Merge branch 'master' of github.com:facebook/rocksdb into inplace

2025-12-06 17:27:55 +00:00 · 2013-10-31 11:51:03 -07:00
parent fe25070242 138a8eee8e
commit b4fab3be2a
31 changed files with 1418 additions and 313 deletions
--- a/db/builder.cc
+++ b/db/builder.cc
@@ -15,12 +15,23 @@
 #include "db/table_cache.h"
 #include "db/version_edit.h"
 #include "rocksdb/db.h"
+#include "rocksdb/table.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
+#include "rocksdb/options.h"
+#include "table/block_based_table_builder.h"
 #include "util/stop_watch.h"

 namespace rocksdb {

+class TableFactory;
+
+TableBuilder* GetTableBuilder(const Options& options, WritableFile* file,
+                              CompressionType compression_type) {
+  return options.table_factory->GetTableBuilder(options, file,
+                                                compression_type);
+}
+
 Status BuildTable(const std::string& dbname,
                  Env* env,
                  const Options& options,
@@ -52,8 +63,9 @@ Status BuildTable(const std::string& dbname,
    if (!s.ok()) {
      return s;
    }
-    TableBuilder* builder = new TableBuilder(options, file.get(), 0,
-                                             enable_compression);
+
+    TableBuilder* builder = GetTableBuilder(options, file.get(),
+                                            options.compression);

    // the first key is the smallest key
    Slice key = iter->key();
--- a/db/builder.h
+++ b/db/builder.h
@@ -9,6 +9,7 @@
 #include "rocksdb/comparator.h"
 #include "rocksdb/status.h"
 #include "rocksdb/types.h"
+#include "rocksdb/options.h"

 namespace rocksdb {

@@ -20,6 +21,12 @@ class EnvOptions;
 class Iterator;
 class TableCache;
 class VersionEdit;
+class TableBuilder;
+class WritableFile;
+
+
+extern TableBuilder* GetTableBuilder(const Options& options, WritableFile* file,
+                                     CompressionType compression_type);

 // Build a Table file from the contents of *iter.  The generated file
 // will be named according to meta->number.  On success, the rest of
--- a/db/corruption_test.cc
+++ b/db/corruption_test.cc
@@ -15,12 +15,12 @@
 #include <sys/types.h>
 #include "rocksdb/cache.h"
 #include "rocksdb/env.h"
+#include "rocksdb/table.h"
 #include "rocksdb/write_batch.h"
 #include "db/db_impl.h"
 #include "db/filename.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "table/table.h"
 #include "util/logging.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
--- a/db/db_impl.cc
+++ b/db/db_impl.cc
@@ -41,10 +41,10 @@
 #include "rocksdb/merge_operator.h"
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
-#include "rocksdb/table_builder.h"
+#include "rocksdb/table.h"
+#include "port/port.h"
 #include "table/block.h"
 #include "table/merger.h"
-#include "table/table.h"
 #include "table/two_level_iterator.h"
 #include "util/auto_roll_logger.h"
 #include "util/build_version.h"
@@ -211,6 +211,27 @@ Options SanitizeOptions(const std::string& dbname,
  return result;
 }

+CompressionType GetCompressionType(const Options& options, int level,
+                                   const bool enable_compression) {
+  if (!enable_compression) {
+    // disable compression
+    return kNoCompression;
+  }
+  // If the use has specified a different compression level for each level,
+  // then pick the compresison for that level.
+  if (!options.compression_per_level.empty()) {
+    const int n = options.compression_per_level.size() - 1;
+    // It is possible for level_ to be -1; in that case, we use level
+    // 0's compression.  This occurs mostly in backwards compatibility
+    // situations when the builder doesn't know what level the file
+    // belongs to.  Likewise, if level_ is beyond the end of the
+    // specified compression levels, use the last value.
+    return options.compression_per_level[std::max(0, std::min(level, n))];
+  } else {
+    return options.compression;
+  }
+}
+
 DBImpl::DBImpl(const Options& options, const std::string& dbname)
    : env_(options.env),
      dbname_(dbname),
@@ -1774,9 +1795,12 @@ Status DBImpl::OpenCompactionOutputFile(CompactionState* compact) {
    compact->outfile->SetPreallocationBlockSize(
      1.1 * versions_->MaxFileSizeForLevel(compact->compaction->output_level()));

-    compact->builder.reset(new TableBuilder(options_, compact->outfile.get(),
-                                            compact->compaction->output_level(),
-                                            compact->compaction->enable_compression()));
+    CompressionType compression_type = GetCompressionType(
+        options_, compact->compaction->output_level(),
+        compact->compaction->enable_compression());
+
+    compact->builder.reset(
+        GetTableBuilder(options_, compact->outfile.get(), compression_type));
  }
  return s;
 }
@@ -2026,9 +2050,9 @@ Status DBImpl::DoCompactionWork(CompactionState* compact) {
          compaction_filter_value.clear();
          bool to_delete =
            compaction_filter->Filter(compact->compaction->level(),
-                                      ikey.user_key, value,
-                                      &compaction_filter_value,
-                                      &value_changed);
+                                               ikey.user_key, value,
+                                               &compaction_filter_value,
+                                               &value_changed);
          if (to_delete) {
            // make a copy of the original key
            delete_key.assign(key.data(), key.data() + key.size());
--- a/db/db_impl.h
+++ b/db/db_impl.h
@@ -444,4 +444,13 @@ extern Options SanitizeOptions(const std::string& db,
                               const InternalFilterPolicy* ipolicy,
                               const Options& src);

