restAPI HDP 【Ambari】Python调用Rest API 获取YARN HA状态信息并发送钉钉告警

濾 个人主页——开着拖拉机回家_Linux,大数据运维-CSDN博客 ✨

嬨嬨嬨嬨 嬨嬨嬨嬨 嬨嬨嬨嬨嬨嬨

感谢点赞和关注 ，每天进步一点点！加油！

目录

一、概述

二、集群版本信息

三、组件状态信息获取

三、告警实现

一、概述

Ambari 借鉴了很多成熟分布式软件的 API 设计。Rest API 就是一个很好地体现。通过 Ambari 的 Rest API，可以在脚本中通过 curl 维护整个集群。并且，我们可以用 Rest API 实现一些无法在 Ambari GUI 上面做的操作。

二、集群版本信息

三、组件状态信息获取

参考：【Ambari】Python调用Rest API 获取集群状态信息并发送钉钉告警-CSDN博客

RESOURCEMANAGER停止

curl -u admin:admin -i -H 'X-Requested-By:ambari' -X PUT -d '{"RequestInfo":{"context":"Restart RESOURCEMANAGER via REST"},"Body" : {"HostRoles" : {"state":"INSTALLED"}}}' http://192.168.2.153:8080/api/v1/clusters/winner/hosts/hdp105/host_components/RESOURCEMANAGER

-u Ambari登录用户：密码-i -H获取http请求的完整头部信息，包括请求方法、请求地址、请求头信息等-X 同时想发 HEAD、GET 或 POST 请求，需在 -X 中声明要使用的请求方式

ambari页面显示停止成功调用

ambari页面RM服务停止

RESOURCEMANAGER启动

curl -u admin:admin -i -H 'X-Requested-By:ambari' -X PUT -d '{"RequestInfo":{"context":"Restart RESOURCEMANAGER via REST"},"Body" : {"HostRoles" : {"state":"STARTED"}}}' http://192.168.2.153:8080/api/v1/clusters/winner/hosts/hdp105/host_components/RESOURCEMANAGER

直接使用RESTART

curl -uadmin:admin -H 'X-Requested-By: ambari' -X POST -d '{"RequestInfo":{"command":"RESTART","context":"Restart RESOURCEMANAGER via REST","operation_level":{"level":"HOST","cluster_name":"winner"}},"Requests/resource_filters":[{"service_name":"YARN","component_name":"RESOURCEMANAGER","hosts":"hdp103"}]}' http://192.168.2.153:8080/api/v1/clusters/winner/requests

