* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2016, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#define DEBUG_SUBSYSTEM S_LOV
+#include <linux/random.h>
+
#include "lov_cl_internal.h"
static inline struct lov_device *lov_object_dev(struct lov_object *obj)
struct cl_object *obj, struct cl_io *io);
int (*llo_getattr)(const struct lu_env *env, struct cl_object *obj,
struct cl_attr *attr);
+ int (*llo_flush)(const struct lu_env *env, struct cl_object *obj,
+ struct ldlm_lock *lock);
};
static int lov_layout_wait(const struct lu_env *env, struct lov_object *lov);
+static struct lov_stripe_md *lov_lsm_addref(struct lov_object *lov);
static void lov_lsm_put(struct lov_stripe_md *lsm)
{
* Lov object layout operations.
*
*/
-static int lov_init_empty(const struct lu_env *env, struct lov_device *dev,
- struct lov_object *lov, struct lov_stripe_md *lsm,
- const struct cl_object_conf *conf,
- union lov_layout_state *state)
+
+static struct cl_object *lov_sub_find(const struct lu_env *env,
+ struct cl_device *dev,
+ const struct lu_fid *fid,
+ const struct cl_object_conf *conf)
{
- return 0;
+ struct lu_object *o;
+
+ ENTRY;
+
+ o = lu_object_find_at(env, cl2lu_dev(dev), fid, &conf->coc_lu);
+ LASSERT(ergo(!IS_ERR(o), o->lo_dev->ld_type == &lovsub_device_type));
+ RETURN(lu2cl(o));
}
-static struct cl_object *lov_sub_find(const struct lu_env *env,
- struct cl_device *dev,
- const struct lu_fid *fid,
- const struct cl_object_conf *conf)
+static int lov_page_slice_fixup(struct lov_object *lov,
+ struct cl_object *stripe)
{
- struct lu_object *o;
+ struct cl_object_header *hdr = cl_object_header(&lov->lo_cl);
+ struct cl_object *o;
- ENTRY;
- o = lu_object_find_at(env, cl2lu_dev(dev), fid, &conf->coc_lu);
- LASSERT(ergo(!IS_ERR(o), o->lo_dev->ld_type == &lovsub_device_type));
- RETURN(lu2cl(o));
+ if (stripe == NULL)
+ return hdr->coh_page_bufsize - lov->lo_cl.co_slice_off -
+ cfs_size_round(sizeof(struct lov_page));
+
+ cl_object_for_each(o, stripe)
+ o->co_slice_off += hdr->coh_page_bufsize;
+
+ return cl_object_header(stripe)->coh_page_bufsize;
}
static int lov_init_sub(const struct lu_env *env, struct lov_object *lov,
- struct cl_object *subobj, struct lov_layout_raid0 *r0,
- struct lov_oinfo *oinfo, int idx)
+ struct cl_object *subobj, struct lov_oinfo *oinfo,
+ int idx)
{
struct cl_object_header *hdr;
struct cl_object_header *subhdr;
return -EIO;
}
- hdr = cl_object_header(lov2cl(lov));
+ hdr = cl_object_header(lov2cl(lov));
subhdr = cl_object_header(subobj);
CDEBUG(D_INODE, DFID"@%p[%d:%d] -> "DFID"@%p: ostid: "DOSTID
spin_lock(&subhdr->coh_attr_guard);
parent = subhdr->coh_parent;
if (parent == NULL) {
+ struct lovsub_object *lso = cl2lovsub(subobj);
+
subhdr->coh_parent = hdr;
spin_unlock(&subhdr->coh_attr_guard);
subhdr->coh_nesting = hdr->coh_nesting + 1;
lu_object_ref_add(&subobj->co_lu, "lov-parent", lov);
- r0->lo_sub[stripe] = cl2lovsub(subobj);
- r0->lo_sub[stripe]->lso_super = lov;
- r0->lo_sub[stripe]->lso_index = idx;
+ lso->lso_super = lov;
+ lso->lso_index = idx;
result = 0;
} else {
struct lu_object *old_obj;
old_obj = lu_object_locate(&parent->coh_lu, &lov_device_type);
LASSERT(old_obj != NULL);
old_lov = cl2lov(lu2cl(old_obj));
- if (old_lov->lo_layout_invalid) {
+ if (test_bit(LO_LAYOUT_INVALID, &old_lov->lo_obj_flags)) {
/* the object's layout has already changed but isn't
* refreshed */
lu_object_unhash(env, &subobj->co_lu);
return result;
}
-static int lov_page_slice_fixup(struct lov_object *lov,
- struct cl_object *stripe)
-{
- struct cl_object_header *hdr = cl_object_header(&lov->lo_cl);
- struct cl_object *o;
-
- if (stripe == NULL)
- return hdr->coh_page_bufsize - lov->lo_cl.co_slice_off -
- cfs_size_round(sizeof(struct lov_page));
-
- cl_object_for_each(o, stripe)
- o->co_slice_off += hdr->coh_page_bufsize;
-
- return cl_object_header(stripe)->coh_page_bufsize;
-}
-
static int lov_init_raid0(const struct lu_env *env, struct lov_device *dev,
- struct lov_object *lov, int index,
- struct lov_layout_raid0 *r0)
+ struct lov_object *lov, unsigned int index,
+ const struct cl_object_conf *conf,
+ struct lov_layout_entry *lle)
{
- struct lov_thread_info *lti = lov_env_info(env);
- struct cl_object_conf *subconf = <i->lti_stripe_conf;
- struct lu_fid *ofid = <i->lti_fid;
- struct cl_object *stripe;
+ struct lov_layout_raid0 *r0 = &lle->lle_raid0;
+ struct lov_thread_info *lti = lov_env_info(env);
+ struct cl_object_conf *subconf = <i->lti_stripe_conf;
+ struct lu_fid *ofid = <i->lti_fid;
+ struct cl_object *stripe;
struct lov_stripe_md_entry *lse = lov_lse(lov, index);
int result;
- int psz;
+ int psz, sz;
int i;
ENTRY;
spin_lock_init(&r0->lo_sub_lock);
r0->lo_nr = lse->lsme_stripe_count;
- LASSERT(r0->lo_nr <= lov_targets_nr(dev));
+ r0->lo_trunc_stripeno = -1;
- OBD_ALLOC_LARGE(r0->lo_sub, r0->lo_nr * sizeof r0->lo_sub[0]);
+ OBD_ALLOC_PTR_ARRAY_LARGE(r0->lo_sub, r0->lo_nr);
if (r0->lo_sub == NULL)
GOTO(out, result = -ENOMEM);
if (IS_ERR(stripe))
GOTO(out, result = PTR_ERR(stripe));
- result = lov_init_sub(env, lov, stripe, r0, oinfo,
+ result = lov_init_sub(env, lov, stripe, oinfo,
lov_comp_index(index, i));
if (result == -EAGAIN) { /* try again */
--i;
}
if (result == 0) {
- int sz = lov_page_slice_fixup(lov, stripe);
+ r0->lo_sub[i] = cl2lovsub(stripe);
+
+ sz = lov_page_slice_fixup(lov, stripe);
LASSERT(ergo(psz > 0, psz == sz));
psz = sz;
}
RETURN(result);
}
+static void lov_subobject_kill(const struct lu_env *env, struct lov_object *lov,
+ struct lov_layout_raid0 *r0,
+ struct lovsub_object *los, int idx)
+{
+ struct cl_object *sub;
+ struct lu_site *site;
+ wait_queue_head_t *wq;
+
+ LASSERT(r0->lo_sub[idx] == los);
+
+ sub = lovsub2cl(los);
+ site = sub->co_lu.lo_dev->ld_site;
+ wq = lu_site_wq_from_fid(site, &sub->co_lu.lo_header->loh_fid);
+
+ cl_object_kill(env, sub);
+ /* release a reference to the sub-object and ... */
+ lu_object_ref_del(&sub->co_lu, "lov-parent", lov);
+ cl_object_put(env, sub);
+
+ /* ... wait until it is actually destroyed---sub-object clears its
+ * ->lo_sub[] slot in lovsub_object_free() */
+ wait_event(*wq, r0->lo_sub[idx] != los);
+ LASSERT(r0->lo_sub[idx] == NULL);
+}
+
+static void lov_delete_raid0(const struct lu_env *env, struct lov_object *lov,
+ struct lov_layout_entry *lle)
+{
+ struct lov_layout_raid0 *r0 = &lle->lle_raid0;
+
+ ENTRY;
+
+ if (r0->lo_sub != NULL) {
+ int i;
+
+ for (i = 0; i < r0->lo_nr; ++i) {
+ struct lovsub_object *los = r0->lo_sub[i];
+
+ if (los != NULL) {
+ cl_object_prune(env, &los->lso_cl);
+ /*
+ * If top-level object is to be evicted from
+ * the cache, so are its sub-objects.
