc;
+}
+
static int lmv_get_root(struct obd_export *exp, const char *fileset,
struct lu_fid *fid)
{
}
static int lmv_getxattr(struct obd_export *exp, const struct lu_fid *fid,
- u64 valid, const char *name,
- const char *input, int input_size, int output_size,
- int flags, struct ptlrpc_request **request)
+ u64 obd_md_valid, const char *name, size_t buf_size,
+ struct ptlrpc_request **req)
{
struct obd_device *obd = exp->exp_obd;
struct lmv_obd *lmv = &obd->u.lmv;
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
- rc = md_getxattr(tgt->ltd_exp, fid, valid, name, input,
- input_size, output_size, flags, request);
+ rc = md_getxattr(tgt->ltd_exp, fid, obd_md_valid, name, buf_size, req);
RETURN(rc);
}
static int lmv_setxattr(struct obd_export *exp, const struct lu_fid *fid,
- u64 valid, const char *name,
- const char *input, int input_size, int output_size,
- int flags, __u32 suppgid,
- struct ptlrpc_request **request)
+ u64 obd_md_valid, const char *name,
+ const void *value, size_t value_size,
+ unsigned int xattr_flags, u32 suppgid,
+ struct ptlrpc_request **req)
{
struct obd_device *obd = exp->exp_obd;
struct lmv_obd *lmv = &obd->u.lmv;
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
- rc = md_setxattr(tgt->ltd_exp, fid, valid, name, input,
- input_size, output_size, flags, suppgid,
- request);
+ rc = md_setxattr(tgt->ltd_exp, fid, obd_md_valid, name,
+ value, value_size, xattr_flags, suppgid, req);
RETURN(rc);
}
RETURN(PTR_ERR(tgt));
if (op_data->op_flags & MF_GET_MDT_IDX) {
- op_data->op_mds = tgt->ltd_idx;
+ op_data->op_mds = tgt->ltd_index;
RETURN(0);
}
RETURN(rc);
}
-/**
- * Choosing the MDT by name or FID in @op_data.
- * For non-striped directory, it will locate MDT by fid.
- * For striped-directory, it will locate MDT by name. And also
- * it will reset op_fid1 with the FID of the choosen stripe.
- **/
-struct lmv_tgt_desc *
-lmv_locate_target_for_name(struct lmv_obd *lmv, struct lmv_stripe_md *lsm,
- const char *name, int namelen, struct lu_fid *fid,
- u32 *mds)
+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,
+ __u32 *mds, bool post_migrate)
{
- struct lmv_tgt_desc *tgt;
- const struct lmv_oinfo *oinfo;
+ struct lmv_tgt_desc *tgt;
+ const struct lmv_oinfo *oinfo;
+
+ if (!lmv_dir_striped(lsm) || !namelen) {
+ tgt = lmv_find_target(lmv, fid);
+ if (IS_ERR(tgt))
+ return tgt;
+
+ *mds = tgt->ltd_index;
+ return tgt;
+ }
if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_BAD_NAME_HASH)) {
if (cfs_fail_val >= lsm->lsm_md_stripe_count)
- RETURN(ERR_PTR(-EBADF));
+ return ERR_PTR(-EBADF);
oinfo = &lsm->lsm_md_oinfo[cfs_fail_val];
} else {
- oinfo = lsm_name_to_stripe_info(lsm, name, namelen);
+ oinfo = lsm_name_to_stripe_info(lsm, name, namelen,
+ post_migrate);
if (IS_ERR(oinfo))
- RETURN(ERR_CAST(oinfo));
+ return ERR_CAST(oinfo);
}
- if (fid != NULL)
- *fid = oinfo->lmo_fid;
- if (mds != NULL)
- *mds = oinfo->lmo_mds;
-
+ *fid = oinfo->lmo_fid;
+ *mds = oinfo->lmo_mds;
tgt = lmv_get_target(lmv, oinfo->lmo_mds, NULL);
- CDEBUG(D_INFO, "locate on mds %u "DFID"\n", oinfo->lmo_mds,
- PFID(&oinfo->lmo_fid));
+ CDEBUG(D_INODE, "locate MDT %u parent "DFID"\n", *mds, PFID(fid));
+
return tgt;
}
/**
- * Locate mds by fid or name
+ * Locate MDT of op_data->op_fid1
*
- * For striped directory (lsm != NULL), it will locate the stripe
- * by name hash (see lsm_name_to_stripe_info()). Note: if the hash_type
- * is unknown, it will return -EBADFD, and lmv_intent_lookup might need
- * walk through all of stripes to locate the entry.
+ * For striped directory, it will locate the stripe by name hash, if hash_type
+ * is unknown, it will return the stripe specified by 'op_data->op_stripe_index'
+ * 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 normal direcotry, it will locate MDS by FID directly.
* \param[in] lmv LMV device
* \param[in] op_data client MD stack parameters, name, namelen
* mds_num etc.
- * \param[in] fid object FID used to locate MDS.
*
* retval pointer to the lmv_tgt_desc if succeed.
* ERR_PTR(errno) if failed.
*/
-struct lmv_tgt_desc*
-lmv_locate_mds(struct lmv_obd *lmv, struct md_op_data *op_data,
- struct lu_fid *fid)
+struct lmv_tgt_desc *
+lmv_locate_tgt(struct lmv_obd *lmv, struct md_op_data *op_data)
{
- struct lmv_stripe_md *lsm = op_data->op_mea1;
- struct lmv_tgt_desc *tgt;
+ struct lmv_stripe_md *lsm = op_data->op_mea1;
+ struct lmv_oinfo *oinfo;
+ struct lmv_tgt_desc *tgt;
+
+ if (lmv_dir_foreign(lsm))
+ return ERR_PTR(-ENODATA);
/* During creating VOLATILE file, it should honor the mdt
* 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) {
- int i;
tgt = lmv_get_target(lmv, op_data->op_mds, NULL);
if (IS_ERR(tgt))
return tgt;
- if (lsm != NULL) {
+ if (lmv_dir_striped(lsm)) {
+ int i;
+
/* refill the right parent fid */
for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
- struct lmv_oinfo *oinfo;
-
oinfo = &lsm->lsm_md_oinfo[i];
if (oinfo->lmo_mds == op_data->op_mds) {
- *fid = oinfo->lmo_fid;
+ op_data->op_fid1 = oinfo->lmo_fid;
break;
}
}
if (i == lsm->lsm_md_stripe_count)
- *fid = lsm->lsm_md_oinfo[0].lmo_fid;
+ op_data->op_fid1 = lsm->lsm_md_oinfo[0].lmo_fid;
}
+ } else if (lmv_dir_bad_hash(lsm)) {
+ LASSERT(op_data->op_stripe_index < lsm->lsm_md_stripe_count);
+ oinfo = &lsm->lsm_md_oinfo[op_data->op_stripe_index];
- return tgt;
+ op_data->op_fid1 = oinfo->lmo_fid;
+ op_data->op_mds = oinfo->lmo_mds;
+ tgt = lmv_get_target(lmv, oinfo->lmo_mds, NULL);
+ } 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);
+ }
+ } else {
+ tgt = lmv_locate_tgt_by_name(lmv, op_data->op_mea1,
+ op_data->op_name, op_data->op_namelen,
+ &op_data->op_fid1, &op_data->op_mds,
+ op_data->op_post_migrate);
}
- if (lsm == NULL || op_data->op_namelen == 0) {
- tgt = lmv_find_target(lmv, fid);
+ return tgt;
+}
+
+/* Locate MDT of op_data->op_fid2 for link/rename */
+static struct lmv_tgt_desc *
+lmv_locate_tgt2(struct lmv_obd *lmv, struct md_op_data *op_data)
+{
+ struct lmv_tgt_desc *tgt;
+ int rc;
+
+ LASSERT(op_data->op_name);
+ if (lmv_dir_migrating(op_data->op_mea2)) {
+ struct lu_fid fid1 = op_data->op_fid1;
+ struct lmv_stripe_md *lsm1 = op_data->op_mea1;
+ struct ptlrpc_request *request = NULL;
+
+ /*
+ * avoid creating new file under old layout of migrating
+ * directory, check it here.
