@nxtedition/rocksdb 1.0.0

package/deps/rocksdb/rocksdb/include/rocksdb/table_properties.h

@@ -0,0 +1,280 @@
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#pragma once
+
+#include <stdint.h>
+#include <map>
+#include <string>
+#include "rocksdb/status.h"
+#include "rocksdb/types.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+// -- Table Properties
+// Other than basic table properties, each table may also have the user
+// collected properties.
+// The value of the user-collected properties are encoded as raw bytes --
+// users have to interpret these values by themselves.
+// Note: To do prefix seek/scan in `UserCollectedProperties`, you can do
+// something similar to:
+//
+// UserCollectedProperties props = ...;
+// for (auto pos = props.lower_bound(prefix);
+//      pos != props.end() && pos->first.compare(0, prefix.size(), prefix) == 0;
+//      ++pos) {
+//   ...
+// }
+typedef std::map<std::string, std::string> UserCollectedProperties;
+
+// table properties' human-readable names in the property block.
+struct TablePropertiesNames {
+  static const std::string kDbId;
+  static const std::string kDbSessionId;
+  static const std::string kDbHostId;
+  static const std::string kDataSize;
+  static const std::string kIndexSize;
+  static const std::string kIndexPartitions;
+  static const std::string kTopLevelIndexSize;
+  static const std::string kIndexKeyIsUserKey;
+  static const std::string kIndexValueIsDeltaEncoded;
+  static const std::string kFilterSize;
+  static const std::string kRawKeySize;
+  static const std::string kRawValueSize;
+  static const std::string kNumDataBlocks;
+  static const std::string kNumEntries;
+  static const std::string kDeletedKeys;
+  static const std::string kMergeOperands;
+  static const std::string kNumRangeDeletions;
+  static const std::string kFormatVersion;
+  static const std::string kFixedKeyLen;
+  static const std::string kFilterPolicy;
+  static const std::string kColumnFamilyName;
+  static const std::string kColumnFamilyId;
+  static const std::string kComparator;
+  static const std::string kMergeOperator;
+  static const std::string kPrefixExtractorName;
+  static const std::string kPropertyCollectors;
+  static const std::string kCompression;
+  static const std::string kCompressionOptions;
+  static const std::string kCreationTime;
+  static const std::string kOldestKeyTime;
+  static const std::string kFileCreationTime;
+};
+
+extern const std::string kPropertiesBlock;
+extern const std::string kCompressionDictBlock;
+extern const std::string kRangeDelBlock;
+
+// `TablePropertiesCollector` provides the mechanism for users to collect
+// their own properties that they are interested in. This class is essentially
+// a collection of callback functions that will be invoked during table
+// building. It is constructed with TablePropertiesCollectorFactory. The methods
+// don't need to be thread-safe, as we will create exactly one
+// TablePropertiesCollector object per table and then call it sequentially
+class TablePropertiesCollector {
+ public:
+  virtual ~TablePropertiesCollector() {}
+
+  // DEPRECATE User defined collector should implement AddUserKey(), though
+  //           this old function still works for backward compatible reason.
+  // Add() will be called when a new key/value pair is inserted into the table.
+  // @params key    the user key that is inserted into the table.
+  // @params value  the value that is inserted into the table.
+  virtual Status Add(const Slice& /*key*/, const Slice& /*value*/) {
+    return Status::InvalidArgument(
+        "TablePropertiesCollector::Add() deprecated.");
+  }
+
+  // AddUserKey() will be called when a new key/value pair is inserted into the
+  // table.
+  // @params key    the user key that is inserted into the table.
+  // @params value  the value that is inserted into the table.
+  virtual Status AddUserKey(const Slice& key, const Slice& value,
+                            EntryType /*type*/, SequenceNumber /*seq*/,
+                            uint64_t /*file_size*/) {
+    // For backwards-compatibility.
+    return Add(key, value);
+  }
+
+  // Called after each new block is cut
+  virtual void BlockAdd(uint64_t /* blockRawBytes */,
+                        uint64_t /* blockCompressedBytesFast */,
+                        uint64_t /* blockCompressedBytesSlow */) {
+    // Nothing to do here. Callback registers can override.
