diff options
Diffstat (limited to 'src/os')
-rw-r--r-- | src/os/DBObjectMap.cc | 5 | ||||
-rw-r--r-- | src/os/DBObjectMap.h | 2 | ||||
-rw-r--r-- | src/os/ObjectStore.h | 52 | ||||
-rw-r--r-- | src/os/bluestore/BlueFS.cc | 64 | ||||
-rw-r--r-- | src/os/bluestore/BlueStore.cc | 186 | ||||
-rw-r--r-- | src/os/bluestore/BlueStore.h | 18 | ||||
-rw-r--r-- | src/os/bluestore/bluefs_types.cc | 4 | ||||
-rw-r--r-- | src/os/bluestore/bluefs_types.h | 1 | ||||
-rw-r--r-- | src/os/kstore/KStore.cc | 72 | ||||
-rw-r--r-- | src/os/kstore/KStore.h | 8 | ||||
-rw-r--r-- | src/os/memstore/MemStore.cc | 70 | ||||
-rw-r--r-- | src/os/memstore/MemStore.h | 15 |
12 files changed, 364 insertions, 133 deletions
diff --git a/src/os/DBObjectMap.cc b/src/os/DBObjectMap.cc index 7da9a67be62..65627b5f818 100644 --- a/src/os/DBObjectMap.cc +++ b/src/os/DBObjectMap.cc @@ -519,6 +519,11 @@ bufferlist DBObjectMap::DBObjectMapIteratorImpl::value() return cur_iter->value(); } +std::string_view DBObjectMap::DBObjectMapIteratorImpl::value_as_sv() +{ + return cur_iter->value_as_sv(); +} + int DBObjectMap::DBObjectMapIteratorImpl::status() { return r; diff --git a/src/os/DBObjectMap.h b/src/os/DBObjectMap.h index 444f21eb815..1e1452010e7 100644 --- a/src/os/DBObjectMap.h +++ b/src/os/DBObjectMap.h @@ -393,6 +393,7 @@ private: int next() override { ceph_abort(); return 0; } std::string key() override { ceph_abort(); return ""; } ceph::buffer::list value() override { ceph_abort(); return ceph::buffer::list(); } + std::string_view value_as_sv() override { ceph_abort(); return std::string_view(); } int status() override { return 0; } }; @@ -431,6 +432,7 @@ private: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; int status() override; bool on_parent() { diff --git a/src/os/ObjectStore.h b/src/os/ObjectStore.h index 521435b6c31..df3ae920a2f 100644 --- a/src/os/ObjectStore.h +++ b/src/os/ObjectStore.h @@ -29,6 +29,7 @@ #include <errno.h> #include <sys/stat.h> +#include <functional> #include <map> #include <memory> #include <vector> @@ -735,15 +736,6 @@ public: std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) = 0; -#ifdef WITH_SEASTAR - virtual int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) = 0; -#endif - /// Filters keys into out which are defined on oid virtual int omap_check_keys( CollectionHandle &c, ///< [in] Collection containing oid @@ -766,6 +758,48 @@ public: const ghobject_t &oid ///< [in] object ) = 0; + struct omap_iter_seek_t { + std::string seek_position; + enum { + // start with provided key (seek_position), if it exists + LOWER_BOUND, + // skip provided key (seek_position) even if it exists + UPPER_BOUND + } seek_type = LOWER_BOUND; + static omap_iter_seek_t min_lower_bound() { return {}; } + }; + enum class omap_iter_ret_t { + STOP, + NEXT + }; + /** + * Iterate over object map with user-provided callable + * + * Warning! The callable is executed under lock on bluestore + * operations in c. Do not use bluestore methods on c while + * iterating. (Filling in a transaction is no problem). + * + * @param c collection + * @param oid object + * @param start_from where the iterator should point to at + * the beginning + * @param visitor callable that takes OMAP key and corresponding + * value as string_views and controls iteration + * by the return. It is executed for every object's + * OMAP entry from `start_from` till end of the + * object's OMAP or till the iteration is stopped + * by `STOP`. Please note that if there is no such + * entry, `visitor` will be called 0 times. + * @return