请求响应接受

四、告警实现

python 脚本实现RM HA的监控告警

# -*- coding: utf-8 -*-

import logging

import time

from imp import reload

import requests

import json

import sys

"""

~~~~~~~~~~~~

author: kangll

date: 2023/12/6 13:29

desc:

-- curl 请求，如下为测试链接

curl -u admin:admin -i -H X-Requested-By:ambari -XGET http://192.168.2.153:8080/api/v1/clusters/winner/hosts/winner

http://192.168.2.153:8080/api/v1/clusters/winner/hosts/hdp105/host_components/RESOURCEMANAGER

-- datanode 启动

curl -u admin:admin -i -H 'X-Requested-By:ambari' -X PUT -d '{"RequestInfo":{"context":"Start RESOURCEMANAGER via REST"}

,"Body" : {"ServiceInfo" : {"state":"STARTED"}}}' http://192.168.2.153:8080/api/v1/clusters/winner/services/HDFS

"""

reload(sys)

sys.setdefaultencoding('utf8')

__author__ = 'kanglilong '

logger = logging.getLogger('mylogger')

logger.setLevel(level=logging.INFO)

# Ambari rest api 访问地址

control_url = "http://192.168.2.153:8080/api/v1/clusters/winner/hosts"

# ambari web 登录账号

AUTH = ("admin", "admin")

headers = {'Content-Type': 'application/json;charset=utf-8'}

# 钉钉URL

api_url = "https://oapi.dingtalk.com/robot/send?access_token=f4e0f344306ce9b6eec60bec95d5aa7c57f4264a791458dc09121dd7e948ac64"

# RM hostname

rm_hostname_01 = "hdp103"

rm_hostname_02 = "hdp105"

requests_rm_url = "http://192.168.2.153:8080/api/v1/clusters/winner/requests"

def getHostComponentsStatus():

"""

获取某个服务器上某个组件的状态信息

:param host:

:return: component_dict 组件与其状态

status 当前节点状态是否符合期望，

getStatus 是否获取到了状态

"""

now_time = time.localtime(time.time())

formatted_time = time.strftime('%Y-%m-%d %H:%M:%S', now_time)

json_text = {

"RequestInfo": {

"command": "RESTART",

"context": "Restart RESOURCEMANAGER via REST",

"operation_level": {

"level": "HOST",

"cluster_name": "winner"

}

},

"Requests/resource_filters": [{

"service_name": "YARN",

"component_name": "RESOURCEMANAGER",

"hosts": "{}".format(rm_hostname_01)

}]

}

get_rm_status_url_01 = control_url + "/{}/host_components/RESOURCEMANAGER".format(rm_hostname_01)

get_rm_status_url_02 = control_url + "/{}/host_components/RESOURCEMANAGER".format(rm_hostname_02)

print("-----------------")

rep01 = requests.get(get_rm_status_url_01, auth=AUTH)

# 如果状态码是20x 则获取成功

print(rep01.status_code)

if str(rep01.status_code).startswith("200"):

jsonRep01 = json.loads(rep01.text)

component_name_01 = jsonRep01['HostRoles']['component_name']

status_01 = jsonRep01['HostRoles']['state']

ha_state_01 = jsonRep01['HostRoles']['ha_state']

host_name_01 = jsonRep01['HostRoles']['host_name'] # STARTED

else:

# 没有正常获取到状态

print("没有正常获取到状态")

rep02 = requests.get(get_rm_status_url_02, auth=AUTH)

# 如果状态码是20x 则获取成功

print(rep02.status_code)

if str(rep02.status_code).startswith("200"):

jsonRep02 = json.loads(rep02.text)

component_name_02 = jsonRep02['HostRoles']['component_name']

status_02 = jsonRep02['HostRoles']['state']

ha_state_02 = jsonRep02['HostRoles']['ha_state']

host_name_02 = jsonRep02['HostRoles']['host_name'] # STARTED

else:

# 没有正常获取到状态

print("没有正常获取到状态")

# RM 为 STARTED status

if component_name_01 == component_name_02 and status_01 == "STARTED" and status_02 == "STARTED":

# 两个RM都为STANDBY则重启其中一个

if ha_state_01 == ha_state_02 and ha_state_01 == "STANDBY" and ha_state_02 == "STANDBY":

text = "告警对象：主机名：" + host_name_01 + ', ' + host_name_02 + ' \n组件名称：' + component_name_01 + " \n告警内容：HDP集群服务 " + component_name_01 + " 高可用状态异常 " + ha_state_01 + ", 触发重启" + "\n告警时间：" + formatted_time

send_msg(text)

print("RESOURCEMANAGER state abnormal.")

restart_res = requests.post(requests_rm_url, data=json.dumps(json_text), auth=AUTH, headers=headers)

print(restart_res.text)

if str(restart_res.status_code).startswith("202"):

# 没有正常获取到状态

print("重启请求发送成功!")

else:

# 没有正常获取到状态

print("重启请求发送成功!")

else:

#

print("RESOURCEMANAGER state normal.")

def send_msg(text):

"""

:param text: 告警文本

:return:

"""

json_text = {

"msgtype": "text",

"text": {

"content": text

}, "at": {

"atMobiles": ["1786881xxxx"]

}

}

requests.post(api_url, json.dumps(json_text), headers=headers).content

getHostComponentsStatus()

钉钉告警发送成功

RM 重启一台RM操作完成，触发HA的强制切换

需要添加配置 ambari.properties

vi /etc/ambari-server/conf/ambari.properties

# 添加如下配置

api.csrfPrevention.enabled=false

# 重启

ambari-server restart

request请求返回的状态码

参考文章

 您阅读本篇文章共花了：