+ */
+ lov_subobject_kill(env, lov, r0, los, i);
+ }
+ }
+ }
+
+ EXIT;
+}
+
+static void lov_fini_raid0(const struct lu_env *env,
+ struct lov_layout_entry *lle)
+{
+ struct lov_layout_raid0 *r0 = &lle->lle_raid0;
+
+ if (r0->lo_sub != NULL) {
+ OBD_FREE_PTR_ARRAY_LARGE(r0->lo_sub, r0->lo_nr);
+ r0->lo_sub = NULL;
+ }
+}
+
+static int lov_print_raid0(const struct lu_env *env, void *cookie,
+ lu_printer_t p, const struct lov_layout_entry *lle)
+{
+ const struct lov_layout_raid0 *r0 = &lle->lle_raid0;
+ int i;
+
+ for (i = 0; i < r0->lo_nr; ++i) {
+ struct lu_object *sub;
+
+ if (r0->lo_sub[i] != NULL) {
+ sub = lovsub2lu(r0->lo_sub[i]);
+ lu_object_print(env, cookie, p, sub);
+ } else {
+ (*p)(env, cookie, "sub %d absent\n", i);
+ }
+ }
+ return 0;
+}
+
+static int lov_attr_get_raid0(const struct lu_env *env, struct lov_object *lov,
+ unsigned int index, struct lov_layout_entry *lle,
+ struct cl_attr **lov_attr)
+{
+ struct lov_layout_raid0 *r0 = &lle->lle_raid0;
+ struct lov_stripe_md *lsm = lov->lo_lsm;
+ struct ost_lvb *lvb = &lov_env_info(env)->lti_lvb;
+ struct cl_attr *attr = &r0->lo_attr;
+ __u64 kms = 0;
+ int result = 0;
+
+ if (r0->lo_attr_valid) {
+ *lov_attr = attr;
+ return 0;
+ }
+
+ memset(lvb, 0, sizeof(*lvb));
+
+ /* XXX: timestamps can be negative by sanity:test_39m,
+ * how can it be? */
+ lvb->lvb_atime = LLONG_MIN;
+ lvb->lvb_ctime = LLONG_MIN;
+ lvb->lvb_mtime = LLONG_MIN;
+
+ /*
+ * XXX that should be replaced with a loop over sub-objects,
+ * doing cl_object_attr_get() on them. But for now, let's
+ * reuse old lov code.
+ */
+
+ /*
+ * XXX take lsm spin-lock to keep lov_merge_lvb_kms()
+ * happy. It's not needed, because new code uses
+ * ->coh_attr_guard spin-lock to protect consistency of
+ * sub-object attributes.
+ */
+ lov_stripe_lock(lsm);
+ result = lov_merge_lvb_kms(lsm, index, lvb, &kms);
+ lov_stripe_unlock(lsm);
+ if (result == 0) {
+ cl_lvb2attr(attr, lvb);
+ attr->cat_kms = kms;
+ r0->lo_attr_valid = 1;
+ *lov_attr = attr;
+ }
+
+ return result;
+}
+
+static struct lov_comp_layout_entry_ops raid0_ops = {
+ .lco_init = lov_init_raid0,
+ .lco_fini = lov_fini_raid0,
+ .lco_getattr = lov_attr_get_raid0,
+};
+
+static int lov_attr_get_dom(const struct lu_env *env, struct lov_object *lov,
+ unsigned int index, struct lov_layout_entry *lle,
+ struct cl_attr **lov_attr)
+{
+ struct lov_layout_dom *dom = &lle->lle_dom;
+ struct lov_oinfo *loi = dom->lo_loi;
+ struct cl_attr *attr = &dom->lo_dom_r0.lo_attr;
+
+ if (dom->lo_dom_r0.lo_attr_valid) {
+ *lov_attr = attr;
+ return 0;
+ }
+
+ if (OST_LVB_IS_ERR(loi->loi_lvb.lvb_blocks))
+ return OST_LVB_GET_ERR(loi->loi_lvb.lvb_blocks);
+
+ cl_lvb2attr(attr, &loi->loi_lvb);
+
+ /* DoM component size can be bigger than stripe size after
+ * client's setattr RPC, so do not count anything beyond
+ * component end. Alternatively, check that limit on server
+ * and do not allow size overflow there. */
+ if (attr->cat_size > lle->lle_extent->e_end)
+ attr->cat_size = lle->lle_extent->e_end;
+
+ attr->cat_kms = attr->cat_size;
+
+ dom->lo_dom_r0.lo_attr_valid = 1;
+ *lov_attr = attr;
+
+ return 0;
+}
+
+/**
+ * Lookup FLD to get MDS index of the given DOM object FID.
+ *
+ * \param[in] ld LOV device
+ * \param[in] fid FID to lookup
+ * \param[out] nr index in MDC array to return back
+ *
+ * \retval 0 and \a mds filled with MDS index if successful
+ * \retval negative value on error
+ */
+static int lov_fld_lookup(struct lov_device *ld, const struct lu_fid *fid,
+ __u32 *nr)
+{
+ __u32 mds_idx;
+ int i, rc;
+
+ ENTRY;
+
+ rc = fld_client_lookup(&ld->ld_lmv->u.lmv.lmv_fld, fid_seq(fid),
+ &mds_idx, LU_SEQ_RANGE_MDT, NULL);
+ if (rc) {
+ CERROR("%s: error while looking for mds number. Seq %#llx"
+ ", err = %d\n", lu_dev_name(cl2lu_dev(&ld->ld_cl)),
+ fid_seq(fid), rc);
+ RETURN(rc);
+ }
+
+ CDEBUG(D_INODE, "FLD lookup got mds #%x for fid="DFID"\n",
+ mds_idx, PFID(fid));
+
+ /* find proper MDC device in the array */
+ for (i = 0; i < ld->ld_md_tgts_nr; i++) {
+ if (ld->ld_md_tgts[i].ldm_mdc != NULL &&
+ ld->ld_md_tgts[i].ldm_idx == mds_idx)
+ break;
+ }
+
+ if (i == ld->ld_md_tgts_nr) {
+ CERROR("%s: cannot find corresponding MDC device for mds #%x "
+ "for fid="DFID"\n", lu_dev_name(cl2lu_dev(&ld->ld_cl)),
+ mds_idx, PFID(fid));
+ rc = -EINVAL;
+ } else {
+ *nr = i;
+ }
+ RETURN(rc);
+}
+
+/**
+ * Implementation of lov_comp_layout_entry_ops::lco_init for DOM object.
+ *
+ * Init the DOM object for the first time. It prepares also RAID0 entry
+ * for it to use in common methods with ordinary RAID0 layout entries.
+ *
+ * \param[in] env execution environment
+ * \param[in] dev LOV device
+ * \param[in] lov LOV object
+ * \param[in] index Composite layout entry index in LSM
+ * \param[in] lle Composite LOV layout entry
+ */
+static int lov_init_dom(const struct lu_env *env, struct lov_device *dev,
+ struct lov_object *lov, unsigned int index,
+ const struct cl_object_conf *conf,
+ struct lov_layout_entry *lle)
+{
+ struct lov_thread_info *lti = lov_env_info(env);
+ struct lov_stripe_md_entry *lsme = lov_lse(lov, index);
+ struct cl_object *clo;
+ struct lu_object *o = lov2lu(lov);
+ const struct lu_fid *fid = lu_object_fid(o);
+ struct cl_device *mdcdev;
+ struct lov_oinfo *loi = NULL;
+ struct cl_object_conf *sconf = <i->lti_stripe_conf;
+ int rc;
+ __u32 idx = 0;
+
+ ENTRY;
+
+ /* DOM entry may be not zero index due to FLR but must start from 0 */
+ if (unlikely(lle->lle_extent->e_start != 0)) {
+ CERROR("%s: DOM entry must be the first stripe in a mirror\n",
+ lov2obd(dev->ld_lov)->obd_name);
+ dump_lsm(D_ERROR, lov->lo_lsm);
+ RETURN(-EINVAL);
+ }
+
+ /* find proper MDS device */
+ rc = lov_fld_lookup(dev, fid, &idx);
+ if (rc)
+ RETURN(rc);
+
+ LASSERTF(dev->ld_md_tgts[idx].ldm_mdc != NULL,
+ "LOV md target[%u] is NULL\n", idx);
+
+ /* check lsm is DOM, more checks are needed */
+ LASSERT(lsme->lsme_stripe_count == 0);
+
+ /*
+ * Create lower cl_objects.
+ */
+ mdcdev = dev->ld_md_tgts[idx].ldm_mdc;
+
+ LASSERTF(mdcdev != NULL, "non-initialized mdc subdev\n");
+
+ /* DoM object has no oinfo in LSM entry, create it exclusively */
+ OBD_SLAB_ALLOC_PTR_GFP(loi, lov_oinfo_slab, GFP_NOFS);
+ if (loi == NULL)
+ RETURN(-ENOMEM);
+
+ fid_to_ostid(lu_object_fid(lov2lu(lov)), &loi->loi_oi);
+
+ sconf->u.coc_oinfo = loi;
+again:
+ clo = lov_sub_find(env, mdcdev, fid, sconf);
+ if (IS_ERR(clo))
+ GOTO(out, rc = PTR_ERR(clo));
+
+ rc = lov_init_sub(env, lov, clo, loi, lov_comp_index(index, 0));
+ if (rc == -EAGAIN) /* try again */
+ goto again;
+ else if (rc != 0)
+ GOTO(out, rc);
+
+ lle->lle_dom.lo_dom = cl2lovsub(clo);
+ spin_lock_init(&lle->lle_dom.lo_dom_r0.lo_sub_lock);
+ lle->lle_dom.lo_dom_r0.lo_nr = 1;
+ lle->lle_dom.lo_dom_r0.lo_sub = &lle->lle_dom.lo_dom;
+ lle->lle_dom.lo_loi = loi;
+
+ rc = lov_page_slice_fixup(lov, clo);
+ RETURN(rc);
+
+out:
+ if (loi != NULL)
+ OBD_SLAB_FREE_PTR(loi, lov_oinfo_slab);
+ return rc;
+}
+
+/**
+ * Implementation of lov_layout_operations::llo_fini for DOM object.
