SERVER-32198 Get rid of CollectionShardingState::collectionIsSharded

(cherry picked from commit 80de0da37b00dbeed576b28a842cb172b6714358)

SERVER-35773 Remove references to the CatalogCache from MetadataManager

(cherry picked from commit 2aa65a86193e5d38934a4f2d6b0a8298e2432485)

SERVER-32198 Add support for an optional `vWanted` to StaleConfigInfo

(cherry picked from commit 60559a00b81293184922b3418a8e56610edf8dd9)

SERVER-36054 Remove ScopedCollectionMetadata's operator bool

(cherry picked from commit c9c340ad6e9e1f33cb001a8375c62d6b16138c74)

SERVER-36054 Remove more unused methods from CSS/MetadataManager

(cherry picked from commit ca04f5bcf9bfa73c9162b3a77225c997c6deec8a)

SERVER-36116 Get rid of CollectionShardingState::resetAll

(cherry picked from commit db1cc80d13d203b6351f5510f7756cc1c7bfc0ea)

SERVER-36054 Get rid of unused methods from CollectionShardingState

(cherry picked from commit 884d232473dca72e0872f0e540d4c3108c1e0b3d)

SERVER-36164 Decouple ScopedCollectionMetadata from MetadataManager

(cherry picked from commit d91262c4a2ed7d94923c3b1c5ff5d208aa981c73)

SERVER-29908 Move CollectionShardingState under sharding_api_d

(cherry picked from commit e491e284e8066929c8272c96a3128241ab481be8)

SERVER-29908 Remove ShardingState::appendInfo

Expose the ShardingState properties and move the appendInfo logic to be
entirely inside the 'getShardingState' function, which is its only
consumer.

(cherry picked from commit 24e411d5cd7f64c5b4da25a351529cd1873284b8)

SERVER-29908 Move 'updateConfigServerOpTimeFromMetadata' out of ShardingState

(cherry picked from commit 7a97557ce5bf74dc2b663762b7a5ffb9c958d580)

SERVER-29908 Move all runtime logic out of ShardingState

... and move it into a ShardingInitializationMongoD class, which is
responsible for driving the sharding-awareness of the node and setting
it onto ShardingState.

Also gets rid of the 'sharding' library, so there is no more library
dependency cycle.

(cherry picked from commit 200c3dc58410d8b3287a2075cc9b2ad085100e83)

SERVER-29908 Fold the 'sharding_connection_hook' library into 'sharding_initialization'

... and also remove dependency of MongoS on the replication coordinator

(cherry picked from commit fab6864f4edcae7bb304f79e601f1f62cc376a77)