+ */
+ tgt = lmv_locate_tgt_by_name(lmv, op_data->op_mea2,
+ op_data->op_name, op_data->op_namelen,
+ &op_data->op_fid2, &op_data->op_mds, false);
if (IS_ERR(tgt))
- return tgt;
+ RETURN(tgt);
+
+ op_data->op_fid1 = op_data->op_fid2;
+ op_data->op_mea1 = op_data->op_mea2;
+ rc = md_getattr_name(tgt->ltd_exp, op_data, &request);
+ op_data->op_fid1 = fid1;
+ op_data->op_mea1 = lsm1;
+ if (!rc) {
+ ptlrpc_req_finished(request);
+ RETURN(ERR_PTR(-EEXIST));
+ }
- op_data->op_mds = tgt->ltd_idx;
- return tgt;
+ if (rc != -ENOENT)
+ RETURN(ERR_PTR(rc));
}
- return lmv_locate_target_for_name(lmv, lsm, op_data->op_name,
- op_data->op_namelen, fid,
- &op_data->op_mds);
+ return lmv_locate_tgt_by_name(lmv, op_data->op_mea2, op_data->op_name,
+ op_data->op_namelen, &op_data->op_fid2,
+ &op_data->op_mds, true);
}
int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
gid_t gid, cfs_cap_t cap_effective, __u64 rdev,
struct ptlrpc_request **request)
{
- struct obd_device *obd = exp->exp_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_tgt_desc *tgt;
- int rc;
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt;
+ int rc;
+
ENTRY;
if (!lmv->desc.ld_active_tgt_count)
RETURN(-EIO);
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+ if (lmv_dir_bad_hash(op_data->op_mea1))
+ RETURN(-EBADF);
+
+ 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.
+ */
+ 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);
+ }
+
+ if (rc != -ENOENT)
+ RETURN(rc);
+
+ op_data->op_post_migrate = true;
+ }
+
+ tgt = lmv_locate_tgt(lmv, op_data);
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 */
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
- op_data->op_mds = tgt->ltd_idx;
- } else {
- CDEBUG(D_CONFIG, "Server doesn't support striped dirs\n");
+ op_data->op_mds = tgt->ltd_index;
}
CDEBUG(D_INODE, "CREATE obj "DFID" -> mds #%x\n",
CDEBUG(D_INODE, "ENQUEUE on "DFID"\n", PFID(&op_data->op_fid1));
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+ tgt = lmv_find_target(lmv, &op_data->op_fid1);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
CDEBUG(D_INODE, "ENQUEUE on "DFID" -> mds #%u\n",
- PFID(&op_data->op_fid1), tgt->ltd_idx);
+ PFID(&op_data->op_fid1), tgt->ltd_index);
rc = md_enqueue(tgt->ltd_exp, einfo, policy, op_data, lockh,
extra_lock_flags);
RETURN(rc);
}
-static int
+int
lmv_getattr_name(struct obd_export *exp,struct md_op_data *op_data,
struct ptlrpc_request **preq)
{
- struct ptlrpc_request *req = NULL;
- struct obd_device *obd = exp->exp_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_tgt_desc *tgt;
- struct mdt_body *body;
- int rc;
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt;
+ struct mdt_body *body;
+ int rc;
+
ENTRY;
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+retry:
+ tgt = lmv_locate_tgt(lmv, op_data);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
CDEBUG(D_INODE, "GETATTR_NAME for %*s on "DFID" -> mds #%d\n",
(int)op_data->op_namelen, op_data->op_name,
- PFID(&op_data->op_fid1), tgt->ltd_idx);
+ PFID(&op_data->op_fid1), tgt->ltd_index);
rc = md_getattr_name(tgt->ltd_exp, op_data, preq);
- if (rc != 0)
+ if (rc == -ENOENT && lmv_dir_retry_check_update(op_data)) {
+ ptlrpc_req_finished(*preq);
+ *preq = NULL;
+ goto retry;
+ }
+
+ if (rc)
RETURN(rc);
body = req_capsule_server_get(&(*preq)->rq_pill, &RMF_MDT_BODY);
LASSERT(body != NULL);
if (body->mbo_valid & OBD_MD_MDS) {
- struct lu_fid rid = body->mbo_fid1;
- CDEBUG(D_INODE, "Request attrs for "DFID"\n",
- PFID(&rid));
-
- tgt = lmv_find_target(lmv, &rid);
- if (IS_ERR(tgt)) {
- ptlrpc_req_finished(*preq);
- preq = NULL;
- RETURN(PTR_ERR(tgt));
- }
-
- op_data->op_fid1 = rid;
+ op_data->op_fid1 = body->mbo_fid1;
op_data->op_valid |= OBD_MD_FLCROSSREF;
op_data->op_namelen = 0;
op_data->op_name = NULL;
- rc = md_getattr_name(tgt->ltd_exp, op_data, &req);
+
ptlrpc_req_finished(*preq);
- *preq = req;
+ *preq = NULL;
+
+ goto retry;
}
RETURN(rc);
RETURN(PTR_ERR(tgt));
}
- if (tgt->ltd_idx != op_tgt) {
+ if (tgt->ltd_index != op_tgt) {
CDEBUG(D_INODE, "EARLY_CANCEL on "DFID"\n", PFID(fid));
policy.l_inodebits.bits = bits;
rc = md_cancel_unused(tgt->ltd_exp, fid, &policy,
op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
op_data->op_cap = cfs_curproc_cap_pack();
- if (op_data->op_mea2 != NULL) {
- struct lmv_stripe_md *lsm = op_data->op_mea2;
- const struct lmv_oinfo *oinfo;
-
- oinfo = lsm_name_to_stripe_info(lsm, op_data->op_name,
- op_data->op_namelen);
- if (IS_ERR(oinfo))
- RETURN(PTR_ERR(oinfo));
-
- op_data->op_fid2 = oinfo->lmo_fid;
- }
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid2);
+ tgt = lmv_locate_tgt2(lmv, op_data);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
* Cancel UPDATE lock on child (fid1).
