openGauss数据库源码解析系列文章——AI技术（四）：指标采集、预测与异常检测

def forecast(args):
    …
    # 如果没有指定预测方式，则默认使用’auto_arima’算法
    if not args.forecast_method:
        forecast_alg = get_instance('auto_arima')
    else:
        forecast_alg = get_instance(args.forecast_method)
    # 指标预测功能函数
    def forecast_metric(name, train_ts, save_path=None):
        …
            forecast_alg.fit(timeseries=train_ts)
            dates, values = forecast_alg.forecast(
                period=TimeString(args.forecast_periods).standard)
        date_range = "{start_date}~{end_date}".format(start_date=dates[0],
                                               end_date=dates[-1])
        display_table.add_row(
            [name, date_range, min(values), max(values), sum(values) / len(values)]
        )
# 校验存储路径
        if save_path:
            if not os.path.exists(os.path.dirname(save_path)):
                os.makedirs(os.path.dirname(save_path))
            with open(save_path, mode='w') as f:
                for date, value in zip(dates, values):
                    f.write(date + ',' + str(value) + '\n')
    # 从本地sqlite中抽取需要的数据
    with sqlite_storage.SQLiteStorage(database_path) as db:
        if args.metric_name:
            timeseries = db.get_timeseries(table=args.metric_name, period=max_rows)
            forecast_metric(args.metric_name, timeseries, args.save_path)
        else:
# 获取sqlite中所有的表名
            tables = db.get_all_tables()
            # 从每个表中抽取训练数据进行预测
for table in tables:
                timeseries = db.get_timeseries(table=table, period=max_rows)
                forecast_metric(table, timeseries)
# 输出结果
    print(display_table.get_string())
 
# 代码远程部署
def deploy(args):
    print('Please input the password of {user}@{host}: '.format(user=args.user, host=args.host))
# 格式化代码远程部署指令
    command = 'sh start.sh --deploy {host} {user} {project_path}' \
        .format(user=args.user,
                host=args.host,
                project_path=args.project_path)
    # 判断指令执行情况
if subprocess.call(shlex.split(command), cwd=SBIN_PATH) == 0:
        print("\nExecute successfully.")
    else:
        print("\nExecute unsuccessfully.")
… 
# 展示当前监控的参数
def show_metrics():
…
 
# 项目总入口
def main():
   …

class Daemon:
    """
    This class implements the function of running a process in the background."""
    
    def __init__(self):
        …
def daemon_process(self):
        # 注册退出函数
        atexit.register(lambda: os.remove(self.pid_file))
        signal.signal(signal.SIGTERM, handle_sigterm)
# 启动进程
    @staticmethod
    def start(self):
        try:
            self.daemon_process()
        except RuntimeError as msg:
            abnormal_exit(msg)
 
        self.function(*self.args, **self.kwargs)
    # 停止进程
    def stop(self):
        if not os.path.exists(self.pid_file):
            abnormal_exit("Process not running.")
 
        read_pid = read_pid_file(self.pid_file)
        if read_pid > 0:
            os.kill(read_pid, signal.SIGTERM)
        if read_pid_file(self.pid_file) < 0:
            os.remove(self.pid_file)

def agent_main():
…
    # 初始化通道管理器
cm = ChannelManager()
# 初始化数据源
    source = DBSource()
    http_sink = HttpSink(interval=params['sink_timer_interval'], url=url, context=context)
    source.channel_manager = cm
    http_sink.channel_manager = cm
    # 获取参数文件里面的功能函数
    for task_name, task_func in get_funcs(metric_task):
        source.add_task(name=task_name,
                        interval=params['source_timer_interval'],
                        task=task_func,
                        maxsize=params['channel_capacity'])
    source.start()
    http_sink.start()

# 通过时间戳获取最近一段时间的数据
def select_timeseries_by_timestamp(self, table, period):
…
# 通过编号获取最近一段时间的数据
def select_timeseries_by_number(self, table, number):
     …

class AlgModel(object):
    """
    This is the base class for forecasting algorithms.
    If we want to use our own forecast algorithm, we should follow some rules.
    """
 
    def __init__(self):
        pass
 
    @abstractmethod
    def fit(self, timeseries):
        pass
 
    @abstractmethod
    def forecast(self, period):
        pass
 
    def save(self, model_path):
        pass
 
    def load(self, model_path):
        pass

python main.py start –role collector

python main.py stop –role collector

python main.py start --user xxx --host xxx.xxx.xxx.xxx –project-path xxx –role collector

python main.py stop --user xxx --host xxx.xxx.xxx.xxx –project-path xxx –role collector

python main.py show_metrics

python main.py forecast –metric-name io_read –forecast-periods 60S –save-path predict_result

python main.py deploy –user xxx –host xxx.xxx.xxx.xxx –project-path xxx