leveldb 0.0.1

data/ext/leveldb/db/db_impl.h

@@ -0,0 +1,203 @@
+// 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.
+
+#ifndef STORAGE_LEVELDB_DB_DB_IMPL_H_
+#define STORAGE_LEVELDB_DB_DB_IMPL_H_
+
+#include <deque>
+#include <set>
+#include "db/dbformat.h"
+#include "db/log_writer.h"
+#include "db/snapshot.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+#include "port/port.h"
+#include "port/thread_annotations.h"
+
+namespace leveldb {
+
+class MemTable;
+class TableCache;
+class Version;
+class VersionEdit;
+class VersionSet;
+
+class DBImpl : public DB {
+ public:
+  DBImpl(const Options& options, const std::string& dbname);
+  virtual ~DBImpl();
+
+  // Implementations of the DB interface
+  virtual Status Put(const WriteOptions&, const Slice& key, const Slice& value);
+  virtual Status Delete(const WriteOptions&, const Slice& key);
+  virtual Status Write(const WriteOptions& options, WriteBatch* updates);
+  virtual Status Get(const ReadOptions& options,
+                     const Slice& key,
+                     std::string* value);
+  virtual Iterator* NewIterator(const ReadOptions&);
+  virtual const Snapshot* GetSnapshot();
+  virtual void ReleaseSnapshot(const Snapshot* snapshot);
+  virtual bool GetProperty(const Slice& property, std::string* value);
+  virtual void GetApproximateSizes(const Range* range, int n, uint64_t* sizes);
+  virtual void CompactRange(const Slice* begin, const Slice* end);
+
+  // Extra methods (for testing) that are not in the public DB interface
+
+  // Compact any files in the named level that overlap [*begin,*end]
+  void TEST_CompactRange(int level, const Slice* begin, const Slice* end);
+
+  // Force current memtable contents to be compacted.
+  Status TEST_CompactMemTable();
+
+  // Return an internal iterator over the current state of the database.
+  // The keys of this iterator are internal keys (see format.h).
+  // The returned iterator should be deleted when no longer needed.
+  Iterator* TEST_NewInternalIterator();
+
+  // Return the maximum overlapping data (in bytes) at next level for any
+  // file at a level >= 1.
+  int64_t TEST_MaxNextLevelOverlappingBytes();
+
+ private:
+  friend class DB;
+  struct CompactionState;
+  struct Writer;
+
+  Iterator* NewInternalIterator(const ReadOptions&,
+                                SequenceNumber* latest_snapshot);
+
+  Status NewDB();
+
+  // Recover the descriptor from persistent storage.  May do a significant
+  // amount of work to recover recently logged updates.  Any changes to
+  // be made to the descriptor are added to *edit.
+  Status Recover(VersionEdit* edit) EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  void MaybeIgnoreError(Status* s) const;
+
+  // Delete any unneeded files and stale in-memory entries.
+  void DeleteObsoleteFiles();
+
+  // Compact the in-memory write buffer to disk.  Switches to a new
+  // log-file/memtable and writes a new descriptor iff successful.
+  Status CompactMemTable()
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status RecoverLogFile(uint64_t log_number,
+                        VersionEdit* edit,
+                        SequenceNumber* max_sequence)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status WriteLevel0Table(MemTable* mem, VersionEdit* edit, Version* base)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status MakeRoomForWrite(bool force /* compact even if there is room? */)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  WriteBatch* BuildBatchGroup(Writer** last_writer);
+
+  void MaybeScheduleCompaction() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  static void BGWork(void* db);
+  void BackgroundCall();
+  Status BackgroundCompaction() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  void CleanupCompaction(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  Status DoCompactionWork(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status OpenCompactionOutputFile(CompactionState* compact);
+  Status FinishCompactionOutputFile(CompactionState* compact, Iterator* input);
+  Status InstallCompactionResults(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  // Constant after construction
+  Env* const env_;
+  const InternalKeyComparator internal_comparator_;
+  const InternalFilterPolicy internal_filter_policy_;
+  const Options options_;  // options_.comparator == &internal_comparator_
+  bool owns_info_log_;
+  bool owns_cache_;
+  const std::string dbname_;
+
+  // table_cache_ provides its own synchronization
+  TableCache* table_cache_;
+
+  // Lock over the persistent DB state.  Non-NULL iff successfully acquired.