*/
op_data->op_flags |= MF_MDC_CANCEL_FID2;
- rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_idx, LCK_EX,
+ rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_index, LCK_EX,
MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID1);
if (rc != 0)
RETURN(rc);
RETURN(rc);
}
-static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
- const char *old, size_t oldlen,
- const char *new, size_t newlen,
- struct ptlrpc_request **request)
+static int lmv_migrate(struct obd_export *exp, struct md_op_data *op_data,
+ const char *name, size_t namelen,
+ struct ptlrpc_request **request)
{
- struct obd_device *obd = exp->exp_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_tgt_desc *src_tgt;
- struct lmv_tgt_desc *tgt_tgt;
- struct obd_export *target_exp;
- struct mdt_body *body;
- int rc;
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_stripe_md *lsm = op_data->op_mea1;
+ struct lmv_tgt_desc *parent_tgt;
+ struct lmv_tgt_desc *sp_tgt;
+ struct lmv_tgt_desc *tp_tgt = NULL;
+ struct lmv_tgt_desc *child_tgt;
+ struct lmv_tgt_desc *tgt;
+ struct lu_fid target_fid;
+ int rc;
+
ENTRY;
- LASSERT(oldlen != 0);
+ LASSERT(op_data->op_cli_flags & CLI_MIGRATE);
- CDEBUG(D_INODE, "RENAME %.*s in "DFID":%d to %.*s in "DFID":%d\n",
- (int)oldlen, old, PFID(&op_data->op_fid1),
- op_data->op_mea1 ? op_data->op_mea1->lsm_md_stripe_count : 0,
- (int)newlen, new, PFID(&op_data->op_fid2),
- op_data->op_mea2 ? op_data->op_mea2->lsm_md_stripe_count : 0);
+ CDEBUG(D_INODE, "MIGRATE "DFID"/%.*s\n",
+ PFID(&op_data->op_fid1), (int)namelen, name);
op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
op_data->op_cap = cfs_curproc_cap_pack();
- if (op_data->op_cli_flags & CLI_MIGRATE) {
- LASSERTF(fid_is_sane(&op_data->op_fid3), "invalid FID "DFID"\n",
- PFID(&op_data->op_fid3));
-
- if (op_data->op_mea1 != NULL) {
- struct lmv_stripe_md *lsm = op_data->op_mea1;
- struct lmv_tgt_desc *tmp;
-
- /* Fix the parent fid for striped dir */
- tmp = lmv_locate_target_for_name(lmv, lsm, old,
- oldlen,
- &op_data->op_fid1,
- NULL);
- if (IS_ERR(tmp))
- RETURN(PTR_ERR(tmp));
- }
-
- rc = lmv_fid_alloc(NULL, exp, &op_data->op_fid2, op_data);
- if (rc != 0)
- RETURN(rc);
- src_tgt = lmv_find_target(lmv, &op_data->op_fid3);
- if (IS_ERR(src_tgt))
- RETURN(PTR_ERR(src_tgt));
+ parent_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+ if (IS_ERR(parent_tgt))
+ RETURN(PTR_ERR(parent_tgt));
- target_exp = src_tgt->ltd_exp;
- } else {
- if (op_data->op_mea1 != NULL) {
- struct lmv_stripe_md *lsm = op_data->op_mea1;
+ if (lmv_dir_striped(lsm)) {
+ __u32 hash_type = lsm->lsm_md_hash_type;
+ __u32 stripe_count = lsm->lsm_md_stripe_count;
- src_tgt = lmv_locate_target_for_name(lmv, lsm, old,
- oldlen,
- &op_data->op_fid1,
- &op_data->op_mds);
- } else {
- src_tgt = lmv_find_target(lmv, &op_data->op_fid1);
+ /*
+ * old stripes are appended after new stripes for migrating
+ * directory.
+ */
+ if (lmv_dir_migrating(lsm)) {
+ hash_type = lsm->lsm_md_migrate_hash;
+ stripe_count -= lsm->lsm_md_migrate_offset;
}
- if (IS_ERR(src_tgt))
- RETURN(PTR_ERR(src_tgt));
+ rc = lmv_name_to_stripe_index(hash_type, stripe_count, name,
+ namelen);
+ if (rc < 0)
+ RETURN(rc);
- if (op_data->op_mea2 != NULL) {
- struct lmv_stripe_md *lsm = op_data->op_mea2;
+ if (lmv_dir_migrating(lsm))
+ rc += lsm->lsm_md_migrate_offset;
- tgt_tgt = lmv_locate_target_for_name(lmv, lsm, new,
- newlen,
- &op_data->op_fid2,
- &op_data->op_mds);
- } else {
- tgt_tgt = lmv_find_target(lmv, &op_data->op_fid2);
+ /* save it in fid4 temporarily for early cancel */
+ op_data->op_fid4 = lsm->lsm_md_oinfo[rc].lmo_fid;
+ sp_tgt = lmv_get_target(lmv, lsm->lsm_md_oinfo[rc].lmo_mds,
+ NULL);
+ if (IS_ERR(sp_tgt))
+ RETURN(PTR_ERR(sp_tgt));
+ /*
+ * if parent is being migrated too, fill op_fid2 with target
+ * stripe fid, otherwise the target stripe is not created yet.
+ */
+ if (lmv_dir_migrating(lsm)) {
+ hash_type = lsm->lsm_md_hash_type &
+ ~LMV_HASH_FLAG_MIGRATION;
+ stripe_count = lsm->lsm_md_migrate_offset;
+
+ rc = lmv_name_to_stripe_index(hash_type, stripe_count,
+ name, namelen);
+ if (rc < 0)
+ RETURN(rc);
+
+ op_data->op_fid2 = lsm->lsm_md_oinfo[rc].lmo_fid;
+ tp_tgt = lmv_get_target(lmv,
+ lsm->lsm_md_oinfo[rc].lmo_mds,
+ NULL);
+ if (IS_ERR(tp_tgt))
+ RETURN(PTR_ERR(tp_tgt));
}
- if (IS_ERR(tgt_tgt))
- RETURN(PTR_ERR(tgt_tgt));
-
- target_exp = tgt_tgt->ltd_exp;
+ } else {
+ sp_tgt = parent_tgt;
}
- /*
- * LOOKUP lock on src child (fid3) should also be cancelled for
- * src_tgt in mdc_rename.
- */
- op_data->op_flags |= MF_MDC_CANCEL_FID1 | MF_MDC_CANCEL_FID3;
+ child_tgt = lmv_find_target(lmv, &op_data->op_fid3);
+ if (IS_ERR(child_tgt))
+ RETURN(PTR_ERR(child_tgt));
- /*
- * Cancel UPDATE locks on tgt parent (fid2), tgt_tgt is its
- * own target.
- */
- rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
- LCK_EX, MDS_INODELOCK_UPDATE,
- MF_MDC_CANCEL_FID2);
-
- if (rc != 0)
+ 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);
+ if (rc)
RETURN(rc);
+
/*
- * Cancel LOOKUP locks on source child (fid3) for parent tgt_tgt.