+    return;
+  }
+
+  // Finish() will be called when a table has already been built and is ready
+  // for writing the properties block.
+  // @params properties  User will add their collected statistics to
+  // `properties`.
+  virtual Status Finish(UserCollectedProperties* properties) = 0;
+
+  // Return the human-readable properties, where the key is property name and
+  // the value is the human-readable form of value.
+  virtual UserCollectedProperties GetReadableProperties() const = 0;
+
+  // The name of the properties collector can be used for debugging purpose.
+  virtual const char* Name() const = 0;
+
+  // EXPERIMENTAL Return whether the output file should be further compacted
+  virtual bool NeedCompact() const { return false; }
+};
+
+// Constructs TablePropertiesCollector. Internals create a new
+// TablePropertiesCollector for each new table
+class TablePropertiesCollectorFactory {
+ public:
+  struct Context {
+    uint32_t column_family_id;
+    static const uint32_t kUnknownColumnFamily;
+  };
+
+  virtual ~TablePropertiesCollectorFactory() {}
+  // has to be thread-safe
+  virtual TablePropertiesCollector* CreateTablePropertiesCollector(
+      TablePropertiesCollectorFactory::Context context) = 0;
+
+  // The name of the properties collector can be used for debugging purpose.
+  virtual const char* Name() const = 0;
+
+  // Can be overridden by sub-classes to return the Name, followed by
+  // configuration info that will // be logged to the info log when the
+  // DB is opened
+  virtual std::string ToString() const { return Name(); }
+};
+
+// TableProperties contains a bunch of read-only properties of its associated
+// table.
+struct TableProperties {
+ public:
+  // the total size of all data blocks.
+  uint64_t data_size = 0;
+  // the size of index block.
+  uint64_t index_size = 0;
+  // Total number of index partitions if kTwoLevelIndexSearch is used
+  uint64_t index_partitions = 0;
+  // Size of the top-level index if kTwoLevelIndexSearch is used
+  uint64_t top_level_index_size = 0;
+  // Whether the index key is user key. Otherwise it includes 8 byte of sequence
+  // number added by internal key format.
+  uint64_t index_key_is_user_key = 0;
+  // Whether delta encoding is used to encode the index values.
+  uint64_t index_value_is_delta_encoded = 0;
+  // the size of filter block.
+  uint64_t filter_size = 0;
+  // total raw key size
+  uint64_t raw_key_size = 0;
+  // total raw value size
+  uint64_t raw_value_size = 0;
+  // the number of blocks in this table
+  uint64_t num_data_blocks = 0;
+  // the number of entries in this table
+  uint64_t num_entries = 0;
+  // the number of deletions in the table
+  uint64_t num_deletions = 0;
+  // the number of merge operands in the table
+  uint64_t num_merge_operands = 0;
+  // the number of range deletions in this table
+  uint64_t num_range_deletions = 0;
+  // format version, reserved for backward compatibility
+  uint64_t format_version = 0;
+  // If 0, key is variable length. Otherwise number of bytes for each key.
+  uint64_t fixed_key_len = 0;
+  // ID of column family for this SST file, corresponding to the CF identified
+  // by column_family_name.
+  uint64_t column_family_id = ROCKSDB_NAMESPACE::
+      TablePropertiesCollectorFactory::Context::kUnknownColumnFamily;
+  // Timestamp of the latest key. 0 means unknown.
+  // TODO(sagar0): Should be changed to latest_key_time ... but don't know the
+  // full implications of backward compatibility. Hence retaining for now.
+  uint64_t creation_time = 0;
+  // Timestamp of the earliest key. 0 means unknown.
+  uint64_t oldest_key_time = 0;
+  // Actual SST file creation time. 0 means unknown.
+  uint64_t file_creation_time = 0;
+
+  // DB identity
+  // db_id is an identifier generated the first time the DB is created
+  // If DB identity is unset or unassigned, `db_id` will be an empty string.
+  std::string db_id;
+
+  // DB session identity
+  // db_session_id is an identifier that gets reset every time the DB is opened
+  // If DB session identity is unset or unassigned, `db_session_id` will be an
+  // empty string.
+  std::string db_session_id;
+
+  // Location of the machine hosting the DB instance
+  // db_host_id identifies the location of the host in some form
+  // (hostname by default, but can also be any string of the user's choosing).