+  FileLock* db_lock_;
+
+  // State below is protected by mutex_
+  port::Mutex mutex_;
+  port::AtomicPointer shutting_down_;
+  port::CondVar bg_cv_;          // Signalled when background work finishes
+  MemTable* mem_;
+  MemTable* imm_;                // Memtable being compacted
+  port::AtomicPointer has_imm_;  // So bg thread can detect non-NULL imm_
+  WritableFile* logfile_;
+  uint64_t logfile_number_;
+  log::Writer* log_;
+
+  // Queue of writers.
+  std::deque<Writer*> writers_;
+  WriteBatch* tmp_batch_;
+
+  SnapshotList snapshots_;
+
+  // Set of table files to protect from deletion because they are
+  // part of ongoing compactions.
+  std::set<uint64_t> pending_outputs_;
+
+  // Has a background compaction been scheduled or is running?
+  bool bg_compaction_scheduled_;
+
+  // Information for a manual compaction
+  struct ManualCompaction {
+    int level;
+    bool done;
+    const InternalKey* begin;   // NULL means beginning of key range
+    const InternalKey* end;     // NULL means end of key range
+    InternalKey tmp_storage;    // Used to keep track of compaction progress
+  };
+  ManualCompaction* manual_compaction_;
+
+  VersionSet* versions_;
+
+  // Have we encountered a background error in paranoid mode?
+  Status bg_error_;
+  int consecutive_compaction_errors_;
+
+  // Per level compaction stats.  stats_[level] stores the stats for
+  // compactions that produced data for the specified "level".
+  struct CompactionStats {
+    int64_t micros;
+    int64_t bytes_read;
+    int64_t bytes_written;
+
+    CompactionStats() : micros(0), bytes_read(0), bytes_written(0) { }
+
+    void Add(const CompactionStats& c) {
+      this->micros += c.micros;
+      this->bytes_read += c.bytes_read;
+      this->bytes_written += c.bytes_written;
+    }
+  };
+  CompactionStats stats_[config::kNumLevels];
+
+  // No copying allowed
+  DBImpl(const DBImpl&);
+  void operator=(const DBImpl&);
+
+  const Comparator* user_comparator() const {
+    return internal_comparator_.user_comparator();
+  }
+};
+
+// Sanitize db options.  The caller should delete result.info_log if
+// it is not equal to src.info_log.
+extern Options SanitizeOptions(const std::string& db,
+                               const InternalKeyComparator* icmp,
+                               const InternalFilterPolicy* ipolicy,
+                               const Options& src);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_DB_IMPL_H_

data/ext/leveldb/db/db_iter.cc

@@ -0,0 +1,299 @@
+// 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.
+
+#include "db/db_iter.h"
+
+#include "db/filename.h"
+#include "db/dbformat.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+#include "port/port.h"
+#include "util/logging.h"
+#include "util/mutexlock.h"
+
+namespace leveldb {
+
+#if 0
+static void DumpInternalIter(Iterator* iter) {
+  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+    ParsedInternalKey k;
+    if (!ParseInternalKey(iter->key(), &k)) {
+      fprintf(stderr, "Corrupt '%s'\n", EscapeString(iter->key()).c_str());
+    } else {
+      fprintf(stderr, "@ '%s'\n", k.DebugString().c_str());
+    }
+  }
+}
+#endif
+
+namespace {
+
+// Memtables and sstables that make the DB representation contain
+// (userkey,seq,type) => uservalue entries.  DBIter
+// combines multiple entries for the same userkey found in the DB
+// representation into a single entry while accounting for sequence
+// numbers, deletion markers, overwrites, etc.
+class DBIter: public Iterator {
+ public:
+  // Which direction is the iterator currently moving?
+  // (1) When moving forward, the internal iterator is positioned at
+  //     the exact entry that yields this->key(), this->value()
+  // (2) When moving backwards, the internal iterator is positioned
+  //     just before all entries whose user key == this->key().