+
+// Determine compression type, based on user options, level of the output
+// file and whether compression is disabled.
+// If enable_compression is false, then compression is always disabled no
+// matter what the values of the other two parameters are.
+// Otherwise, the compression type is determined based on options and level.
+CompressionType GetCompressionType(const Options& options, int level,
+                                   const bool enable_compression);
+
 }  // namespace rocksdb
--- a/db/db_impl_readonly.cc
+++ b/db/db_impl_readonly.cc
@@ -29,11 +29,10 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/status.h"
-#include "rocksdb/table_builder.h"
+#include "rocksdb/table.h"
 #include "port/port.h"
 #include "table/block.h"
 #include "table/merger.h"
-#include "table/table.h"
 #include "table/two_level_iterator.h"
 #include "util/coding.h"
 #include "util/logging.h"
--- a/db/db_test.cc
+++ b/db/db_test.cc
@@ -20,7 +20,7 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/env.h"
-#include "table/table.h"
+#include "rocksdb/table.h"
 #include "util/hash.h"
 #include "util/logging.h"
 #include "util/mutexlock.h"
--- a/db/dbformat.h
+++ b/db/dbformat.h
@@ -13,7 +13,7 @@
 #include "rocksdb/db.h"
 #include "rocksdb/filter_policy.h"
 #include "rocksdb/slice.h"
-#include "rocksdb/table_builder.h"
+#include "rocksdb/table.h"
 #include "rocksdb/types.h"
 #include "util/coding.h"
 #include "util/logging.h"
--- a/db/simple_table_db_test.cc
+++ b/db/simple_table_db_test.cc
@@ -0,0 +1,793 @@
+// 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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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.
+#include <algorithm>
+#include <set>
+
+#include "rocksdb/db.h"
+#include "rocksdb/filter_policy.h"
+#include "db/db_impl.h"
+#include "db/filename.h"
+#include "db/version_set.h"
+#include "db/write_batch_internal.h"
+#include "db/db_statistics.h"
+#include "rocksdb/cache.h"
+#include "rocksdb/compaction_filter.h"
+#include "rocksdb/env.h"
+#include "rocksdb/table.h"
+#include "util/hash.h"
+#include "util/logging.h"
+#include "util/mutexlock.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+#include "utilities/merge_operators.h"
+
+using std::unique_ptr;
+
+namespace rocksdb {
+
+// SimpleTable is a simple table format for UNIT TEST ONLY. It is not built
+// as production quality.
+// SimpleTable requires the input key size to be fixed 16 bytes, value cannot
+// be longer than 150000 bytes and stored data on disk in this format:
+// +--------------------------------------------+  <= key1 offset
+// | key1            | value_size (4 bytes) |   |
+// +----------------------------------------+   |
+// | value1                                     |
+// |                                            |
+// +----------------------------------------+---+  <= key2 offset
+// | key2            | value_size (4 bytes) |   |
+// +----------------------------------------+   |
+// | value2                                     |
+// |                                            |
+// |        ......                              |
+// +-----------------+--------------------------+   <= index_block_offset
+// | key1            | key1 offset (8 bytes)    |
+// +-----------------+--------------------------+
+// | key2            | key2 offset (8 bytes)    |
+// +-----------------+--------------------------+
+// | key3            | key3 offset (8 bytes)    |
+// +-----------------+--------------------------+
+// |        ......                              |
+// +-----------------+------------+-------------+
+// | index_block_offset (8 bytes) |
+// +------------------------------+
+
+// SimpleTable is a simple table format for UNIT TEST ONLY. It is not built
+// as production quality.
+class SimpleTableReader: public TableReader {
+public:
+  // Attempt to open the table that is stored in bytes [0..file_size)
+  // of "file", and read the metadata entries necessary to allow
+  // retrieving data from the table.
+  //
+  // If successful, returns ok and sets "*table" to the newly opened
+  // table.  The client should delete "*table" when no longer needed.
+  // If there was an error while initializing the table, sets "*table"
+  // to nullptr and returns a non-ok status.  Does not take ownership of
+  // "*source", but the client must ensure that "source" remains live
+  // for the duration of the returned table's lifetime.
+  //
+  // *file must remain live while this Table is in use.
+  static Status Open(const Options& options, const EnvOptions& soptions,
+                     unique_ptr<RandomAccessFile> && file, uint64_t file_size,
+                     unique_ptr<TableReader>* table_reader);
+
+  bool PrefixMayMatch(const Slice& internal_prefix) override;
+
+  Iterator* NewIterator(const ReadOptions&) override;
+
+  Status Get(
