def __init__(self):
try:
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s %(name)-12s %(levelname)-8s %(message)s',
datefmt='%m-%d %H:%M',
filename=cluster_config.PATH_TO_LOG_FILE)
self.db = Db_Connector()
except:
e = sys.exc_info()[1]
print 'NagiosPassiveServer error :', e
def __init__(self):
try:
logging.basicConfig(level=logging.DEBUG, format = '%(asctime)s %(name)-12s %(levelname)-8s %(message)s', datefmt='%m-%d %H:%M', filename=cluster_config.PATH_TO_LOG_FILE)
self.db = Db_Connector()
except:
e = sys.exc_info()[1]
print 'NagiosPassiveServer error :', e
class NagiosPassiveServer:
def __init__(self):
try:
logging.basicConfig(level=logging.DEBUG, format = '%(asctime)s %(name)-12s %(levelname)-8s %(message)s', datefmt='%m-%d %H:%M', filename=cluster_config.PATH_TO_LOG_FILE)
self.db = Db_Connector()
except:
e = sys.exc_info()[1]
print 'NagiosPassiveServer error :', e
def register_passive_check(self, hostname, service, status, number):
print './passive_check.sh %s %s %s %s'%(hostname,service,status,number)
status, output = commands.getstatusoutput('./send_passive_check_nagios.sh %s %s %s %s'%(hostname,service,status,number) )
print 'status: ',status
print 'output: ',output
if status == 0:
print 'ok'
else:
print'error'
def process_notification(self,data, ipAddress):
print 'data : ' , data
instance_id = self.db.get_id_by_ip(ipAddress)
vm = self.db.get_vm_info(instance_id['instance_id'])
hostname = "%s_%s_%s"%(vm['user'],vm['instance_id'],vm['node_hostname'])
memPercentage = int( 100*(data['memory']['used'])/float(data['memory']['total']))
self.register_passive_check(hostname, 'RAM', 0, '"'+str(memPercentage) + ';'+str((data['memory']['used']/1024))+'/'+str((data['memory']['total']/1024))+'"')
#CPU
if data['loadavg']['1'] >= 3.0:
output = "CRITICAL - load average: %.2f, %.2f, %.2f" % (data['loadavg']['1'],data['loadavg']['5'],data['loadavg']['10'])
elif data['loadavg']['1'] >= 1.5:
output = "WARNING - load average: %.2f, %.2f, %.2f" % (data['loadavg']['1'],data['loadavg']['5'],data['loadavg']['10'])
else:
print 'data: ', data['loadavg']['1']
output = "OK - load average: %.2f, %.2f, %.2f" % (data['loadavg']['1'],data['loadavg']['5'],data['loadavg']['10'])
self.register_passive_check(hostname, 'Cpu_Load', 0, '"'+output+'"')
#HTTP Connections
self.register_passive_check(hostname, 'HTTP_Connections', 0, '"'+data['http']['nconexoes']+'"')
return True
def __init__(self):
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s %(name)-12s %(levelname)-8s %(message)s',
datefmt='%m-%d %H:%M',
filename=cluster_config.PATH_TO_LOG_FILE)
self.db = Db_Connector()
server = SimpleXMLRPCServer(
(cluster_config.LISTEN_IP, cluster_config.LISTEN_PORT),
logRequests=True,
requestHandler=RequestHandler)
server.register_function(self.get_vm_notification)
try:
server.serve_forever()
except:
e = sys.exc_info()[1]
logging.error(
"server execution error in server_passive_checks: %s" % e)
class Generate_VMs_Nagios_Conf:
hostnames = []
nodes_group = []
def __init__(self):
self.db = Db_Connector()
self.create_nagios_conf_running_vms();
self.reload_nagios_if_necessary()
def reload_nagios_if_necessary(self):
# getting date for logging purposes
now = datetime.datetime.now()
print now.strftime("%d-%m-%Y %H:%M:%S")
if os.path.isfile(running_vms.cluster.cluster_config.VMS_NAGIOS_FILE):
md5a = commands.getoutput("md5sum "+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF+" | awk '{ print $1 }'")
md5b = commands.getoutput("md5sum %s | awk ' { print $1 }'"%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
if md5a != md5b:
print 'Moving File'
os.system('mv '+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF + ' %s'%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
