summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--src/common/ceph_time.h17
-rw-r--r--src/crimson/os/alienstore/alien_store.cc17
-rw-r--r--src/kv/KeyValueDB.h22
-rw-r--r--src/kv/RocksDBStore.cc92
-rw-r--r--src/kv/RocksDBStore.h4
-rw-r--r--src/os/DBObjectMap.cc5
-rw-r--r--src/os/DBObjectMap.h2
-rw-r--r--src/os/ObjectStore.h52
-rw-r--r--src/os/bluestore/BlueStore.cc151
-rw-r--r--src/os/bluestore/BlueStore.h18
-rw-r--r--src/os/kstore/KStore.cc72
-rw-r--r--src/os/kstore/KStore.h8
-rw-r--r--src/os/memstore/MemStore.cc70
-rw-r--r--src/os/memstore/MemStore.h15
-rw-r--r--src/osd/PrimaryLogPG.cc49
-rw-r--r--src/test/ObjectMap/KeyValueDBMemory.cc21
-rw-r--r--src/test/objectstore/ObjectStoreImitator.h10
17 files changed, 502 insertions, 123 deletions
diff --git a/src/common/ceph_time.h b/src/common/ceph_time.h
index 01feff4c063..0b05be5372e 100644
--- a/src/common/ceph_time.h
+++ b/src/common/ceph_time.h
@@ -342,6 +342,23 @@ public:
}
};
+// Please note time_guard is not thread safety -- multiple threads
+// updating same diff_accumulator can corrupt it.
+template <class ClockT = mono_clock>
+class time_guard {
+ const typename ClockT::time_point start;
+ timespan& diff_accumulator;
+
+public:
+ time_guard(timespan& diff_accumulator)
+ : start(ClockT::now()),
+ diff_accumulator(diff_accumulator) {
+ }
+ ~time_guard() {
+ diff_accumulator += ClockT::now() - start;
+ }
+};
+
namespace time_detail {
// So that our subtractions produce negative spans rather than
// arithmetic underflow.
diff --git a/src/crimson/os/alienstore/alien_store.cc b/src/crimson/os/alienstore/alien_store.cc
index a9c69f4660e..db6decd84f9 100644
--- a/src/crimson/os/alienstore/alien_store.cc
+++ b/src/crimson/os/alienstore/alien_store.cc
@@ -435,8 +435,21 @@ auto AlienStore::omap_get_values(CollectionRef ch,
return do_with_op_gate(omap_values_t{}, [=, this] (auto &values) {
return tp->submit(ch->get_cid().hash_to_shard(tp->size()), [=, this, &values] {
auto c = static_cast<AlienCollection*>(ch.get());
- return store->omap_get_values(c->collection, oid, start,
- reinterpret_cast<map<string, bufferlist>*>(&values));
+ return store->omap_iterate(
+ c->collection, oid,
+ ObjectStore::omap_iter_seek_t{
+ .seek_position = start.value_or(std::string{}),
+ // FIXME: classical OSDs begins iteration from LOWER_BOUND
+ // (or UPPER_BOUND if filter_prefix > start). However, these
+ // bits are not implemented yet
+ .seek_type = ObjectStore::omap_iter_seek_t::UPPER_BOUND
+ },
+ [&values]
+ (std::string_view key, std::string_view value) mutable {
+ values[std::string{key}].append(value);
+ // FIXME: there is limit on number of entries yet
+ return ObjectStore::omap_iter_ret_t::NEXT;
+ });
}).then([&values] (int r)
-> read_errorator::future<std::tuple<bool, omap_values_t>> {
if (r == -ENOENT) {
diff --git a/src/kv/KeyValueDB.h b/src/kv/KeyValueDB.h
index 858742d511e..d926840180e 100644
--- a/src/kv/KeyValueDB.h
+++ b/src/kv/KeyValueDB.h
@@ -9,6 +9,7 @@
#include <map>
#include <optional>
#include <string>
+#include <string_view>
#include <boost/scoped_ptr.hpp>
#include "include/encoding.h"
#include "common/Formatter.h"
@@ -211,6 +212,10 @@ public:
return "";
}
virtual ceph::buffer::list value() = 0;
+ // When valid() returns true, value returned as string-view
+ // is guaranteed to be valid until iterator is moved to another
+ // position; that is until call to next() / seek_to_first() / etc.
