filiptepper-leveldb-ruby 0.14

data/leveldb/table/two_level_iterator.cc

@@ -0,0 +1,182 @@
+// 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 "table/two_level_iterator.h"
+
+#include "leveldb/table.h"
+#include "table/block.h"
+#include "table/format.h"
+#include "table/iterator_wrapper.h"
+
+namespace leveldb {
+
+namespace {
+
+typedef Iterator* (*BlockFunction)(void*, const ReadOptions&, const Slice&);
+
+class TwoLevelIterator: public Iterator {
+ public:
+  TwoLevelIterator(
+    Iterator* index_iter,
+    BlockFunction block_function,
+    void* arg,
+    const ReadOptions& options);
+
+  virtual ~TwoLevelIterator();
+
+  virtual void Seek(const Slice& target);
+  virtual void SeekToFirst();
+  virtual void SeekToLast();
+  virtual void Next();
+  virtual void Prev();
+
+  virtual bool Valid() const {
+    return data_iter_.Valid();
+  }
+  virtual Slice key() const {
+    assert(Valid());
+    return data_iter_.key();
+  }
+  virtual Slice value() const {
+    assert(Valid());
+    return data_iter_.value();
+  }
+  virtual Status status() const {
+    // It'd be nice if status() returned a const Status& instead of a Status
+    if (!index_iter_.status().ok()) {
+      return index_iter_.status();
+    } else if (data_iter_.iter() != NULL && !data_iter_.status().ok()) {
+      return data_iter_.status();
+    } else {
+      return status_;
+    }
+  }
+
+ private:
+  void SaveError(const Status& s) {
+    if (status_.ok() && !s.ok()) status_ = s;
+  }
+  void SkipEmptyDataBlocksForward();
+  void SkipEmptyDataBlocksBackward();
+  void SetDataIterator(Iterator* data_iter);
+  void InitDataBlock();
+
+  BlockFunction block_function_;
+  void* arg_;
+  const ReadOptions options_;
+  Status status_;
+  IteratorWrapper index_iter_;
+  IteratorWrapper data_iter_; // May be NULL
+  // If data_iter_ is non-NULL, then "data_block_handle_" holds the
+  // "index_value" passed to block_function_ to create the data_iter_.
+  std::string data_block_handle_;
+};
+
+TwoLevelIterator::TwoLevelIterator(
+    Iterator* index_iter,
+    BlockFunction block_function,
+    void* arg,
+    const ReadOptions& options)
+    : block_function_(block_function),
+      arg_(arg),
+      options_(options),
+      index_iter_(index_iter),
+      data_iter_(NULL) {
+}
+
+TwoLevelIterator::~TwoLevelIterator() {
+}
+
+void TwoLevelIterator::Seek(const Slice& target) {
+  index_iter_.Seek(target);
+  InitDataBlock();
+  if (data_iter_.iter() != NULL) data_iter_.Seek(target);
+  SkipEmptyDataBlocksForward();
+}
+
+void TwoLevelIterator::SeekToFirst() {
+  index_iter_.SeekToFirst();
+  InitDataBlock();
+  if (data_iter_.iter() != NULL) data_iter_.SeekToFirst();
+  SkipEmptyDataBlocksForward();
+}
+
+void TwoLevelIterator::SeekToLast() {
+  index_iter_.SeekToLast();
+  InitDataBlock();
+  if (data_iter_.iter() != NULL) data_iter_.SeekToLast();
+  SkipEmptyDataBlocksBackward();
+}
+
+void TwoLevelIterator::Next() {
+  assert(Valid());
+  data_iter_.Next();
+  SkipEmptyDataBlocksForward();
+}
+
+void TwoLevelIterator::Prev() {
+  assert(Valid());
+  data_iter_.Prev();
+  SkipEmptyDataBlocksBackward();
+}
+
+
+void TwoLevelIterator::SkipEmptyDataBlocksForward() {
+  while (data_iter_.iter() == NULL || !data_iter_.Valid()) {
+    // Move to next block
+    if (!index_iter_.Valid()) {
+      SetDataIterator(NULL);
+      return;
+    }
+    index_iter_.Next();
+    InitDataBlock();
+    if (data_iter_.iter() != NULL) data_iter_.SeekToFirst();
+  }
+}
+
+void TwoLevelIterator::SkipEmptyDataBlocksBackward() {
+  while (data_iter_.iter() == NULL || !data_iter_.Valid()) {
+    // Move to next block
+    if (!index_iter_.Valid()) {
+      SetDataIterator(NULL);
+      return;
+    }
+    index_iter_.Prev();
+    InitDataBlock();
+    if (data_iter_.iter() != NULL) data_iter_.SeekToLast();
+  }
+}
+
+void TwoLevelIterator::SetDataIterator(Iterator* data_iter) {
+  if (data_iter_.iter() != NULL) SaveError(data_iter_.status());
+  data_iter_.Set(data_iter);
+}
+
+void TwoLevelIterator::InitDataBlock() {
+  if (!index_iter_.Valid()) {
+    SetDataIterator(NULL);
+  } else {
+    Slice handle = index_iter_.value();
+    if (data_iter_.iter() != NULL && handle.compare(data_block_handle_) == 0) {
+      // data_iter_ is already constructed with this iterator, so
+      // no need to change anything
+    } else {
+      Iterator* iter = (*block_function_)(arg_, options_, handle);
+      data_block_handle_.assign(handle.data(), handle.size());
+      SetDataIterator(iter);
+    }
+  }
+}
+
+}  // namespace
+
+Iterator* NewTwoLevelIterator(
+    Iterator* index_iter,
+    BlockFunction block_function,
+    void* arg,
+    const ReadOptions& options) {
+  return new TwoLevelIterator(index_iter, block_function, arg, options);
+}
+
+}  // namespace leveldb