else:
print 'no changes'
else:
os.system('mv '+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF + ' %s'%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
def reload_nagios(self):
os.system(running_vms.cluster.cluster_config.COMMAND_TO_RELOAD_NAGIOS)
def create_nagios_conf_running_vms(self):
vms = self.db.get_info_for_monitoring_running_Vms()
if len(vms) > 0:
try:
fh = open(running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF,'w')
try:
tree = ET.parse('basic_monitoring.xml')
except TypeError, e:
print 'error :',e
for vm in vms:
#Check if the machine has a valide ip address, if not , it's not possible to monitorate
if vm['public_dns_name'] != '0.0.0.0':
hostname = "%s_%s_%s"%(vm['user'],vm['instance_id'],vm['node_hostname'])
self.hostnames.append(hostname)
alias = "%s/%s(%s-%s)"%(vm['user'],vm['instance_id'],vm['node_hostname'],vm['node_ip'])
if vm['node_ip'] != '':
vm_host = [vm['node_ip'],hostname]
self.nodes_group.append(vm_host)
host_def = self.define_host(hostname, alias, vm['public_dns_name'])
fh.write(host_def)
service = tree.findall('services/service')
for s in service:
child = s.getchildren()
services = self.define_passive_service(hostname, child)
fh.write(services)
hostgroup = self.define_hostgroup()
fh.write(hostgroup)
fh.close()
except IOError, (errno, strerror):
print "I/O error ({0}): {1}".format(errno,strerror)
def __init__(self):
self.db = Db_Connector()
self.create_nagios_conf_running_vms();
self.reload_nagios_if_necessary()
class NagiosPassiveServer:
def __init__(self):
try:
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s %(name)-12s %(levelname)-8s %(message)s',
datefmt='%m-%d %H:%M',
filename=cluster_config.PATH_TO_LOG_FILE)
self.db = Db_Connector()
except:
e = sys.exc_info()[1]
print 'NagiosPassiveServer error :', e
def register_passive_check(self, hostname, service, status, number):
print './passive_check.sh %s %s %s %s' % (hostname, service, status,
number)
status, output = commands.getstatusoutput(
'./send_passive_check_nagios.sh %s %s %s %s' %
(hostname, service, status, number))
print 'status: ', status
print 'output: ', output
if status == 0:
print 'ok'
else:
print 'error'
def process_notification(self, data, ipAddress):
print 'data : ', data
instance_id = self.db.get_id_by_ip(ipAddress)
vm = self.db.get_vm_info(instance_id['instance_id'])
hostname = "%s_%s_%s" % (vm['user'], vm['instance_id'],
vm['node_hostname'])
memPercentage = int(100 * (data['memory']['used']) /
float(data['memory']['total']))
self.register_passive_check(
hostname, 'RAM', 0, '"' + str(memPercentage) + ';' + str(
(data['memory']['used'] / 1024)) + '/' + str(
(data['memory']['total'] / 1024)) + '"')
#CPU
if data['loadavg']['1'] >= 3.0:
output = "CRITICAL - load average: %.2f, %.2f, %.2f" % (
data['loadavg']['1'], data['loadavg']['5'],
data['loadavg']['10'])
elif data['loadavg']['1'] >= 1.5:
output = "WARNING - load average: %.2f, %.2f, %.2f" % (
data['loadavg']['1'], data['loadavg']['5'],
data['loadavg']['10'])
else:
print 'data: ', data['loadavg']['1']
output = "OK - load average: %.2f, %.2f, %.2f" % (
data['loadavg']['1'], data['loadavg']['5'],
data['loadavg']['10'])
self.register_passive_check(hostname, 'Cpu_Load', 0,
'"' + output + '"')
#HTTP Connections
self.register_passive_check(hostname, 'HTTP_Connections', 0,
'"' + data['http']['nconexoes'] + '"')
return True
def __init__(self):
self.db = Db_Connector()
now = datetime.datetime.now()
self.create_nagios_conf_running_vms()
self.reload_nagios_if_necessary()
class Generate_VMs_Nagios_Conf:
def __init__(self):
self.db = Db_Connector()
now = datetime.datetime.now()