+ * for directory, send migrate request to the MDT where the object will
+ * be migrated to, because we can't create a striped directory remotely.
+ *
+ * otherwise, send to the MDT where source is located because regular
+ * file may open lease.
+ *
+ * NB. if MDT doesn't support DIR_MIGRATE, send to source MDT too for
+ * backward compatibility.
*/
- if (fid_is_sane(&op_data->op_fid3)) {
- struct lmv_tgt_desc *tgt;
-
- tgt = lmv_find_target(lmv, &op_data->op_fid1);
+ if (S_ISDIR(op_data->op_mode) &&
+ (exp_connect_flags2(exp) & OBD_CONNECT2_DIR_MIGRATE)) {
+ tgt = lmv_find_target(lmv, &target_fid);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
+ } else {
+ tgt = child_tgt;
+ }
- /* Cancel LOOKUP lock on its parent */
- rc = lmv_early_cancel(exp, tgt, op_data, src_tgt->ltd_idx,
- LCK_EX, MDS_INODELOCK_LOOKUP,
- MF_MDC_CANCEL_FID3);
- if (rc != 0)
+ /* cancel UPDATE lock of parent master object */
+ rc = lmv_early_cancel(exp, parent_tgt, op_data, tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID1);
+ if (rc)
+ RETURN(rc);
+
+ /* cancel UPDATE lock of source parent */
+ if (sp_tgt != parent_tgt) {
+ /*
+ * migrate RPC packs master object FID, because we can only pack
+ * two FIDs in reint RPC, but MDS needs to know both source
+ * parent and target parent, and it will obtain them from master
+ * FID and LMV, the other FID in RPC is kept for target.
+ *
+ * since this FID is not passed to MDC, cancel it anyway.
+ */
+ rc = lmv_early_cancel(exp, sp_tgt, op_data, -1, LCK_EX,
+ MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID4);
+ if (rc)
RETURN(rc);
- rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
- LCK_EX, MDS_INODELOCK_ELC,
+ op_data->op_flags &= ~MF_MDC_CANCEL_FID4;
+ }
+ op_data->op_fid4 = target_fid;
+
+ /* cancel UPDATE locks of target parent */
+ rc = lmv_early_cancel(exp, tp_tgt, op_data, tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID2);
+ if (rc)
+ RETURN(rc);
+
+ /* cancel LOOKUP lock of source if source is remote object */
+ if (child_tgt != sp_tgt) {
+ rc = lmv_early_cancel(exp, sp_tgt, op_data, tgt->ltd_index,
+ LCK_EX, MDS_INODELOCK_LOOKUP,
MF_MDC_CANCEL_FID3);
- if (rc != 0)
+ if (rc)
RETURN(rc);
}
-retry_rename:
- /*
- * Cancel all the locks on tgt child (fid4).
- */
+ /* cancel ELC locks of source */
+ rc = lmv_early_cancel(exp, child_tgt, op_data, tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_ELC, MF_MDC_CANCEL_FID3);
+ if (rc)
+ RETURN(rc);
+
+ rc = md_rename(tgt->ltd_exp, op_data, name, namelen, NULL, 0, request);
+
+ RETURN(rc);
+}
+
+static int lmv_rename(struct obd_export *exp, struct md_op_data *op_data,
+ const char *old, size_t oldlen,
+ const char *new, size_t newlen,
+ struct ptlrpc_request **request)
+{
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *sp_tgt;
+ struct lmv_tgt_desc *tp_tgt = NULL;
+ struct lmv_tgt_desc *src_tgt = NULL;
+ struct lmv_tgt_desc *tgt;
+ struct mdt_body *body;
+ int rc;
+
+ ENTRY;
+
+ LASSERT(oldlen != 0);
+
+ if (op_data->op_cli_flags & CLI_MIGRATE) {
+ rc = lmv_migrate(exp, op_data, old, oldlen, request);
+ RETURN(rc);
+ }
+
+ op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
+ op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
+ op_data->op_cap = cfs_curproc_cap_pack();
+
+ op_data->op_name = new;
+ op_data->op_namelen = newlen;
+
+ tp_tgt = lmv_locate_tgt2(lmv, op_data);
+ if (IS_ERR(tp_tgt))
+ RETURN(PTR_ERR(tp_tgt));
+
+ /* Since the target child might be destroyed, and it might become
+ * orphan, and we can only check orphan on the local MDT right now, so
+ * we send rename request to the MDT where target child is located. If
+ * target child does not exist, then it will send the request to the
+ * target parent */
if (fid_is_sane(&op_data->op_fid4)) {
- struct lmv_tgt_desc *tgt;
+ tgt = lmv_find_target(lmv, &op_data->op_fid4);
+ if (IS_ERR(tgt))
+ RETURN(PTR_ERR(tgt));
+ } else {
+ tgt = tp_tgt;
+ }
+
+ op_data->op_flags |= MF_MDC_CANCEL_FID4;
+
+ /* cancel UPDATE locks of target parent */
+ rc = lmv_early_cancel(exp, tp_tgt, op_data, tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID2);
+ if (rc != 0)
+ RETURN(rc);
+
+ if (fid_is_sane(&op_data->op_fid4)) {
+ /* cancel LOOKUP lock of target on target parent */
+ if (tgt != tp_tgt) {
+ rc = lmv_early_cancel(exp, tp_tgt, op_data,
+ tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_LOOKUP,
+ MF_MDC_CANCEL_FID4);
+ if (rc != 0)
+ RETURN(rc);
+ }
+ }
- rc = lmv_early_cancel(exp, NULL, op_data, src_tgt->ltd_idx,
+ if (fid_is_sane(&op_data->op_fid3)) {
+ src_tgt = lmv_find_target(lmv, &op_data->op_fid3);
+ if (IS_ERR(src_tgt))
+ RETURN(PTR_ERR(src_tgt));
+
+ /* cancel ELC locks of source */
+ rc = lmv_early_cancel(exp, src_tgt, op_data, tgt->ltd_index,
LCK_EX, MDS_INODELOCK_ELC,
- MF_MDC_CANCEL_FID4);
+ MF_MDC_CANCEL_FID3);
if (rc != 0)
RETURN(rc);
+ }
- tgt = lmv_find_target(lmv, &op_data->op_fid4);
- if (IS_ERR(tgt))
- RETURN(PTR_ERR(tgt));
+ op_data->op_name = old;
+ op_data->op_namelen = oldlen;
+retry:
+ sp_tgt = lmv_locate_tgt(lmv, op_data);
+ if (IS_ERR(sp_tgt))
+ RETURN(PTR_ERR(sp_tgt));
+
+ /* cancel UPDATE locks of source parent */