+      const ReadOptions&, const Slice& key, void* arg,
+      bool (*handle_result)(void* arg, const Slice& k, const Slice& v, bool),
+      void (*mark_key_may_exist)(void*) = nullptr) override;
+
+  uint64_t ApproximateOffsetOf(const Slice& key) override;
+
+  bool TEST_KeyInCache(const ReadOptions& options, const Slice& key) override;
+
+  void SetupForCompaction() override;
+
+  TableStats& GetTableStats() override;
+
+  ~SimpleTableReader();
+
+private:
+  struct Rep;
+  Rep* rep_;
+
+  explicit SimpleTableReader(Rep* rep) {
+    rep_ = rep;
+  }
+  friend class TableCache;
+  friend class SimpleTableIterator;
+
+  Status GetOffset(const Slice& target, uint64_t* offset);
+
+  // No copying allowed
+  explicit SimpleTableReader(const TableReader&) = delete;
+  void operator=(const TableReader&) = delete;
+};
+
+// Iterator to iterate SimpleTable
+class SimpleTableIterator: public Iterator {
+public:
+  explicit SimpleTableIterator(SimpleTableReader* table);
+  ~SimpleTableIterator();
+
+  bool Valid() const;
+
+  void SeekToFirst();
+
+  void SeekToLast();
+
+  void Seek(const Slice& target);
+
+  void Next();
+
+  void Prev();
+
+  Slice key() const;
+
+  Slice value() const;
+
+  Status status() const;
+
+private:
+  SimpleTableReader* table_;
+  uint64_t offset_;
+  uint64_t next_offset_;
+  Slice key_;
+  Slice value_;
+  char tmp_str_[4];
+  char* key_str_;
+  char* value_str_;
+  int value_str_len_;
+  Status status_;
+  // No copying allowed
+  SimpleTableIterator(const SimpleTableIterator&) = delete;
+  void operator=(const Iterator&) = delete;
+};
+
+struct SimpleTableReader::Rep {
+  ~Rep() {
+  }
+  Rep(const EnvOptions& storage_options, uint64_t index_start_offset,
+      int num_entries) :
+      soptions(storage_options), index_start_offset(index_start_offset),
+      num_entries(num_entries) {
+  }
+
+  Options options;
+  const EnvOptions& soptions;
+  Status status;
+  unique_ptr<RandomAccessFile> file;
+  uint64_t index_start_offset;
+  int num_entries;
+  TableStats table_stats;
+
+  const static int user_key_size = 16;
+  const static int offset_length = 8;
+  const static int key_footer_len = 8;
+
+  static int GetInternalKeyLength() {
+    return user_key_size + key_footer_len;
+  }
+};
+
+SimpleTableReader::~SimpleTableReader() {
+  delete rep_;
+}
+
+Status SimpleTableReader::Open(const Options& options,
+                               const EnvOptions& soptions,
+                               unique_ptr<RandomAccessFile> && file,
+                               uint64_t size,
+                               unique_ptr<TableReader>* table_reader) {
+  char footer_space[Rep::offset_length];
+  Slice footer_input;
+  Status s = file->Read(size - Rep::offset_length, Rep::offset_length,
+                        &footer_input, footer_space);
+  if (s.ok()) {
+    uint64_t index_start_offset = DecodeFixed64(footer_space);
+
+    int num_entries = (size - Rep::offset_length - index_start_offset)
+        / (Rep::GetInternalKeyLength() + Rep::offset_length);
+    SimpleTableReader::Rep* rep = new SimpleTableReader::Rep(soptions,
+                                                             index_start_offset,
+                                                             num_entries);
+
+    rep->file = std::move(file);
+    rep->options = options;
+    table_reader->reset(new SimpleTableReader(rep));
+  }
+  return s;
+}
+
+void SimpleTableReader::SetupForCompaction() {
+}
+
+TableStats& SimpleTableReader::GetTableStats() {
+  return rep_->table_stats;
+}
+
+bool SimpleTableReader::PrefixMayMatch(const Slice& internal_prefix) {
+  return true;
+}
+
+Iterator* SimpleTableReader::NewIterator(const ReadOptions& options) {
+  return new SimpleTableIterator(this);
+}
+
+Status SimpleTableReader::GetOffset(const Slice& target, uint64_t* offset) {
+  uint32_t left = 0;
+  uint32_t right = rep_->num_entries - 1;
+  char key_chars[Rep::GetInternalKeyLength()];
+  Slice tmp_slice;
+
+  uint32_t target_offset = 0;
+  while (left <= right) {
+    uint32_t mid = (left + right + 1) / 2;
+
+    uint64_t offset_to_read = rep_->index_start_offset
+        + (Rep::GetInternalKeyLength() + Rep::offset_length) * mid;
+    Status s = rep_->file->Read(offset_to_read, Rep::GetInternalKeyLength(),
+                                &tmp_slice, key_chars);
+    if (!s.ok()) {
+      return s;
+    }
+
+    int compare_result = rep_->options.comparator->Compare(tmp_slice, target);
+
+    if (compare_result < 0) {
+      if (left == right) {
+        target_offset = right + 1;
+        break;
+      }
+      left = mid;
+    } else {
+      if (left == right) {
+        target_offset = left;
+        break;
+      }
+      right = mid - 1;
+    }
+  }
+
+  if (target_offset >= (uint32_t) rep_->num_entries) {
+    *offset = rep_->index_start_offset;
+    return Status::OK();
+  }
+
+  char value_offset_chars[Rep::offset_length];
+