+ *
+ * Finish the DOM object and free related memory.
+ *
+ * \param[in] env execution environment
+ * \param[in] lov LOV object
+ * \param[in] state LOV layout state
+ */
+static void lov_fini_dom(const struct lu_env *env,
+ struct lov_layout_entry *lle)
+{
+ if (lle->lle_dom.lo_dom != NULL)
+ lle->lle_dom.lo_dom = NULL;
+ if (lle->lle_dom.lo_loi != NULL)
+ OBD_SLAB_FREE_PTR(lle->lle_dom.lo_loi, lov_oinfo_slab);
+}
+
+static struct lov_comp_layout_entry_ops dom_ops = {
+ .lco_init = lov_init_dom,
+ .lco_fini = lov_fini_dom,
+ .lco_getattr = lov_attr_get_dom,
+};
+
static int lov_init_composite(const struct lu_env *env, struct lov_device *dev,
struct lov_object *lov, struct lov_stripe_md *lsm,
const struct cl_object_conf *conf,
union lov_layout_state *state)
{
struct lov_layout_composite *comp = &state->composite;
+ struct lov_layout_entry *lle;
+ struct lov_mirror_entry *lre;
unsigned int entry_count;
unsigned int psz = 0;
+ unsigned int mirror_count;
+ int flr_state = lsm->lsm_flags & LCM_FL_FLR_MASK;
int result = 0;
- int i;
+ unsigned int seq;
+ int i, j;
+ bool dom_size = 0;
ENTRY;
LASSERT(lsm->lsm_entry_count > 0);
LASSERT(lov->lo_lsm == NULL);
lov->lo_lsm = lsm_addref(lsm);
- lov->lo_layout_invalid = true;
+ set_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
+
+ dump_lsm(D_INODE, lsm);
entry_count = lsm->lsm_entry_count;
- comp->lo_entry_count = entry_count;
- OBD_ALLOC(comp->lo_entries, entry_count * sizeof(*comp->lo_entries));
+ spin_lock_init(&comp->lo_write_lock);
+ comp->lo_flags = lsm->lsm_flags;
+ comp->lo_mirror_count = lsm->lsm_mirror_count + 1;
+ comp->lo_entry_count = lsm->lsm_entry_count;
+ comp->lo_preferred_mirror = -1;
+
+ if (equi(flr_state == LCM_FL_NONE, comp->lo_mirror_count > 1))
+ RETURN(-EINVAL);
+
+ OBD_ALLOC_PTR_ARRAY(comp->lo_mirrors, comp->lo_mirror_count);
+ if (comp->lo_mirrors == NULL)
+ RETURN(-ENOMEM);
+
+ OBD_ALLOC_PTR_ARRAY(comp->lo_entries, entry_count);
if (comp->lo_entries == NULL)
RETURN(-ENOMEM);
- for (i = 0; i < entry_count; i++) {
- struct lov_layout_entry *le = &comp->lo_entries[i];
+ /* Initiate all entry types and extents data at first */
+ for (i = 0, j = 0, mirror_count = 1; i < entry_count; i++) {
+ int mirror_id = 0;
+
+ lle = &comp->lo_entries[i];
+
+ lle->lle_lsme = lsm->lsm_entries[i];
+ lle->lle_type = lov_entry_type(lle->lle_lsme);
+ switch (lle->lle_type) {
+ case LOV_PATTERN_RAID0:
+ lle->lle_comp_ops = &raid0_ops;
+ break;
+ case LOV_PATTERN_MDT:
+ /* Allowed to have several DOM stripes in different
+ * mirrors with the same DoM size.
+ */
+ if (!dom_size) {
+ dom_size = lle->lle_lsme->lsme_extent.e_end;
+ } else if (dom_size !=
+ lle->lle_lsme->lsme_extent.e_end) {
+ CERROR("%s: DOM entries with different sizes\n",
+ lov2obd(dev->ld_lov)->obd_name);
+ dump_lsm(D_ERROR, lsm);
+ RETURN(-EINVAL);
+ }
+ lle->lle_comp_ops = &dom_ops;
+ break;
+ case LOV_PATTERN_FOREIGN:
+ lle->lle_comp_ops = NULL;
+ break;
+ default:
+ CERROR("%s: unknown composite layout entry type %i\n",
+ lov2obd(dev->ld_lov)->obd_name,
+ lsm->lsm_entries[i]->lsme_pattern);
+ dump_lsm(D_ERROR, lsm);
+ RETURN(-EIO);
+ }
+
+ lle->lle_extent = &lle->lle_lsme->lsme_extent;
+ lle->lle_valid = !(lle->lle_lsme->lsme_flags & LCME_FL_STALE);
+
+ if (flr_state != LCM_FL_NONE)
+ mirror_id = mirror_id_of(lle->lle_lsme->lsme_id);
+
+ lre = &comp->lo_mirrors[j];
+ if (i > 0) {
+ if (mirror_id == lre->lre_mirror_id) {
+ lre->lre_valid |= lle->lle_valid;
+ lre->lre_stale |= !lle->lle_valid;
+ lre->lre_foreign |=
+ lsme_is_foreign(lle->lle_lsme);
+ lre->lre_end = i;
+ continue;
+ }
+
+ /* new mirror detected, assume that the mirrors
+ * are shorted in layout */
+ ++mirror_count;
+ ++j;
+ if (j >= comp->lo_mirror_count)
+ break;
+
+ lre = &comp->lo_mirrors[j];
+ }
+
+ /* entries must be sorted by mirrors */
+ lre->lre_mirror_id = mirror_id;
+ lre->lre_start = lre->lre_end = i;
+ lre->lre_preferred = !!(lle->lle_lsme->lsme_flags &
+ LCME_FL_PREF_RD);
+ lre->lre_valid = lle->lle_valid;
+ lre->lre_stale = !lle->lle_valid;
+ lre->lre_foreign = lsme_is_foreign(lle->lle_lsme);
+ }
+
+ /* sanity check for FLR */
+ if (mirror_count != comp->lo_mirror_count) {
+ CDEBUG(D_INODE, DFID
+ " doesn't have the # of mirrors it claims, %u/%u\n",
+ PFID(lu_object_fid(lov2lu(lov))), mirror_count,
+ comp->lo_mirror_count + 1);
+
+ GOTO(out, result = -EINVAL);
+ }
+
+ lov_foreach_layout_entry(lov, lle) {
+ int index = lov_layout_entry_index(lov, lle);
- le->lle_extent = lsm->lsm_entries[i]->lsme_extent;
/**
* If the component has not been init-ed on MDS side, for
* PFL layout, we'd know that the components beyond this one
* will be dynamically init-ed later on file write/trunc ops.
