SnowFlake算法生成id的结果是一个64bit大小的整数,它的结构如下图:
1位
,不用。二进制中最高位为1的都是负数,但是我们生成的id一般都使用整数,所以这个最高位固定是0-
41位
,用来记录时间戳(毫秒)。- 41位可以表示$2^{41}-1$个数字,
- 如果只用来表示正整数(计算机中正数包含0),可以表示的数值范围是:0 至 $2^{41}-1$,减1是因为可表示的数值范围是从0开始算的,而不是1。
- 也就是说41位可以表示$2^{41}-1$个毫秒的值,转化成单位年则是$(2^{41}-1) / (1000 * 60 * 60 * 24 * 365) = 69$年
-
10位
,用来记录工作机器id。- 可以部署在$2^{10} = 1024$个节点,包括
5位datacenterId
和5位workerId
5位(bit)
可以表示的最大正整数是$2^{5}-1 = 31$,即可以用0、1、2、3、....31这32个数字,来表示不同的datecenterId或workerId
- 可以部署在$2^{10} = 1024$个节点,包括
-
12位
,序列号,用来记录同毫秒内产生的不同id。12位(bit)
可以表示的最大正整数是$2^{12}-1 = 4095$,即可以用0、1、2、3、....4094这4095个数字,来表示同一机器同一时间截(毫秒)内产生的4095个ID序号
由于在Java中64bit的整数是long类型,所以在Java中SnowFlake算法生成的id就是long来存储的。
SnowFlake可以保证:
- 所有生成的id按时间趋势递增
- 整个分布式系统内不会产生重复id(因为有datacenterId和workerId来做区分)
java 代码实现1
public class IdWorker{
private long workerId;
private long datacenterId;
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;
}
private long twepoch = 1288834974657L;
private long workerIdBits = 5L;
private long datacenterIdBits = 5L;
private long maxWorkerId = -1L ^ (-1L << workerIdBits);
private long maxDatacenterId = -1L ^ (-1L << datacenterIdBits);
private long sequenceBits = 12L;
private long workerIdShift = sequenceBits;
private long datacenterIdShift = sequenceBits + workerIdBits;
private long timestampLeftShift = sequenceBits + workerIdBits + datacenterIdBits;
private long sequenceMask = -1L ^ (-1L << sequenceBits);
private long lastTimestamp = -1L;
public long getWorkerId(){
return workerId;
}
public long getDatacenterId(){
return datacenterId;
}
public long getTimestamp(){
return System.currentTimeMillis();
}
public synchronized long nextId() {
long timestamp = timeGen();
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));
}
if (lastTimestamp == timestamp) {
sequence = (sequence + 1) & sequenceMask;
if (sequence == 0) {
timestamp = tilNextMillis(lastTimestamp);
}
} else {
sequence = 0;
}
lastTimestamp = timestamp;
return ((timestamp - twepoch) << timestampLeftShift) |
(datacenterId << datacenterIdShift) |
(workerId << workerIdShift) |
sequence;
}
private long tilNextMillis(long lastTimestamp) {
long timestamp = timeGen();
while (timestamp <= lastTimestamp) {
timestamp = timeGen();
}
return timestamp;
}
private long timeGen(){
return System.currentTimeMillis();
}
//---------------测试---------------
public static void main(String[] args) {
IdWorker worker = new IdWorker(1,1,1);
for (int i = 0; i < 30; i++) {
System.out.println(worker.nextId());
}
}
}
java代码实现2
/**
* Twitter_Snowflake<br>
* SnowFlake的结构如下(每部分用-分开):<br>
* 0 - 0000000000 0000000000 0000000000 0000000000 0 - 00000 - 00000 - 000000000000 <br>
* 1位标识,由于long基本类型在Java中是带符号的,最高位是符号位,正数是0,负数是1,所以id一般是正数,最高位是0<br>
* 41位时间截(毫秒级),注意,41位时间截不是存储当前时间的时间截,而是存储时间截的差值(当前时间截 - 开始时间截)
* 得到的值),这里的的开始时间截,一般是我们的id生成器开始使用的时间,由我们程序来指定的(如下下面程序IdWorker类的startTime属性)。41位的时间截,可以使用69年,年T = (1L << 41) / (1000L * 60 * 60 * 24 * 365) = 69<br>
* 10位的数据机器位,可以部署在1024个节点,包括5位datacenterId和5位workerId<br>
