twitter的snowflake算法

推特的工程师snowflake也提出了一个在分布式系统中生成唯一序列的方法；

java中的UUID也是一种可取的方法，他的缺点是序列号太长了。

snowflake算法最原始的形式是用scala语言写的https://github.com/twitter/snowflake/releases/tag/snowflake-2010

核心代码为其IdWorker这个类实现，其原理结构如下，分别用一个0表示一位，用—分割开部分的作用：

在上面的字符串中，第一位为未使用（实际上也可作为long的符号位），接下来的41位为毫秒级时间，然后5位datacenter标识位，5位机器ID（并不算标识符，实际是为线程标识），然后12位该毫秒内的当前毫秒内的计数，加起来刚好64位，为一个Long型。

java实现：

package mine;

import util.Trie;

/** Snowflake */
public class IdWorker {

  private final long twepoch = 1288834974657L;
  private final long workerIdBits = 5L;
  private final long datacenterIdBits = 5L;
  private final long maxWorkerId = -1L ^ (-1L << workerIdBits);
  private final long maxDatacenterId = -1L ^ (-1L << datacenterIdBits);
  private final long sequenceBits = 12L;
  private final long workerIdShift = sequenceBits;
  private final long datacenterIdShift = sequenceBits + workerIdBits;
  private final long timestampLeftShift = sequenceBits + workerIdBits + datacenterIdBits;
  private final long sequenceMask = -1L ^ (-1L << sequenceBits);

  private long workerId;
  private long datacenterId;
  private long sequence = 0L;
  private long lastTimestamp = -1L;

  public IdWorker(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;
  }

  public synchronized long nextId() {
    long timestamp = timeGen();
    if (timestamp < 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 = 0L;
    }

    lastTimestamp = timestamp;

    return ((timestamp - twepoch) << timestampLeftShift) | (datacenterId << datacenterIdShift) | (workerId << workerIdShift) | sequence;
  }

  protected long tilNextMillis(long lastTimestamp) {
    long timestamp = timeGen();
    while (timestamp <= lastTimestamp) {
      timestamp = timeGen();
    }
    return timestamp;
  }

  protected long timeGen() {
    return System.currentTimeMillis();
  }

  private static Trie trie=new Trie();
  public static void main(String[] args) {
      long time0 = System.currentTimeMillis();
      IdWorker idWorker = new IdWorker(0, 0);
      for (int i = 0; i < 3000000; i++) {
          long id = idWorker.nextId();
          trie.insert(""+id);
          //System.out.println(id);
      }
      long time = (int)((System.currentTimeMillis()-time0)/1000);
      System.out.println("Time:"+time+"s  conflict:"+trie.count);
  }
}

测试：一百万条数据都没有冲突；

package mine;

import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

import util.Trie;

public class IdWorkerTest extends Thread{
    private static Trie trie=new Trie();
    private static Object lock = new Object();
    private static int count=0;
    static IdWorker worker = new IdWorker(0,0);
    public void run(){
        long squence =worker.nextId();
        System.out.println(squence);
        synchronized(lock){
            trie.insert(""+squence);
            count++;
            if(count%100==0){
                System.out.println("生成第"+count+"条数据  冲突计数："+trie.count);
            }
        }
    }

    public static void main(String[] args) {
        // TODO Auto-generated method stub
        int n =10000;
        ExecutorService executor = Executors.newFixedThreadPool(n);
        for(int i=0;i<100*n;i++){
            Thread thread = new IdWorkerTest();
            executor.execute(thread);
        }
        executor.shutdown();
        while(!executor.isTerminated()){}
        System.out.println("生成第"+count+"条数据  冲突计数："+trie.count);
        System.out.println("done");
    }

}