爲aws上各個region的elbv2進行配置監控告警,監控使用的是aws的cloudwatch,告警使用的是aws的snspython
每個region下有多個elb2,每個elb2下又分爲80和443的listen,目前是須要對每個listen都配置以上四個監控需求,因此總體來講工做量比較大。
json
採用aws的cli工具進行批量建立告警。
bash
aws elbv2 describe-load-balancers; //獲取到該可用區內全部lb的信息
複製代碼
aws elbv2 describe-listeners --load-balancer-arn XXXXXXX; //獲取某一個lb的信息複製代碼
if __name__ == '__main__':
# 1.獲取lb2的arn
print("1. 獲取當前可用區全部lb2全部的arn。")
arndict = getAllArn()
sns = "arn:aws:sns:ap-south-1:2617960:AWS_Alert_Ops"
getSimpleArnAndTaggroup(arndict,sns)複製代碼
aws configure //key等信息不須要輸入直接回車便可,直接輸入該ops機器所在的region,目前美圖所涉及的region有:
ap-south-1, //孟買
us-west-2, //俄勒岡
ap-southeast-1, //新加坡
ap-northeast-1, //東京複製代碼
def getHealthyHostCountComm(lbname,port,taggroup,lbarn,sns):
comm = ''' %s cloudwatch put-metric-alarm \ --alarm-name 'AWS_ELB_%s_PORT_%s_HealthyHostCount' \ //警報的名稱 --alarm-description 'aws elb HealthyHostCount' \ //警報描述 --metric-name HealthyHostCount \ //警報類型,可選類型有HTTPCode_Target_4XX_Count,UnHealthyHostCount,HealthyHostCount等 --namespace AWS/ApplicationELB \ //報警的對象,可選類型有AWS/ApplicationELB,AWS/RDS,AWS/EC2等 --statistic Maximum \ //對採集數據的一個判斷 --period 60 \ //每次採集數據的週期 --threshold 0 \ //告警的閾值 --evaluation-periods 1 \ //採集的次數,總時間=次數*週期時間 --datapoints-to-alarm 1 \ //知足告警條件超過閾值的次數 --comparison-operator LessThanOrEqualToThreshold \ //當前值與閾值對於操做,GreaterThanOrEqualToThreshold,GreaterThanThreshold,LessThanThreshold,LessThanOrEqualToThreshold --treat-missing-data notBreaching \ //對於不知足告警條件的數據處理方式,missing,notBreaching,breaching,ignore --alarm-actions '%s' \ //告警方式,這裏填寫的是sns的arn值 --dimensions 'Name=TargetGroup,Value=targetgroup/%s' 'Name=LoadBalancer,Value=app/%s' ''' %(Contants['AWSCLI'],lbname,port,sns,taggroup,lbarn)
return comm複製代碼
#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Version : 1.0
# @Time : 2018/5/28 18:12
# @Author : *************
# @File : aws_elb_add_alert.py
# @Function: aws elb批量配置告警
# @Note : 因爲每個可用區都有一臺ops機器,因此每個可用區須要單獨執行此腳本,或者用ansible
import os,sys,commands,re,json
Contants = {
"AWSCLI":'/usr/bin/aws',
"AWSREGION":['ap-south-1','us-west-2','ap-southeast-1','ap-northeast-1'] #孟買,俄勒岡,新加坡,東京
}
# 構造字典
class CreateDict(dict):
def __getitem__(self, item):
try:
return dict.__getitem__(self, item)
except KeyError:
value = self[item] = type(self)()
return value
#########################################################################################################
# 配置告警
# HealthyHostCount,一分鐘檢查一次,當健康主機數量等於0,就告警。健康主機的最大值小於等於0就告警
def getHealthyHostCountComm(lbname,port,taggroup,lbarn,sns):
comm = ''' %s cloudwatch put-metric-alarm \ --alarm-name 'AWS_ELB_%s_PORT_%s_HealthyHostCount' \ --alarm-description 'aws elb HealthyHostCount' \ --metric-name HealthyHostCount \ --namespace AWS/ApplicationELB \ --statistic Maximum \ --period 60 \ --threshold 0 \ --evaluation-periods 1 \ --datapoints-to-alarm 1 \ --comparison-operator LessThanOrEqualToThreshold \ --treat-missing-data notBreaching \ --alarm-actions '%s' \ --dimensions 'Name=TargetGroup,Value=targetgroup/%s' 'Name=LoadBalancer,Value=app/%s' ''' %(Contants['AWSCLI'],lbname,port,sns,taggroup,lbarn)
return comm
# UnHealthyHostCount 五分鐘檢查一次,當不健康主機數量大於或等於1個,就告警. 不健康主機數量的最小值大於等於1就告警
def getUnHealthyHostCountComm(lbname,port,taggroup,lbarn,sns):
comm = ''' %s cloudwatch put-metric-alarm \ --alarm-name 'AWS_ELB_%s_PORT_%s_UnHealthyHostCount' \ --alarm-description 'aws elb UnHealthyHostCount' \ --metric-name UnHealthyHostCount \ --namespace AWS/ApplicationELB \ --statistic Minimum \ --period 300 \ --threshold 1 \ --evaluation-periods 1 \ --datapoints-to-alarm 1 \ --comparison-operator GreaterThanOrEqualToThreshold \ --treat-missing-data notBreaching \ --alarm-actions '%s' \ --dimensions 'Name=TargetGroup,Value=targetgroup/%s' 'Name=LoadBalancer,Value=app/%s' ''' %(Contants['AWSCLI'],lbname,port,sns,taggroup,lbarn)
