Python开发

python实现雪花算法根据时间戳生成id

import time
import uwsgi
import os
 
# 64位ID的划分
# 这是用来记录机器id的, 默认情况下这10bit会分成两部分前5bit代表数据中心,后5bit代表某个数据中心的机器id,默认情况下计算大概可以支持32*32 - 1= 1023台机器。
WORKER_ID_BITS = 5  # 某个数据中心的机器id
DATACENTER_ID_BITS = 5  # 数据中心
SEQUENCE_BITS = 12  # 循环位,来对应1毫秒内产生的不同的id, 大概可以满足1毫秒并发生成2^12-1=4095次id的要求
 
# 最大取值计算
MAX_WORKER_ID = -1 ^ (-1 << WORKER_ID_BITS)  # 2**5-1 0b11111
MAX_DATACENTER_ID = -1 ^ (-1 << DATACENTER_ID_BITS)
# 移位偏移计算
WOKER_ID_SHIFT = SEQUENCE_BITS
DATACENTER_ID_SHIFT = SEQUENCE_BITS + WORKER_ID_BITS
TIMESTAMP_LEFT_SHIFT = SEQUENCE_BITS + WORKER_ID_BITS + DATACENTER_ID_BITS
# 序号循环掩码
SEQUENCE_MASK = -1 ^ (-1 << SEQUENCE_BITS)
# Twitter元年时间戳
TWEPOCH = 1288834974657
 
 
class InvalidSystemClock(Exception):
    """
    时钟回拨异常
    """
    pass
 
 
class IdWorker(object):
    """
    用于生成IDs
    """
    def __init__(self, datacenter_id=0, worker_id=0, sequence=0):
        """
        初始化
        :param datacenter_id: 数据中心(机器区域)ID
        :param worker_id: 机器ID
        :param sequence: 起始序号
        """
        print("uwsgi.worker_id():", uwsgi.worker_id())
        worker_id = uwsgi.worker_id()
        print(f"init_IdWorker worker_id:{worker_id}")
        # sanity check
        if worker_id > MAX_WORKER_ID or worker_id < 0:
            raise ValueError('worker_id值越界')
 
        if datacenter_id > MAX_DATACENTER_ID or datacenter_id < 0:
            raise ValueError('datacenter_id值越界')
        self.worker_id = worker_id
        self.datacenter_id = datacenter_id
        self.sequence = sequence
        self.last_timestamp = -1  # 上次计算的时间戳
 
    def _gen_timestamp(self):
        """
        生成整数时间戳
        :return:int timestamp
        """
        return int(time.time() * 1000)
 
    def get_ids(self, count):
        ids = []
        for i in range(count):
            ids.append(self.get_id())
        return ids
 
    def get_id(self):
        """
        获取新ID
        :return:
        """
        timestamp = self._gen_timestamp()
        # 时钟回拨
        if timestamp < self.last_timestamp:
            print('clock is moving backwards. Rejecting requests until {}'.
                  format(self.last_timestamp))
            raise InvalidSystemClock
        if timestamp == self.last_timestamp:
            self.sequence = (self.sequence + 1) & SEQUENCE_MASK
            if self.sequence == 0:
                timestamp = self._til_next_millis(self.last_timestamp)
        else:
            self.sequence = 0
        self.last_timestamp = timestamp
        new_id = ((timestamp - TWEPOCH) << TIMESTAMP_LEFT_SHIFT) | (self.datacenter_id << DATACENTER_ID_SHIFT) | \
             (self.worker_id << WOKER_ID_SHIFT) | self.sequence
        return str(new_id)
 
    def _til_next_millis(self, last_timestamp):
        """
        等到下一毫秒
        """
        timestamp = self._gen_timestamp()
        while timestamp <= last_timestamp:
            timestamp = self._gen_timestamp()
        return timestamp
 
 
if __name__ == '__main__':
    worker = IdWorker(datacenter_id=0, worker_id=1)
    print(worker.get_id())
    print(len(str(worker.get_id())))

鉴于多进程会出现生成的唯一id相同的问题:因为uwsgi项目启动是多进程的形式,所以我采取用每个uwsgi woker id作为雪花生成器的机器id-worker_id; 分布式的情况,可以将你的集群中的机器编号,将每个机器的编号代入datacenter_id。这样正常的生产环境就可以保证生成的雪花id相同了。可以根据循环位个数来增加雪花id每毫秒生成的最大数量。理论上无限大