+ rc = lmv_early_cancel(exp, sp_tgt, op_data, tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_UPDATE, MF_MDC_CANCEL_FID1);
+ if (rc != 0)
+ RETURN(rc);
- /* Since the target child might be destroyed, and it might
- * become orphan, and we can only check orphan on the local
- * MDT right now, so we send rename request to the MDT where
- * target child is located. If target child does not exist,
- * then it will send the request to the target parent */
- target_exp = tgt->ltd_exp;
+ if (fid_is_sane(&op_data->op_fid3)) {
+ /* cancel LOOKUP lock of source on source parent */
+ if (src_tgt != sp_tgt) {
+ rc = lmv_early_cancel(exp, sp_tgt, op_data,
+ tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_LOOKUP,
+ MF_MDC_CANCEL_FID3);
+ if (rc != 0)
+ RETURN(rc);
+ }
}
- rc = md_rename(target_exp, op_data, old, oldlen, new, newlen,
- request);
+rename:
+ CDEBUG(D_INODE, "RENAME "DFID"/%.*s to "DFID"/%.*s\n",
+ PFID(&op_data->op_fid1), (int)oldlen, old,
+ PFID(&op_data->op_fid2), (int)newlen, new);
- if (rc != 0 && rc != -EXDEV)
+ rc = md_rename(tgt->ltd_exp, op_data, old, oldlen, new, newlen,
+ request);
+ if (rc == -ENOENT && lmv_dir_retry_check_update(op_data)) {
+ ptlrpc_req_finished(*request);
+ *request = NULL;
+ goto retry;
+ }
+
+ if (rc && rc != -EXDEV)
RETURN(rc);
body = req_capsule_server_get(&(*request)->rq_pill, &RMF_MDT_BODY);
if (likely(!(body->mbo_valid & OBD_MD_MDS)))
RETURN(rc);
- CDEBUG(D_INODE, "%s: try rename to another MDT for "DFID"\n",
- exp->exp_obd->obd_name, PFID(&body->mbo_fid1));
-
op_data->op_fid4 = body->mbo_fid1;
+
ptlrpc_req_finished(*request);
*request = NULL;
- goto retry_rename;
+
+ tgt = lmv_find_target(lmv, &op_data->op_fid4);
+ if (IS_ERR(tgt))
+ RETURN(PTR_ERR(tgt));
+
+ if (fid_is_sane(&op_data->op_fid4)) {
+ /* cancel LOOKUP lock of target on target parent */
+ if (tgt != tp_tgt) {
+ rc = lmv_early_cancel(exp, tp_tgt, op_data,
+ tgt->ltd_index, LCK_EX,
+ MDS_INODELOCK_LOOKUP,
+ MF_MDC_CANCEL_FID4);
+ if (rc != 0)
+ RETURN(rc);
+ }
+ }
+
+ goto rename;
}
static int lmv_setattr(struct obd_export *exp, struct md_op_data *op_data,
int rc = 0;
ENTRY;
- CDEBUG(D_INODE, "SETATTR for "DFID", valid 0x%x\n",
- PFID(&op_data->op_fid1), op_data->op_attr.ia_valid);
+ CDEBUG(D_INODE, "SETATTR for "DFID", valid 0x%x/0x%x\n",
+ PFID(&op_data->op_fid1), op_data->op_attr.ia_valid,
+ op_data->op_xvalid);
op_data->op_flags |= MF_MDC_CANCEL_FID1;
tgt = lmv_find_target(lmv, &op_data->op_fid1);
struct stripe_dirent ldc_stripes[0];
};
-static inline void put_stripe_dirent(struct stripe_dirent *stripe)
+static inline void stripe_dirent_unload(struct stripe_dirent *stripe)
{
if (stripe->sd_page) {
kunmap(stripe->sd_page);
int i;
for (i = 0; i < ctxt->ldc_count; i++)
- put_stripe_dirent(&ctxt->ldc_stripes[i]);
+ stripe_dirent_unload(&ctxt->ldc_stripes[i]);
+}
+
+/* if @ent is dummy, or . .., get next */
+static struct lu_dirent *stripe_dirent_get(struct lmv_dir_ctxt *ctxt,
+ struct lu_dirent *ent,
+ int stripe_index)
+{
+ for (; ent; ent = lu_dirent_next(ent)) {
+ /* Skip dummy entry */
+ if (le16_to_cpu(ent->lde_namelen) == 0)
+ continue;
+
+ /* skip . and .. for other stripes */
+ if (stripe_index &&
+ (strncmp(ent->lde_name, ".",
+ le16_to_cpu(ent->lde_namelen)) == 0 ||
+ strncmp(ent->lde_name, "..",
+ le16_to_cpu(ent->lde_namelen)) == 0))
+ continue;
+
+ if (le64_to_cpu(ent->lde_hash) >= ctxt->ldc_hash)
+ break;
+ }
+
+ return ent;
}
-static struct lu_dirent *stripe_dirent_next(struct lmv_dir_ctxt *ctxt,
+static struct lu_dirent *stripe_dirent_load(struct lmv_dir_ctxt *ctxt,
struct stripe_dirent *stripe,
int stripe_index)
{
+ struct md_op_data *op_data = ctxt->ldc_op_data;
+ struct lmv_oinfo *oinfo;
+ struct lu_fid fid = op_data->op_fid1;
+ struct inode *inode = op_data->op_data;
+ struct lmv_tgt_desc *tgt;
struct lu_dirent *ent = stripe->sd_ent;
__u64 hash = ctxt->ldc_hash;
- __u64 end;
int rc = 0;
+
ENTRY;
LASSERT(stripe == &ctxt->ldc_stripes[stripe_index]);
-
- if (stripe->sd_eof)
- RETURN(NULL);
-
- if (ent) {
- ent = lu_dirent_next(ent);
- if (!ent) {
-check_eof:
- end = le64_to_cpu(stripe->sd_dp->ldp_hash_end);
- LASSERTF(hash <= end, "hash %llx end %llx\n",
- hash, end);
+ LASSERT(!ent);
+
+ do {
+ if (stripe->sd_page) {
+ __u64 end = le64_to_cpu(stripe->sd_dp->ldp_hash_end);
+
+ /* @hash should be the last dirent hash */
+ LASSERTF(hash <= end,
+ "ctxt@%p stripe@%p hash %llx end %llx\n",
+ ctxt, stripe, hash, end);
+ /* unload last page */
+ stripe_dirent_unload(stripe);
+ /* eof */
if (end == MDS_DIR_END_OFF) {
- stripe->sd_ent = NULL;
stripe->sd_eof = true;
- RETURN(NULL);
+ break;
}
-
- put_stripe_dirent(stripe);
hash = end;
}
- }
-
- if (!ent) {
- struct md_op_data *op_data = ctxt->ldc_op_data;
- struct lmv_oinfo *oinfo;
- struct lu_fid fid = op_data->op_fid1;
- struct inode *inode = op_data->op_data;
- struct lmv_tgt_desc *tgt;
-
- LASSERT(!stripe->sd_page);
oinfo = &op_data->op_mea1->lsm_md_oinfo[stripe_index];
+ if (!oinfo->lmo_root) {
+ rc = -ENOENT;
+ break;
+ }
+
tgt = lmv_get_target(ctxt->ldc_lmv, oinfo->lmo_mds, NULL);
- if (IS_ERR(tgt))
- GOTO(out, rc = PTR_ERR(tgt));
+ if (IS_ERR(tgt)) {
+ rc = PTR_ERR(tgt);
