存储原理:根据hash算法计算出存储地址,计算根据负载因子(需要存储大小/可分配内存块大小),根据最适合的负载因子去匹配存储地址
分布式原理:一个负载均衡的机子分发不同的请求到不同的服务器,分发原理,根据不同机子负责不同的hashcode来匹配
package com.test;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.util.List;
import java.util.SortedMap;
import java.util.TreeMap;
public class Care
{
public class Shard<S> { // S类封装了机器节点的信息 ,如name、password、ip、port等
private TreeMap<Long, S> nodes; // 虚拟节点
private List<S> shards; // 真实机器节点
private final int NODE_NUM = 100; // 每个机器节点关联的虚拟节点个数
public Shard(List<S> shards) {
super();
this.shards = shards;
init();
}
private void init() { // 初始化一致性hash环
nodes = new TreeMap<Long, S>();
for (int i = 0; i != shards.size(); ++i) { // 每个真实机器节点都需要关联虚拟节点
final S shardInfo = shards.get(i);
for (int n = 0; n < NODE_NUM; n++)
// 一个真实机器节点关联NODE_NUM个虚拟节点
nodes.put(hash("SHARD-" + i + "-NODE-" + n), shardInfo);
}
}
public S getShardInfo(String key) {
SortedMap<Long, S> tail = nodes.tailMap(hash(key)); // 沿环的顺时针找到一个虚拟节点
if (tail.size() == 0) {
return nodes.get(nodes.firstKey());
}
return tail.get(tail.firstKey()); // 返回该虚拟节点对应的真实机器节点的信息
}
/**
* MurMurHash算法,是非加密HASH算法,性能很高,
* 比传统的CRC32,MD5,SHA-1(这两个算法都是加密HASH算法,复杂度本身就很高,带来的性能上的损害也不可避免)
* 等HASH算法要快很多,而且据说这个算法的碰撞率很低.
*/
private Long hash(String key) {
ByteBuffer buf = ByteBuffer.wrap(key.getBytes());
int seed = 0x1234ABCD;
ByteOrder byteOrder = buf.order();
buf.order(ByteOrder.LITTLE_ENDIAN);
long m = 0xc6a4a7935bd1e995L;
int r = 47;
long h = seed ^ (buf.remaining() * m);
long k;
while (buf.remaining() >= 8) {
k = buf.getLong();
k *= m;
k ^= k >>> r;
k *= m;
h ^= k;
h *= m;
}
if (buf.remaining() > 0) {
ByteBuffer finish = ByteBuffer.allocate(8).order(
ByteOrder.LITTLE_ENDIAN);
// for big-endian version, do this first:
// finish.position(8-buf.remaining());
finish.put(buf).rewind();
h ^= finish.getLong();
h *= m;
}
h ^= h >>> r;
h *= m;
h ^= h >>> r;
buf.order(byteOrder);
return h;
}
}
}
package com.test;
public class NormalHash
{
/**
* 加法hash
*
* @param key
* 字符串
* @param prime
* 一个质数
* @return hash结果
*/
public static int additiveHash(String key, int prime) {
int hash, i;
for (hash = key.length(), i = 0; i < key.length(); i++)
hash += key.charAt(i);
return (hash % prime);
}
/**
* 旋转hash
*
* @param key
* 输入字符串
* @param prime
* 质数
* @return hash值
*/
public static int rotatingHash(String key, int prime) {
int hash, i;
for (hash = key.length(), i = 0; i < key.length(); ++i)
hash = (hash << 4) ^ (hash >> 28) ^ key.charAt(i);
return (hash % prime);
// return (hash ^ (hash>>10) ^ (hash>>20));
}
/**
* MASK值,随便找一个值,最好是质数
*/
static int M_MASK = 0x8765fed1;
/**
* 一次一个hash
*
* @param key
* 输入字符串
* @return 输出hash值
*/
public static int oneByOneHash(String key) {
int hash, i;
for (hash = 0, i = 0; i < key.length(); ++i) {
hash += key.charAt(i);
hash += (hash << 10);
hash ^= (hash >> 6);
}
hash += (hash << 3);
hash ^= (hash >> 11);
hash += (hash << 15);
// return (hash & M_MASK);
return hash;
}
/**
* Bernstein's hash
*
* @param key
* 输入字节数组
* @param level
* 初始hash常量
* @return 结果hash
*/
public static int bernstein(String key) {
int hash = 0;
int i;
for (i = 0; i < key.length(); ++i)
hash = 33 * hash + key.charAt(i);
return hash;
}
/**
* Universal Hashing
*/
public static int universal(char[] key, int mask, int[] tab) {
int hash = key.length, i, len = key.length;
for (i = 0; i < (len << 3); i += 8) {
char k = key[i >> 3];
if ((k & 0x01) == 0)
hash ^= tab[i + 0];
if ((k & 0x02) == 0)
hash ^= tab[i + 1];
if ((k & 0x04) == 0)
hash ^= tab[i + 2];
if ((k & 0x08) == 0)
hash ^= tab[i + 3];
if ((k & 0x10) == 0)
hash ^= tab[i + 4];
if ((k & 0x20) == 0)
hash ^= tab[i + 5];
if ((k & 0x40) == 0)
hash ^= tab[i + 6];
if ((k & 0x80) == 0)
hash ^= tab[i + 7];
}
return (hash & mask);
}
/**
* Zobrist Hashing
*/
public static int zobrist(char[] key, int mask, int[][] tab) {
int hash, i;
for (hash = key.length, i = 0; i < key.length; ++i)
hash ^= tab[i][key[i]];
return (hash & mask);
}
// LOOKUP3
// 见Bob Jenkins(3).c文件
// 32位FNV算法
static int M_SHIFT = 0;
/**
* 32位的FNV算法
*
* @param data
* 数组