+  // It can potentially change whenever the DB is opened
+  std::string db_host_id;
+
+  // Name of the column family with which this SST file is associated.
+  // If column family is unknown, `column_family_name` will be an empty string.
+  std::string column_family_name;
+
+  // The name of the filter policy used in this table.
+  // If no filter policy is used, `filter_policy_name` will be an empty string.
+  std::string filter_policy_name;
+
+  // The name of the comparator used in this table.
+  std::string comparator_name;
+
+  // The name of the merge operator used in this table.
+  // If no merge operator is used, `merge_operator_name` will be "nullptr".
+  std::string merge_operator_name;
+
+  // The name of the prefix extractor used in this table
+  // If no prefix extractor is used, `prefix_extractor_name` will be "nullptr".
+  std::string prefix_extractor_name;
+
+  // The names of the property collectors factories used in this table
+  // separated by commas
+  // {collector_name[1]},{collector_name[2]},{collector_name[3]} ..
+  std::string property_collectors_names;
+
+  // The compression algo used to compress the SST files.
+  std::string compression_name;
+
+  // Compression options used to compress the SST files.
+  std::string compression_options;
+
+  // user collected properties
+  UserCollectedProperties user_collected_properties;
+  UserCollectedProperties readable_properties;
+
+  // The offset of the value of each property in the file.
+  std::map<std::string, uint64_t> properties_offsets;
+
+  // convert this object to a human readable form
+  //   @prop_delim: delimiter for each property.
+  std::string ToString(const std::string& prop_delim = "; ",
+                       const std::string& kv_delim = "=") const;
+
+  // Aggregate the numerical member variables of the specified
+  // TableProperties.
+  void Add(const TableProperties& tp);
+
+  // Subset of properties that make sense when added together
+  // between tables. Keys match field names in this class instead
+  // of using full property names.
+  std::map<std::string, uint64_t> GetAggregatablePropertiesAsMap() const;
+};
+
+// Extra properties
+// Below is a list of non-basic properties that are collected by database
+// itself. Especially some properties regarding to the internal keys (which
+// is unknown to `table`).
+//
+// DEPRECATED: these properties now belong as TableProperties members. Please
+// use TableProperties::num_deletions and TableProperties::num_merge_operands,
+// respectively.
+extern uint64_t GetDeletedKeys(const UserCollectedProperties& props);
+extern uint64_t GetMergeOperands(const UserCollectedProperties& props,
+                                 bool* property_present);
+
+}  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/include/rocksdb/thread_status.h

@@ -0,0 +1,188 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// This file defines the structures for exposing run-time status of any
+// rocksdb-related thread.  Such run-time status can be obtained via
+// GetThreadList() API.
+//
+// Note that all thread-status features are still under-development, and
+// thus APIs and class definitions might subject to change at this point.
+// Will remove this comment once the APIs have been finalized.
+
+#pragma once
+
+#include <stdint.h>
+#include <cstddef>
+#include <map>
+#include <string>
+#include <utility>
+#include <vector>
+
+#if !defined(ROCKSDB_LITE) && !defined(NROCKSDB_THREAD_STATUS) && \
+    defined(ROCKSDB_SUPPORT_THREAD_LOCAL)
+#define ROCKSDB_USING_THREAD_STATUS
+#endif
+
+namespace ROCKSDB_NAMESPACE {
+
+// TODO(yhchiang): remove this function once c++14 is available
+//                 as std::max will be able to cover this.
+// Current MS compiler does not support constexpr
+template <int A, int B>
+struct constexpr_max {
+  static const int result = (A > B) ? A : B;
+};
+
+// A structure that describes the current status of a thread.
+// The status of active threads can be fetched using
+// ROCKSDB_NAMESPACE::GetThreadList().
+struct ThreadStatus {
+  // The type of a thread.
+  enum ThreadType : int {
+    HIGH_PRIORITY = 0,  // RocksDB BG thread in high-pri thread pool
+    LOW_PRIORITY,       // RocksDB BG thread in low-pri thread pool
+    USER,               // User thread (Non-RocksDB BG thread)
+    BOTTOM_PRIORITY,    // RocksDB BG thread in bottom-pri thread pool
+    NUM_THREAD_TYPES
+  };
+
+  // The type used to refer to a thread operation.
