简介
分布式id算法, 生成的id是一个long类型, java中long类型是8个字节, 64bit
- 第1位占用1bit,其值始终是0,可看做是符号位不使用。
- 第2位开始的41位是时间戳,41-bit位可表示2^41个数,每个数代表毫秒,那么雪花算法可用的时间年限是(1L<<41)/(1000L_3600_24*365)=69 年的时间。
- 中间的10-bit位可表示机器数,即2^10 = 1024台机器,但是一般情况下我们不会部署这么台机器。如果我们对IDC(互联网数据中心)有需求,还可以将 10-bit 分 5-bit 给 IDC,分5-bit给工作机器。这样就可以表示32个IDC,每个IDC下可以有32台机器,具体的划分可以根据自身需求定义。
- 最后12-bit位是自增序列,可表示2^12 = 4096个数。
另外,⼀切互联⽹公司也基于上述的⽅案封装了⼀些分布式ID⽣成器,⽐如滴滴的tinyid(基于数 据库实现)、百度的uidgenerator(基于SnowFlake)和美团的leaf(基于数据库和SnowFlake)
实现
public class IdWorker{
//下面两个每个5位,加起来就是10位的工作机器id
private long workerId; //工作id
private long datacenterId; //数据id
//12位的序列号
private long sequence;
public IdWorker(long workerId, long datacenterId, long sequence){
// sanity check for workerId
if (workerId > maxWorkerId || workerId < 0) {
throw new IllegalArgumentException(String.format("worker Id can't be greater than %d or less than 0",maxWorkerId));
}
if (datacenterId > maxDatacenterId || datacenterId < 0) {
throw new IllegalArgumentException(String.format("datacenter Id can't be greater than %d or less than 0",maxDatacenterId));
}
System.out.printf("worker starting. timestamp left shift %d, datacenter id bits %d, worker id bits %d, sequence bits %d, workerid %d",
timestampLeftShift, datacenterIdBits, workerIdBits, sequenceBits, workerId);
this.workerId = workerId;
this.datacenterId = datacenterId;
this.sequence = sequence;
}
//初始时间戳
private long twepoch = 1288834974657L;
//长度为5位
private long workerIdBits = 5L;
private long datacenterIdBits = 5L;
//最大值
private long maxWorkerId = -1L ^ (-1L << workerIdBits);
private long maxDatacenterId = -1L ^ (-1L << datacenterIdBits);
//序列号id长度
private long sequenceBits = 12L;
//序列号最大值
private long sequenceMask = -1L ^ (-1L << sequenceBits);
//工作id需要左移的位数,12位
private long workerIdShift = sequenceBits;
//数据id需要左移位数 12+5=17位
private long datacenterIdShift = sequenceBits + workerIdBits;
//时间戳需要左移位数 12+5+5=22位
private long timestampLeftShift = sequenceBits + workerIdBits + datacenterIdBits;
//上次时间戳,初始值为负数
private long lastTimestamp = -1L;
public long getWorkerId(){
return workerId;
}
public long getDatacenterId(){
return datacenterId;
}
public long getTimestamp(){
return System.currentTimeMillis();
}
//下一个ID生成算法
public synchronized long nextId() {
long timestamp = timeGen();
//获取当前时间戳如果小于上次时间戳,则表示时间戳获取出现异常
if (timestamp < lastTimestamp) {
System.err.printf("clock is moving backwards. Rejecting requests until %d.", lastTimestamp);
throw new RuntimeException(String.format("Clock moved backwards. Refusing to generate id for %d milliseconds",
lastTimestamp - timestamp));
}
//获取当前时间戳如果等于上次时间戳
//说明:还处在同一毫秒内,则在序列号加1;否则序列号赋值为0,从0开始。
if (lastTimestamp == timestamp) { // 0 - 4095
sequence = (sequence + 1) & sequenceMask;
if (sequence == 0) {
timestamp = tilNextMillis(lastTimestamp);
}
} else {
sequence = 0;
}
//将上次时间戳值刷新
lastTimestamp = timestamp;
/**
* 返回结果:
* (timestamp - twepoch) << timestampLeftShift) 表示将时间戳减去初始时间戳,再左移相应位数
* (datacenterId << datacenterIdShift) 表示将数据id左移相应位数
* (workerId << workerIdShift) 表示将工作id左移相应位数
* | 是按位或运算符,例如:x | y,只有当x,y都为0的时候结果才为0,其它情况结果都为1。
* 因为个部分只有相应位上的值有意义,其它位上都是0,所以将各部分的值进行 | 运算就能得到最终拼接好的id
*/
return ((timestamp - twepoch) << timestampLeftShift) |
(datacenterId << datacenterIdShift) |
(workerId << workerIdShift) |
sequence;
}
//获取时间戳,并与上次时间戳比较
private long tilNextMillis(long lastTimestamp) {
long timestamp = timeGen();
while (timestamp <= lastTimestamp) {
timestamp = timeGen();
}
return timestamp;
}
//获取系统时间戳
private long timeGen(){
return System.currentTimeMillis();
}
public static void main(String[] args) {
IdWorker worker = new IdWorker(21,10,0);
for (int i = 0; i < 100; i++) {
System.out.println(worker.nextId());
}
}
}