*/
- if (!lsm_entry_inited(lsm, i))
+ if (!lsme_inited(lle->lle_lsme))
continue;
- result = lov_init_raid0(env, dev, lov, i, &le->lle_raid0);
+ if (lsme_is_foreign(lle->lle_lsme))
+ continue;
+
+ result = lle->lle_comp_ops->lco_init(env, dev, lov, index,
+ conf, lle);
if (result < 0)
break;
LASSERT(ergo(psz > 0, psz == result));
psz = result;
}
+
if (psz > 0)
cl_object_header(&lov->lo_cl)->coh_page_bufsize += psz;
- return result > 0 ? 0 : result;
-}
+ /* decide the preferred mirror. It uses the hash value of lov_object
+ * so that different clients would use different mirrors for read. */
+ mirror_count = 0;
+ seq = hash_long((unsigned long)lov, 8);
+ for (i = 0; i < comp->lo_mirror_count; i++) {
+ unsigned int idx = (i + seq) % comp->lo_mirror_count;
-static int lov_init_released(const struct lu_env *env,
- struct lov_device *dev, struct lov_object *lov,
- struct lov_stripe_md *lsm,
- const struct cl_object_conf *conf,
- union lov_layout_state *state)
-{
- LASSERT(lsm != NULL);
- LASSERT(lsm->lsm_is_released);
- LASSERT(lov->lo_lsm == NULL);
+ lre = lov_mirror_entry(lov, idx);
+ if (lre->lre_stale)
+ continue;
- lov->lo_lsm = lsm_addref(lsm);
- return 0;
-}
+ if (lre->lre_foreign)
+ continue;
-static struct cl_object *lov_find_subobj(const struct lu_env *env,
- struct lov_object *lov,
- struct lov_stripe_md *lsm,
- int index)
-{
- struct lov_device *dev = lu2lov_dev(lov2lu(lov)->lo_dev);
- struct lov_thread_info *lti = lov_env_info(env);
- struct lu_fid *ofid = <i->lti_fid;
- struct lov_oinfo *oinfo;
- struct cl_device *subdev;
- int entry = lov_comp_entry(index);
- int stripe = lov_comp_stripe(index);
- int ost_idx;
- int rc;
- struct cl_object *result;
+ mirror_count++; /* valid mirror */
- if (lov->lo_type != LLT_COMP)
- GOTO(out, result = NULL);
+ if (lre->lre_preferred || comp->lo_preferred_mirror < 0)
+ comp->lo_preferred_mirror = idx;
+ }
+ if (!mirror_count) {
+ CDEBUG(D_INODE, DFID
+ " doesn't have any valid mirrors\n",
+ PFID(lu_object_fid(lov2lu(lov))));
- if (entry >= lsm->lsm_entry_count ||
- stripe >= lsm->lsm_entries[entry]->lsme_stripe_count)
- GOTO(out, result = NULL);
+ comp->lo_preferred_mirror = 0;
+ }
- oinfo = lsm->lsm_entries[entry]->lsme_oinfo[stripe];
- ost_idx = oinfo->loi_ost_idx;
- rc = ostid_to_fid(ofid, &oinfo->loi_oi, ost_idx);
- if (rc != 0)
- GOTO(out, result = NULL);
+ LASSERT(comp->lo_preferred_mirror >= 0);
- subdev = lovsub2cl_dev(dev->ld_target[ost_idx]);
- result = lov_sub_find(env, subdev, ofid, NULL);
+ EXIT;
out:
- if (result == NULL)
- result = ERR_PTR(-EINVAL);
- return result;
+ return result > 0 ? 0 : result;
}
-static int lov_delete_empty(const struct lu_env *env, struct lov_object *lov,
- union lov_layout_state *state)
+static int lov_init_empty(const struct lu_env *env, struct lov_device *dev,
+ struct lov_object *lov, struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
- LASSERT(lov->lo_type == LLT_EMPTY || lov->lo_type == LLT_RELEASED);
-
- lov_layout_wait(env, lov);
return 0;
}
-static void lov_subobject_kill(const struct lu_env *env, struct lov_object *lov,
- struct lov_layout_raid0 *r0,
- struct lovsub_object *los, int idx)
+static int lov_init_released(const struct lu_env *env,
+ struct lov_device *dev, struct lov_object *lov,
+ struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
- struct cl_object *sub;
- struct lu_site *site;
- struct lu_site_bkt_data *bkt;
- wait_queue_t *waiter;
-
- LASSERT(r0->lo_sub[idx] == los);
-
- sub = lovsub2cl(los);
- site = sub->co_lu.lo_dev->ld_site;
- bkt = lu_site_bkt_from_fid(site, &sub->co_lu.lo_header->loh_fid);
-
- cl_object_kill(env, sub);
- /* release a reference to the sub-object and ... */
- lu_object_ref_del(&sub->co_lu, "lov-parent", lov);
- cl_object_put(env, sub);
+ LASSERT(lsm != NULL);
+ LASSERT(lsm->lsm_is_released);
+ LASSERT(lov->lo_lsm == NULL);
- /* ... wait until it is actually destroyed---sub-object clears its
- * ->lo_sub[] slot in lovsub_object_fini() */
- if (r0->lo_sub[idx] == los) {
- waiter = &lov_env_info(env)->lti_waiter;
- init_waitqueue_entry(waiter, current);
- add_wait_queue(&bkt->lsb_marche_funebre, waiter);
- set_current_state(TASK_UNINTERRUPTIBLE);
- while (1) {
- /* this wait-queue is signaled at the end of
- * lu_object_free(). */
- set_current_state(TASK_UNINTERRUPTIBLE);
- spin_lock(&r0->lo_sub_lock);
- if (r0->lo_sub[idx] == los) {
- spin_unlock(&r0->lo_sub_lock);
- schedule();
- } else {
- spin_unlock(&r0->lo_sub_lock);
- set_current_state(TASK_RUNNING);
- break;
- }
- }
- remove_wait_queue(&bkt->lsb_marche_funebre, waiter);
- }
- LASSERT(r0->lo_sub[idx] == NULL);
+ lov->lo_lsm = lsm_addref(lsm);
+ return 0;
}
-static void lov_delete_raid0(const struct lu_env *env, struct lov_object *lov,
- struct lov_layout_raid0 *r0)
+static int lov_init_foreign(const struct lu_env *env,
+ struct lov_device *dev, struct lov_object *lov,
+ struct lov_stripe_md *lsm,
+ const struct cl_object_conf *conf,
+ union lov_layout_state *state)
{
- ENTRY;
-
- if (r0->lo_sub != NULL) {
- int i;
+ LASSERT(lsm != NULL);
+ LASSERT(lov->lo_type == LLT_FOREIGN);
+ LASSERT(lov->lo_lsm == NULL);
- for (i = 0; i < r0->lo_nr; ++i) {
- struct lovsub_object *los = r0->lo_sub[i];
+ lov->lo_lsm = lsm_addref(lsm);
+ return 0;
+}
- if (los != NULL) {
- cl_object_prune(env, &los->lso_cl);
- /*
- * If top-level object is to be evicted from
- * the cache, so are its sub-objects.
- */
- lov_subobject_kill(env, lov, r0, los, i);
- }
- }
- }
+static int lov_delete_empty(const struct lu_env *env, struct lov_object *lov,
+ union lov_layout_state *state)
+{
+ LASSERT(lov->lo_type == LLT_EMPTY || lov->lo_type == LLT_RELEASED ||
+ lov->lo_type == LLT_FOREIGN);
- EXIT;
+ lov_layout_wait(env, lov);
+ return 0;
}
static int lov_delete_composite(const struct lu_env *env,
lov_layout_wait(env, lov);
if (comp->lo_entries)
- lov_foreach_layout_entry(lov, entry)
- lov_delete_raid0(env, lov, &entry->lle_raid0);
+ lov_foreach_layout_entry(lov, entry) {
+ if (entry->lle_lsme && lsme_is_foreign(entry->lle_lsme))
+ continue;
+
+ lov_delete_raid0(env, lov, entry);
+ }
RETURN(0);
}
LASSERT(lov->lo_type == LLT_EMPTY || lov->lo_type == LLT_RELEASED);
}
-static void lov_fini_raid0(const struct lu_env *env,
- struct lov_layout_raid0 *r0)
-{
- if (r0->lo_sub != NULL) {
- OBD_FREE_LARGE(r0->lo_sub, r0->lo_nr * sizeof r0->lo_sub[0]);
- r0->lo_sub = NULL;
- }
-}
-
static void lov_fini_composite(const struct lu_env *env,
struct lov_object *lov,
union lov_layout_state *state)
struct lov_layout_entry *entry;
lov_foreach_layout_entry(lov, entry)
- lov_fini_raid0(env, &entry->lle_raid0);
+ if (entry->lle_comp_ops)
+ entry->lle_comp_ops->lco_fini(env, entry);
- OBD_FREE(comp->lo_entries,
- comp->lo_entry_count * sizeof(*comp->lo_entries));
+ OBD_FREE_PTR_ARRAY(comp->lo_entries, comp->lo_entry_count);
comp->lo_entries = NULL;
}
+ if (comp->lo_mirrors != NULL) {
+ OBD_FREE_PTR_ARRAY(comp->lo_mirrors, comp->lo_mirror_count);
+ comp->lo_mirrors = NULL;
+ }
+
+ memset(comp, 0, sizeof(*comp));
+
dump_lsm(D_INODE, lov->lo_lsm);
lov_free_memmd(&lov->lo_lsm);
static int lov_print_empty(const struct lu_env *env, void *cookie,
lu_printer_t p, const struct lu_object *o)
{
- (*p)(env, cookie, "empty %d\n", lu2lov(o)->lo_layout_invalid);
+ (*p)(env, cookie, "empty %d\n",
+ test_bit(LO_LAYOUT_INVALID, &lu2lov(o)->lo_obj_flags));
return 0;
}
-static int lov_print_raid0(const struct lu_env *env, void *cookie,
- lu_printer_t p, struct lov_layout_raid0 *r0)
-{
- int i;
-
- for (i = 0; i < r0->lo_nr; ++i) {
- struct lu_object *sub;
-
- if (r0->lo_sub[i] != NULL) {
- sub = lovsub2lu(r0->lo_sub[i]);
- lu_object_print(env, cookie, p, sub);
- } else {
- (*p)(env, cookie, "sub %d absent\n", i);
- }
- }
- return 0;
-}
-
static int lov_print_composite(const struct lu_env *env, void *cookie,
lu_printer_t p, const struct lu_object *o)
{
(*p)(env, cookie, "entries: %d, %s, lsm{%p 0x%08X %d %u}:\n",
lsm->lsm_entry_count,
- lov->lo_layout_invalid ? "invalid" : "valid", lsm,
- lsm->lsm_magic, atomic_read(&lsm->lsm_refc),
+ test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags) ? "invalid" :
+ "valid", lsm, lsm->lsm_magic, atomic_read(&lsm->lsm_refc),
lsm->lsm_layout_gen);
for (i = 0; i < lsm->lsm_entry_count; i++) {
struct lov_stripe_md_entry *lse = lsm->lsm_entries[i];
+ struct lov_layout_entry *lle = lov_entry(lov, i);
- (*p)(env, cookie, DEXT ": { 0x%08X, %u, %u, %#x, %u, %u }\n",
+ (*p)(env, cookie,
+ DEXT ": { 0x%08X, %u, %#x, %u, %#x, %u, %u }\n",
PEXT(&lse->lsme_extent), lse->lsme_magic,
- lse->lsme_id, lse->lsme_layout_gen, lse->lsme_flags,
- lse->lsme_stripe_count, lse->lsme_stripe_size);
- lov_print_raid0(env, cookie, p, lov_r0(lov, i));
+ lse->lsme_id, lse->lsme_pattern, lse->lsme_layout_gen,
+ lse->lsme_flags, lse->lsme_stripe_count,
+ lse->lsme_stripe_size);
+
+ if (!lsme_is_foreign(lse))
+ lov_print_raid0(env, cookie, p, lle);
}
return 0;
(*p)(env, cookie,
"released: %s, lsm{%p 0x%08X %d %u}:\n",
- lov->lo_layout_invalid ? "invalid" : "valid", lsm,
+ test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags) ? "invalid" :
+ "valid", lsm, lsm->lsm_magic, atomic_read(&lsm->lsm_refc),
+ lsm->lsm_layout_gen);
+ return 0;
+}
+
+static int lov_print_foreign(const struct lu_env *env, void *cookie,
+ lu_printer_t p, const struct lu_object *o)
+{
+ struct lov_object *lov = lu2lov(o);
+ struct lov_stripe_md *lsm = lov->lo_lsm;
+
+ (*p)(env, cookie,
+ "foreign: %s, lsm{%p 0x%08X %d %u}:\n",
+ test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags) ?