+ break;
+ }
- /* op_data will be shared by each stripe, so we need
- * reset these value for each stripe */
+ /* op_data is shared by stripes, reset after use */
op_data->op_fid1 = oinfo->lmo_fid;
op_data->op_fid2 = oinfo->lmo_fid;
op_data->op_data = oinfo->lmo_root;
op_data->op_data = inode;
if (rc)
- GOTO(out, rc);
-
- stripe->sd_dp = page_address(stripe->sd_page);
- ent = lu_dirent_start(stripe->sd_dp);
- }
-
- for (; ent; ent = lu_dirent_next(ent)) {
- /* Skip dummy entry */
- if (le16_to_cpu(ent->lde_namelen) == 0)
- continue;
-
- /* skip . and .. for other stripes */
- if (stripe_index &&
- (strncmp(ent->lde_name, ".",
- le16_to_cpu(ent->lde_namelen)) == 0 ||
- strncmp(ent->lde_name, "..",
- le16_to_cpu(ent->lde_namelen)) == 0))
- continue;
-
- if (le64_to_cpu(ent->lde_hash) >= hash)
break;
- }
- if (!ent)
- goto check_eof;
- EXIT;
+ stripe->sd_dp = page_address(stripe->sd_page);
+ ent = stripe_dirent_get(ctxt, lu_dirent_start(stripe->sd_dp),
+ stripe_index);
+ /* in case a page filled with ., .. and dummy, read next */
+ } while (!ent);
-out:
stripe->sd_ent = ent;
- /* treat error as eof, so dir can be partially accessed */
if (rc) {
- put_stripe_dirent(stripe);
+ LASSERT(!ent);
+ /* treat error as eof, so dir can be partially accessed */
stripe->sd_eof = true;
LCONSOLE_WARN("dir "DFID" stripe %d readdir failed: %d, "
"directory is partially accessed!\n",
PFID(&ctxt->ldc_op_data->op_fid1), stripe_index,
rc);
}
- return ent;
+
+ RETURN(ent);
}
static int lmv_file_resync(struct obd_export *exp, struct md_op_data *data)
continue;
if (!stripe->sd_ent) {
- /* locate starting entry */
- stripe_dirent_next(ctxt, stripe, i);
+ stripe_dirent_load(ctxt, stripe, i);
if (!stripe->sd_ent) {
LASSERT(stripe->sd_eof);
continue;
stripe = &ctxt->ldc_stripes[min];
ent = stripe->sd_ent;
/* pop found dirent */
- stripe_dirent_next(ctxt, stripe, min);
+ stripe->sd_ent = stripe_dirent_get(ctxt, lu_dirent_next(ent),
+ min);
}
return ent;
struct md_callback *cb_op, __u64 offset,
struct page **ppage)
{
- struct obd_device *obd = exp->exp_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_stripe_md *lsm = op_data->op_mea1;
- struct lmv_tgt_desc *tgt;
- int rc;
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt;
+ int rc;
+
ENTRY;
- if (unlikely(lsm != NULL)) {
+ if (unlikely(lmv_dir_foreign(op_data->op_mea1)))
+ RETURN(-ENODATA);
+
+ if (unlikely(lmv_dir_striped(op_data->op_mea1))) {
rc = lmv_striped_read_page(exp, op_data, cb_op, offset, ppage);
RETURN(rc);
}
* negative errno if failed.
*/
static int lmv_unlink(struct obd_export *exp, struct md_op_data *op_data,
- struct ptlrpc_request **request)
+ struct ptlrpc_request **request)
{
- struct obd_device *obd = exp->exp_obd;
- struct lmv_obd *lmv = &obd->u.lmv;
- struct lmv_tgt_desc *tgt = NULL;
- struct lmv_tgt_desc *parent_tgt = NULL;
- struct mdt_body *body;
- int rc;
- int stripe_index = 0;
- struct lmv_stripe_md *lsm = op_data->op_mea1;
- ENTRY;
-
-retry_unlink:
- /* For striped dir, we need to locate the parent as well */
- if (lsm != NULL) {
- struct lmv_tgt_desc *tmp;
-
- LASSERT(op_data->op_name != NULL &&
- op_data->op_namelen != 0);
-
- tmp = lmv_locate_target_for_name(lmv, lsm,
- op_data->op_name,
- op_data->op_namelen,
- &op_data->op_fid1,
- &op_data->op_mds);
-
- /* return -EBADFD means unknown hash type, might
- * need try all sub-stripe here */
- if (IS_ERR(tmp) && PTR_ERR(tmp) != -EBADFD)
- RETURN(PTR_ERR(tmp));
-
- /* Note: both migrating dir and unknown hash dir need to
- * try all of sub-stripes, so we need start search the
- * name from stripe 0, but migrating dir is already handled
- * inside lmv_locate_target_for_name(), so we only check
- * unknown hash type directory here */
- if (!lmv_is_known_hash_type(lsm->lsm_md_hash_type)) {
- struct lmv_oinfo *oinfo;
-
- oinfo = &lsm->lsm_md_oinfo[stripe_index];
-
- op_data->op_fid1 = oinfo->lmo_fid;
- op_data->op_mds = oinfo->lmo_mds;
- }
- }
-
-try_next_stripe:
- /* Send unlink requests to the MDT where the child is located */
- if (likely(!fid_is_zero(&op_data->op_fid2)))
- tgt = lmv_find_target(lmv, &op_data->op_fid2);
- else if (lsm != NULL)
- tgt = lmv_get_target(lmv, op_data->op_mds, NULL);
- else
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+ struct obd_device *obd = exp->exp_obd;
+ struct lmv_obd *lmv = &obd->u.lmv;
+ struct lmv_tgt_desc *tgt;
+ struct lmv_tgt_desc *parent_tgt;
+ struct mdt_body *body;
+ int rc;
- if (IS_ERR(tgt))
- RETURN(PTR_ERR(tgt));
+ ENTRY;
op_data->op_fsuid = from_kuid(&init_user_ns, current_fsuid());
op_data->op_fsgid = from_kgid(&init_user_ns, current_fsgid());
op_data->op_cap = cfs_curproc_cap_pack();
+retry:
+ parent_tgt = lmv_locate_tgt(lmv, op_data);
+ if (IS_ERR(parent_tgt))
+ RETURN(PTR_ERR(parent_tgt));
+
+ if (likely(!fid_is_zero(&op_data->op_fid2))) {
+ tgt = lmv_find_target(lmv, &op_data->op_fid2);
+ if (IS_ERR(tgt))
+ RETURN(PTR_ERR(tgt));
+ } else {
+ tgt = parent_tgt;
+ }
+
/*
* If child's fid is given, cancel unused locks for it if it is from
* another export than parent.
*/
op_data->op_flags |= MF_MDC_CANCEL_FID1 | MF_MDC_CANCEL_FID3;
- /*
- * Cancel FULL locks on child (fid3).
