python nagios监控cloudstack集群的host机状态示例

663424

cloudstack集群中，host主机有时候状态不正常，从而影响到iaas的业务，于是写了个监控脚本来进行监控，如下：

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49

#cat check_cs_host #!/usr/bin/python #desc: this script is to check the status of hosts  in cloudstack #     can use -h to show usage import os,sys import json from optparse import OptionParser E_OK = 0 E_WARNING = 1 E_CRITICAL = 2 E_UNKNOWN = 3 E_CODE = E_OK parser = OptionParser() parser.add_option("-i","--ignore",dest="ignore",           help="ipaddress that ignore to check ") (options,args) = parser.parse_args() comm = '/usr/bin/cloudmonkey -d json list hosts type=Routing filter=ipaddress,state' performance = '' info = '' host_info = os.popen(comm).read() host_json = json.loads(host_info)['host'] if options.ignore:     for item in host_json:         if not item['ipaddress'] in options.ignore and item['state'] != 'Up':             info += '%s : %s' % (item['ipaddress'],item['state'])                  E_CODE = E_CRITICAL else:     for item in host_json:                 if item['state'] != 'Up':                         info += '%s:%s; ' % (item['ipaddress'],item['state'])                         E_CODE = E_CRITICAL    if E_CODE == E_OK :     performance += 'OK' elif E_CODE == E_WARNING:         performance = 'WARNING-' + info elif E_CODE == E_CRITICAL:     performance = 'CRITICAL-' + info else:     performance = 'UNKNOWN-' + info print performance sys.exit(E_CODE)

脚本可以添加 -i 或 --ignore参数来忽略一些host的监控告警
如忽略172.16.2.5和172.16.2.6这两台host的状态不正常告警，可以这么写：
check_cs_host --ignore=172.16.2.5,172.16.2.6