AWS告警优化

(1)AWS添加sns，略过

(2)添加自定义webhook钉钉机器人，略过。

(3)编写lambda函数脚本，利用cloudwatch触发告警。

# -*- coding: utf-8 -*-
import json
import os
import re
import datetime
from botocore.vendored import requests

def time_format(str_time):
    ''' 时间的时区转换为东8区 '''
    Ymd = str_time.split('T')[0]
    HMS = str_time.split('T')[1].split('.')[0]
    str_time = '%s %s' % (Ymd, HMS)
    time = datetime.datetime.strptime(str_time, "%Y-%m-%d %H:%M:%S")
    format_time = time + datetime.timedelta(hours=8)
    return format_time


def size_b_to_other(size):
    """用于转换容量单位"""
    units = ['B', 'KB', 'MB', 'GB', 'TB']
    # 处理异常
    if size < 1024:
        return size

    # 遍历单位的位置并用取整除赋值
    for unit in units:
        if size >= 1024:
            size //= 1024
        else:
            size_h = '{} {}'.format(size, unit)
            return size_h

    size_h = '{} {}'.format(size, unit)
    return size_h
    
    
    
def lambda_handler(event, context):
   #钉钉机器人url
    url = "xxxxxxxx"
    # 解析要使用的字段
    Sns = event['Records'][0]['Sns']
    Subject = Sns['Subject']
    if "ALARM" in Subject:
        title = "<font color=#FF0000 size=3>AWS 报警触发</font>"
        tag_word = " 连续"
    elif "OK" in Subject:
        title = "<font color=#008000 size=3>AWS 报警恢复</font>"
        tag_word = " 未连续"
    elif "INSUFFICIENT_DATA" in Subject:
        title = "AWS 报警异常(数据不足)"
        tag_word = " , Insufficient Data 未连续"        
   
    Timestamp = Sns['Timestamp']
    Message = Sns['Message']
    Message = json.loads(Message)
    
    try:
        
        Region = Message['Region']
        AlarmName = Message['AlarmName']
        service_key = Message['Trigger']['Dimensions'][0]['name']
        service_value = Message['Trigger']['Dimensions'][0]['value']
        MetricName = Message['Trigger']['MetricName']
        Namespace = Message['Trigger']['Namespace']
        Period = Message['Trigger']['Period']
        EvaluationPeriods = Message['Trigger']['EvaluationPeriods']
        Threshold = Message['Trigger']['Threshold']
        StateChangeTime = Message['StateChangeTime']
        NewStateReason = Message['NewStateReason']
        AlarmDescription = Message['AlarmDescription']

        if "INSUFFICIENT_DATA" not in Subject:
                
            # 转换cloudwatch单位为友好单位
            lastpoint = re.findall(r'[[](.*?)[)]', NewStateReason)
            lastpoint_data = size_b_to_other(float('%.2f' % float(lastpoint[0].split(' (')[0])))
            lastpoint_time = datetime.datetime.strptime(lastpoint[0].split(' (')[1],"%d/%m/%y %H:%M:%S")
            lastpoint_time = lastpoint_time + datetime.timedelta(hours=8)
        else:
            lastpoint_data = 'null'
            lastpoint_time = time_format(StateChangeTime)

    except:
        Message = json.dumps(Message, sort_keys=True, indent=2)
        content = title + "

>报警主题："  + Subject +  
            "

>详细信息："  + Message +  
            "

>备注信息：消息解析异常"


    pagrem = {
    "msgtype":"markdown",
        "markdown": {
              "title": "AWS告警" + "...."  ,
             "text":"报警主题 ：" + title  +
                "

>监控指标："  + AlarmName + 
                "

>报警时间："  + str(lastpoint_time)   +
                "

>报警资源："  + str(service_key) + " : " + str(service_value)  +
                "

>报警信息："  + "当前值=" + str(lastpoint_data) + tag_word + str(EvaluationPeriods) + "次达到 " + "阀值=" + str(size_b_to_other(Threshold))  +
                "

>业务备注："  + str(AlarmDescription) 
        },
        "at":{
            "atMobiles":[
                "15527453712"
            ]
    },
        "isAtAll": "False"
    }
    headers={
        'Content-Type':'application/json'
    }    
    requests.post(url, data=json.dumps(pagrem), headers=headers)

效果图：