error code, zero on success + */ + virtual int omap_iterate( + CollectionHandle &c, + const ghobject_t &oid, + omap_iter_seek_t start_from, + std::function<omap_iter_ret_t(std::string_view, + std::string_view)> visitor + ) = 0; + virtual int flush_journal() { return -EOPNOTSUPP; } virtual int dump_journal(std::ostream& out) { return -EOPNOTSUPP; } diff --git a/src/os/bluestore/BlueFS.cc b/src/os/bluestore/BlueFS.cc index e123a0a200a..50f293d45fd 100644 --- a/src/os/bluestore/BlueFS.cc +++ b/src/os/bluestore/BlueFS.cc @@ -1706,7 +1706,8 @@ int BlueFS::_replay(bool noop, bool to_stdout) << " fnode=" << fnode << " delta=" << delta << dendl; - ceph_assert(delta.offset == fnode.allocated); + // be leanient, if there is no extents just produce error message + ceph_assert(delta.offset == fnode.allocated || delta.extents.empty()); } if (cct->_conf->bluefs_log_replay_check_allocations) { int r = _check_allocations(fnode, @@ -3793,7 +3794,7 @@ int BlueFS::truncate(FileWriter *h, uint64_t offset)/*_WF_L*/ if (offset > fnode.size) { ceph_abort_msg("truncate up not supported"); } - ceph_assert(offset <= fnode.size); + _flush_bdev(h); { std::lock_guard ll(log.lock); @@ -3802,43 +3803,42 @@ int BlueFS::truncate(FileWriter *h, uint64_t offset)/*_WF_L*/ vselector->sub_usage(h->file->vselector_hint, fnode); uint64_t x_off = 0; auto p = fnode.seek(offset, &x_off); - uint64_t cut_off = - (p == fnode.extents.end()) ? 0 : p2roundup(x_off, alloc_size[p->bdev]); - uint64_t new_allocated; - if (0 == cut_off) { - // whole pextent to remove - changed_extents = true; - new_allocated = offset; - } else if (cut_off < p->length) { - dirty.pending_release[p->bdev].insert(p->offset + cut_off, p->length - cut_off); - new_allocated = (offset - x_off) + cut_off; - p->length = cut_off; - changed_extents = true; - ++p; - } else { - ceph_assert(cut_off >= p->length); - new_allocated = (offset - x_off) + p->length; - // just leave it here - ++p; - } - while (p != fnode.extents.end()) { - dirty.pending_release[p->bdev].insert(p->offset, p->length); - p = fnode.extents.erase(p); - changed_extents = true; + if (p != fnode.extents.end()) { + uint64_t cut_off = p2roundup(x_off, alloc_size[p->bdev]); + if (0 == cut_off) { + // whole pextent to remove + fnode.allocated = offset; + changed_extents = true; + } else if (cut_off < p->length) { + dirty.pending_release[p->bdev].insert(p->offset + cut_off, + p->length - cut_off); + fnode.allocated = (offset - x_off) + cut_off; + p->length = cut_off; + changed_extents = true; + ++p; + } else { + // cut_off > p->length means that we misaligned the extent + ceph_assert(cut_off == p->length); + fnode.allocated = (offset - x_off) + p->length; + ++p; // leave extent untouched + } + while (p != fnode.extents.end()) { + dirty.pending_release[p->bdev].insert(p->offset, p->length); + p = fnode.extents.erase(p); + changed_extents = true; + } } if (changed_extents) { fnode.size = offset; - fnode.allocated = new_allocated; fnode.reset_delta(); + fnode.recalc_allocated(); log.t.op_file_update(fnode); // sad, but is_dirty must be set to signal flushing of the log h->file->is_dirty = true; - } else { - if (offset != fnode.size) { - fnode.size = offset; - //skipping log.t.op_file_update_inc, it will be done by flush() - h->file->is_dirty = true; - } + } else if (offset != fnode.size) { + fnode.size = offset; + // skipping log.t.op_file_update_inc, it will be done by flush() + h->file->is_dirty = true; } vselector->add_usage(h->file->vselector_hint, fnode); } diff --git a/src/os/bluestore/BlueStore.cc