+  // A thread operation describes high-level action of a thread.
+  // Examples include compaction and flush.
+  enum OperationType : int {
+    OP_UNKNOWN = 0,
+    OP_COMPACTION,
+    OP_FLUSH,
+    NUM_OP_TYPES
+  };
+
+  enum OperationStage : int {
+    STAGE_UNKNOWN = 0,
+    STAGE_FLUSH_RUN,
+    STAGE_FLUSH_WRITE_L0,
+    STAGE_COMPACTION_PREPARE,
+    STAGE_COMPACTION_RUN,
+    STAGE_COMPACTION_PROCESS_KV,
+    STAGE_COMPACTION_INSTALL,
+    STAGE_COMPACTION_SYNC_FILE,
+    STAGE_PICK_MEMTABLES_TO_FLUSH,
+    STAGE_MEMTABLE_ROLLBACK,
+    STAGE_MEMTABLE_INSTALL_FLUSH_RESULTS,
+    NUM_OP_STAGES
+  };
+
+  enum CompactionPropertyType : int {
+    COMPACTION_JOB_ID = 0,
+    COMPACTION_INPUT_OUTPUT_LEVEL,
+    COMPACTION_PROP_FLAGS,
+    COMPACTION_TOTAL_INPUT_BYTES,
+    COMPACTION_BYTES_READ,
+    COMPACTION_BYTES_WRITTEN,
+    NUM_COMPACTION_PROPERTIES
+  };
+
+  enum FlushPropertyType : int {
+    FLUSH_JOB_ID = 0,
+    FLUSH_BYTES_MEMTABLES,
+    FLUSH_BYTES_WRITTEN,
+    NUM_FLUSH_PROPERTIES
+  };
+
+  // The maximum number of properties of an operation.
+  // This number should be set to the biggest NUM_XXX_PROPERTIES.
+  static const int kNumOperationProperties =
+      constexpr_max<NUM_COMPACTION_PROPERTIES, NUM_FLUSH_PROPERTIES>::result;
+
+  // The type used to refer to a thread state.
+  // A state describes lower-level action of a thread
+  // such as reading / writing a file or waiting for a mutex.
+  enum StateType : int {
+    STATE_UNKNOWN = 0,
+    STATE_MUTEX_WAIT = 1,
+    NUM_STATE_TYPES
+  };
+
+  ThreadStatus(const uint64_t _id, const ThreadType _thread_type,
+               const std::string& _db_name, const std::string& _cf_name,
+               const OperationType _operation_type,
+               const uint64_t _op_elapsed_micros,
+               const OperationStage _operation_stage,
+               const uint64_t _op_props[], const StateType _state_type)
+      : thread_id(_id),
+        thread_type(_thread_type),
+        db_name(_db_name),
+        cf_name(_cf_name),
+        operation_type(_operation_type),
+        op_elapsed_micros(_op_elapsed_micros),
+        operation_stage(_operation_stage),
+        state_type(_state_type) {
+    for (int i = 0; i < kNumOperationProperties; ++i) {
+      op_properties[i] = _op_props[i];
+    }
+  }
+
+  // An unique ID for the thread.
+  const uint64_t thread_id;
+
+  // The type of the thread, it could be HIGH_PRIORITY,
+  // LOW_PRIORITY, and USER
+  const ThreadType thread_type;
+
+  // The name of the DB instance where the thread is currently
+  // involved with.  It would be set to empty string if the thread
+  // does not involve in any DB operation.
+  const std::string db_name;
+
+  // The name of the column family where the thread is currently
+  // It would be set to empty string if the thread does not involve
+  // in any column family.
+  const std::string cf_name;
+
+  // The operation (high-level action) that the current thread is involved.
+  const OperationType operation_type;
+
+  // The elapsed time of the current thread operation in microseconds.
+  const uint64_t op_elapsed_micros;
+
+  // An integer showing the current stage where the thread is involved
+  // in the current operation.
+  const OperationStage operation_stage;
+
+  // A list of properties that describe some details about the current
+  // operation.  Same field in op_properties[] might have different
+  // meanings for different operations.
