rocksdb/util/bloom.cc
Dhruba Borthakur aa42c66814 Fix all warnings generated by -Wall option to the compiler.
Summary:
The default compilation process now uses "-Wall" to compile.
Fix all compilation error generated by gcc.

Test Plan: make all check

Reviewers: heyongqiang, emayanke, sheki

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D6525
2012-11-06 14:07:31 -08:00

107 lines
3.2 KiB
C++

// 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_;
uint32_t (*hash_func_)(const Slice& key);
void initialize() {
// 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;
}
public:
explicit BloomFilterPolicy(int bits_per_key,
uint32_t (*hash_func)(const Slice& key))
: bits_per_key_(bits_per_key), hash_func_(hash_func) {
initialize();
}
explicit BloomFilterPolicy(int bits_per_key)
: bits_per_key_(bits_per_key) {
hash_func_ = BloomHash;
initialize();
}
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 < (size_t)n; i++) {
// Use double-hashing to generate a sequence of hash values.
// See analysis in [Kirsch,Mitzenmacher 2006].
uint32_t h = hash_func_(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 = hash_func_(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