+  enum Direction {
+    kForward,
+    kReverse
+  };
+
+  DBIter(const std::string* dbname, Env* env,
+         const Comparator* cmp, Iterator* iter, SequenceNumber s)
+      : dbname_(dbname),
+        env_(env),
+        user_comparator_(cmp),
+        iter_(iter),
+        sequence_(s),
+        direction_(kForward),
+        valid_(false) {
+  }
+  virtual ~DBIter() {
+    delete iter_;
+  }
+  virtual bool Valid() const { return valid_; }
+  virtual Slice key() const {
+    assert(valid_);
+    return (direction_ == kForward) ? ExtractUserKey(iter_->key()) : saved_key_;
+  }
+  virtual Slice value() const {
+    assert(valid_);
+    return (direction_ == kForward) ? iter_->value() : saved_value_;
+  }
+  virtual Status status() const {
+    if (status_.ok()) {
+      return iter_->status();
+    } else {
+      return status_;
+    }
+  }
+
+  virtual void Next();
+  virtual void Prev();
+  virtual void Seek(const Slice& target);
+  virtual void SeekToFirst();
+  virtual void SeekToLast();
+
+ private:
+  void FindNextUserEntry(bool skipping, std::string* skip);
+  void FindPrevUserEntry();
+  bool ParseKey(ParsedInternalKey* key);
+
+  inline void SaveKey(const Slice& k, std::string* dst) {
+    dst->assign(k.data(), k.size());
+  }
+
+  inline void ClearSavedValue() {
+    if (saved_value_.capacity() > 1048576) {
+      std::string empty;
+      swap(empty, saved_value_);
+    } else {
+      saved_value_.clear();
+    }
+  }
+
+  const std::string* const dbname_;
+  Env* const env_;
+  const Comparator* const user_comparator_;
+  Iterator* const iter_;
+  SequenceNumber const sequence_;
+
+  Status status_;
+  std::string saved_key_;     // == current key when direction_==kReverse
+  std::string saved_value_;   // == current raw value when direction_==kReverse
+  Direction direction_;
+  bool valid_;
+
+  // No copying allowed
+  DBIter(const DBIter&);
+  void operator=(const DBIter&);
+};
+
+inline bool DBIter::ParseKey(ParsedInternalKey* ikey) {
+  if (!ParseInternalKey(iter_->key(), ikey)) {
+    status_ = Status::Corruption("corrupted internal key in DBIter");
+    return false;
+  } else {
+    return true;
+  }
+}
+
+void DBIter::Next() {
+  assert(valid_);
+
+  if (direction_ == kReverse) {  // Switch directions?
+    direction_ = kForward;
+    // iter_ is pointing just before the entries for this->key(),
+    // so advance into the range of entries for this->key() and then
+    // use the normal skipping code below.
+    if (!iter_->Valid()) {
+      iter_->SeekToFirst();
+    } else {
+      iter_->Next();
+    }
+    if (!iter_->Valid()) {
+      valid_ = false;
+      saved_key_.clear();
+      return;
+    }
+  }
+
+  // Temporarily use saved_key_ as storage for key to skip.
+  std::string* skip = &saved_key_;
+  SaveKey(ExtractUserKey(iter_->key()), skip);
+  FindNextUserEntry(true, skip);
+}
+
+void DBIter::FindNextUserEntry(bool skipping, std::string* skip) {
+  // Loop until we hit an acceptable entry to yield
+  assert(iter_->Valid());
+  assert(direction_ == kForward);
+  do {
+    ParsedInternalKey ikey;
+    if (ParseKey(&ikey) && ikey.sequence <= sequence_) {
+      switch (ikey.type) {
+        case kTypeDeletion:
+          // Arrange to skip all upcoming entries for this key since
+          // they are hidden by this deletion.
+          SaveKey(ikey.user_key, skip);
+          skipping = true;
+          break;
+        case kTypeValue:
+          if (skipping &&
+              user_comparator_->Compare(ikey.user_key, *skip) <= 0) {
+            // Entry hidden
+          } else {
+            valid_ = true;
+            saved_key_.clear();
+            return;
+          }
+          break;
+      }
+    }
+    iter_->Next();
+  } while (iter_->Valid());
+  saved_key_.clear();
+  valid_ = false;
+}
+
+void DBIter::Prev() {
+  assert(valid_);
+
+  if (direction_ == kForward) {  // Switch directions?