+  int64_t offset_for_value_offset = rep_->index_start_offset
+      + (Rep::GetInternalKeyLength() + Rep::offset_length) * target_offset
+      + Rep::GetInternalKeyLength();
+  Status s = rep_->file->Read(offset_for_value_offset, Rep::offset_length,
+                              &tmp_slice, value_offset_chars);
+  if (s.ok()) {
+    *offset = DecodeFixed64(value_offset_chars);
+  }
+  return s;
+}
+
+Status SimpleTableReader::Get(
+    const ReadOptions& options, const Slice& k, void* arg,
+    bool (*saver)(void*, const Slice&, const Slice&, bool),
+    void (*mark_key_may_exist)(void*)) {
+  Status s;
+  SimpleTableIterator* iter = new SimpleTableIterator(this);
+  for (iter->Seek(k); iter->Valid(); iter->Next()) {
+    if (!(*saver)(arg, iter->key(), iter->value(), true)) {
+      break;
+    }
+  }
+  s = iter->status();
+  delete iter;
+  return s;
+}
+
+bool SimpleTableReader::TEST_KeyInCache(const ReadOptions& options,
+                                        const Slice& key) {
+  return false;
+}
+
+uint64_t SimpleTableReader::ApproximateOffsetOf(const Slice& key) {
+  return 0;
+}
+
+SimpleTableIterator::SimpleTableIterator(SimpleTableReader* table) :
+    table_(table) {
+  key_str_ = new char[SimpleTableReader::Rep::GetInternalKeyLength()];
+  value_str_len_ = -1;
+  SeekToFirst();
+}
+
+SimpleTableIterator::~SimpleTableIterator() {
+ delete[] key_str_;
+ if (value_str_len_ >= 0) {
+   delete[] value_str_;
+ }
+}
+
+bool SimpleTableIterator::Valid() const {
+  return offset_ < table_->rep_->index_start_offset && offset_ >= 0;
+}
+
+void SimpleTableIterator::SeekToFirst() {
+  next_offset_ = 0;
+  Next();
+}
+
+void SimpleTableIterator::SeekToLast() {
+  assert(false);
+}
+
+void SimpleTableIterator::Seek(const Slice& target) {
+  Status s = table_->GetOffset(target, &next_offset_);
+  if (!s.ok()) {
+    status_ = s;
+  }
+  Next();
+}
+
+void SimpleTableIterator::Next() {
+  offset_ = next_offset_;
+  if (offset_ >= table_->rep_->index_start_offset) {
+    return;
+  }
+  Slice result;
+  int internal_key_size = SimpleTableReader::Rep::GetInternalKeyLength();
+
+  Status s = table_->rep_->file->Read(next_offset_, internal_key_size, &result,
+                                      key_str_);
+  next_offset_ += internal_key_size;
+  key_ = result;
+
+  Slice value_size_slice;
+  s = table_->rep_->file->Read(next_offset_, 4, &value_size_slice, tmp_str_);
+  next_offset_ += 4;
+  uint32_t value_size = DecodeFixed32(tmp_str_);
+
+  Slice value_slice;
+  if ((int) value_size > value_str_len_) {
+    if (value_str_len_ >= 0) {
+      delete[] value_str_;
+    }
+    value_str_ = new char[value_size];
+    value_str_len_ = value_size;
+  }
+  s = table_->rep_->file->Read(next_offset_, value_size, &value_slice,
+                               value_str_);
+  next_offset_ += value_size;
+  value_ = value_slice;
+}
+
+void SimpleTableIterator::Prev() {
+  assert(false);
+}
+
+Slice SimpleTableIterator::key() const {
+  Log(table_->rep_->options.info_log, "key!!!!");
+  return key_;
+}
+
+Slice SimpleTableIterator::value() const {
+  return value_;
+}
+
+Status SimpleTableIterator::status() const {
+  return status_;
+}
+
+class SimpleTableBuilder: public TableBuilder {
+public:
+  // Create a builder that will store the contents of the table it is
+  // building in *file.  Does not close the file.  It is up to the
+  // caller to close the file after calling Finish(). The output file
+  // will be part of level specified by 'level'.  A value of -1 means
+  // that the caller does not know which level the output file will reside.
+  SimpleTableBuilder(const Options& options, WritableFile* file,
+                     CompressionType compression_type);
+
+  // REQUIRES: Either Finish() or Abandon() has been called.
+  ~SimpleTableBuilder();
+
+  // Add key,value to the table being constructed.
+  // REQUIRES: key is after any previously added key according to comparator.
+  // REQUIRES: Finish(), Abandon() have not been called
+  void Add(const Slice& key, const Slice& value) override;
+
+  // Return non-ok iff some error has been detected.
+  Status status() const override;
+
+  // Finish building the table.  Stops using the file passed to the
+  // constructor after this function returns.
+  // REQUIRES: Finish(), Abandon() have not been called
+  Status Finish() override;
+
+  // Indicate that the contents of this builder should be abandoned.  Stops
+  // using the file passed to the constructor after this function returns.
+  // If the caller is not going to call Finish(), it must call Abandon()
+  // before destroying this builder.
+  // REQUIRES: Finish(), Abandon() have not been called
+  void Abandon() override;
+
+  // Number of calls to Add() so far.
+  uint64_t NumEntries() const override;
+
+  // Size of the file generated so far.  If invoked after a successful