self.create_nagios_conf_running_vms()
self.reload_nagios_if_necessary()
def reload_nagios_if_necessary(self):
# getting date for logging purposes
now = datetime.datetime.now()
print now.strftime("%d-%m-%Y %H:%M:%S")
if os.path.isfile(running_vms.cluster.cluster_config.VMS_NAGIOS_FILE):
md5a = commands.getoutput(
"md5sum " +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
" | awk '{ print $1 }'")
md5b = commands.getoutput(
"md5sum %s | awk ' { print $1 }'" %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
if md5a != md5b:
print 'Moving File'
os.system('mv ' +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
' %s' %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
else:
print 'no changes'
else:
os.system('mv ' +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
' %s' %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
def reload_nagios(self):
os.system(running_vms.cluster.cluster_config.COMMAND_TO_RELOAD_NAGIOS)
def create_nagios_conf_running_vms(self):
vms = self.db.get_info_for_monitoring_running_Vms()
vms_str = ''
try:
fh = open(running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF, 'w')
nodes_groups = []
hostnames = []
for vm in vms:
#Check if the machine has a valide ip address, if not , it's not possible to monitorate
if vm['public_dns_name'] != '0.0.0.0':
hostname = "%s_%s_%s" % (vm['user'], vm['instance_id'],
vm['node_hostname'])
hostnames.append(hostname)
alias = "%s/%s(%s-%s)" % (vm['user'], vm['instance_id'],
vm['node_hostname'],
vm['node_ip'])
#Verify if there's a node where the vm runs associate, if yes add dependence
if vm['node_ip'] != '':
conf = "define host {\n \
use linux-server \n \
address %s\n \
host_name %s\n \
alias %s\n \
}\n" % (vm['public_dns_name'], hostname, alias)
else:
conf = "define host {\n \
use linux-server \n \
address %s\n \
host_name %s\n \
alias %s\n \
}\n" % (vm['public_dns_name'], hostname, alias)
service_conf = self.define_service(
hostname, 'PING', 'check_ping!100.0,20%!500.0,60%')
service_conf_passive = self.define_service_passive(
hostname)
fh.write(conf)
fh.write(service_conf)
fh.write(service_conf_passive)
vms_str = vms_str + "%s, " % hostname
vm_group = [hostname, vm['node_ip']]
nodes_groups.append(vm_group)
service_group = self.define_service_group(vms_str)
hostgroup = self.define_hostgroup(vms_str, nodes_groups)
self.remove_old_conf()
# fh.write(service_group)
fh.write(hostgroup)
fh.close()
except IOError as (errno, strerror):
print "I/O error ({0}): {1}".format(errno, strerror)
class Generate_VMs_Nagios_Conf:
hostnames = []
nodes_group = []
def __init__(self):
self.db = Db_Connector()
self.create_nagios_conf_running_vms()
self.reload_nagios_if_necessary()
def reload_nagios_if_necessary(self):
# getting date for logging purposes
now = datetime.datetime.now()
print now.strftime("%d-%m-%Y %H:%M:%S")
if os.path.isfile(running_vms.cluster.cluster_config.VMS_NAGIOS_FILE):
md5a = commands.getoutput(
"md5sum " +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
" | awk '{ print $1 }'")
md5b = commands.getoutput(
"md5sum %s | awk ' { print $1 }'" %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
if md5a != md5b:
print 'Moving File'
os.system('mv ' +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
' %s' %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
else:
print 'no changes'
else:
os.system('mv ' +
running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF +
' %s' %
running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
def reload_nagios(self):
os.system(running_vms.cluster.cluster_config.COMMAND_TO_RELOAD_NAGIOS)
def create_nagios_conf_running_vms(self):
vms = self.db.get_info_for_monitoring_running_Vms()
