Nginx源码完全注释（6）core/murmurhash

下面是摘自 Google Code 的 Murmurhash 开源项目主页上的 Murmurhash2，Nginx 就是采用的这个。

uint32_t MurmurHash2 ( const void * key, int len, uint32_t seed )
{
  // 'm' and 'r' are mixing constants generated offline.
  // They're not really 'magic', they just happen to work well.

  const uint32_t m = 0x5bd1e995;
  const int r = 24;

  // Initialize the hash to a 'random' value

  uint32_t h = seed ^ len;

  // Mix 4 bytes at a time into the hash

  const unsigned char * data = (const unsigned char *)key;

  while(len >= 4)
  {
    uint32_t k = *(uint32_t*)data;

    k *= m;
    k ^= k >> r;
    k *= m;

    h *= m;
    h ^= k;

    data += 4;
    len -= 4;
  }

  // Handle the last few bytes of the input array

  switch(len)
  {
  case 3: h ^= data[2] << 16;
  case 2: h ^= data[1] << 8;
  case 1: h ^= data[0];
      h *= m;
  };

  // Do a few final mixes of the hash to ensure the last few
  // bytes are well-incorporated.

  h ^= h >> 13;
  h *= m;
  h ^= h >> 15;

  return h;
}

下面是 Nginx 中 Murmurhash 的源码，基本与上面无异。

uint32_t
ngx_murmur_hash2(u_char *data, size_t len)
{
    uint32_t  h, k;

    h = 0 ^ len;

    while (len >= 4) {
        k  = data[0];
        k |= data[1] << 8;
        k |= data[2] << 16;
        k |= data[3] << 24;

        k *= 0x5bd1e995;
        k ^= k >> 24;
        k *= 0x5bd1e995;

        h *= 0x5bd1e995;
        h ^= k;

        data += 4;
        len -= 4;
    }

    switch (len) {
    case 3:
        h ^= data[2] << 16;
    case 2:
        h ^= data[1] << 8;
    case 1:
        h ^= data[0];
        h *= 0x5bd1e995;
    }

    h ^= h >> 13;
    h *= 0x5bd1e995;
    h ^= h >> 15;

    return h;
}

Reference

1. Murmurhash2