哈希算法在很多系统中有应用，除了在hashmap等数据结构中用外在负载均衡上也有应用，hash算法的性能直接影响很多底层应用，最近在看leveldb源码看到里面用到的hash算法，具体记录一下。
MurmurHash算法介绍
MurmurHash 是一种非加密型哈希函数，适用于一般的哈希检索操作。由Austin Appleby github地址 在2008年发明，并出现了多个变种，都已经发布到了公有领域。与其它流行的哈希函数相比，对于规律性较强的key，MurmurHash的随机分布特征表现更良好，现在在libstdc++，hadoop和nginx等很多著名开源项目中使用。 MurmurHash3的实现，代码
void MurmurHash3_x64_128 ( const void * key, const int len,
const uint32_t seed, void * out )
{
const uint8_t * data = (const uint8_t*)key;
const int nblocks = len / 16;
uint64_t h1 = seed;
uint64_t h2 = seed;
const uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
const uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f);
//----------
// body
const uint64_t * blocks = (const uint64_t *)(data);
for(int i = 0; i < nblocks; i++)
{
uint64_t k1 = getblock64(blocks,i*2+0);
uint64_t k2 = getblock64(blocks,i*2+1);
k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;
k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
}
//----------
// tail
const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
uint64_t k1 = 0;
uint64_t k2 = 0;
switch(len & 15)
{
case 15: k2 ^= ((uint64_t)tail[14]) << 48;
case 14: k2 ^= ((uint64_t)tail[13]) << 40;
case 13: k2 ^= ((uint64_t)tail[12]) << 32;
case 12: k2 ^= ((uint64_t)tail[11]) << 24;
case 11: k2 ^= ((uint64_t)tail[10]) << 16;
case 10: k2 ^= ((uint64_t)tail[ 9]) << 8;
case 9: k2 ^= ((uint64_t)tail[ 8]) << 0;
k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
case 8: k1 ^= ((uint64_t)tail[ 7]) << 56;
case 7: k1 ^= ((uint64_t)tail[ 6]) << 48;
case 6: k1 ^= ((uint64_t)tail[ 5]) << 40;
case 5: k1 ^= ((uint64_t)tail[ 4]) << 32;
case 4: k1 ^= ((uint64_t)tail[ 3]) << 24;
case 3: k1 ^= ((uint64_t)tail[ 2]) << 16;
case 2: k1 ^= ((uint64_t)tail[ 1]) << 8;
case 1: k1 ^= ((uint64_t)tail[ 0]) << 0;
k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
};
//----------
// finalization
h1 ^= len; h2 ^= len;
h1 += h2;
h2 += h1;
h1 = fmix64(h1);
h2 = fmix64(h2);
h1 += h2;
h2 += h1;
((uint64_t*)out)[0] = h1;
((uint64_t*)out)[1] = h2;
}
leveldb实现
uint32_t Hash(const char* data, size_t n, uint32_t seed) {
// Similar to murmur hash
const uint32_t m = 0xc6a4a793;
const uint32_t r = 24;
const char* limit = data + n;
uint32_t h = seed ^ (n * m);
// Pick up four bytes at a time
while (data + 4 <= limit) {
uint32_t w = DecodeFixed32(data);
data += 4;
h += w;
h *= m;
h ^= (h >> 16);
}
// Pick up remaining bytes
switch (limit - data) {
case 3:
h += static_cast<unsigned char>(data[2]) << 16;
FALLTHROUGH_INTENDED;
case 2:
h += static_cast<unsigned char>(data[1]) << 8;
FALLTHROUGH_INTENDED;
case 1:
h += static_cast<unsigned char>(data[0]);
h *= m;
h ^= (h >> r);
break;
}
return h;
}
总结
MurmurHash算法的速度大概是FNV算法的三倍左右，并且相对简单，随机型更好，可以用作以后的工作和使用。