* 12位序列,毫秒内的计数,12位的计数顺序号支持每个节点每毫秒(同一机器,同一时间截)产生4096个ID序号<br>
* 加起来刚好64位,为一个Long型。<br>
* SnowFlake的优点是,整体上按照时间自增排序,并且整个分布式系统内不会产生ID碰撞(由数据中心ID和机器ID作区分),并且效率较高,经测试,SnowFlake每秒能够产生26万ID左右。
*/
public class SnowflakeIdWorker {
// ==============================Fields===========================================
/** 开始时间截 (2015-01-01) */
private final long twepoch = 1420041600000L;
/** 机器id所占的位数 */
private final long workerIdBits = 5L;
/** 数据标识id所占的位数 */
private final long datacenterIdBits = 5L;
/** 支持的最大机器id,结果是31 (这个移位算法可以很快的计算出几位二进制数所能表示的最大十进制数) */
private final long maxWorkerId = -1L ^ (-1L << workerIdBits);
/** 支持的最大数据标识id,结果是31 */
private final long maxDatacenterId = -1L ^ (-1L << datacenterIdBits);
/** 序列在id中占的位数 */
private final long sequenceBits = 12L;
/** 机器ID向左移12位 */
private final long workerIdShift = sequenceBits;
/** 数据标识id向左移17位(12+5) */
private final long datacenterIdShift = sequenceBits + workerIdBits;
/** 时间截向左移22位(5+5+12) */
private final long timestampLeftShift = sequenceBits + workerIdBits + datacenterIdBits;
/** 生成序列的掩码,这里为4095 (0b111111111111=0xfff=4095) */
private final long sequenceMask = -1L ^ (-1L << sequenceBits);
/** 工作机器ID(0~31) */
private long workerId;
/** 数据中心ID(0~31) */
private long datacenterId;
/** 毫秒内序列(0~4095) */
private long sequence = 0L;
/** 上次生成ID的时间截 */
private long lastTimestamp = -1L;
//==============================Constructors=====================================
/**
* 构造函数
* @param workerId 工作ID (0~31)
* @param datacenterId 数据中心ID (0~31)
*/
public SnowflakeIdWorker(long workerId, long datacenterId) {
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));
}
this.workerId = workerId;
this.datacenterId = datacenterId;
}
// ==============================Methods==========================================
/**
* 获得下一个ID (该方法是线程安全的)
* @return SnowflakeId
*/
public synchronized long nextId() {
long timestamp = timeGen();
//如果当前时间小于上一次ID生成的时间戳,说明系统时钟回退过这个时候应当抛出异常
if (timestamp < lastTimestamp) {
throw new RuntimeException(
String.format("Clock moved backwards. Refusing to generate id for %d milliseconds", lastTimestamp - timestamp));
}
//如果是同一时间生成的,则进行毫秒内序列
if (lastTimestamp == timestamp) {
sequence = (sequence + 1) & sequenceMask;
//毫秒内序列溢出
if (sequence == 0) {
//阻塞到下一个毫秒,获得新的时间戳
timestamp = tilNextMillis(lastTimestamp);
}
}
//时间戳改变,毫秒内序列重置
else {
sequence = 0L;
}
//上次生成ID的时间截
lastTimestamp = timestamp;
//移位并通过或运算拼到一起组成64位的ID
return ((timestamp - twepoch) << timestampLeftShift) //
| (datacenterId << datacenterIdShift) //
| (workerId << workerIdShift) //
| sequence;
}
/**
* 阻塞到下一个毫秒,直到获得新的时间戳
* @param lastTimestamp 上次生成ID的时间截
* @return 当前时间戳
*/
protected long tilNextMillis(long lastTimestamp) {
long timestamp = timeGen();
while (timestamp <= lastTimestamp) {
timestamp = timeGen();
}
return timestamp;
}
/**
* 返回以毫秒为单位的当前时间
* @return 当前时间(毫秒)
*/
protected long timeGen() {
return System.currentTimeMillis();
}