- */
- parent_tgt = lmv_find_target(lmv, &op_data->op_fid1);
- if (IS_ERR(parent_tgt))
- RETURN(PTR_ERR(parent_tgt));
-
- if (parent_tgt != tgt) {
- rc = lmv_early_cancel(exp, parent_tgt, op_data, tgt->ltd_idx,
+ if (parent_tgt != tgt)
+ rc = lmv_early_cancel(exp, parent_tgt, op_data, tgt->ltd_index,
LCK_EX, MDS_INODELOCK_LOOKUP,
MF_MDC_CANCEL_FID3);
- }
- rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_idx, LCK_EX,
+ rc = lmv_early_cancel(exp, NULL, op_data, tgt->ltd_index, LCK_EX,
MDS_INODELOCK_ELC, MF_MDC_CANCEL_FID3);
- if (rc != 0)
+ if (rc)
RETURN(rc);
CDEBUG(D_INODE, "unlink with fid="DFID"/"DFID" -> mds #%u\n",
- PFID(&op_data->op_fid1), PFID(&op_data->op_fid2), tgt->ltd_idx);
+ PFID(&op_data->op_fid1), PFID(&op_data->op_fid2),
+ tgt->ltd_index);
rc = md_unlink(tgt->ltd_exp, op_data, request);
- if (rc != 0 && rc != -EREMOTE && rc != -ENOENT)
- RETURN(rc);
-
- /* Try next stripe if it is needed. */
- if (rc == -ENOENT && lsm != NULL && lmv_need_try_all_stripes(lsm)) {
- struct lmv_oinfo *oinfo;
-
- stripe_index++;
- if (stripe_index >= lsm->lsm_md_stripe_count)
- RETURN(rc);
-
- oinfo = &lsm->lsm_md_oinfo[stripe_index];
-
- op_data->op_fid1 = oinfo->lmo_fid;
- op_data->op_mds = oinfo->lmo_mds;
-
+ if (rc == -ENOENT && lmv_dir_retry_check_update(op_data)) {
ptlrpc_req_finished(*request);
*request = NULL;
-
- goto try_next_stripe;
+ goto retry;
}
+ if (rc != -EREMOTE)
+ RETURN(rc);
+
body = req_capsule_server_get(&(*request)->rq_pill, &RMF_MDT_BODY);
if (body == NULL)
RETURN(-EPROTO);
if (likely(!(body->mbo_valid & OBD_MD_MDS)))
RETURN(rc);
- CDEBUG(D_INODE, "%s: try unlink to another MDT for "DFID"\n",
- exp->exp_obd->obd_name, PFID(&body->mbo_fid1));
-
- /* This is a remote object, try remote MDT, Note: it may
- * try more than 1 time here, Considering following case
- * /mnt/lustre is root on MDT0, remote1 is on MDT1
- * 1. Initially A does not know where remote1 is, it send
- * unlink RPC to MDT0, MDT0 return -EREMOTE, it will
- * resend unlink RPC to MDT1 (retry 1st time).
- *
- * 2. During the unlink RPC in flight,
- * client B mv /mnt/lustre/remote1 /mnt/lustre/remote2
- * and create new remote1, but on MDT0
- *
- * 3. MDT1 get unlink RPC(from A), then do remote lock on
- * /mnt/lustre, then lookup get fid of remote1, and find
- * it is remote dir again, and replay -EREMOTE again.
- *
- * 4. Then A will resend unlink RPC to MDT0. (retry 2nd times).
- *
- * In theory, it might try unlimited time here, but it should
- * be very rare case. */
+ /* This is a remote object, try remote MDT. */
op_data->op_fid2 = body->mbo_fid1;
ptlrpc_req_finished(*request);
*request = NULL;
- goto retry_unlink;
+ tgt = lmv_find_target(lmv, &op_data->op_fid2);
+ if (IS_ERR(tgt))
+ RETURN(PTR_ERR(tgt));
+
+ goto retry;
}
static int lmv_precleanup(struct obd_device *obd)
{
ENTRY;
libcfs_kkuc_group_rem(&obd->obd_uuid, 0, KUC_GRP_HSM);
- fld_client_proc_fini(&obd->u.lmv.lmv_fld);
+ fld_client_debugfs_fini(&obd->u.lmv.lmv_fld);
lprocfs_obd_cleanup(obd);
lprocfs_free_md_stats(obd);
RETURN(0);
else
lsm->lsm_md_hash_type = le32_to_cpu(lmm1->lmv_hash_type);
lsm->lsm_md_layout_version = le32_to_cpu(lmm1->lmv_layout_version);
+ lsm->lsm_md_migrate_offset = le32_to_cpu(lmm1->lmv_migrate_offset);
+ lsm->lsm_md_migrate_hash = le32_to_cpu(lmm1->lmv_migrate_hash);
cplen = strlcpy(lsm->lsm_md_pool_name, lmm1->lmv_pool_name,
sizeof(lsm->lsm_md_pool_name));
if (cplen >= sizeof(lsm->lsm_md_pool_name))
RETURN(-E2BIG);
- CDEBUG(D_INFO, "unpack lsm count %d, master %d hash_type %d"
+ CDEBUG(D_INFO, "unpack lsm count %d, master %d hash_type %#x "
"layout_version %d\n", lsm->lsm_md_stripe_count,
lsm->lsm_md_master_mdt_index, lsm->lsm_md_hash_type,
lsm->lsm_md_layout_version);
for (i = 0; i < stripe_count; i++) {
fid_le_to_cpu(&lsm->lsm_md_oinfo[i].lmo_fid,
&lmm1->lmv_stripe_fids[i]);
+ /*
+ * set default value -1, so lmv_locate_tgt() knows this stripe
+ * target is not initialized.