b/src/os/bluestore/BlueStore.cc index a024a0c2105..8f1d995fa8d 100644 --- a/src/os/bluestore/BlueStore.cc +++ b/src/os/bluestore/BlueStore.cc @@ -4830,7 +4830,7 @@ void BlueStore::Onode::rewrite_omap_key(const string& old, string *out) out->append(old.c_str() + out->length(), old.size() - out->length()); } -void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) +size_t BlueStore::Onode::calc_userkey_offset_in_omap_key() const { size_t pos = sizeof(uint64_t) + 1; if (!onode.is_pgmeta_omap()) { @@ -4840,9 +4840,15 @@ void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) pos += sizeof(uint64_t); } } - *user_key = key.substr(pos); + return pos; } +void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) +{ + *user_key = key.substr(calc_userkey_offset_in_omap_key()); +} + + void BlueStore::Onode::finish_write(TransContext* txc, uint32_t offset, uint32_t length) { while (true) { @@ -5519,7 +5525,13 @@ BlueStore::OmapIteratorImpl::OmapIteratorImpl( if (o->onode.has_omap()) { o->get_omap_key(string(), &head); o->get_omap_tail(&tail); + auto start1 = mono_clock::now(); it->lower_bound(head); + c->store->log_latency( + __func__, + l_bluestore_omap_seek_to_first_lat, + mono_clock::now() - start1, + c->store->cct->_conf->bluestore_log_omap_iterator_age); } } BlueStore::OmapIteratorImpl::~OmapIteratorImpl() @@ -5654,6 +5666,13 @@ bufferlist BlueStore::OmapIteratorImpl::value() return it->value(); } +std::string_view BlueStore::OmapIteratorImpl::value_as_sv() +{ + std::shared_lock l(c->lock); + ceph_assert(it->valid()); + return it->value_as_sv(); +} + // ===================================== @@ -6911,8 +6930,19 @@ int BlueStore::_check_main_bdev_label() return -EIO; } if (bluestore_bdev_label_require_all && r != 0) { - derr << __func__ << " not all labels read properly" << dendl; - return -EIO; + // We are about to complain that some labels failed. + // But in case if we expanded block device some labels will not be good. + uint64_t lsize = std::max(BDEV_LABEL_BLOCK_SIZE, min_alloc_size); + uint32_t valid_locations = 0; + for (uint64_t loc : bdev_label_positions) { + if (loc + lsize <= bdev_label.size) { + ++valid_locations; + } + } + if (valid_locations != bdev_label_valid_locations.size()) { + derr << __func__ << " not all labels read properly" << dendl; + return -EIO; + } } return 0; } @@ -8948,11 +8978,25 @@ int BlueStore::expand_devices(ostream& out) _close_db_and_around(); // mount in read/write to sync expansion changes + if (bdev_label_multi) { + // We need not do fsck, because we can be broken - size is increased, + // but we might not have labels set. + cct->_conf.set_val_or_die("bluestore_fsck_on_mount", "false"); + } r = _mount(); ceph_assert(r == 0); if (fm && fm->is_null_manager()) { // we grow the allocation range, must reflect it in the allocation file alloc->init_add_free(size0, size - size0); + if (bdev_label_multi) { + uint64_t lsize = std::max(BDEV_LABEL_BLOCK_SIZE, min_alloc_size); + for (uint64_t loc : bdev_label_positions) { + if ((loc >= size0) && (loc + lsize <= size)) { + bdev_label_valid_locations.push_back(loc); + } + } + _write_bdev_label(cct, bdev, path + "/block", bdev_label, bdev_label_valid_locations); + } need_to_destage_allocation_file = true; } umount(); @@ -13601,52 +13645,6 @@ int BlueStore::omap_get_values( return r; } -#ifdef WITH_SEASTAR -int BlueStore::omap_get_values( - CollectionHandle &c_, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<string> &start_after, ///< [in] Keys to get - map<string, bufferlist> *output ///< [out] Returned keys and values - ) -{ - Collection *c = static_cast<Collection *>(c_.get()); - dout(15) << __func__ << " " << c->get_cid() << " oid " << oid << dendl; - if (!c->exists) - return -ENOENT; - std::shared_lock l(c->lock); - int r = 0; - OnodeRef o = c->get_onode(oid, false); - if (!o || !o->exists) { - r = -ENOENT; - goto out; - } - if (!o->onode.has_omap()) { - goto out; - } - o->flush(); - { - ObjectMap::ObjectMapIterator iter = get_omap_iterator(c_, oid); - if (!iter) { - r = -ENOENT; - goto out; - } - if (start_after) { - iter->upper_bound(*start_after); - } else { - iter->seek_to_first(); - } - for (; iter->valid(); iter->next()) { - output->insert(make_pair(iter->key(), iter->value())); - } - } - -out: - dout(10) << __func__ << " " << c->get_cid() << " oid " << oid << " = " << r - << dendl; - return r; -} -#endif - int BlueStore::omap_check_keys( CollectionHandle &c_, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -13724,6 +13722,94 @@ ObjectMap::ObjectMapIterator BlueStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(logger,c, o, it)); } +int BlueStore::omap_iterate( + CollectionHandle &c_, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) +{ + Collection *c = static_cast<Collection *>(c_.get()); + dout(10) << __func__ << " " << c->get_cid() << " " << oid << dendl; + if (!c->exists) { + return -ENOENT; + } + std::shared_lock l(c->lock); + OnodeRef o = c->get_onode(oid, false); + if (!o || !o->exists) { + dout(10) << __func__ << " " << oid << "doesn't exist" <<dendl; + return -ENOENT; + } + o->flush(); + dout(10) << __func__ << " has_omap = " << (int)o->onode.has_omap() <<dendl; + if (!o->onode.has_omap()) { + // nothing to do + return 0; + } + + KeyValueDB::Iterator it; + { + auto bounds = KeyValueDB::IteratorBounds(); + std::string lower_bound, upper_bound; + o->get_omap_key(string(), &lower_bound); + o->get_omap_tail(&upper_bound); + bounds.lower_bound = std::move(lower_bound); + bounds.upper_bound = std::move(upper_bound); + it = db->get_iterator(o->get_omap_prefix(), 0, std::move(bounds)); + } + + // seek the iterator + { + std::string key; + o->get_omap_key(start_from.seek_position, &key); + auto start = ceph::mono_clock::now(); + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it->lower_bound(key); + c->store->log_latency( + __func__, + l_bluestore_omap_lower_bound_lat, + ceph::mono_clock::now() - start, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + } else { + it->upper_bound(key); + c->store->log_latency( + __func__, + l_bluestore_omap_upper_bound_lat, + ceph::mono_clock::now() - start, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + } + } + + // iterate! + std::string tail; + o->get_omap_tail(&tail); + const std::string_view::size_type userkey_offset_in_dbkey = + o->calc_userkey_offset_in_omap_key(); + ceph::timespan next_lat_acc{0}; + while (it->valid()) { + const auto& db_key = it->raw_key_as_sv().second; + if (db_key >= tail) { + break; + } + std::string_view user_key = db_key.substr(userkey_offset_in_dbkey); + omap_iter_ret_t ret = f(user_key, it->value_as_sv()); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + ceph::time_guard<ceph::mono_clock>{next_lat_acc}; + it->next(); + } else { + ceph_abort(); + } + } + c->store->log_latency( + __func__, + l_bluestore_omap_next_lat, + next_lat_acc, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + return 0; +} + // ----------------- // write helpers diff --git a/src/os/bluestore/BlueStore.h b/src/os/bluestore/BlueStore.h index 99f8d057cf0..5549f97ffea 100644 --- a/src/os/bluestore/BlueStore.h +++ b/src/os/bluestore/BlueStore.h @@ -1457,6 +1457,7 @@ public: } void rewrite_omap_key(const std::string& old, std::string *out); + size_t calc_userkey_offset_in_omap_key() const; void decode_omap_key(const std::string& key, std::string *user_key); void finish_write(TransContext* txc, uint32_t offset, uint32_t length); @@ -1753,6 +1754,7 @@ public: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; std::string tail_key() override { return tail; } @@ -3416,15 +3418,6 @@ public: std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) override; -#ifdef WITH_SEASTAR - int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) override; -#endif - /// Filters keys into out which are defined on oid int omap_check_keys( CollectionHandle &c, ///< [in] Collection containing oid @@ -3438,6 +3431,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override { fsid = u; } diff --git a/src/os/bluestore/bluefs_types.cc b/src/os/bluestore/bluefs_types.cc index e18dd490140..fe77f7f74d8 100644 --- a/src/os/bluestore/bluefs_types.cc +++ b/src/os/bluestore/bluefs_types.cc @@ -154,7 +154,9 @@ mempool::bluefs::vector<bluefs_extent_t>::iterator bluefs_fnode_t::seek( assert(it != extents_index.begin()); --it; assert(offset >= *it); - p += it - extents_index.begin(); + uint32_t skip = it - extents_index.begin(); + ceph_assert(skip <= extents.size()); + p += skip; offset -= *it; } diff --git a/src/os/bluestore/bluefs_types.h b/src/os/bluestore/bluefs_types.h index 627118c12f8..08b3ca0cf41 100644 --- a/src/os/bluestore/bluefs_types.h +++ b/src/os/bluestore/bluefs_types.h @@ -89,6 +89,7 @@ struct bluefs_fnode_t { void recalc_allocated() { allocated = 0; extents_index.reserve(extents.size()); + extents_index.clear(); for (auto& p : extents) { extents_index.emplace_back(allocated); allocated += p.length; diff --git a/src/os/kstore/KStore.cc b/src/os/kstore/KStore.cc index 7158486ca38..a069d429155 100644 --- a/src/os/kstore/KStore.cc +++ b/src/os/kstore/KStore.cc @@ -1651,6 +1651,13 @@ bufferlist KStore::OmapIteratorImpl::value() return it->value(); } +std::string_view KStore::OmapIteratorImpl::value_as_sv() +{ + std::shared_lock l{c->lock}; + ceph_assert(it->valid()); + return it->value_as_sv(); +} + int KStore::omap_get( CollectionHandle& ch, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -1866,6 +1873,71 @@ ObjectMap::ObjectMapIterator KStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(c, o, it)); } +int KStore::omap_iterate( + CollectionHandle &ch, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f) +{ + dout(10) << __func__ << " " << ch->cid << " " << oid << dendl; + Collection *c = static_cast<Collection*>(ch.get()); + { + std::shared_lock l{c->lock}; + + OnodeRef o = c->get_onode(oid, false); + if (!o || !o->exists) { + dout(10) << __func__ << " " << oid << "doesn't exist" <<dendl; + return -ENOENT; + } + o->flush(); + dout(10) << __func__ << " header = " << o->onode.omap_head <<dendl; + + KeyValueDB::Iterator it = db->get_iterator(PREFIX_OMAP); + std::string tail; + std::string seek_key; + if (o->onode.omap_head) { + return 0; // nothing to do + } + + // acquire data depedencies for seek & iterate + get_omap_key(o->onode.omap_head, start_from.seek_position, &seek_key); + get_omap_tail(o->onode.omap_head, &tail); + + // acquire the iterator + { + it = db->get_iterator(PREFIX_OMAP); + } + + // seek the iterator + { + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it->lower_bound(seek_key); + } else { + it->upper_bound(seek_key); + } + } + + // iterate! + while (it->valid()) { + std::string user_key; + if (const auto& db_key = it->raw_key().second; db_key >= tail) { + break; + } else { + decode_omap_key(db_key, &user_key); + } + omap_iter_ret_t ret = f(user_key, it->value_as_sv()); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + it->next(); + } else { + ceph_abort(); + } + } + } + return 0; +} + // ----------------- // write helpers diff --git a/src/os/kstore/KStore.h b/src/os/kstore/KStore.h index 9a9d413c66a..06115d3cab7 100644 --- a/src/os/kstore/KStore.h +++ b/src/os/kstore/KStore.h @@ -180,6 +180,7 @@ public: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; int status() override { return 0; } @@ -553,6 +554,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override { fsid = u; } diff --git a/src/os/memstore/MemStore.cc b/src/os/memstore/MemStore.cc index 89cb09361cf..f9d3bf0d8a2 100644 --- a/src/os/memstore/MemStore.cc +++ b/src/os/memstore/MemStore.cc @@ -537,30 +537,6 @@ int MemStore::omap_get_values( return 0; } -#ifdef WITH_SEASTAR -int MemStore::omap_get_values( - CollectionHandle& ch, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) -{ - dout(10) << __func__ << " " << ch->cid << " " << oid << dendl; - Collection *c = static_cast<Collection*>(ch.get()); - ObjectRef o = c->get_object(oid); - if (!o) - return -ENOENT; - assert(start_after); - std::lock_guard lock{o->omap_mutex}; - for (auto it = o->omap.upper_bound(*start_after); - it != std::end(o->omap); - ++it) { - out->insert(*it); - } - return 0; -} -#endif - int MemStore::omap_check_keys( CollectionHandle& ch, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -622,6 +598,10 @@ public: std::lock_guard lock{o->omap_mutex}; return it->second; } + std::string_view value_as_sv() override { + std::lock_guard lock{o->omap_mutex}; + return std::string_view{it->second.c_str(), it->second.length()}; + } int status() override { return 0; } @@ -639,6 +619,48 @@ ObjectMap::ObjectMapIterator MemStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(c, o)); } +int MemStore::omap_iterate( + CollectionHandle &ch, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f) +{ + Collection *c = static_cast<Collection*>(ch.get()); + ObjectRef o = c->get_object(oid); + if (!o) { + return -ENOENT; + } + + { + std::lock_guard lock{o->omap_mutex}; + + // obtain seek the iterator + decltype(o->omap)::iterator it; + { + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it = o->omap.lower_bound(start_from.seek_position); + } else { + it = o->omap.upper_bound(start_from.seek_position); + } + } + + // iterate! + while (it != o->omap.end()) { + // potentially rectifying memcpy but who cares for memstore? + omap_iter_ret_t ret = + f(it->first, std::string_view{it->second.c_str(), it->second.length()}); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + ++it; + } else { + ceph_abort(); + } + } + } + return 0; +} + // --------------- // write operations diff --git a/src/os/memstore/MemStore.h b/src/os/memstore/MemStore.h index 2abe552891f..9621773598f 100644 --- a/src/os/memstore/MemStore.h +++ b/src/os/memstore/MemStore.h @@ -363,14 +363,6 @@ public: const std::set<std::string> &keys, ///< [in] Keys to get std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) override; -#ifdef WITH_SEASTAR - int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) override; -#endif using ObjectStore::omap_check_keys; /// Filters keys into out which are defined on oid @@ -387,6 +379,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override; uuid_d get_fsid() override; |