+ virtual std::string_view value_as_sv() = 0;
virtual int status() = 0;
virtual ~SimplestIteratorImpl() {}
};
@@ -220,7 +225,12 @@ public:
virtual ~IteratorImpl() {}
virtual int seek_to_last() = 0;
virtual int prev() = 0;
+ // When valid() returns true, key returned as string-view
+ // is guaranteed to be valid until iterator is moved to another
+ // position; that is until call to next() / seek_to_first() / etc.
+ virtual std::string_view key_as_sv() = 0;
virtual std::pair<std::string, std::string> raw_key() = 0;
+ virtual std::pair<std::string_view, std::string_view> raw_key_as_sv() = 0;
virtual ceph::buffer::ptr value_as_ptr() {
ceph::buffer::list bl = value();
if (bl.length() == 1) {
@@ -247,7 +257,9 @@ public:
virtual int next() = 0;
virtual int prev() = 0;
virtual std::string key() = 0;
+ virtual std::string_view key_as_sv() = 0;
virtual std::pair<std::string,std::string> raw_key() = 0;
+ virtual std::pair<std::string_view, std::string_view> raw_key_as_sv() = 0;
virtual bool raw_key_is_prefixed(const std::string &prefix) = 0;
virtual ceph::buffer::list value() = 0;
virtual ceph::buffer::ptr value_as_ptr() {
@@ -258,6 +270,7 @@ public:
return ceph::buffer::ptr();
}
}
+ virtual std::string_view value_as_sv() = 0;
virtual int status() = 0;
virtual size_t key_size() {
return 0;
@@ -315,15 +328,24 @@ private:
std::string key() override {
return generic_iter->key();
}
+ std::string_view key_as_sv() override {
+ return generic_iter->key_as_sv();
+ }
std::pair<std::string, std::string> raw_key() override {
return generic_iter->raw_key();
}
+ std::pair<std::string_view, std::string_view> raw_key_as_sv() override {
+ return generic_iter->raw_key_as_sv();
+ }
ceph::buffer::list value() override {
return generic_iter->value();
}
ceph::buffer::ptr value_as_ptr() override {
return generic_iter->value_as_ptr();
}
+ std::string_view value_as_sv() override {
+ return generic_iter->value_as_sv();
+ }
int status() override {
return generic_iter->status();
}
diff --git a/src/kv/RocksDBStore.cc b/src/kv/RocksDBStore.cc
index ca63ea06484..51d224b67c0 100644
--- a/src/kv/RocksDBStore.cc
+++ b/src/kv/RocksDBStore.cc
@@ -6,6 +6,7 @@
#include <memory>
#include <set>
#include <string>
+#include <string_view>
#include <errno.h>
#include <unistd.h>
#include <sys/types.h>
@@ -47,6 +48,7 @@ using std::ostream;
using std::pair;
using std::set;
using std::string;
+using std::string_view;
using std::unique_ptr;
using std::vector;
@@ -1992,7 +1994,7 @@ int RocksDBStore::split_key(rocksdb::Slice in, string *prefix, string *key)
// Find separator inside Slice
char* separator = (char*) memchr(in.data(), 0, in.size());
- if (separator == NULL)
+ if (separator == nullptr)
return -EINVAL;
prefix_len = size_t(separator - in.data());
if (prefix_len >= in.size())
@@ -2006,6 +2008,27 @@ int RocksDBStore::split_key(rocksdb::Slice in, string *prefix, string *key)
return 0;
}
+// TODO: deduplicate the code, preferrably by removing the string variant
+int RocksDBStore::split_key(rocksdb::Slice in, string_view *prefix, string_view *key)
+{
+ size_t prefix_len = 0;
+
+ // Find separator inside Slice
+ char* separator = (char*) memchr(in.data(), 0, in.size());
+ if (separator == nullptr)
+ return -EINVAL;
+ prefix_len = size_t(separator - in.data());
+ if (prefix_len >= in.size())
+ return -EINVAL;
+
+ // Fetch prefix and/or key directly from Slice
+ if (prefix)