+ */
+ lsm->lsm_md_oinfo[i].lmo_mds = (u32)-1;
+ if (!fid_is_sane(&lsm->lsm_md_oinfo[i].lmo_fid))
+ continue;
+
rc = lmv_fld_lookup(lmv, &lsm->lsm_md_oinfo[i].lmo_fid,
&lsm->lsm_md_oinfo[i].lmo_mds);
- if (rc != 0)
+ if (rc == -ENOENT)
+ continue;
+
+ if (rc)
RETURN(rc);
+
CDEBUG(D_INFO, "unpack fid #%d "DFID"\n", i,
PFID(&lsm->lsm_md_oinfo[i].lmo_fid));
}
RETURN(rc);
}
+static inline int lmv_unpack_user_md(struct obd_export *exp,
+ struct lmv_stripe_md *lsm,
+ const struct lmv_user_md *lmu)
+{
+ lsm->lsm_md_magic = le32_to_cpu(lmu->lum_magic);
+ lsm->lsm_md_stripe_count = le32_to_cpu(lmu->lum_stripe_count);
+ lsm->lsm_md_master_mdt_index = le32_to_cpu(lmu->lum_stripe_offset);
+ lsm->lsm_md_hash_type = le32_to_cpu(lmu->lum_hash_type);
+
+ return 0;
+}
+
static int lmv_unpackmd(struct obd_export *exp, struct lmv_stripe_md **lsmp,
const union lmv_mds_md *lmm, size_t lmm_size)
{
/* Free memmd */
if (lsm != NULL && lmm == NULL) {
int i;
- for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
- /* For migrating inode, the master stripe and master
- * object will be the same, so do not need iput, see
- * ll_update_lsm_md */
- if (!(lsm->lsm_md_hash_type & LMV_HASH_FLAG_MIGRATION &&
- i == 0) && lsm->lsm_md_oinfo[i].lmo_root != NULL)
- iput(lsm->lsm_md_oinfo[i].lmo_root);
+ struct lmv_foreign_md *lfm = (struct lmv_foreign_md *)lsm;
+
+ if (lfm->lfm_magic == LMV_MAGIC_FOREIGN) {
+ size_t lfm_size;
+
+ lfm_size = lfm->lfm_length + offsetof(typeof(*lfm),
+ lfm_value[0]);
+ OBD_FREE_LARGE(lfm, lfm_size);
+ RETURN(0);
+ }
+
+ if (lmv_dir_striped(lsm)) {
+ for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+ if (lsm->lsm_md_oinfo[i].lmo_root)
+ iput(lsm->lsm_md_oinfo[i].lmo_root);
+ }
+ lsm_size = lmv_stripe_md_size(lsm->lsm_md_stripe_count);
+ } else {
+ lsm_size = lmv_stripe_md_size(0);
}
- lsm_size = lmv_stripe_md_size(lsm->lsm_md_stripe_count);
OBD_FREE(lsm, lsm_size);
*lsmp = NULL;
RETURN(0);
}
+ /* foreign lmv case */
+ if (le32_to_cpu(lmm->lmv_magic) == LMV_MAGIC_FOREIGN) {
+ struct lmv_foreign_md *lfm = (struct lmv_foreign_md *)lsm;
+
+ if (lfm == NULL) {
+ OBD_ALLOC_LARGE(lfm, lmm_size);
+ if (lfm == NULL)
+ RETURN(-ENOMEM);
+ *lsmp = (struct lmv_stripe_md *)lfm;
+ }
+ lfm->lfm_magic = le32_to_cpu(lmm->lmv_foreign_md.lfm_magic);
+ lfm->lfm_length = le32_to_cpu(lmm->lmv_foreign_md.lfm_length);
+ lfm->lfm_type = le32_to_cpu(lmm->lmv_foreign_md.lfm_type);
+ lfm->lfm_flags = le32_to_cpu(lmm->lmv_foreign_md.lfm_flags);
+ memcpy(&lfm->lfm_value, &lmm->lmv_foreign_md.lfm_value,
+ lfm->lfm_length);
+ RETURN(lmm_size);
+ }
+
if (le32_to_cpu(lmm->lmv_magic) == LMV_MAGIC_STRIPE)
RETURN(-EPERM);
*/
lsm_size = lmv_stripe_md_size(0);
- lsm_size = lmv_stripe_md_size(lmv_mds_md_stripe_count_get(lmm));
if (lsm == NULL) {
OBD_ALLOC(lsm, lsm_size);
if (lsm == NULL)
case LMV_MAGIC_V1:
rc = lmv_unpack_md_v1(exp, lsm, &lmm->lmv_md_v1);
break;
+ case LMV_USER_MAGIC:
+ rc = lmv_unpack_user_md(exp, lsm, &lmm->lmv_user_md);
+ break;
default:
CERROR("%s: unrecognized magic %x\n", exp->exp_obd->obd_name,
le32_to_cpu(lmm->lmv_magic));
struct lmv_tgt_desc *tgt = lmv->tgts[0];
ENTRY;
+ if (md->default_lmv) {
+ lmv_free_memmd(md->default_lmv);
+ md->default_lmv = NULL;
+ }
if (md->lmv != NULL) {
lmv_free_memmd(md->lmv);
md->lmv = NULL;
if (!fid_is_sane(&op_data->op_fid2))
RETURN(-EINVAL);
- tgt = lmv_locate_mds(lmv, op_data, &op_data->op_fid1);
+ tgt = lmv_find_target(lmv, &op_data->op_fid1);
if (IS_ERR(tgt))
RETURN(PTR_ERR(tgt));
{
const struct lmv_oinfo *oinfo;
- LASSERT(lsm != NULL);
- oinfo = lsm_name_to_stripe_info(lsm, name, namelen);
+ LASSERT(lmv_dir_striped(lsm));
+
+ oinfo = lsm_name_to_stripe_info(lsm, name, namelen, false);
if (IS_ERR(oinfo))
return PTR_ERR(oinfo);
int rc;
int i;
+ if (!lmv_dir_striped(lsm))
+ return 0;
+
rc = lmv_revalidate_slaves(exp, lsm, cb_blocking, 0);
if (rc < 0)
return rc;
for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
struct inode *inode = lsm->lsm_md_oinfo[i].lmo_root;
- CDEBUG(D_INFO, ""DFID" size %llu, blocks %llu nlink %u,"
- " atime %lu ctime %lu, mtime %lu.\n",
+ if (!inode)
+ continue;
+
+ CDEBUG(D_INFO,
+ "" DFID " size %llu, blocks %llu nlink %u, atime %lld ctime %lld, mtime %lld.\n",
PFID(&lsm->lsm_md_oinfo[i].lmo_fid),
i_size_read(inode), (unsigned long long)inode->i_blocks,
- inode->i_nlink, LTIME_S(inode->i_atime),
- LTIME_S(inode->i_ctime), LTIME_S(inode->i_mtime));
+ inode->i_nlink, (s64)inode->i_atime.tv_sec,
+ (s64)inode->i_ctime.tv_sec, (s64)inode->i_mtime.tv_sec);
/* for slave stripe, it needs to subtract nlink for . and .. */
if (i != 0)
attr->cat_size += i_size_read(inode);
attr->cat_blocks += inode->i_blocks;
- if (attr->cat_atime < LTIME_S(inode->i_atime))
- attr->cat_atime = LTIME_S(inode->i_atime);
+ if (attr->cat_atime < inode->i_atime.tv_sec)
+ attr->cat_atime = inode->i_atime.tv_sec;
- if (attr->cat_ctime < LTIME_S(inode->i_ctime))
- attr->cat_ctime = LTIME_S(inode->i_ctime);
+ if (attr->cat_ctime < inode->i_ctime.tv_sec)
+ attr->cat_ctime = inode->i_ctime.tv_sec;
- if (attr->cat_mtime < LTIME_S(inode->i_mtime))
- attr->cat_mtime = LTIME_S(inode->i_mtime);
+ if (attr->cat_mtime < inode->i_mtime.tv_sec)
+ attr->cat_mtime = inode->i_mtime.tv_sec;
}
return 0;
}
.o_set_info_async = lmv_set_info_async,
.o_notify = lmv_notify,
.o_get_uuid = lmv_get_uuid,
+ .o_fid_alloc = lmv_fid_alloc,
.o_iocontrol = lmv_iocontrol,
.o_quotactl = lmv_quotactl
};