+  uint64_t op_properties[kNumOperationProperties];
+
+  // The state (lower-level action) that the current thread is involved.
+  const StateType state_type;
+
+  // The followings are a set of utility functions for interpreting
+  // the information of ThreadStatus
+
+  static std::string GetThreadTypeName(ThreadType thread_type);
+
+  // Obtain the name of an operation given its type.
+  static const std::string& GetOperationName(OperationType op_type);
+
+  static const std::string MicrosToString(uint64_t op_elapsed_time);
+
+  // Obtain a human-readable string describing the specified operation stage.
+  static const std::string& GetOperationStageName(OperationStage stage);
+
+  // Obtain the name of the "i"th operation property of the
+  // specified operation.
+  static const std::string& GetOperationPropertyName(OperationType op_type,
+                                                     int i);
+
+  // Translate the "i"th property of the specified operation given
+  // a property value.
+  static std::map<std::string, uint64_t> InterpretOperationProperties(
+      OperationType op_type, const uint64_t* op_properties);
+
+  // Obtain the name of a state given its type.
+  static const std::string& GetStateName(StateType state_type);
+};
+
+}  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/include/rocksdb/threadpool.h

@@ -0,0 +1,58 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+#pragma once
+
+#include <functional>
+
+#include "rocksdb/rocksdb_namespace.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+/*
+ * ThreadPool is a component that will spawn N background threads that will
+ * be used to execute scheduled work, The number of background threads could
+ * be modified by calling SetBackgroundThreads().
+ * */
+class ThreadPool {
+ public:
+  virtual ~ThreadPool() {}
+
+  // Wait for all threads to finish.
+  // Discard those threads that did not start
+  // executing
+  virtual void JoinAllThreads() = 0;
+
+  // Set the number of background threads that will be executing the
+  // scheduled jobs.
+  virtual void SetBackgroundThreads(int num) = 0;
+  virtual int GetBackgroundThreads() = 0;
+
+  // Get the number of jobs scheduled in the ThreadPool queue.
+  virtual unsigned int GetQueueLen() const = 0;
+
+  // Waits for all jobs to complete those
+  // that already started running and those that did not
+  // start yet. This ensures that everything that was thrown
+  // on the TP runs even though
+  // we may not have specified enough threads for the amount
+  // of jobs
+  virtual void WaitForJobsAndJoinAllThreads() = 0;
+
+  // Submit a fire and forget jobs
+  // This allows to submit the same job multiple times
+  virtual void SubmitJob(const std::function<void()>&) = 0;
+  // This moves the function in for efficiency
+  virtual void SubmitJob(std::function<void()>&&) = 0;
+};
+
+// NewThreadPool() is a function that could be used to create a ThreadPool
+// with `num_threads` background threads.
+extern ThreadPool* NewThreadPool(int num_threads);
+
+}  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/include/rocksdb/trace_reader_writer.h

@@ -0,0 +1,48 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include "rocksdb/env.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+// Allow custom implementations of TraceWriter and TraceReader.
+// By default, RocksDB provides a way to capture the traces to a file using the
+// factory NewFileTraceWriter(). But users could also choose to export traces to
+// any other system by providing custom implementations of TraceWriter and
+// TraceReader.
+
+// TraceWriter allows exporting RocksDB traces to any system, one operation at
+// a time.
+class TraceWriter {
+ public:
+  TraceWriter() {}
+  virtual ~TraceWriter() {}
+
+  virtual Status Write(const Slice& data) = 0;
+  virtual Status Close() = 0;
+  virtual uint64_t GetFileSize() = 0;
+};
+
+// TraceReader allows reading RocksDB traces from any system, one operation at
+// a time. A RocksDB Replayer could depend on this to replay opertions.
+class TraceReader {
+ public:
+  TraceReader() {}
+  virtual ~TraceReader() {}
+
+  virtual Status Read(std::string* data) = 0;
+  virtual Status Close() = 0;
+};
+
+// Factory methods to read/write traces from/to a file.