+ *prefix = string_view(in.data(), prefix_len);
+ if (key)
+ *key = string_view(separator + 1, in.size() - prefix_len - 1);
+ return 0;
+}
+
void RocksDBStore::compact()
{
dout(2) << __func__ << " starting" << dendl;
@@ -2226,7 +2249,13 @@ int RocksDBStore::RocksDBWholeSpaceIteratorImpl::prev()
string RocksDBStore::RocksDBWholeSpaceIteratorImpl::key()
{
string out_key;
- split_key(dbiter->key(), 0, &out_key);
+ split_key(dbiter->key(), nullptr, &out_key);
+ return out_key;
+}
+string_view RocksDBStore::RocksDBWholeSpaceIteratorImpl::key_as_sv()
+{
+ string_view out_key;
+ split_key(dbiter->key(), nullptr, &out_key);
return out_key;
}
pair<string,string> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key()
@@ -2235,6 +2264,12 @@ pair<string,string> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key()
split_key(dbiter->key(), &prefix, &key);
return make_pair(prefix, key);
}
+pair<string_view,string_view> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key_as_sv()
+{
+ string_view prefix, key;
+ split_key(dbiter->key(), &prefix, &key);
+ return make_pair(prefix, key);
+}
bool RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key_is_prefixed(const string &prefix) {
// Look for "prefix\0" right in rocksb::Slice
@@ -2267,6 +2302,12 @@ bufferptr RocksDBStore::RocksDBWholeSpaceIteratorImpl::value_as_ptr()
return bufferptr(val.data(), val.size());
}
+std::string_view RocksDBStore::RocksDBWholeSpaceIteratorImpl::value_as_sv()
+{
+ rocksdb::Slice val = dbiter->value();
+ return std::string_view{val.data(), val.size()};
+}
+
int RocksDBStore::RocksDBWholeSpaceIteratorImpl::status()
{
return dbiter->status().ok() ? 0 : -1;
@@ -2348,9 +2389,15 @@ public:
string key() override {
return dbiter->key().ToString();
}
+ string_view key_as_sv() override {
+ return dbiter->key().ToStringView();
+ }
std::pair<std::string, std::string> raw_key() override {
return make_pair(prefix, key());
}
+ std::pair<std::string_view, std::string_view> raw_key_as_sv() override {
+ return make_pair(prefix, dbiter->key().ToStringView());
+ }
bufferlist value() override {
return to_bufferlist(dbiter->value());
}
@@ -2358,6 +2405,10 @@ public:
rocksdb::Slice val = dbiter->value();
return bufferptr(val.data(), val.size());
}
+ std::string_view value_as_sv() override {
+ rocksdb::Slice val = dbiter->value();
+ return std::string_view{val.data(), val.size()};
+ }
int status() override {
return dbiter->status().ok() ? 0 : -1;
}
@@ -2668,6 +2719,15 @@ public:
}
}
+ std::string_view key_as_sv() override
+ {
+ if (smaller == on_main) {
+ return main->key_as_sv();
+ } else {
+ return current_shard->second->key_as_sv();
+ }
+ }
+
std::pair<std::string,std::string> raw_key() override
{
if (smaller == on_main) {
@@ -2677,6 +2737,15 @@ public:
}
}
+ std::pair<std::string_view,std::string_view> raw_key_as_sv() override
+ {
+ if (smaller == on_main) {
+ return main->raw_key_as_sv();
+ } else {
+ return { current_shard->first, current_shard->second->key_as_sv() };
+ }
+ }
+
bool raw_key_is_prefixed(const std::string &prefix) override
{
if (smaller == on_main) {
@@ -2695,6 +2764,15 @@ public:
}
}
+ std::string_view value_as_sv() override
+ {
+ if (smaller == on_main) {
+ return main->value_as_sv();
+ } else {
+ return current_shard->second->value_as_sv();
+ }
+ }
+
int status() override
{
//because we already had to inspect key, it must be ok