1 files changed, 171 insertions, 0 deletions

diff --git a/src/mongo/db/s/collection_sharding_runtime.h b/src/mongo/db/s/collection_sharding_runtime.h
new file mode 100644
index 00000000000..0515fde5ab0
--- /dev/null
+++ b/src/mongo/db/s/collection_sharding_runtime.h
@@ -0,0 +1,171 @@
+/**
+ *    Copyright (C) 2018 MongoDB Inc.
+ *
+ *    This program is free software: you can redistribute it and/or  modify
+ *    it under the terms of the GNU Affero General Public License, version 3,
+ *    as published by the Free Software Foundation.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU Affero General Public License for more details.
+ *
+ *    You should have received a copy of the GNU Affero General Public License
+ *    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ *    As a special exception, the copyright holders give permission to link the
+ *    code of portions of this program with the OpenSSL library under certain
+ *    conditions as described in each individual source file and distribute
+ *    linked combinations including the program with the OpenSSL library. You
+ *    must comply with the GNU Affero General Public License in all respects
+ *    for all of the code used other than as permitted herein. If you modify
+ *    file(s) with this exception, you may extend this exception to your
+ *    version of the file(s), but you are not obligated to do so. If you do not
+ *    wish to do so, delete this exception statement from your version. If you
+ *    delete this exception statement from all source files in the program,
+ *    then also delete it in the license file.
+ */
+
+#pragma once
+
+#include "mongo/base/disallow_copying.h"
+#include "mongo/db/namespace_string.h"
+#include "mongo/db/s/collection_sharding_state.h"
+#include "mongo/db/s/metadata_manager.h"
+#include "mongo/util/decorable.h"
+
+namespace mongo {
+
+/**
+ * See the comments for CollectionShardingState for more information on how this class fits in the
+ * sharding architecture.
+ */
+class CollectionShardingRuntime final : public CollectionShardingState,
+                                        public Decorable<CollectionShardingRuntime> {
+    MONGO_DISALLOW_COPYING(CollectionShardingRuntime);
+
+public:
+    CollectionShardingRuntime(ServiceContext* sc,
+                              NamespaceString nss,
+                              executor::TaskExecutor* rangeDeleterExecutor);
+
+    /**
+     * Obtains the sharding state for the specified collection. If it does not exist, it will be
+     * created and will remain active until the collection is dropped or unsharded.
+     *
+     * Must be called with some lock held on the specific collection being looked up and the
+     * returned pointer should never be stored.
+     */
+    static CollectionShardingRuntime* get(OperationContext* opCtx, const NamespaceString& nss);
+
+    /**
+     * Updates the metadata based on changes received from the config server and also resolves the
+     * pending receives map in case some of these pending receives have completed or have been
+     * abandoned.  If newMetadata is null, unshard the collection.
+     *
+     * Must always be called with an exclusive collection lock.
+     */
+    void refreshMetadata(OperationContext* opCtx, std::unique_ptr<CollectionMetadata> newMetadata);
+
+    /**
+     * Marks the collection as not sharded at stepdown time so that no filtering will occur for
+     * slaveOk queries.
+     */
+    void markNotShardedAtStepdown();
+
+    /**
+     * Schedules any documents in `range` for immediate cleanup iff no running queries can depend
+     * on them, and adds the range to the list of pending ranges. Otherwise, returns a notification
+     * that yields bad status immediately.  Does not block.  Call waitStatus(opCtx) on the result
+     * to wait for the deletion to complete or fail.  After that, call waitForClean to ensure no
+     * other deletions are pending for the range.
+     */
+    using CleanupNotification = CollectionRangeDeleter::DeleteNotification;
+    CleanupNotification beginReceive(ChunkRange const& range);
+
+    /*
+     * Removes `range` from the list of pending ranges, and schedules any documents in the range for
+     * immediate cleanup. Does not block.
+     */
+    void forgetReceive(const ChunkRange& range);
+
+    /**
+     * Schedules documents in `range` for cleanup after any running queries that may depend on them
+     * have terminated. Does not block. Fails if range overlaps any current local shard chunk.
+     * Passed kDelayed, an additional delay (configured via server parameter orphanCleanupDelaySecs)
+     * is added to permit (most) dependent queries on secondaries to complete, too.
+     *
+     * Call result.waitStatus(opCtx) to wait for the deletion to complete or fail. If that succeeds,
+     * waitForClean can be called to ensure no other deletions are pending for the range. Call
+     * result.abandon(), instead of waitStatus, to ignore the outcome.
+     */
+    enum CleanWhen { kNow, kDelayed };
+    CleanupNotification cleanUpRange(ChunkRange const& range, CleanWhen when);
+
+    /**
+     * Tracks deletion of any documents within the range, returning when deletion is complete.
+     * Throws if the collection is dropped while it sleeps.
+     */
+    static Status waitForClean(OperationContext* opCtx,
+                               const NamespaceString& nss,
+                               OID const& epoch,
+                               ChunkRange orphanRange);
+
+    /**
+     * Reports whether any range still scheduled for deletion overlaps the argument range. If so,
+     * it returns a notification n such that n->get(opCtx) will wake when the newest overlapping
+     * range's deletion (possibly the one of interest) completes or fails. This should be called
+     * again after each wakeup until it returns boost::none, because there can be more than one
+     * range scheduled for deletion that overlaps its argument.
+     */
+    auto trackOrphanedDataCleanup(ChunkRange const& range) -> boost::optional<CleanupNotification>;
+
+    /**
+     * Returns a range _not_ owned by this shard that starts no lower than the specified
+     * startingFrom key value, if any, or boost::none if there is no such range.
+     */
+    boost::optional<ChunkRange> getNextOrphanRange(BSONObj const& startingFrom);
+
+    /**
+     * BSON output of the pending metadata into a BSONArray
+     */
+    void toBSONPending(BSONArrayBuilder& bb) const {
+        _metadataManager->toBSONPending(bb);
+    }
+
+
+private:
+    friend boost::optional<Date_t> CollectionRangeDeleter::cleanUpNextRange(
+        OperationContext*, NamespaceString const&, OID const&, int, CollectionRangeDeleter*);
+
+    // Namespace this state belongs to.
+    const NamespaceString _nss;
+
+    // Contains all the metadata associated with this collection.
+    std::shared_ptr<MetadataManager> _metadataManager;
+
+    ScopedCollectionMetadata _getMetadata(OperationContext* opCtx) override;
+};
+
+/**
+ * RAII-style class, which obtains a reference to the critical section for the specified collection.
+ */
+class CollectionCriticalSection {
+    MONGO_DISALLOW_COPYING(CollectionCriticalSection);
+
+public:
+    CollectionCriticalSection(OperationContext* opCtx, NamespaceString ns);
+    ~CollectionCriticalSection();
+
+    /**
+     * Enters the commit phase of the critical section and blocks reads.
+     */
+    void enterCommitPhase();
+
+private:
+    NamespaceString _nss;
+
+    OperationContext* _opCtx;
+};
+
+}  // namespace mongo