+ "invalid" : "valid", lsm,
lsm->lsm_magic, atomic_read(&lsm->lsm_refc),
lsm->lsm_layout_gen);
+ (*p)(env, cookie,
+ "raw_ea_content '%.*s'\n",
+ (int)lsm->lsm_foreign_size, (char *)lsm_foreign(lsm));
return 0;
}
return 0;
}
-static int lov_attr_get_raid0(const struct lu_env *env, struct lov_object *lov,
- unsigned int index, struct lov_layout_raid0 *r0)
-
-{
- struct lov_stripe_md *lsm = lov->lo_lsm;
- struct ost_lvb *lvb = &lov_env_info(env)->lti_lvb;
- struct cl_attr *attr = &r0->lo_attr;
- __u64 kms = 0;
- int result = 0;
-
- if (r0->lo_attr_valid)
- return 0;
-
- memset(lvb, 0, sizeof(*lvb));
-
- /* XXX: timestamps can be negative by sanity:test_39m,
- * how can it be? */
- lvb->lvb_atime = LLONG_MIN;
- lvb->lvb_ctime = LLONG_MIN;
- lvb->lvb_mtime = LLONG_MIN;
-
- /*
- * XXX that should be replaced with a loop over sub-objects,
- * doing cl_object_attr_get() on them. But for now, let's
- * reuse old lov code.
- */
-
- /*
- * XXX take lsm spin-lock to keep lov_merge_lvb_kms()
- * happy. It's not needed, because new code uses
- * ->coh_attr_guard spin-lock to protect consistency of
- * sub-object attributes.
- */
- lov_stripe_lock(lsm);
- result = lov_merge_lvb_kms(lsm, index, lvb, &kms);
- lov_stripe_unlock(lsm);
- if (result == 0) {
- cl_lvb2attr(attr, lvb);
- attr->cat_kms = kms;
- r0->lo_attr_valid = 1;
- }
-
- return result;
-}
-
static int lov_attr_get_composite(const struct lu_env *env,
struct cl_object *obj,
struct cl_attr *attr)
struct lov_object *lov = cl2lov(obj);
struct lov_layout_entry *entry;
int result = 0;
- int index = 0;
ENTRY;
attr->cat_size = 0;
attr->cat_blocks = 0;
lov_foreach_layout_entry(lov, entry) {
- struct lov_layout_raid0 *r0 = &entry->lle_raid0;
- struct cl_attr *lov_attr = &r0->lo_attr;
+ struct cl_attr *lov_attr = NULL;
+ int index = lov_layout_entry_index(lov, entry);
+
+ if (!entry->lle_valid)
+ continue;
/* PFL: This component has not been init-ed. */
if (!lsm_entry_inited(lov->lo_lsm, index))
- break;
+ continue;
- result = lov_attr_get_raid0(env, lov, index, r0);
- if (result != 0)
- break;
+ result = entry->lle_comp_ops->lco_getattr(env, lov, index,
+ entry, &lov_attr);
+ if (result < 0)
+ RETURN(result);
+
+ if (lov_attr == NULL)
+ continue;
- index++;
+ CDEBUG(D_INODE, "COMP ID #%i: s=%llu m=%llu a=%llu c=%llu "
+ "b=%llu\n", index - 1, lov_attr->cat_size,
+ lov_attr->cat_mtime, lov_attr->cat_atime,
+ lov_attr->cat_ctime, lov_attr->cat_blocks);
/* merge results */
attr->cat_blocks += lov_attr->cat_blocks;
if (attr->cat_mtime < lov_attr->cat_mtime)
attr->cat_mtime = lov_attr->cat_mtime;
}
- RETURN(result);
+
+ RETURN(0);
+}
+
+static int lov_flush_composite(const struct lu_env *env,
+ struct cl_object *obj,
+ struct ldlm_lock *lock)
+{
+ struct lov_object *lov = cl2lov(obj);
+ struct lov_layout_entry *lle;
+ int rc = -ENODATA;
+
+ ENTRY;
+
+ lov_foreach_layout_entry(lov, lle) {
+ if (!lsme_is_dom(lle->lle_lsme))
+ continue;
+ rc = cl_object_flush(env, lovsub2cl(lle->lle_dom.lo_dom), lock);
+ break;
+ }
+
+ RETURN(rc);
+}
+
+static int lov_flush_empty(const struct lu_env *env, struct cl_object *obj,
+ struct ldlm_lock *lock)
+{
+ return 0;
}
const static struct lov_layout_operations lov_dispatch[] = {
- [LLT_EMPTY] = {
- .llo_init = lov_init_empty,
- .llo_delete = lov_delete_empty,
- .llo_fini = lov_fini_empty,
- .llo_print = lov_print_empty,
- .llo_page_init = lov_page_init_empty,
- .llo_lock_init = lov_lock_init_empty,
- .llo_io_init = lov_io_init_empty,
+ [LLT_EMPTY] = {
+ .llo_init = lov_init_empty,
+ .llo_delete = lov_delete_empty,
+ .llo_fini = lov_fini_empty,
+ .llo_print = lov_print_empty,
+ .llo_page_init = lov_page_init_empty,
+ .llo_lock_init = lov_lock_init_empty,
+ .llo_io_init = lov_io_init_empty,
.llo_getattr = lov_attr_get_empty,
- },
- [LLT_RELEASED] = {
- .llo_init = lov_init_released,
- .llo_delete = lov_delete_empty,
- .llo_fini = lov_fini_released,
- .llo_print = lov_print_released,
- .llo_page_init = lov_page_init_empty,
- .llo_lock_init = lov_lock_init_empty,
- .llo_io_init = lov_io_init_released,
+ .llo_flush = lov_flush_empty,
+ },
+ [LLT_RELEASED] = {
+ .llo_init = lov_init_released,
+ .llo_delete = lov_delete_empty,
+ .llo_fini = lov_fini_released,
+ .llo_print = lov_print_released,
+ .llo_page_init = lov_page_init_empty,
+ .llo_lock_init = lov_lock_init_empty,
+ .llo_io_init = lov_io_init_released,
.llo_getattr = lov_attr_get_empty,
+ .llo_flush = lov_flush_empty,
},
[LLT_COMP] = {
.llo_init = lov_init_composite,
.llo_lock_init = lov_lock_init_composite,
.llo_io_init = lov_io_init_composite,
.llo_getattr = lov_attr_get_composite,
+ .llo_flush = lov_flush_composite,
+ },
+ [LLT_FOREIGN] = {
+ .llo_init = lov_init_foreign,
+ .llo_delete = lov_delete_empty,
+ .llo_fini = lov_fini_released,
+ .llo_print = lov_print_foreign,
+ .llo_page_init = lov_page_init_foreign,
+ .llo_lock_init = lov_lock_init_empty,
+ .llo_io_init = lov_io_init_empty,
+ .llo_getattr = lov_attr_get_empty,
+ .llo_flush = lov_flush_empty,
},
};
lsm->lsm_magic == LOV_MAGIC_COMP_V1)
return LLT_COMP;
+ if (lsm->lsm_magic == LOV_MAGIC_FOREIGN)
+ return LLT_FOREIGN;
+
return LLT_EMPTY;
}
static int lov_layout_wait(const struct lu_env *env, struct lov_object *lov)
{
- struct l_wait_info lwi = { 0 };
ENTRY;
while (atomic_read(&lov->lo_active_ios) > 0) {
PFID(lu_object_fid(lov2lu(lov))),
atomic_read(&lov->lo_active_ios));
- l_wait_event(lov->lo_waitq,
- atomic_read(&lov->lo_active_ios) == 0, &lwi);
+ wait_event_idle(lov->lo_waitq,
+ atomic_read(&lov->lo_active_ios) == 0);
}
RETURN(0);
}
CDEBUG(D_INODE, DFID "Apply new layout lov %p, type %d\n",
PFID(lu_object_fid(lov2lu(lov))), lov, llt);
- lov->lo_type = LLT_EMPTY;
-
/* page bufsize fixup */
cl_object_header(&lov->lo_cl)->coh_page_bufsize -=
lov_page_slice_fixup(lov, NULL);
+ lov->lo_type = llt;
rc = new_ops->llo_init(env, lov_dev, lov, lsm, conf, state);
if (rc != 0) {
struct obd_device *obd = lov2obd(lov_dev->ld_lov);
new_ops->llo_delete(env, lov, state);
new_ops->llo_fini(env, lov, state);
/* this file becomes an EMPTY file. */
+ lov->lo_type = LLT_EMPTY;
GOTO(out, rc);
}
- lov->lo_type = llt;
-
out:
cl_env_put(env, &refcheck);
RETURN(rc);
* Lov object operations.