@@ -3017,9 +3095,15 @@ public:
string key() override {
return iters[0]->key().ToString();
}
+ string_view key_as_sv() override {
+ return iters[0]->key().ToStringView();
+ }
std::pair<std::string, std::string> raw_key() override {
return make_pair(prefix, key());
}
+ std::pair<std::string_view, std::string_view> raw_key_as_sv() override {
+ return make_pair(prefix, iters[0]->key().ToStringView());
+ }
bufferlist value() override {
return to_bufferlist(iters[0]->value());
}
@@ -3027,6 +3111,10 @@ public:
rocksdb::Slice val = iters[0]->value();
return bufferptr(val.data(), val.size());
}
+ std::string_view value_as_sv() override {
+ rocksdb::Slice val = iters[0]->value();
+ return std::string_view{val.data(), val.size()};
+ }
int status() override {
return iters[0]->status().ok() ? 0 : -1;
}
diff --git a/src/kv/RocksDBStore.h b/src/kv/RocksDBStore.h
index 477b209854c..50b91be2bf6 100644
--- a/src/kv/RocksDBStore.h
+++ b/src/kv/RocksDBStore.h
@@ -386,10 +386,13 @@ public:
int next() override;
int prev() override;
std::string key() override;
+ std::string_view key_as_sv() override;
std::pair<std::string,std::string> raw_key() override;
+ std::pair<std::string_view,std::string_view> raw_key_as_sv() override;
bool raw_key_is_prefixed(const std::string &prefix) override;
ceph::bufferlist value() override;
ceph::bufferptr value_as_ptr() override;
+ std::string_view value_as_sv() override;
int status() override;
size_t key_size() override;
size_t value_size() override;
@@ -419,6 +422,7 @@ public:
}
static int split_key(rocksdb::Slice in, std::string *prefix, std::string *key);
+ static int split_key(rocksdb::Slice in, std::string_view *prefix, std::string_view *key);
static std::string past_prefix(const std::string &prefix);
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/BlueStore.cc b/src/os/bluestore/BlueStore.cc
index a024a0c2105..5d7c8ef07d5 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) {
@@ -5654,6 +5660,13 @@ 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();
+}
+
// =====================================
@@ -13601,52 +13614,6 @@ 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 +13691,94 @@ 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/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;
diff --git a/src/osd/PrimaryLogPG.cc b/src/osd/PrimaryLogPG.cc
index 75484edb75d..3324ba9dc91 100644
--- a/src/osd/PrimaryLogPG.cc
+++ b/src/osd/PrimaryLogPG.cc
@@ -7786,27 +7786,34 @@ int PrimaryLogPG::do_osd_ops(OpContext *ctx, vector<OSDOp>& ops)
bool truncated = false;
bufferlist bl;
if (oi.is_omap()) {
- ObjectMap::ObjectMapIterator iter = osd->store->get_omap_iterator(
- ch, ghobject_t(soid)
- );
- if (!iter) {
- result = -ENOENT;
- goto fail;
- }
- iter->upper_bound(start_after);
- if (filter_prefix > start_after) iter->lower_bound(filter_prefix);
- for (num = 0;
- iter->valid() &&
- iter->key().substr(0, filter_prefix.size()) == filter_prefix;
- ++num, iter->next()) {
- dout(20) << "Found key " << iter->key() << dendl;
- if (num >= max_return ||
- bl.length() >= cct->_conf->osd_max_omap_bytes_per_request) {
- truncated = true;
- break;
- }
- encode(iter->key(), bl);
- encode(iter->value(), bl);
+ using omap_iter_seek_t = ObjectStore::omap_iter_seek_t;
+ result = osd->store->omap_iterate(
+ ch, ghobject_t(soid),
+ // try to seek as many keys-at-once as possible for the sake of performance.