+  // Finish() call, returns the size of the final generated file.
+  uint64_t FileSize() const override;
+
+private:
+  struct Rep;
+  Rep* rep_;
+
+  // No copying allowed
+  SimpleTableBuilder(const SimpleTableBuilder&) = delete;
+  void operator=(const SimpleTableBuilder&) = delete;
+};
+
+struct SimpleTableBuilder::Rep {
+  Options options;
+  WritableFile* file;
+  uint64_t offset = 0;
+  Status status;
+
+  uint64_t num_entries = 0;
+
+  bool closed = false;  // Either Finish() or Abandon() has been called.
+
+  const static int user_key_size = 16;
+  const static int offset_length = 8;
+  const static int key_footer_len = 8;
+
+  static int GetInternalKeyLength() {
+    return user_key_size + key_footer_len;
+  }
+
+  std::string index;
+
+  Rep(const Options& opt, WritableFile* f) :
+      options(opt), file(f) {
+  }
+  ~Rep() {
+  }
+};
+
+SimpleTableBuilder::SimpleTableBuilder(const Options& options,
+                                       WritableFile* file,
+                                       CompressionType compression_type) :
+    rep_(new SimpleTableBuilder::Rep(options, file)) {
+}
+
+SimpleTableBuilder::~SimpleTableBuilder() {
+  delete (rep_);
+}
+
+void SimpleTableBuilder::Add(const Slice& key, const Slice& value) {
+  assert((int ) key.size() == Rep::GetInternalKeyLength());
+
+  // Update index
+  rep_->index.append(key.data(), key.size());
+  PutFixed64(&(rep_->index), rep_->offset);
+
+  // Write key-value pair
+  rep_->file->Append(key);
+  rep_->offset += Rep::GetInternalKeyLength();
+
+  std::string size;
+  int value_size = value.size();
+  PutFixed32(&size, value_size);
+  Slice sizeSlice(size);
+  rep_->file->Append(sizeSlice);
+  rep_->file->Append(value);
+  rep_->offset += value_size + 4;
+
+  rep_->num_entries++;
+}
+
+Status SimpleTableBuilder::status() const {
+  return Status::OK();
+}
+
+Status SimpleTableBuilder::Finish() {
+  Rep* r = rep_;
+  assert(!r->closed);
+  r->closed = true;
+
+  uint64_t index_offset = rep_->offset;
+  Slice index_slice(rep_->index);
+  rep_->file->Append(index_slice);
+  rep_->offset += index_slice.size();
+
+  std::string index_offset_str;
+  PutFixed64(&index_offset_str, index_offset);
+  Slice foot_slice(index_offset_str);
+  rep_->file->Append(foot_slice);
+  rep_->offset += foot_slice.size();
+
+  return Status::OK();
+}
+
+void SimpleTableBuilder::Abandon() {
+  rep_->closed = true;
+}
+
+uint64_t SimpleTableBuilder::NumEntries() const {
+  return rep_->num_entries;
+}
+
+uint64_t SimpleTableBuilder::FileSize() const {
+  return rep_->offset;
+}
+
+class SimpleTableFactory: public TableFactory {
+public:
+  ~SimpleTableFactory() {
+  }
+  SimpleTableFactory() {
+  }
+  const char* Name() const override {
+    return "SimpleTable";
+  }
+  Status GetTableReader(const Options& options, const EnvOptions& soptions,
+                        unique_ptr<RandomAccessFile> && file,
+                        uint64_t file_size,
+                        unique_ptr<TableReader>* table_reader) const;
+
+  TableBuilder* GetTableBuilder(const Options& options, WritableFile* file,
+                                CompressionType compression_type) const;
+};
+
+Status SimpleTableFactory::GetTableReader(
+    const Options& options, const EnvOptions& soptions,
+    unique_ptr<RandomAccessFile> && file, uint64_t file_size,
+    unique_ptr<TableReader>* table_reader) const {
+
+  return SimpleTableReader::Open(options, soptions, std::move(file), file_size,
+                                 table_reader);
+}
+
+TableBuilder* SimpleTableFactory::GetTableBuilder(
+    const Options& options, WritableFile* file,
+    CompressionType compression_type) const {
+  return new SimpleTableBuilder(options, file, compression_type);
+}
+
+class SimpleTableDBTest {
+protected:
+public:
+  std::string dbname_;
+  Env* env_;
+  DB* db_;
+
+  Options last_options_;
+
+  SimpleTableDBTest() :
+      env_(Env::Default()) {
+    dbname_ = test::TmpDir() + "/simple_table_db_test";
+    ASSERT_OK(DestroyDB(dbname_, Options()));
+    db_ = nullptr;
+    Reopen();
+  }
+
+  ~SimpleTableDBTest() {
+    delete db_;
+    ASSERT_OK(DestroyDB(dbname_, Options()));
+  }
+
+  // Return the current option configuration.
+  Options CurrentOptions() {
+    Options options;
+    options.table_factory.reset(new SimpleTableFactory());
+    return options;
+  }
+
+  DBImpl* dbfull() {
+    return reinterpret_cast<DBImpl*>(db_);
+  }
+
+  void Reopen(Options* options = nullptr) {
+    ASSERT_OK(TryReopen(options));
+  }
+
+  void Close() {
+    delete db_;
+    db_ = nullptr;
+  }
+
+  void DestroyAndReopen(Options* options = nullptr) {
+    //Destroy using last options
+    Destroy(&last_options_);
+    ASSERT_OK(TryReopen(options));
+  }
+
+  void Destroy(Options* options) {
+    delete db_;
+    db_ = nullptr;
+    ASSERT_OK(DestroyDB(dbname_, *options));
+  }
+
+  Status PureReopen(Options* options, DB** db) {