if len(vms) > 0:
try:
fh = open(running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF,
'w')
try:
tree = ET.parse('basic_monitoring.xml')
except TypeError, e:
print 'error :', e
for vm in vms:
#Check if the machine has a valide ip address, if not , it's not possible to monitorate
if vm['public_dns_name'] != '0.0.0.0':
hostname = "%s_%s_%s" % (vm['user'], vm['instance_id'],
vm['node_hostname'])
self.hostnames.append(hostname)
alias = "%s/%s(%s-%s)" % (
vm['user'], vm['instance_id'], vm['node_hostname'],
vm['node_ip'])
if vm['node_ip'] != '':
vm_host = [vm['node_ip'], hostname]
self.nodes_group.append(vm_host)
host_def = self.define_host(hostname, alias,
vm['public_dns_name'])
fh.write(host_def)
service = tree.findall('services/service')
for s in service:
child = s.getchildren()
services = self.define_passive_service(
hostname, child)
fh.write(services)
hostgroup = self.define_hostgroup()
fh.write(hostgroup)
fh.close()
except IOError, (errno, strerror):
print "I/O error ({0}): {1}".format(errno, strerror)
class Generate_VMs_Nagios_Conf:
def __init__(self):
self.db = Db_Connector()
now = datetime.datetime.now()
self.create_nagios_conf_running_vms();
self.reload_nagios_if_necessary()
def reload_nagios_if_necessary(self):
# getting date for logging purposes
now = datetime.datetime.now()
print now.strftime("%d-%m-%Y %H:%M:%S")
if os.path.isfile(running_vms.cluster.cluster_config.VMS_NAGIOS_FILE):
md5a = commands.getoutput("md5sum "+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF+" | awk '{ print $1 }'")
md5b = commands.getoutput("md5sum %s | awk ' { print $1 }'"%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
if md5a != md5b:
print 'Moving File'
os.system('mv '+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF + ' %s'%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
else:
print 'no changes'
else:
os.system('mv '+running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF + ' %s'%running_vms.cluster.cluster_config.VMS_NAGIOS_FILE)
self.reload_nagios()
def reload_nagios(self):
os.system(running_vms.cluster.cluster_config.COMMAND_TO_RELOAD_NAGIOS)
def create_nagios_conf_running_vms(self):
vms = self.db.get_info_for_monitoring_running_Vms()
vms_str = ''
try:
fh = open(running_vms.cluster.cluster_config.NAGIOS_TEMP_CONF,'w')
nodes_groups = []
hostnames = []
for vm in vms:
#Check if the machine has a valide ip address, if not , it's not possible to monitorate
if vm['public_dns_name'] != '0.0.0.0':
hostname = "%s_%s_%s"%(vm['user'],vm['instance_id'],vm['node_hostname'])
hostnames.append(hostname)
alias = "%s/%s(%s-%s)"%(vm['user'],vm['instance_id'],vm['node_hostname'],vm['node_ip'])
#Verify if there's a node where the vm runs associate, if yes add dependence
if vm['node_ip'] != '':
conf = "define host {\n \
use linux-server \n \
address %s\n \
host_name %s\n \
alias %s\n \
}\n" % (vm['public_dns_name'],hostname,alias)
else:
conf = "define host {\n \
use linux-server \n \
address %s\n \
host_name %s\n \
alias %s\n \
}\n" % (vm['public_dns_name'],hostname,alias)
service_conf = self.define_service(hostname,'PING','check_ping!100.0,20%!500.0,60%')
service_conf_passive = self.define_service_passive(hostname)
fh.write(conf)
fh.write(service_conf)
fh.write(service_conf_passive)
vms_str = vms_str + "%s, "%hostname
vm_group = [ hostname,vm['node_ip'] ]
nodes_groups.append(vm_group)
service_group = self.define_service_group(vms_str)
hostgroup = self.define_hostgroup(vms_str,nodes_groups)
self.remove_old_conf()
# fh.write(service_group)
fh.write(hostgroup)
fh.close()
except IOError as (errno, strerror):
print "I/O error ({0}): {1}".format(errno,strerror)