*
*/
-int lov_object_init(const struct lu_env *env, struct lu_object *obj,
- const struct lu_object_conf *conf)
+static int lov_object_init(const struct lu_env *env, struct lu_object *obj,
+ const struct lu_object_conf *conf)
{
struct lov_object *lov = lu2lov(obj);
struct lov_device *dev = lov_object_dev(lov);
dump_lsm(D_INODE, lsm);
}
- lov_conf_lock(lov);
if (conf->coc_opc == OBJECT_CONF_INVALIDATE) {
- lov->lo_layout_invalid = true;
- GOTO(out, result = 0);
+ set_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
+ GOTO(out_lsm, result = 0);
}
+ lov_conf_lock(lov);
if (conf->coc_opc == OBJECT_CONF_WAIT) {
- if (lov->lo_layout_invalid &&
+ if (test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags) &&
atomic_read(&lov->lo_active_ios) > 0) {
lov_conf_unlock(lov);
result = lov_layout_wait(env, lov);
if ((lsm == NULL && lov->lo_lsm == NULL) ||
((lsm != NULL && lov->lo_lsm != NULL) &&
(lov->lo_lsm->lsm_layout_gen == lsm->lsm_layout_gen) &&
+ (lov->lo_lsm->lsm_flags == lsm->lsm_flags) &&
(lov->lo_lsm->lsm_entries[0]->lsme_pattern ==
lsm->lsm_entries[0]->lsme_pattern))) {
/* same version of layout */
- lov->lo_layout_invalid = false;
+ clear_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
GOTO(out, result = 0);
}
/* will change layout - check if there still exists active IO. */
if (atomic_read(&lov->lo_active_ios) > 0) {
- lov->lo_layout_invalid = true;
+ set_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
GOTO(out, result = -EBUSY);
}
result = lov_layout_change(env, lov, lsm, conf);
- lov->lo_layout_invalid = result != 0;
+ if (result)
+ set_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
+ else
+ clear_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags);
EXIT;
out:
lov_conf_unlock(lov);
+out_lsm:
lov_lsm_put(lsm);
- CDEBUG(D_INODE, DFID" lo_layout_invalid=%d\n",
- PFID(lu_object_fid(lov2lu(lov))), lov->lo_layout_invalid);
+ CDEBUG(D_INODE, DFID" lo_layout_invalid=%u\n",
+ PFID(lu_object_fid(lov2lu(lov))),
+ test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags));
RETURN(result);
}
return LOV_2DISPATCH_NOLOCK(lu2lov(o), llo_print, env, cookie, p, o);
}
-int lov_page_init(const struct lu_env *env, struct cl_object *obj,
- struct cl_page *page, pgoff_t index)
+static int lov_page_init(const struct lu_env *env, struct cl_object *obj,
+ struct cl_page *page, pgoff_t index)
{
return LOV_2DISPATCH_NOLOCK(cl2lov(obj), llo_page_init, env, obj, page,
index);
* Implements cl_object_operations::clo_io_init() method for lov
* layer. Dispatches to the appropriate layout io initialization method.
*/
-int lov_io_init(const struct lu_env *env, struct cl_object *obj,
- struct cl_io *io)
+static int lov_io_init(const struct lu_env *env, struct cl_object *obj,
+ struct cl_io *io)
{
- CL_IO_SLICE_CLEAN(lov_env_io(env), lis_cl);
+ CL_IO_SLICE_CLEAN(lov_env_io(env), lis_preserved);
CDEBUG(D_INODE, DFID "io %p type %d ignore/verify layout %d/%d\n",
PFID(lu_object_fid(&obj->co_lu)), io, io->ci_type,
io->ci_ignore_layout, io->ci_verify_layout);
+ /* IO type CIT_MISC with ci_ignore_layout set are usually invoked from
+ * the OSC layer. It shouldn't take lov layout conf lock in that case,
+ * because as long as the OSC object exists, the layout can't be
+ * reconfigured. */
return LOV_2DISPATCH_MAYLOCK(cl2lov(obj), llo_io_init,
- !io->ci_ignore_layout, env, obj, io);
+ !(io->ci_ignore_layout && io->ci_type == CIT_MISC),
+ env, obj, io);
}
/**
return 0;
}
-int lov_lock_init(const struct lu_env *env, struct cl_object *obj,
+static int lov_lock_init(const struct lu_env *env, struct cl_object *obj,
struct cl_lock *lock, const struct cl_io *io)
{
/* No need to lock because we've taken one refcount of layout. */
int start_stripe, int *stripe_count)
{
struct lov_stripe_md_entry *lsme = lsm->lsm_entries[index];
+ int init_stripe;
int last_stripe;
- u64 obd_start;
- u64 obd_end;
int i, j;
+ init_stripe = lov_stripe_number(lsm, index, ext->e_start);
+
if (ext->e_end - ext->e_start >
lsme->lsme_stripe_size * lsme->lsme_stripe_count) {
- last_stripe = (start_stripe < 1 ? lsme->lsme_stripe_count - 1 :
- start_stripe - 1);
- *stripe_count = lsme->lsme_stripe_count;
+ if (init_stripe == start_stripe) {
+ last_stripe = (start_stripe < 1) ?
+ lsme->lsme_stripe_count - 1 : start_stripe - 1;
+ *stripe_count = lsme->lsme_stripe_count;
+ } else if (init_stripe < start_stripe) {
+ last_stripe = (init_stripe < 1) ?