+    return DB::Open(*options, dbname_, db);
+  }
+
+  Status TryReopen(Options* options = nullptr) {
+    delete db_;
+    db_ = nullptr;
+    Options opts;
+    if (options != nullptr) {
+      opts = *options;
+    } else {
+      opts = CurrentOptions();
+      opts.create_if_missing = true;
+    }
+    last_options_ = opts;
+
+    return DB::Open(opts, dbname_, &db_);
+  }
+
+  Status Put(const Slice& k, const Slice& v) {
+    return db_->Put(WriteOptions(), k, v);
+  }
+
+  Status Delete(const std::string& k) {
+    return db_->Delete(WriteOptions(), k);
+  }
+
+  std::string Get(const std::string& k, const Snapshot* snapshot = nullptr) {
+    ReadOptions options;
+    options.snapshot = snapshot;
+    std::string result;
+    Status s = db_->Get(options, k, &result);
+    if (s.IsNotFound()) {
+      result = "NOT_FOUND";
+    } else if (!s.ok()) {
+      result = s.ToString();
+    }
+    return result;
+  }
+
+
+  int NumTableFilesAtLevel(int level) {
+    std::string property;
+    ASSERT_TRUE(
+        db_->GetProperty("rocksdb.num-files-at-level" + NumberToString(level),
+                         &property));
+    return atoi(property.c_str());
+  }
+
+  // Return spread of files per level
+  std::string FilesPerLevel() {
+    std::string result;
+    int last_non_zero_offset = 0;
+    for (int level = 0; level < db_->NumberLevels(); level++) {
+      int f = NumTableFilesAtLevel(level);
+      char buf[100];
+      snprintf(buf, sizeof(buf), "%s%d", (level ? "," : ""), f);
+      result += buf;
+      if (f > 0) {
+        last_non_zero_offset = result.size();
+      }
+    }
+    result.resize(last_non_zero_offset);
+    return result;
+  }
+
+  std::string IterStatus(Iterator* iter) {
+    std::string result;
+    if (iter->Valid()) {
+      result = iter->key().ToString() + "->" + iter->value().ToString();
+    } else {
+      result = "(invalid)";
+    }
+    return result;
+  }
+};
+
+TEST(SimpleTableDBTest, Empty) {
+  ASSERT_TRUE(db_ != nullptr);
+  ASSERT_EQ("NOT_FOUND", Get("0000000000000foo"));
+}
+
+TEST(SimpleTableDBTest, ReadWrite) {
+  ASSERT_OK(Put("0000000000000foo", "v1"));
+  ASSERT_EQ("v1", Get("0000000000000foo"));
+  ASSERT_OK(Put("0000000000000bar", "v2"));
+  ASSERT_OK(Put("0000000000000foo", "v3"));
+  ASSERT_EQ("v3", Get("0000000000000foo"));
+  ASSERT_EQ("v2", Get("0000000000000bar"));
+}
+
+TEST(SimpleTableDBTest, Flush) {
+  ASSERT_OK(Put("0000000000000foo", "v1"));
+  ASSERT_OK(Put("0000000000000bar", "v2"));
+  ASSERT_OK(Put("0000000000000foo", "v3"));
+  dbfull()->TEST_FlushMemTable();
+  ASSERT_EQ("v3", Get("0000000000000foo"));
+  ASSERT_EQ("v2", Get("0000000000000bar"));
+}
+
+TEST(SimpleTableDBTest, Flush2) {
+  ASSERT_OK(Put("0000000000000bar", "b"));
+  ASSERT_OK(Put("0000000000000foo", "v1"));
+  dbfull()->TEST_FlushMemTable();
+
+  ASSERT_OK(Put("0000000000000foo", "v2"));
+  dbfull()->TEST_FlushMemTable();
+  ASSERT_EQ("v2", Get("0000000000000foo"));
+
+  ASSERT_OK(Put("0000000000000eee", "v3"));
+  dbfull()->TEST_FlushMemTable();
+  ASSERT_EQ("v3", Get("0000000000000eee"));
+
+  ASSERT_OK(Delete("0000000000000bar"));
+  dbfull()->TEST_FlushMemTable();
+  ASSERT_EQ("NOT_FOUND", Get("0000000000000bar"));
+
+  ASSERT_OK(Put("0000000000000eee", "v5"));
+  dbfull()->TEST_FlushMemTable();
+  ASSERT_EQ("v5", Get("0000000000000eee"));
+}
+
+static std::string Key(int i) {
+  char buf[100];
+  snprintf(buf, sizeof(buf), "key_______%06d", i);
+  return std::string(buf);
+}
+
+static std::string RandomString(Random* rnd, int len) {
+  std::string r;
+  test::RandomString(rnd, len, &r);
+  return r;
+}
+
+TEST(SimpleTableDBTest, CompactionTrigger) {
+  Options options = CurrentOptions();
+  options.write_buffer_size = 100 << 10; //100KB
+  options.num_levels = 3;
+  options.max_mem_compaction_level = 0;
+  options.level0_file_num_compaction_trigger = 3;
+  Reopen(&options);
+
+  Random rnd(301);
+
+  for (int num = 0; num < options.level0_file_num_compaction_trigger - 1;
+      num++) {
+    std::vector<std::string> values;
+    // Write 120KB (12 values, each 10K)
+    for (int i = 0; i < 12; i++) {
+      values.push_back(RandomString(&rnd, 10000));
+      ASSERT_OK(Put(Key(i), values[i]));
+    }
+    dbfull()->TEST_WaitForFlushMemTable();
+    ASSERT_EQ(NumTableFilesAtLevel(0), num + 1);
+  }
+
+  //generate one more file in level-0, and should trigger level-0 compaction
+  std::vector<std::string> values;
+  for (int i = 0; i < 12; i++) {
+    values.push_back(RandomString(&rnd, 10000));
+    ASSERT_OK(Put(Key(i), values[i]));
+  }
+  dbfull()->TEST_WaitForCompact();
+
+  ASSERT_EQ(NumTableFilesAtLevel(0), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1), 1);
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  return rocksdb::test::RunAllTests();
+}
--- a/db/table_cache.cc
+++ b/db/table_cache.cc
@@ -12,15 +12,15 @@
 #include "db/filename.h"