+ // note complexity should be logarithmic, so seek(n/2) + seek(n/2) is worse
+ // than just seek(n).
+ ObjectStore::omap_iter_seek_t{
+ .seek_position = std::max(start_after, filter_prefix),
+ .seek_type = filter_prefix > start_after ? omap_iter_seek_t::LOWER_BOUND
+ : omap_iter_seek_t::UPPER_BOUND
+ },
+ [&bl, &truncated, &filter_prefix, &num, max_return,
+ max_bytes=cct->_conf->osd_max_omap_bytes_per_request]
+ (std::string_view key, std::string_view value) mutable {
+ if (key.substr(0, filter_prefix.size()) != filter_prefix) {
+ return ObjectStore::omap_iter_ret_t::STOP;
+ }
+ if (num >= max_return || bl.length() >= max_bytes) {
+ truncated = true;
+ return ObjectStore::omap_iter_ret_t::STOP;
+ }
+ encode(key, bl);
+ encode(value, bl);
+ ++num;
+ return ObjectStore::omap_iter_ret_t::NEXT;
+ });
+ if (result < 0) {
+ goto fail;
}
} // else return empty out_set
encode(num, osd_op.outdata);
diff --git a/src/test/ObjectMap/KeyValueDBMemory.cc b/src/test/ObjectMap/KeyValueDBMemory.cc
index 234e963397e..cfe25930d6a 100644
--- a/src/test/ObjectMap/KeyValueDBMemory.cc
+++ b/src/test/ObjectMap/KeyValueDBMemory.cc
@@ -132,12 +132,26 @@ public:
return "";
}
+ string_view key_as_sv() override {
+ if (valid())
+ return (*it).first.second;
+ else
+ return "";
+ }
+
pair<string,string> raw_key() override {
if (valid())
return (*it).first;
else
return make_pair("", "");
}
+
+ pair<string_view,string_view> raw_key_as_sv() override {
+ if (valid())
+ return (*it).first;
+ else
+ return make_pair("", "");
+ }
bool raw_key_is_prefixed(const string &prefix) override {
return prefix == (*it).first.first;
@@ -150,6 +164,13 @@ public:
return bufferlist();
}
+ std::string_view value_as_sv() override {
+ if (valid())
+ return std::string_view{it->second.c_str(), it->second.length()};
+ else
+ return std::string_view();
+ }
+
int status() override {
return 0;
}
diff --git a/src/test/objectstore/ObjectStoreImitator.h b/src/test/objectstore/ObjectStoreImitator.h
index d71d7f2fe58..875f9041b83 100644
--- a/src/test/objectstore/ObjectStoreImitator.h
+++ b/src/test/objectstore/ObjectStoreImitator.h
@@ -347,6 +347,16 @@ public:
) override {
return {};
}
+
+ int omap_iterate(CollectionHandle &c, ///< [in] collection
+ const ghobject_t &oid, ///< [in] object
+ /// [in] where the iterator should point to at the beginning
+ omap_iter_seek_t start_from,
+ std::function<omap_iter_ret_t(std::string_view, std::string_view)> f
+ ) override {
+ return 0;
+ }
+
void set_fsid(uuid_d u) override {}
uuid_d get_fsid() override { return {}; }
uint64_t estimate_objects_overhead(uint64_t num_objects) override {
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-19 01:28:35 +0100