+ lsme->lsme_stripe_count - 1 : init_stripe - 1;
+ *stripe_count = lsme->lsme_stripe_count -
+ (start_stripe - init_stripe);
+ } else {
+ last_stripe = init_stripe - 1;
+ *stripe_count = init_stripe - start_stripe;
+ }
} else {
for (j = 0, i = start_stripe; j < lsme->lsme_stripe_count;
i = (i + 1) % lsme->lsme_stripe_count, j++) {
- if ((lov_stripe_intersects(lsm, index, i, ext,
- &obd_start, &obd_end)) == 0)
+ if (!lov_stripe_intersects(lsm, index, i, ext, NULL,
+ NULL))
+ break;
+ if ((start_stripe != init_stripe) && (i == init_stripe))
break;
}
*stripe_count = j;
static void fiemap_prepare_and_copy_exts(struct fiemap *fiemap,
struct fiemap_extent *lcl_fm_ext,
int ost_index, unsigned int ext_count,
- int current_extent)
+ int current_extent, int abs_stripeno)
{
char *to;
unsigned int ext;
for (ext = 0; ext < ext_count; ext++) {
- lcl_fm_ext[ext].fe_device = ost_index;
+ set_fe_device_stripenr(&lcl_fm_ext[ext], ost_index,
+ abs_stripeno);
lcl_fm_ext[ext].fe_flags |= FIEMAP_EXTENT_NET;
}
{
struct lov_stripe_md_entry *lsme = lsm->lsm_entries[index];
u64 local_end = fiemap->fm_extents[0].fe_logical;
- u64 lun_start;
u64 lun_end;
u64 fm_end_offset;
int stripe_no = -1;
- int i;
if (fiemap->fm_extent_count == 0 ||
fiemap->fm_extents[0].fe_logical == 0)
return 0;
- /* Find out stripe_no from ost_index saved in the fe_device */
- for (i = 0; i < lsme->lsme_stripe_count; i++) {
- struct lov_oinfo *oinfo = lsme->lsme_oinfo[i];
-
- if (lov_oinfo_is_dummy(oinfo))
- continue;
-
- if (oinfo->loi_ost_idx == fiemap->fm_extents[0].fe_device) {
- stripe_no = i;
- break;
- }
- }
+ stripe_no = *start_stripe;
if (stripe_no == -1)
return -EINVAL;
/* If we have finished mapping on previous device, shift logical
* offset to start of next device */
- if (lov_stripe_intersects(lsm, index, stripe_no, ext,
- &lun_start, &lun_end) != 0 &&
+ if (lov_stripe_intersects(lsm, index, stripe_no, ext, NULL, &lun_end) &&
local_end < lun_end) {
fm_end_offset = local_end;
- *start_stripe = stripe_no;
} else {
/* This is a special value to indicate that caller should
* calculate offset in next stripe. */
struct fiemap_state {
struct fiemap *fs_fm;
- struct lu_extent fs_ext;
+ struct lu_extent fs_ext; /* current entry extent */
u64 fs_length;
- u64 fs_end_offset;
- int fs_cur_extent;
- int fs_cnt_need;
+ u64 fs_end_offset; /* last iteration offset */
+ int fs_cur_extent; /* collected exts so far */
+ int fs_cnt_need; /* # of extents buf can hold */
int fs_start_stripe;
int fs_last_stripe;
- bool fs_device_done;
- bool fs_finish_stripe;
- bool fs_enough;
+ bool fs_device_done; /* enough for this OST */
+ bool fs_finish_stripe; /* reached fs_last_stripe */
+ bool fs_enough; /* enough for this call */
};
-int fiemap_for_stripe(const struct lu_env *env, struct cl_object *obj,
- struct lov_stripe_md *lsm, struct fiemap *fiemap,
- size_t *buflen, struct ll_fiemap_info_key *fmkey,
- int index, int stripeno, struct fiemap_state *fs)
+static struct cl_object *lov_find_subobj(const struct lu_env *env,
+ struct lov_object *lov,
+ struct lov_stripe_md *lsm,
+ int index)
+{
+ struct lov_device *dev = lu2lov_dev(lov2lu(lov)->lo_dev);
+ struct lov_thread_info *lti = lov_env_info(env);
+ struct lu_fid *ofid = <i->lti_fid;
+ struct lov_oinfo *oinfo;
+ struct cl_device *subdev;
+ int entry = lov_comp_entry(index);
+ int stripe = lov_comp_stripe(index);
+ int ost_idx;
+ int rc;
+ struct cl_object *result;
+
+ if (lov->lo_type != LLT_COMP)
+ GOTO(out, result = NULL);
+
+ if (entry >= lsm->lsm_entry_count ||
+ stripe >= lsm->lsm_entries[entry]->lsme_stripe_count)
+ GOTO(out, result = NULL);
+
+ oinfo = lsm->lsm_entries[entry]->lsme_oinfo[stripe];
+ ost_idx = oinfo->loi_ost_idx;
+ rc = ostid_to_fid(ofid, &oinfo->loi_oi, ost_idx);
+ if (rc != 0)
+ GOTO(out, result = NULL);
+
+ subdev = lovsub2cl_dev(dev->ld_target[ost_idx]);
+ result = lov_sub_find(env, subdev, ofid, NULL);
+out:
+ if (result == NULL)
+ result = ERR_PTR(-EINVAL);
+ return result;
+}
+
+static int fiemap_for_stripe(const struct lu_env *env, struct cl_object *obj,
+ struct lov_stripe_md *lsm, struct fiemap *fiemap,
+ size_t *buflen, struct ll_fiemap_info_key *fmkey,
+ int index, int stripe_last, int stripeno,
+ struct fiemap_state *fs)
{
struct lov_stripe_md_entry *lsme = lsm->lsm_entries[index];
struct cl_object *subobj;
struct lov_obd *lov = lu2lov_dev(obj->co_lu.lo_dev)->ld_lov;
struct fiemap_extent *fm_ext = &fs->fs_fm->fm_extents[0];
- u64 req_fm_len; /* Stores length of required mapping */
+ u64 req_fm_len; /* max requested extent coverage */
u64 len_mapped_single_call;
- u64 lun_start;
- u64 lun_end;
- u64 obd_object_end;
+ u64 obd_start;
+ u64 obd_end;
unsigned int ext_count;
/* EOF for object */
bool ost_eof = false;
fs->fs_device_done = false;
/* Find out range of mapping on this stripe */
if ((lov_stripe_intersects(lsm, index, stripeno, &fs->fs_ext,
- &lun_start, &obd_object_end)) == 0)
+ &obd_start, &obd_end)) == 0)
return 0;
if (lov_oinfo_is_dummy(lsme->lsme_oinfo[stripeno]))
return -EIO;
/* If this is a continuation FIEMAP call and we are on
- * starting stripe then lun_start needs to be set to
+ * starting stripe then obd_start needs to be set to
* end_offset */
if (fs->fs_end_offset != 0 && stripeno == fs->fs_start_stripe)
- lun_start = fs->fs_end_offset;
- lun_end = lov_size_to_stripe(lsm, index, fs->fs_ext.e_end, stripeno);
- if (lun_start == lun_end)
+ obd_start = fs->fs_end_offset;
+
+ if (lov_size_to_stripe(lsm, index, fs->fs_ext.e_end, stripeno) ==
+ obd_start)
return 0;
- req_fm_len = obd_object_end - lun_start;
+ req_fm_len = obd_end - obd_start + 1;
fs->fs_fm->fm_length = 0;
len_mapped_single_call = 0;
fs->fs_cur_extent;
}
- lun_start += len_mapped_single_call;
+ obd_start += len_mapped_single_call;
fs->fs_fm->fm_length = req_fm_len - len_mapped_single_call;
req_fm_len = fs->fs_fm->fm_length;
/**
fs->fs_fm->fm_flags |= FIEMAP_EXTENT_LAST;
fs->fs_fm->fm_mapped_extents = 1;
- fm_ext[0].fe_logical = lun_start;
- fm_ext[0].fe_length = obd_object_end - lun_start;
+ fm_ext[0].fe_logical = obd_start;
+ fm_ext[0].fe_length = obd_end - obd_start + 1;
fm_ext[0].fe_flags |= FIEMAP_EXTENT_UNKNOWN;
goto inactive_tgt;
}
- fs->fs_fm->fm_start = lun_start;
+ fs->fs_fm->fm_start = obd_start;
fs->fs_fm->fm_flags &= ~FIEMAP_FLAG_DEVICE_ORDER;
memcpy(&fmkey->lfik_fiemap, fs->fs_fm, sizeof(*fs->fs_fm));
*buflen = fiemap_count_to_size(fs->fs_fm->fm_extent_count);
/* prepare to copy retrived map extents */
len_mapped_single_call = fm_ext[ext_count - 1].fe_logical +
fm_ext[ext_count - 1].fe_length -
- lun_start;
+ obd_start;
/* Have we finished mapping on this device? */
if (req_fm_len <= len_mapped_single_call) {
}
fiemap_prepare_and_copy_exts(fiemap, fm_ext, ost_index,
- ext_count, fs->fs_cur_extent);
+ ext_count, fs->fs_cur_extent,
+ stripe_last + stripeno);
fs->fs_cur_extent += ext_count;
/* Ran out of available extents? */
loff_t whole_start;
loff_t whole_end;
int entry;
- int start_entry;
+ int start_entry = -1;
int end_entry;
int cur_stripe = 0;
int stripe_count;
unsigned int buffer_size = FIEMAP_BUFFER_SIZE;
int rc = 0;
struct fiemap_state fs = { 0 };
+ struct lu_extent range;
+ int cur_ext;
+ int stripe_last;
+ int start_stripe = 0;
+ bool resume = false;
ENTRY;
lsm = lov_lsm_addref(cl2lov(obj));
- if (lsm == NULL)
- RETURN(-ENODATA);
+ if (lsm == NULL) {
+ /* no extent: there is no object for mapping */
+ fiemap->fm_mapped_extents = 0;
+ return 0;
+ }
if (!(fiemap->fm_flags & FIEMAP_FLAG_DEVICE_ORDER)) {
/**
GOTO(out_lsm, rc = -ENOTSUPP);
}
+ /* No support for DOM layout yet. */
+ if (lsme_is_dom(lsm->lsm_entries[0]))
+ GOTO(out_lsm, rc = -ENOTSUPP);
+
if (lsm->lsm_is_released) {
if (fiemap->fm_start < fmkey->lfik_oa.o_size) {
/**
*/
if (fiemap_count_to_size(fiemap->fm_extent_count) > *buflen)
fiemap->fm_extent_count = fiemap_size_to_count(*buflen);
- if (fiemap->fm_extent_count == 0)
- fs.fs_cnt_need = 0;
fs.fs_enough = false;
fs.fs_cur_extent = 0;
if (whole_start > fmkey->lfik_oa.o_size)
GOTO(out_fm_local, rc = -EINVAL);
whole_end = (fiemap->fm_length == OBD_OBJECT_EOF) ?
- fmkey->lfik_oa.o_size :
- whole_start + fiemap->fm_length - 1;
+ fmkey->lfik_oa.o_size + 1 :
+ whole_start + fiemap->fm_length;
/**
* If fiemap->fm_length != OBD_OBJECT_EOF but whole_end exceeds file
* size
*/
- if (whole_end > fmkey->lfik_oa.o_size)
- whole_end = fmkey->lfik_oa.o_size;
+ if (whole_end > fmkey->lfik_oa.o_size + 1)
+ whole_end = fmkey->lfik_oa.o_size + 1;
- start_entry = lov_lsm_entry(lsm, whole_start);
- end_entry = lov_lsm_entry(lsm, whole_end);
- if (end_entry == -1)
- end_entry = lsm->lsm_entry_count - 1;
+ /**
+ * the high 16bits of fe_device remember which stripe the last
+ * call has been arrived, we'd continue from there in this call.