 #include "rocksdb/statistics.h"
-#include "table/table.h"
+#include "rocksdb/table.h"
 #include "util/coding.h"
 #include "util/stop_watch.h"

 namespace rocksdb {

 static void DeleteEntry(const Slice& key, void* value) {
-  Table* table = reinterpret_cast<Table*>(value);
-  delete table;
+  TableReader* table_reader = reinterpret_cast<TableReader*>(value);
+  delete table_reader;
 }

 static void UnrefEntry(void* arg1, void* arg2) {
@@ -63,7 +63,7 @@ Status TableCache::FindTable(const EnvOptions& toptions,
    }
    std::string fname = TableFileName(dbname_, file_number);
    unique_ptr<RandomAccessFile> file;
-    unique_ptr<Table> table;
+    unique_ptr<TableReader> table_reader;
    s = env_->NewRandomAccessFile(fname, &file, toptions);
    RecordTick(options_->statistics, NO_FILE_OPENS);
    if (s.ok()) {
@@ -71,17 +71,19 @@ Status TableCache::FindTable(const EnvOptions& toptions,
        file->Hint(RandomAccessFile::RANDOM);
      }
      StopWatch sw(env_, options_->statistics, TABLE_OPEN_IO_MICROS);
-      s = Table::Open(*options_, toptions, std::move(file), file_size, &table);
+      s = options_->table_factory->GetTableReader(*options_, toptions,
+                                                  std::move(file), file_size,
+                                                  &table_reader);
    }

    if (!s.ok()) {
-      assert(table == nullptr);
+      assert(table_reader == nullptr);
      RecordTick(options_->statistics, NO_FILE_ERRORS);
      // We do not cache error results so that if the error is transient,
      // or somebody repairs the file, we recover automatically.
    } else {
      assert(file.get() == nullptr);
-      *handle = cache_->Insert(key, table.release(), 1, &DeleteEntry);
+      *handle = cache_->Insert(key, table_reader.release(), 1, &DeleteEntry);
    }
  }
  return s;
@@ -91,10 +93,10 @@ Iterator* TableCache::NewIterator(const ReadOptions& options,
                                  const EnvOptions& toptions,
                                  uint64_t file_number,
                                  uint64_t file_size,
-                                  Table** tableptr,
+                                  TableReader** table_reader_ptr,
                                  bool for_compaction) {
-  if (tableptr != nullptr) {
-    *tableptr = nullptr;
+  if (table_reader_ptr != nullptr) {
+    *table_reader_ptr = nullptr;
  }

  Cache::Handle* handle = nullptr;
@@ -104,16 +106,16 @@ Iterator* TableCache::NewIterator(const ReadOptions& options,
    return NewErrorIterator(s);
  }

-  Table* table =
-    reinterpret_cast<Table*>(cache_->Value(handle));
-  Iterator* result = table->NewIterator(options);
+  TableReader* table_reader =
+    reinterpret_cast<TableReader*>(cache_->Value(handle));
+  Iterator* result = table_reader->NewIterator(options);
  result->RegisterCleanup(&UnrefEntry, cache_.get(), handle);
-  if (tableptr != nullptr) {
-    *tableptr = table;
+  if (table_reader_ptr != nullptr) {
+    *table_reader_ptr = table_reader;
  }

  if (for_compaction) {
-    table->SetupForCompaction();
+    table_reader->SetupForCompaction();
  }

  return result;
@@ -132,9 +134,9 @@ Status TableCache::Get(const ReadOptions& options,
                       &handle, table_io,
                       options.read_tier == kBlockCacheTier);
  if (s.ok()) {
-    Table* t =
-      reinterpret_cast<Table*>(cache_->Value(handle));
-    s = t->InternalGet(options, k, arg, saver, mark_key_may_exist);
+    TableReader* t =
+      reinterpret_cast<TableReader*>(cache_->Value(handle));
+    s = t->Get(options, k, arg, saver, mark_key_may_exist);
    cache_->Release(handle);
  } else if (options.read_tier && s.IsIncomplete()) {
    // Couldnt find Table in cache but treat as kFound if no_io set
@@ -154,8 +156,8 @@ bool TableCache::PrefixMayMatch(const ReadOptions& options,
                       file_size, &handle, table_io);
  bool may_match = true;
  if (s.ok()) {
-    Table* t =
-      reinterpret_cast<Table*>(cache_->Value(handle));
+    TableReader* t =
+      reinterpret_cast<TableReader*>(cache_->Value(handle));
    may_match = t->PrefixMayMatch(internal_prefix);
    cache_->Release(handle);
  }
--- a/db/table_cache.h
+++ b/db/table_cache.h
@@ -16,7 +16,7 @@
 #include "rocksdb/env.h"
 #include "rocksdb/cache.h"
 #include "port/port.h"
-#include "table/table.h"
+#include "rocksdb/table.h"

 namespace rocksdb {

@@ -39,7 +39,7 @@ class TableCache {
                        const EnvOptions& toptions,
                        uint64_t file_number,
                        uint64_t file_size,
-                        Table** tableptr = nullptr,
+                        TableReader** table_reader_ptr = nullptr,
                        bool for_compaction = false);