* @return int值
*/
public static int FNVHash(byte[] data) {
int hash = (int) 2166136261L;
for (byte b : data)
hash = (hash * 16777619) ^ b;
if (M_SHIFT == 0)
return hash;
return (hash ^ (hash >> M_SHIFT)) & M_MASK;
}
/**
* 改进的32位FNV算法1
*
* @param data
* 数组
* @return int值
*/
public static int FNVHash1(byte[] data) {
final int p = 16777619;
int hash = (int) 2166136261L;
for (byte b : data)
hash = (hash ^ b) * p;
hash += hash << 13;
hash ^= hash >> 7;
hash += hash << 3;
hash ^= hash >> 17;
hash += hash << 5;
return hash;
}
/**
* 改进的32位FNV算法1
*
* @param data
* 字符串
* @return int值
*/
public static int FNVHash1(String data) {
final int p = 16777619;
int hash = (int) 2166136261L;
for (int i = 0; i < data.length(); i++)
hash = (hash ^ data.charAt(i)) * p;
hash += hash << 13;
hash ^= hash >> 7;
hash += hash << 3;
hash ^= hash >> 17;
hash += hash << 5;
return hash;
}
/**
* Thomas Wang的算法,整数hash
*/
public static int intHash(int key) {
key += ~(key << 15);
key ^= (key >>> 10);
key += (key << 3);
key ^= (key >>> 6);
key += ~(key << 11);
key ^= (key >>> 16);
return key;
}
/**
* RS算法hash
*
* @param str
* 字符串
*/
public static int RSHash(String str) {
int b = 378551;
int a = 63689;
int hash = 0;
for (int i = 0; i < str.length(); i++) {
hash = hash * a + str.charAt(i);
a = a * b;
}
return (hash & 0x7FFFFFFF);
}
/* End Of RS Hash Function */
/**
* JS算法
*/
public static int JSHash(String str) {
int hash = 1315423911;
for (int i = 0; i < str.length(); i++) {
hash ^= ((hash << 5) + str.charAt(i) + (hash >> 2));
}
return (hash & 0x7FFFFFFF);
}
/* End Of JS Hash Function */
/**
* PJW算法
*/
public static int PJWHash(String str) {
int BitsInUnsignedInt = 32;
int ThreeQuarters = (BitsInUnsignedInt * 3) / 4;
int OneEighth = BitsInUnsignedInt / 8;
int HighBits = 0xFFFFFFFF << (BitsInUnsignedInt - OneEighth);
int hash = 0;
int test = 0;
for (int i = 0; i < str.length(); i++) {
hash = (hash << OneEighth) + str.charAt(i);
if ((test = hash & HighBits) != 0) {
hash = ((hash ^ (test >> ThreeQuarters)) & (~HighBits));
}
}
return (hash & 0x7FFFFFFF);
}
/* End Of P. J. Weinberger Hash Function */
/**
* ELF算法
*/
public static int ELFHash(String str) {
int hash = 0;
int x = 0;
for (int i = 0; i < str.length(); i++) {
hash = (hash << 4) + str.charAt(i);
if ((x = (int) (hash & 0xF0000000L)) != 0) {
hash ^= (x >> 24);
hash &= ~x;
}
}
return (hash & 0x7FFFFFFF);
}
/* End Of ELF Hash Function */
/**
* BKDR算法
*/
public static int BKDRHash(String str) {
int seed = 131; // 31 131 1313 13131 131313 etc..
int hash = 0;
for (int i = 0; i < str.length(); i++) {
hash = (hash * seed) + str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of BKDR Hash Function */
/**
* SDBM算法
*/
public static int SDBMHash(String str) {
int hash = 0;
for (int i = 0; i < str.length(); i++) {
hash = str.charAt(i) + (hash << 6) + (hash << 16) - hash;
}
return (hash & 0x7FFFFFFF);
}
/* End Of SDBM Hash Function */
/**
* DJB算法
*/
public static int DJBHash(String str) {
int hash = 5381;
for (int i = 0; i < str.length(); i++) {
hash = ((hash << 5) + hash) + str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of DJB Hash Function */
/**
* DEK算法
*/
public static int DEKHash(String str) {
int hash = str.length();
for (int i = 0; i < str.length(); i++) {
hash = ((hash << 5) ^ (hash >> 27)) ^ str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of DEK Hash Function */
/**
* AP算法
*/
public static int APHash(String str) {
int hash = 0;
for (int i = 0; i < str.length(); i++) {
hash ^= ((i & 1) == 0) ? ((hash << 7) ^ str.charAt(i) ^ (hash >> 3))
: (~((hash << 11) ^ str.charAt(i) ^ (hash >> 5)));
}
// return (hash & 0x7FFFFFFF);
return hash;
}
/* End Of AP Hash Function */
/**
* JAVA自己带的算法
*/
public static int java(String str) {
int h = 0;
int off = 0;
int len = str.length();
for (int i = 0; i < len; i++) {
h = 31 * h + str.charAt(off++);
}
return h;
}
/**
* 混合hash算法,输出64位的值
*/
public static long mixHash(String str) {
long hash = str.hashCode();
hash <<= 32;
hash |= FNVHash1(str);
return hash;
}
}