data/leveldb/table/two_level_iterator.h

@@ -0,0 +1,34 @@
+// 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_TABLE_TWO_LEVEL_ITERATOR_H_
+#define STORAGE_LEVELDB_TABLE_TWO_LEVEL_ITERATOR_H_
+
+#include "leveldb/iterator.h"
+
+namespace leveldb {
+
+struct ReadOptions;
+
+// Return a new two level iterator.  A two-level iterator contains an
+// index iterator whose values point to a sequence of blocks where
+// each block is itself a sequence of key,value pairs.  The returned
+// two-level iterator yields the concatenation of all key/value pairs
+// in the sequence of blocks.  Takes ownership of "index_iter" and
+// will delete it when no longer needed.
+//
+// Uses a supplied function to convert an index_iter value into
+// an iterator over the contents of the corresponding block.
+extern Iterator* NewTwoLevelIterator(
+    Iterator* index_iter,
+    Iterator* (*block_function)(
+        void* arg,
+        const ReadOptions& options,
+        const Slice& index_value),
+    void* arg,
+    const ReadOptions& options);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_TABLE_TWO_LEVEL_ITERATOR_H_

data/leveldb/util/arena.cc

@@ -0,0 +1,68 @@
+// 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 "util/arena.h"
+#include <assert.h>
+
+namespace leveldb {
+
+static const int kBlockSize = 4096;
+
+Arena::Arena() {
+  blocks_memory_ = 0;
+  alloc_ptr_ = NULL;  // First allocation will allocate a block
+  alloc_bytes_remaining_ = 0;
+}
+
+Arena::~Arena() {
+  for (size_t i = 0; i < blocks_.size(); i++) {
+    delete[] blocks_[i];
+  }
+}
+
+char* Arena::AllocateFallback(size_t bytes) {
+  if (bytes > kBlockSize / 4) {
+    // Object is more than a quarter of our block size.  Allocate it separately
+    // to avoid wasting too much space in leftover bytes.
+    char* result = AllocateNewBlock(bytes);
+    return result;
+  }
+
+  // We waste the remaining space in the current block.
+  alloc_ptr_ = AllocateNewBlock(kBlockSize);
+  alloc_bytes_remaining_ = kBlockSize;
+
+  char* result = alloc_ptr_;
+  alloc_ptr_ += bytes;
+  alloc_bytes_remaining_ -= bytes;
+  return result;
+}
+
+char* Arena::AllocateAligned(size_t bytes) {
+  const int align = sizeof(void*);    // We'll align to pointer size
+  assert((align & (align-1)) == 0);   // Pointer size should be a power of 2
+  size_t current_mod = reinterpret_cast<uintptr_t>(alloc_ptr_) & (align-1);
+  size_t slop = (current_mod == 0 ? 0 : align - current_mod);
+  size_t needed = bytes + slop;
+  char* result;
+  if (needed <= alloc_bytes_remaining_) {
+    result = alloc_ptr_ + slop;
+    alloc_ptr_ += needed;
+    alloc_bytes_remaining_ -= needed;
+  } else {
+    // AllocateFallback always returned aligned memory
+    result = AllocateFallback(bytes);
+  }
+  assert((reinterpret_cast<uintptr_t>(result) & (align-1)) == 0);
+  return result;
+}
+
+char* Arena::AllocateNewBlock(size_t block_bytes) {
+  char* result = new char[block_bytes];
+  blocks_memory_ += block_bytes;
+  blocks_.push_back(result);
+  return result;
+}
+
+}  // namespace leveldb

