nagios/plc_to_nagios.py

   1 #!/usr/bin/python
   2
   3 import plc
   4 from plc_config import *
   5 from nagiosobjects import *
   6 from generic import *
   7 import auth
   8 import socket
   9
  10 print Command(command_name="check_plc_api",
  11               command_line="""/usr/share/monitor/nagios/plugins/checkplc.py -H $HOSTNAME$ """).toString()
  12
  13 #print Command(command_name="check_plc_web",
  14 #              command_line="""/usr/share/monitor/nagios/plugins/checkplc.py -H $HOSTNAME$ --sn $SERVICENOTIFICATIONNUMBER$ """).toString()
  15
  16 #print Command(command_name="check_plc_db",
  17 #              command_line="""/usr/share/monitor/nagios/plugins/checkplc.py -H $HOSTNAME$ --sn $SERVICENOTIFICATIONNUMBER$ """).toString()
  18
  19
  20 globalhost = [Host(    name="planetlab-server",
  21                     use="generic-host",
  22                     check_period="24x7",
  23                     check_interval="120",
  24                     retry_interval="10",
  25                     max_check_attempts="6",
  26                     check_command="check_http",
  27                     first_notification_delay=0, # 60*24*.5, # wait half a day before taking any action
  28                     contact_groups="admins",
  29                     register="0"),
  30
  31               Service(name="planetlab-server-service",
  32                     active_checks_enabled="1",
  33                     passive_checks_enabled="1",
  34                     parallelize_check="1",
  35                     obsess_over_service="1",
  36                     check_freshness="0",
  37                     notifications_enabled="1",
  38                     event_handler_enabled="1",
  39                     flap_detection_enabled="1",
  40                     failure_prediction_enabled="1",
  41                     process_perf_data="1",
  42                     retain_status_information="1",
  43                     retain_nonstatus_information="1",
  44                     is_volatile="0",
  45                     check_period="24x7",
  46                     max_check_attempts="3",
  47                     normal_check_interval="15",     # NOTE: make this reasonable for N machines.
  48                     retry_check_interval="5",
  49                     notification_options="w,u,c,r",
  50                     notification_interval="60",
  51                     notification_period="24x7",
  52                     contact_groups="admins",
  53                     register="0")
  54             ]
  55
  56 globalservices = []
  57 for service in [('HTTP', "HTTP Server"),
  58                 ('API', "PLC API"),
  59                 ]:
  60     globalservices.append(ServiceGroup(servicegroup_name=service[0], alias=service[1]))
  61
  62 for obj in globalhost + globalservices:
  63     print obj.toString()
  64
  65 #plc_hosts = [ PLC_MONITOR_HOST, PLC_WWW_HOST, PLC_BOOT_HOST, PLC_PLANETFLOW_HOST, ]
  66 plc_hosts = [ PLC_WWW_HOST, PLC_BOOT_HOST, ]
  67
  68 print HostGroup(hostgroup_name="allplcservers", alias="allplcservers").toString()
  69
  70 hostname_list = []
  71 for host in plc_hosts:
  72     shortname = host
  73     ip = socket.gethostbyname(host)
  74
  75     h = Host(use="planetlab-server",
  76                 host_name="%s" % host,
  77                 alias=host,
  78                 address=ip,
  79                 hostgroups="allplcservers")
  80
  81     print h.toString()
  82
  83     hostname_list.append(host)
  84
  85 # NOTE: use all hostnames at site to create HostEscalations for down-notices
  86 if len(hostname_list) > 0:
  87
  88     hn_list = ",".join(hostname_list)
  89
  90     s1 = Service(use="planetlab-server-service",
  91                     host_name=hn_list,
  92                     service_description="API",
  93                     display_name="API",
  94                     servicegroups="NET,API",
  95                     check_command="check_plc_api")
  96
  97         ## NOTE: try to repair the host, if it is online and 'mode' indicates a problem
  98         #se1 = ServiceEscalation(host_name=hn_list,
  99         #                        service_description="bRUNLEVEL",
 100         #                        first_notification=1,
 101         #                        last_notification=0,
 102         #                        escalation_options="w,c,r",
 103         #                        notification_interval=20,
 104         #                        contacts="automate-service-repair-contact")
 105
 106     for service in [s1]:
 107         print service.toString()
 108