return comm
# HTTP_5XX 一分鐘採集一次,週期爲1分鐘,1個數據點中有1次超過閾值就告警,當5xx超過10個爲超過閾值
def getHTTP_5XXComm(lbname,port,taggroup,lbarn,sns):
comm = ''' %s cloudwatch put-metric-alarm \ --alarm-name 'AWS_ELB_%s_PORT_%s_HTTP_5XX' \ --alarm-description 'aws elb http 5xx alert' \ --metric-name HTTPCode_Target_5XX_Count \ --namespace AWS/ApplicationELB \ --statistic Sum \ --period 60 \ --threshold 10 \ --comparison-operator GreaterThanOrEqualToThreshold \ --treat-missing-data notBreaching \ --evaluation-periods 1 \ --datapoints-to-alarm 1 \ --alarm-actions '%s' \ --dimensions 'Name=LoadBalancer,Value=app/%s' '''%(Contants['AWSCLI'],lbname,port,sns,lbarn)
return comm
# HTTP_4XX 一分鐘採集一次,週期爲5分鐘,5個數據點中有三次超過閾值就告警,當4xx超過10%爲超過閾值
def getHTTP_4XXComm(lbname,port,taggroup,lbarn,sns):
comm = ''' %s cloudwatch put-metric-alarm \ --alarm-name 'AWS_ELB_%s_PORT_%s_HTTP_4XX' \ --alarm-description 'aws elb http 4xx alert' \ --metric-name HTTPCode_Target_4XX_Count \ --namespace AWS/ApplicationELB \ --statistic Sum \ --period 60 \ --threshold 10 \ --comparison-operator GreaterThanOrEqualToThreshold \ --treat-missing-data notBreaching \ --evaluation-periods 5 \ --datapoints-to-alarm 3 \ --unit Percent \ --alarm-actions '%s' \ --dimensions 'Name=TargetGroup,Value=targetgroup/%s' 'Name=LoadBalancer,Value=app/%s' ''' %(Contants['AWSCLI'],lbname,port,sns,taggroup,lbarn)
return comm
# 執行命令函數
def execCommand(comm):
try:
(exitstatus, outtext) = commands.getstatusoutput(comm)
return outtext
except Exception as e:
print(e)
# 獲取當前可用區內全部lb2的基礎信息
def getAllArn():
comm1 = "%s elbv2 describe-load-balancers" % Contants['AWSCLI']
AllLb2Details = eval(execCommand(comm1))['LoadBalancers']
arndict = CreateDict()
for i in range(0,len(AllLb2Details)):
lbarn = AllLb2Details[i]["LoadBalancerArn"]
lbname = AllLb2Details[i]["LoadBalancerName"]
arndict[lbname]["lbarn"] = lbarn
comm2 = "%s elbv2 describe-listeners --load-balancer-arn %s" %(Contants['AWSCLI'],lbarn)
alllisten = eval(execCommand(comm2))['Listeners']
for j in range(0,len(alllisten)):
taggroup = alllisten[j]['DefaultActions'][0]['TargetGroupArn']
port = alllisten[j]['Port']
arndict[lbname]["lbgroup"][port] = taggroup
return json.dumps(arndict)
# 獲取簡寫
def getSimpleArnAndTaggroup(arndict,sns):
for lbname,lbvalue in eval(arndict).iteritems():
lbarn = re.split(r'loadbalancer/app/',lbvalue['lbarn'])[-1]
for port,taggroup in lbvalue['lbgroup'].iteritems():
print("######################################################")
taggroup = re.split(r':targetgroup/',taggroup)[-1]
print("#####開始配置HealthyHostCountAlert#####")
comm1 = getHealthyHostCountComm(lbname,port,taggroup,lbarn,sns)
print(comm1)
execCommand(comm1)
print("#####開始配置UnHealthyHostCountAlert#####")
comm2 = getUnHealthyHostCountComm(lbname,port,taggroup,lbarn,sns)
print(comm2)
execCommand(comm2)
print("#####開始配置HTTP_5XX#####")
comm3 = getHTTP_5XXComm(lbname,port,taggroup,lbarn,sns)
print(comm3)
execCommand(comm3)
print("#####開始配置HTTP_4XX#####")
comm4 = getHTTP_4XXComm(lbname,port,taggroup,lbarn,sns)
print(comm4)
execCommand(comm4)
if __name__ == '__main__':
# 1.獲取lb2的arn
print("1. 獲取當前可用區全部lb2全部的arn。")
arndict = getAllArn()
sns = "arn:aws:sns:us-west-2:217608:AWS_Alert_Ops"
getSimpleArnAndTaggroup(arndict,sns)
複製代碼