andreacavalli/rocksdb
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

bits_per_key is already configurable. It defines how many bloom bits will be used for every key in the database.

Browse Source 
My change in this patch is to make the Hash code that is used for blooms to be confgurable. In fact,
one can specify a modified HashCode that inspects only parts of the Key to generate the Hash (used
by booms).

Test Plan: none

Differential Revision: https://reviews.facebook.net/D4059
This commit is contained in:
Dhruba Borthakur 2012-07-09 17:31:12 -07:00
parent 80c663882a
commit d11b637f34
1 changed files with 17 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
util/bloom.cc
View File

@ -18,16 +18,27 @@ class BloomFilterPolicy : public FilterPolicy {
private: private:
size_t bits_per_key_; size_t bits_per_key_;
size_t k_; size_t k_;
uint32_t (*hash_func_)(const Slice& key);
public: void initialize() {
explicit BloomFilterPolicy(int bits_per_key)
: bits_per_key_(bits_per_key) {
// We intentionally round down to reduce probing cost a little bit // 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) k_ = static_cast<size_t>(bits_per_key_ * 0.69); // 0.69 =~ ln(2)
if (k_ < 1) k_ = 1; if (k_ < 1) k_ = 1;
if (k_ > 30) k_ = 30; 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 { virtual const char* Name() const {
return "leveldb.BuiltinBloomFilter"; return "leveldb.BuiltinBloomFilter";
} }
@ -50,7 +61,7 @@ class BloomFilterPolicy : public FilterPolicy {
for (size_t i = 0; i < n; i++) { for (size_t i = 0; i < n; i++) {
// Use double-hashing to generate a sequence of hash values. // Use double-hashing to generate a sequence of hash values.
// See analysis in [Kirsch,Mitzenmacher 2006]. // See analysis in [Kirsch,Mitzenmacher 2006].
uint32_t h = BloomHash(keys[i]); uint32_t h = hash_func_(keys[i]);
const uint32_t delta = (h >> 17) | (h << 15); // Rotate right 17 bits const uint32_t delta = (h >> 17) | (h << 15); // Rotate right 17 bits
for (size_t j = 0; j < k_; j++) { for (size_t j = 0; j < k_; j++) {
const uint32_t bitpos = h % bits; const uint32_t bitpos = h % bits;
@ -76,7 +87,7 @@ class BloomFilterPolicy : public FilterPolicy {
return true; return true;
} }
uint32_t h = BloomHash(key); uint32_t h = hash_func_(key);
const uint32_t delta = (h >> 17) | (h << 15); // Rotate right 17 bits const uint32_t delta = (h >> 17) | (h << 15); // Rotate right 17 bits
for (size_t j = 0; j < k; j++) { for (size_t j = 0; j < k; j++) {
const uint32_t bitpos = h % bits; const uint32_t bitpos = h % bits;