+ */
+ if (fiemap->fm_extent_count && fiemap->fm_extents[0].fe_logical)
+ resume = true;
+ stripe_last = get_fe_stripenr(&fiemap->fm_extents[0]);
+ /**
+ * stripe_last records stripe number we've been processed in the last
+ * call
+ */
+ end_entry = lsm->lsm_entry_count - 1;
+ cur_stripe = 0;
+ for (entry = 0; entry <= end_entry; entry++) {
+ lsme = lsm->lsm_entries[entry];
+ if (cur_stripe + lsme->lsme_stripe_count >= stripe_last) {
+ start_entry = entry;
+ start_stripe = stripe_last - cur_stripe;
+ break;
+ }
- if (start_entry == -1 || end_entry == -1)
+ cur_stripe += lsme->lsme_stripe_count;
+ }
+ if (start_entry == -1) {
+ CERROR(DFID": FIEMAP does not init start entry, cur_stripe=%d, "
+ "stripe_last=%d\n", PFID(lu_object_fid(&obj->co_lu)),
+ cur_stripe, stripe_last);
GOTO(out_fm_local, rc = -EINVAL);
+ }
+ /**
+ * @start_entry & @start_stripe records the position of fiemap
+ * resumption @stripe_last keeps recording the absolution position
+ * we'are processing. @resume indicates we'd honor @start_stripe.
+ */
+
+ range.e_start = whole_start;
+ range.e_end = whole_end;
for (entry = start_entry; entry <= end_entry; entry++) {
+ /* remeber to update stripe_last accordingly */
lsme = lsm->lsm_entries[entry];
- if (!lsme_inited(lsme))
- break;
+ /* FLR could contain component holes between entries */
+ if (!lsme_inited(lsme)) {
+ stripe_last += lsme->lsme_stripe_count;
+ resume = false;
+ continue;
+ }
- if (entry == start_entry)
- fs.fs_ext.e_start = whole_start;
- else
+ if (!lu_extent_is_overlapped(&range, &lsme->lsme_extent)) {
+ stripe_last += lsme->lsme_stripe_count;
+ resume = false;
+ continue;
+ }
+
+ /* prepare for a component entry iteration */
+ if (lsme->lsme_extent.e_start > whole_start)
fs.fs_ext.e_start = lsme->lsme_extent.e_start;
- if (entry == end_entry)
+ else
+ fs.fs_ext.e_start = whole_start;
+ if (lsme->lsme_extent.e_end > whole_end)
fs.fs_ext.e_end = whole_end;
else
- fs.fs_ext.e_end = lsme->lsme_extent.e_end - 1;
- fs.fs_length = fs.fs_ext.e_end - fs.fs_ext.e_start + 1;
+ fs.fs_ext.e_end = lsme->lsme_extent.e_end;
/* Calculate start stripe, last stripe and length of mapping */
- fs.fs_start_stripe = lov_stripe_number(lsm, entry,
- fs.fs_ext.e_start);
+ if (resume) {
+ fs.fs_start_stripe = start_stripe;
+ /* put stripe_last to the first stripe of the comp */
+ stripe_last -= start_stripe;
+ resume = false;
+ } else {
+ fs.fs_start_stripe = lov_stripe_number(lsm, entry,
+ fs.fs_ext.e_start);
+ }
fs.fs_last_stripe = fiemap_calc_last_stripe(lsm, entry,
&fs.fs_ext, fs.fs_start_stripe,
&stripe_count);
- fs.fs_end_offset = fiemap_calc_fm_end_offset(fiemap, lsm, entry,
- &fs.fs_ext, &fs.fs_start_stripe);
+ /**
+ * A new mirror component is under process, reset
+ * fs.fs_end_offset and then fiemap_for_stripe() starts from
+ * the overlapping extent, otherwise starts from
+ * fs.fs_end_offset.
+ */
+ if (entry > start_entry && lsme->lsme_extent.e_start == 0) {
+ /* new mirror */
+ fs.fs_end_offset = 0;
+ } else {
+ fs.fs_end_offset = fiemap_calc_fm_end_offset(fiemap,
+ lsm, entry, &fs.fs_ext,
+ &fs.fs_start_stripe);
+ }
+
/* Check each stripe */
for (cur_stripe = fs.fs_start_stripe; stripe_count > 0;
--stripe_count,
cur_stripe = (cur_stripe + 1) % lsme->lsme_stripe_count) {
+ /* reset fs_finish_stripe */
+ fs.fs_finish_stripe = false;
rc = fiemap_for_stripe(env, obj, lsm, fiemap, buflen,
- fmkey, entry, cur_stripe, &fs);
+ fmkey, entry, stripe_last,
+ cur_stripe, &fs);
if (rc < 0)
GOTO(out_fm_local, rc);
- if (fs.fs_enough)
+ if (fs.fs_enough) {
+ stripe_last += cur_stripe;
GOTO(finish, rc);
+ }
if (fs.fs_finish_stripe)
break;
} /* for each stripe */
- } /* for covering layout component */
- /*
- * We've traversed all components, set @entry to the last component
- * entry, it's for the last stripe check.
- */
- entry--;
+ stripe_last += lsme->lsme_stripe_count;
+ } /* for covering layout component entry */
+
finish:
+ if (fs.fs_cur_extent > 0)
+ cur_ext = fs.fs_cur_extent - 1;
+ else
+ cur_ext = 0;
+
+ /* done all the processing */
+ if (entry > end_entry)
+ fiemap->fm_extents[cur_ext].fe_flags |= FIEMAP_EXTENT_LAST;
+
/* Indicate that we are returning device offsets unless file just has
* single stripe */
if (lsm->lsm_entry_count > 1 ||
if (fiemap->fm_extent_count == 0)
goto skip_last_device_calc;
- /* Check if we have reached the last stripe and whether mapping for that
- * stripe is done. */
- if ((cur_stripe == fs.fs_last_stripe) && fs.fs_device_done)
- fiemap->fm_extents[fs.fs_cur_extent - 1].fe_flags |=
- FIEMAP_EXTENT_LAST;
skip_last_device_calc:
fiemap->fm_mapped_extents = fs.fs_cur_extent;
out_fm_local:
cl->cl_size = lov_comp_md_size(lsm);
cl->cl_layout_gen = lsm->lsm_layout_gen;
+ cl->cl_is_released = lsm->lsm_is_released;
cl->cl_is_composite = lsm_is_composite(lsm->lsm_magic);
rc = lov_lsm_pack(lsm, buf->lb_buf, buf->lb_len);
lov_lsm_put(lsm);
- RETURN(rc < 0 ? rc : 0);
+ /* return error or number of bytes */
+ RETURN(rc);
}
static loff_t lov_object_maxbytes(struct cl_object *obj)
return maxbytes;
}
+static int lov_object_flush(const struct lu_env *env, struct cl_object *obj,
+ struct ldlm_lock *lock)
+{
+ return LOV_2DISPATCH_MAYLOCK(cl2lov(obj), llo_flush, true, env, obj,
+ lock);
+}
+
static const struct cl_object_operations lov_ops = {
.coo_page_init = lov_page_init,
.coo_lock_init = lov_lock_init,
.coo_layout_get = lov_object_layout_get,
.coo_maxbytes = lov_object_maxbytes,
.coo_fiemap = lov_object_fiemap,
+ .coo_object_flush = lov_object_flush
};
static const struct lu_object_operations lov_lu_obj_ops = {
- .loo_object_init = lov_object_init,
- .loo_object_delete = lov_object_delete,
- .loo_object_release = NULL,
- .loo_object_free = lov_object_free,
- .loo_object_print = lov_object_print,
- .loo_object_invariant = NULL
+ .loo_object_init = lov_object_init,
+ .loo_object_delete = lov_object_delete,
+ .loo_object_release = NULL,
+ .loo_object_free = lov_object_free,
+ .loo_object_print = lov_object_print,
+ .loo_object_invariant = NULL,
};
struct lu_object *lov_object_alloc(const struct lu_env *env,
RETURN(obj);
}
-struct lov_stripe_md *lov_lsm_addref(struct lov_object *lov)
+static struct lov_stripe_md *lov_lsm_addref(struct lov_object *lov)
{
struct lov_stripe_md *lsm = NULL;
lsm = lsm_addref(lov->lo_lsm);
CDEBUG(D_INODE, "lsm %p addref %d/%d by %p.\n",
lsm, atomic_read(&lsm->lsm_refc),
- lov->lo_layout_invalid, current);
+ test_bit(LO_LAYOUT_INVALID, &lov->lo_obj_flags),
+ current);
}
lov_conf_thaw(lov);
return lsm;
}
case LLT_RELEASED:
case LLT_EMPTY:
+ /* fall through */
+ case LLT_FOREIGN:
break;
default:
LBUG();
git://git.whamcloud.com / fs / lustre-release.git / blobdiff