data/leveldb/util/arena.h

@@ -0,0 +1,68 @@
+// 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_UTIL_ARENA_H_
+#define STORAGE_LEVELDB_UTIL_ARENA_H_
+
+#include <cstddef>
+#include <vector>
+#include <assert.h>
+#include <stdint.h>
+
+namespace leveldb {
+
+class Arena {
+ public:
+  Arena();
+  ~Arena();
+
+  // Return a pointer to a newly allocated memory block of "bytes" bytes.
+  char* Allocate(size_t bytes);
+
+  // Allocate memory with the normal alignment guarantees provided by malloc
+  char* AllocateAligned(size_t bytes);
+
+  // Returns an estimate of the total memory usage of data allocated
+  // by the arena (including space allocated but not yet used for user
+  // allocations).
+  size_t MemoryUsage() const {
+    return blocks_memory_ + blocks_.capacity() * sizeof(char*);
+  }
+
+ private:
+  char* AllocateFallback(size_t bytes);
+  char* AllocateNewBlock(size_t block_bytes);
+
+  // Allocation state
+  char* alloc_ptr_;
+  size_t alloc_bytes_remaining_;
+
+  // Array of new[] allocated memory blocks
+  std::vector<char*> blocks_;
+
+  // Bytes of memory in blocks allocated so far
+  size_t blocks_memory_;
+
+  // No copying allowed
+  Arena(const Arena&);
+  void operator=(const Arena&);
+};
+
+inline char* Arena::Allocate(size_t bytes) {
+  // The semantics of what to return are a bit messy if we allow
+  // 0-byte allocations, so we disallow them here (we don't need
+  // them for our internal use).
+  assert(bytes > 0);
+  if (bytes <= alloc_bytes_remaining_) {
+    char* result = alloc_ptr_;
+    alloc_ptr_ += bytes;
+    alloc_bytes_remaining_ -= bytes;
+    return result;
+  }
+  return AllocateFallback(bytes);
+}
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_UTIL_ARENA_H_

data/leveldb/util/arena_test.cc

@@ -0,0 +1,68 @@
+// 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 "util/arena.h"
+
+#include "util/random.h"
+#include "util/testharness.h"
+
+namespace leveldb {
+
+class ArenaTest { };
+
+TEST(ArenaTest, Empty) {
+  Arena arena;
+}
+
+TEST(ArenaTest, Simple) {
+  std::vector<std::pair<size_t, char*> > allocated;
+  Arena arena;
+  const int N = 100000;
+  size_t bytes = 0;
+  Random rnd(301);
+  for (int i = 0; i < N; i++) {
+    size_t s;
+    if (i % (N / 10) == 0) {
+      s = i;
+    } else {
+      s = rnd.OneIn(4000) ? rnd.Uniform(6000) :
+          (rnd.OneIn(10) ? rnd.Uniform(100) : rnd.Uniform(20));
+    }
+    if (s == 0) {
+      // Our arena disallows size 0 allocations.
+      s = 1;
+    }
+    char* r;
+    if (rnd.OneIn(10)) {
+      r = arena.AllocateAligned(s);
+    } else {
+      r = arena.Allocate(s);
+    }
+
+    for (int b = 0; b < s; b++) {
+      // Fill the "i"th allocation with a known bit pattern
+      r[b] = i % 256;
+    }
+    bytes += s;
+    allocated.push_back(std::make_pair(s, r));
+    ASSERT_GE(arena.MemoryUsage(), bytes);
+    if (i > N/10) {
+      ASSERT_LE(arena.MemoryUsage(), bytes * 1.10);
+    }
+  }
+  for (int i = 0; i < allocated.size(); i++) {
+    size_t num_bytes = allocated[i].first;
+    const char* p = allocated[i].second;
+    for (int b = 0; b < num_bytes; b++) {
+      // Check the "i"th allocation for the known bit pattern
+      ASSERT_EQ(int(p[b]) & 0xff, i % 256);
+    }
+  }
+}
+
+}  // namespace leveldb
+
+int main(int argc, char** argv) {
+  return leveldb::test::RunAllTests();
+}