  // If a seek to internal key "k" in specified file finds an entry,
--- a/db/table_stats_collector_test.cc
+++ b/db/table_stats_collector_test.cc
@@ -10,9 +10,8 @@
 #include "db/dbformat.h"
 #include "db/db_impl.h"
 #include "db/table_stats_collector.h"
-#include "rocksdb/table_builder.h"
 #include "rocksdb/table_stats.h"
-#include "table/table.h"
+#include "rocksdb/table.h"
 #include "util/coding.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
@@ -21,7 +20,7 @@ namespace rocksdb {

 class TableStatsTest {
 private:
-  unique_ptr<Table> table_;
+  unique_ptr<TableReader> table_reader_;
 };

 // TODO(kailiu) the following classes should be moved to some more general
@@ -89,21 +88,21 @@ void MakeBuilder(
    std::unique_ptr<TableBuilder>* builder) {
  writable->reset(new FakeWritableFile);
  builder->reset(
-      new TableBuilder(options, writable->get())
-  );
+      options.table_factory->GetTableBuilder(options, writable->get(),
+                                             options.compression));
 }

 void OpenTable(
    const Options& options,
    const std::string& contents,
-    std::unique_ptr<Table>* table) {
+    std::unique_ptr<TableReader>* table_reader) {
  std::unique_ptr<RandomAccessFile> file(new FakeRandomeAccessFile(contents));
-  auto s = Table::Open(
+  auto s = options.table_factory->GetTableReader(
      options,
      EnvOptions(),
      std::move(file),
      contents.size(),
-      table
+      table_reader
  );
  ASSERT_OK(s);
 }
@@ -176,9 +175,9 @@ TEST(TableStatsTest, CustomizedTableStatsCollector) {
    ASSERT_OK(builder->Finish());

    // -- Step 2: Open table
-    std::unique_ptr<Table> table;
-    OpenTable(options, writable->contents(), &table);
-    const auto& stats = table->GetTableStats().user_collected_stats;
+    std::unique_ptr<TableReader> table_reader;
+    OpenTable(options, writable->contents(), &table_reader);
+    const auto& stats = table_reader->GetTableStats().user_collected_stats;

    ASSERT_EQ("Rocksdb", stats.at("TableStatsTest"));

@@ -234,9 +233,9 @@ TEST(TableStatsTest, InternalKeyStatsCollector) {

    ASSERT_OK(builder->Finish());

-    std::unique_ptr<Table> table;
-    OpenTable(options, writable->contents(), &table);
-    const auto& stats = table->GetTableStats().user_collected_stats;
+    std::unique_ptr<TableReader> table_reader;
+    OpenTable(options, writable->contents(), &table_reader);
+    const auto& stats = table_reader->GetTableStats().user_collected_stats;

    uint64_t deleted = 0;
    Slice key(stats.at(InternalKeyTableStatsNames::kDeletedKeys));
--- a/db/version_set.cc
+++ b/db/version_set.cc
@@ -19,7 +19,7 @@
 #include "db/table_cache.h"
 #include "rocksdb/env.h"
 #include "rocksdb/merge_operator.h"
-#include "rocksdb/table_builder.h"
+#include "rocksdb/table.h"
 #include "table/merger.h"
 #include "table/two_level_iterator.h"
 #include "util/coding.h"
@@ -294,11 +294,11 @@ struct Saver {
 };
 }

-// Called from TableCache::Get and InternalGet when file/block in which key may
-// exist are not there in TableCache/BlockCache respectively. In this case we
-// can't guarantee that key does not exist and are not permitted to do IO to be
-// certain.Set the status=kFound and value_found=false to let the caller know
-// that key may exist but is not there in memory
+// Called from TableCache::Get and Table::Get when file/block in which
+// key may  exist are not there in TableCache/BlockCache respectively. In this
+// case we  can't guarantee that key does not exist and are not permitted to do
+// IO to be  certain.Set the status=kFound and value_found=false to let the
+// caller know that key may exist but is not there in memory
 static void MarkKeyMayExist(void* arg) {
  Saver* s = reinterpret_cast<Saver*>(arg);
  s->state = kFound;
@@ -1920,12 +1920,12 @@ uint64_t VersionSet::ApproximateOffsetOf(Version* v, const InternalKey& ikey) {
      } else {
        // "ikey" falls in the range for this table.  Add the
        // approximate offset of "ikey" within the table.
-        Table* tableptr;
+        TableReader* table_reader_ptr;
        Iterator* iter = table_cache_->NewIterator(
            ReadOptions(), storage_options_, files[i]->number,
-            files[i]->file_size, &tableptr);
-        if (tableptr != nullptr) {
-          result += tableptr->ApproximateOffsetOf(ikey.Encode());
+            files[i]->file_size, &table_reader_ptr);
+        if (table_reader_ptr != nullptr) {
+          result += table_reader_ptr->ApproximateOffsetOf(ikey.Encode());
        }
        delete iter;
      }