//==============================Test=============================================
/** 测试 */
public static void main(String[] args) {
SnowflakeIdWorker idWorker = new SnowflakeIdWorker(0, 0);
for (int i = 0; i < 1000; i++) {
long id = idWorker.nextId();
System.out.println(Long.toBinaryString(id));
System.out.println(id);
}
}
}
java代码实现3
public class SnowFlake {
// 起始的时间戳
private final static long START_STMP = 1480166465631L;
// 每一部分占用的位数,就三个
private final static long SEQUENCE_BIT = 12;// 序列号占用的位数
private final static long MACHINE_BIT = 5; // 机器标识占用的位数
private final static long DATACENTER_BIT = 5;// 数据中心占用的位数
// 每一部分最大值
private final static long MAX_DATACENTER_NUM = -1L ^ (-1L << DATACENTER_BIT);
private final static long MAX_MACHINE_NUM = -1L ^ (-1L << MACHINE_BIT);
private final static long MAX_SEQUENCE = -1L ^ (-1L << SEQUENCE_BIT);
// 每一部分向左的位移
private final static long MACHINE_LEFT = SEQUENCE_BIT;
private final static long DATACENTER_LEFT = SEQUENCE_BIT + MACHINE_BIT;
private final static long TIMESTMP_LEFT = DATACENTER_LEFT + DATACENTER_BIT;
private long datacenterId; // 数据中心
private long machineId; // 机器标识
private long sequence = 0L; // 序列号
private long lastStmp = -1L;// 上一次时间戳
public SnowFlake(long datacenterId, long machineId) {
if (datacenterId > MAX_DATACENTER_NUM || datacenterId < 0) {
throw new IllegalArgumentException("datacenterId can't be greater than MAX_DATACENTER_NUM or less than 0");
}
if (machineId > MAX_MACHINE_NUM || machineId < 0) {
throw new IllegalArgumentException("machineId can't be greater than MAX_MACHINE_NUM or less than 0");
}
this.datacenterId = datacenterId;
this.machineId = machineId;
}
//产生下一个ID
public synchronized long nextId() {
long currStmp = getNewstmp();
if (currStmp < lastStmp) {
throw new RuntimeException("Clock moved backwards. Refusing to generate id");
}
if (currStmp == lastStmp) {
//if条件里表示当前调用和上一次调用落在了相同毫秒内,只能通过第三部分,序列号自增来判断为唯一,所以+1.
sequence = (sequence + 1) & MAX_SEQUENCE;
//同一毫秒的序列数已经达到最大,只能等待下一个毫秒
if (sequence == 0L) {
currStmp = getNextMill();
}
} else {
//不同毫秒内,序列号置为0
//执行到这个分支的前提是currTimestamp > lastTimestamp,说明本次调用跟上次调用对比,已经不再同一个毫秒内了,这个时候序号可以重新回置0了。
sequence = 0L;
}
lastStmp = currStmp;
//就是用相对毫秒数、机器ID和自增序号拼接
return (currStmp - START_STMP) << TIMESTMP_LEFT //时间戳部分
| datacenterId << DATACENTER_LEFT //数据中心部分
| machineId << MACHINE_LEFT //机器标识部分
| sequence; //序列号部分
}
private long getNextMill() {
long mill = getNewstmp();
while (mill <= lastStmp) {
mill = getNewstmp();
}
return mill;
}
private long getNewstmp() {
return System.currentTimeMillis();
}
}
测试代码
public class Test {
public static void main(String[] args) {
// 构造方法设置机器码:第9个机房的第20台机器
SnowFlake snowFlake = new SnowFlake(9, 20);
for(int i =0; i <(1<< 12); i++){
System.out.println(snowFlake.nextId());
}
}
}
参考博文:https://segmentfault.com/a/1190000011282426
https://www.cnblogs.com/relucent/p/4955340.html
https://blog.youkuaiyun.com/weixin_39433171/article/details/80672312