data/leveldb/util/bloom.cc

@@ -0,0 +1,95 @@
+// Copyright (c) 2012 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 "leveldb/filter_policy.h"
+
+#include "leveldb/slice.h"
+#include "util/hash.h"
+
+namespace leveldb {
+
+namespace {
+static uint32_t BloomHash(const Slice& key) {
+  return Hash(key.data(), key.size(), 0xbc9f1d34);
+}
+
+class BloomFilterPolicy : public FilterPolicy {
+ private:
+  size_t bits_per_key_;
+  size_t k_;
+
+ public:
+  explicit BloomFilterPolicy(int bits_per_key)
+      : bits_per_key_(bits_per_key) {
+    // We intentionally round down to reduce probing cost a little bit
+    k_ = static_cast<size_t>(bits_per_key * 0.69);  // 0.69 =~ ln(2)
+    if (k_ < 1) k_ = 1;
+    if (k_ > 30) k_ = 30;
+  }
+
+  virtual const char* Name() const {
+    return "leveldb.BuiltinBloomFilter";
+  }
+
+  virtual void CreateFilter(const Slice* keys, int n, std::string* dst) const {
+    // Compute bloom filter size (in both bits and bytes)
+    size_t bits = n * bits_per_key_;
+
+    // For small n, we can see a very high false positive rate.  Fix it
+    // by enforcing a minimum bloom filter length.
+    if (bits < 64) bits = 64;
+
+    size_t bytes = (bits + 7) / 8;
+    bits = bytes * 8;
+
+    const size_t init_size = dst->size();
+    dst->resize(init_size + bytes, 0);
+    dst->push_back(static_cast<char>(k_));  // Remember # of probes in filter
+    char* array = &(*dst)[init_size];
+    for (size_t i = 0; i < n; i++) {
+      // Use double-hashing to generate a sequence of hash values.
+      // See analysis in [Kirsch,Mitzenmacher 2006].
+      uint32_t h = BloomHash(keys[i]);
+      const uint32_t delta = (h >> 17) | (h << 15);  // Rotate right 17 bits
+      for (size_t j = 0; j < k_; j++) {
+        const uint32_t bitpos = h % bits;
+        array[bitpos/8] |= (1 << (bitpos % 8));
+        h += delta;
+      }
+    }
+  }
+
+  virtual bool KeyMayMatch(const Slice& key, const Slice& bloom_filter) const {
+    const size_t len = bloom_filter.size();
+    if (len < 2) return false;
+
+    const char* array = bloom_filter.data();
+    const size_t bits = (len - 1) * 8;
+
+    // Use the encoded k so that we can read filters generated by
+    // bloom filters created using different parameters.
+    const size_t k = array[len-1];
+    if (k > 30) {
+      // Reserved for potentially new encodings for short bloom filters.
+      // Consider it a match.
+      return true;
+    }
+
+    uint32_t h = BloomHash(key);
+    const uint32_t delta = (h >> 17) | (h << 15);  // Rotate right 17 bits
+    for (size_t j = 0; j < k; j++) {
+      const uint32_t bitpos = h % bits;
+      if ((array[bitpos/8] & (1 << (bitpos % 8))) == 0) return false;
+      h += delta;
+    }
+    return true;
+  }
+};
+}
+
+const FilterPolicy* NewBloomFilterPolicy(int bits_per_key) {
+  return new BloomFilterPolicy(bits_per_key);
+}
+
+}  // namespace leveldb