+Status NewFileTraceWriter(Env* env, const EnvOptions& env_options,
+                          const std::string& trace_filename,
+                          std::unique_ptr<TraceWriter>* trace_writer);
+Status NewFileTraceReader(Env* env, const EnvOptions& env_options,
+                          const std::string& trace_filename,
+                          std::unique_ptr<TraceReader>* trace_reader);
+}  // namespace ROCKSDB_NAMESPACE

package/deps/rocksdb/rocksdb/include/rocksdb/transaction_log.h

@@ -0,0 +1,121 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <memory>
+#include <vector>
+#include "rocksdb/status.h"
+#include "rocksdb/types.h"
+#include "rocksdb/write_batch.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class LogFile;
+typedef std::vector<std::unique_ptr<LogFile>> VectorLogPtr;
+
+enum WalFileType {
+  /* Indicates that WAL file is in archive directory. WAL files are moved from
+   * the main db directory to archive directory once they are not live and stay
+   * there until cleaned up. Files are cleaned depending on archive size
+   * (Options::WAL_size_limit_MB) and time since last cleaning
+   * (Options::WAL_ttl_seconds).
+   */
+  kArchivedLogFile = 0,
+
+  /* Indicates that WAL file is live and resides in the main db directory */
+  kAliveLogFile = 1
+};
+
+class LogFile {
+ public:
+  LogFile() {}
+  virtual ~LogFile() {}
+
+  // Returns log file's pathname relative to the main db dir
+  // Eg. For a live-log-file = /000003.log
+  //     For an archived-log-file = /archive/000003.log
+  virtual std::string PathName() const = 0;
+
+  // Primary identifier for log file.
+  // This is directly proportional to creation time of the log file
+  virtual uint64_t LogNumber() const = 0;
+
+  // Log file can be either alive or archived
+  virtual WalFileType Type() const = 0;
+
+  // Starting sequence number of writebatch written in this log file
+  virtual SequenceNumber StartSequence() const = 0;
+
+  // Size of log file on disk in Bytes
+  virtual uint64_t SizeFileBytes() const = 0;
+};
+
+struct BatchResult {
+  SequenceNumber sequence = 0;
+  std::unique_ptr<WriteBatch> writeBatchPtr;
+
+  // Add empty __ctor and __dtor for the rule of five
+  // However, preserve the original semantics and prohibit copying
+  // as the std::unique_ptr member does not copy.
+  BatchResult() {}
+
+  ~BatchResult() {}
+
+  BatchResult(const BatchResult&) = delete;
+
+  BatchResult& operator=(const BatchResult&) = delete;
+
+  BatchResult(BatchResult&& bResult)
+      : sequence(std::move(bResult.sequence)),
+        writeBatchPtr(std::move(bResult.writeBatchPtr)) {}
+
+  BatchResult& operator=(BatchResult&& bResult) {
+    sequence = std::move(bResult.sequence);
+    writeBatchPtr = std::move(bResult.writeBatchPtr);
+    return *this;
+  }
+};
+
+// A TransactionLogIterator is used to iterate over the transactions in a db.
+// One run of the iterator is continuous, i.e. the iterator will stop at the
+// beginning of any gap in sequences
+class TransactionLogIterator {
+ public:
+  TransactionLogIterator() {}
+  virtual ~TransactionLogIterator() {}
+
+  // An iterator is either positioned at a WriteBatch or not valid.
+  // This method returns true if the iterator is valid.
+  // Can read data from a valid iterator.
+  virtual bool Valid() = 0;
+
+  // Moves the iterator to the next WriteBatch.
+  // REQUIRES: Valid() to be true.
+  virtual void Next() = 0;
+
+  // Returns ok if the iterator is valid.
+  // Returns the Error when something has gone wrong.
+  virtual Status status() = 0;
+
+  // If valid return's the current write_batch and the sequence number of the
+  // earliest transaction contained in the batch.
+  // ONLY use if Valid() is true and status() is OK.
+  virtual BatchResult GetBatch() = 0;
+
+  // The read options for TransactionLogIterator.
+  struct ReadOptions {
+    // If true, all data read from underlying storage will be
+    // verified against corresponding checksums.
+    // Default: true
+    bool verify_checksums_;
+
+    ReadOptions() : verify_checksums_(true) {}
+
+    explicit ReadOptions(bool verify_checksums)
+        : verify_checksums_(verify_checksums) {}
+  };
+};
+}  // namespace ROCKSDB_NAMESPACE