+    // iter_ is pointing at the current entry.  Scan backwards until
+    // the key changes so we can use the normal reverse scanning code.
+    assert(iter_->Valid());  // Otherwise valid_ would have been false
+    SaveKey(ExtractUserKey(iter_->key()), &saved_key_);
+    while (true) {
+      iter_->Prev();
+      if (!iter_->Valid()) {
+        valid_ = false;
+        saved_key_.clear();
+        ClearSavedValue();
+        return;
+      }
+      if (user_comparator_->Compare(ExtractUserKey(iter_->key()),
+                                    saved_key_) < 0) {
+        break;
+      }
+    }
+    direction_ = kReverse;
+  }
+
+  FindPrevUserEntry();
+}
+
+void DBIter::FindPrevUserEntry() {
+  assert(direction_ == kReverse);
+
+  ValueType value_type = kTypeDeletion;
+  if (iter_->Valid()) {
+    do {
+      ParsedInternalKey ikey;
+      if (ParseKey(&ikey) && ikey.sequence <= sequence_) {
+        if ((value_type != kTypeDeletion) &&
+            user_comparator_->Compare(ikey.user_key, saved_key_) < 0) {
+          // We encountered a non-deleted value in entries for previous keys,
+          break;
+        }
+        value_type = ikey.type;
+        if (value_type == kTypeDeletion) {
+          saved_key_.clear();
+          ClearSavedValue();
+        } else {
+          Slice raw_value = iter_->value();
+          if (saved_value_.capacity() > raw_value.size() + 1048576) {
+            std::string empty;
+            swap(empty, saved_value_);
+          }
+          SaveKey(ExtractUserKey(iter_->key()), &saved_key_);
+          saved_value_.assign(raw_value.data(), raw_value.size());
+        }
+      }
+      iter_->Prev();
+    } while (iter_->Valid());
+  }
+
+  if (value_type == kTypeDeletion) {
+    // End
+    valid_ = false;
+    saved_key_.clear();
+    ClearSavedValue();
+    direction_ = kForward;
+  } else {
+    valid_ = true;
+  }
+}
+
+void DBIter::Seek(const Slice& target) {
+  direction_ = kForward;
+  ClearSavedValue();
+  saved_key_.clear();
+  AppendInternalKey(
+      &saved_key_, ParsedInternalKey(target, sequence_, kValueTypeForSeek));
+  iter_->Seek(saved_key_);
+  if (iter_->Valid()) {
+    FindNextUserEntry(false, &saved_key_ /* temporary storage */);
+  } else {
+    valid_ = false;
+  }
+}
+
+void DBIter::SeekToFirst() {
+  direction_ = kForward;
+  ClearSavedValue();
+  iter_->SeekToFirst();
+  if (iter_->Valid()) {
+    FindNextUserEntry(false, &saved_key_ /* temporary storage */);
+  } else {
+    valid_ = false;
+  }
+}
+
+void DBIter::SeekToLast() {
+  direction_ = kReverse;
+  ClearSavedValue();
+  iter_->SeekToLast();
+  FindPrevUserEntry();
+}
+
+}  // anonymous namespace
+
+Iterator* NewDBIterator(
+    const std::string* dbname,
+    Env* env,
+    const Comparator* user_key_comparator,
+    Iterator* internal_iter,
+    const SequenceNumber& sequence) {
+  return new DBIter(dbname, env, user_key_comparator, internal_iter, sequence);
+}
+
+}  // namespace leveldb

data/ext/leveldb/db/db_iter.h

@@ -0,0 +1,26 @@
+// 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.
+
+#ifndef STORAGE_LEVELDB_DB_DB_ITER_H_
+#define STORAGE_LEVELDB_DB_DB_ITER_H_
+
+#include <stdint.h>
+#include "leveldb/db.h"
+#include "db/dbformat.h"
+
+namespace leveldb {
+
+// Return a new iterator that converts internal keys (yielded by
+// "*internal_iter") that were live at the specified "sequence" number
+// into appropriate user keys.
+extern Iterator* NewDBIterator(
+    const std::string* dbname,
+    Env* env,
+    const Comparator* user_key_comparator,
+    Iterator* internal_iter,
+    const SequenceNumber& sequence);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_DB_ITER_H_