def execstr(self, host, check):
res = None
try:
print('doing ' + check + ' on ' + host)
host = Hosts.objects.get(name=host)
check = HostChecks.objects.get(name=check)
if host.enabled is True and check.enabled is True:
# run = sh.Command("./bin/runthis.sh")
# res = str(run(check.arg))
computestr(check, host, res)
# print(oid + ' on ' + address + ' equals ' + res)
except Exception as e:
print('doing ' + check.name + ' on ' + host.name + ' failed')
# update the error count
setMetadata(host.name + ':' + check.name + '::lasterror',
str(timezone.now()))
setMetadata(
host.name + ':' + check.name + '::nberror',
int(getMetadata(host.name + ':' + check.name + '::nberror', 0)) +
1)
# Log the error to the database.
ErrorLog(hostcheck=check,
host=host,
event=e.__class__.__name__,
error=str(e),
value=res).save()
return res
def snmpgetbool(self, host, check):
res = None
try:
print('doing ' + check + ' on ' + host)
host = Hosts.objects.get(name=host)
if host.enabled is True:
check = HostChecks.objects.get(name=check)
address = host.address
community = host.community
oid = check.arg
# res = str(snmp_get(oid, hostname=address, community=community, version=1).value)
computebool(check, host, res)
# print(oid + ' on ' + address + ' equals ' + res)
except Exception as e:
print('doing ' + check.name + ' on ' + host.name + ' failed')
# update the error count
setMetadata(host.name + ':' + check.name + '::lasterror',
str(timezone.now()))
setMetadata(
host.name + ':' + check.name + '::nberror',
int(getMetadata(host.name + ':' + check.name + '::nberror', 0)) +
1)
# Log the error to the database.
ErrorLog(hostcheck=check,
host=host,
event=e.__class__.__name__,
error=str(e),
value=res).save()
return res
def setNotifs(request, host, check, status):
if not request.user.has_perm('webview.silence_check'):
raise PermissionDenied
# toggle notification status per host-check combo. uses switchery in the UI.
host = get_object_or_404(Hosts, name=host)
check = get_object_or_404(HostChecks, name=check)
if status == "false":
status = False
else:
status = True
setMetadata(host.name + ":" + check.name + "::notifs", status)
return HttpResponse("done")
def getDelay(request, days):
# Pulls the info for the avg task delay info bubble at the top )
# if days is None:
# days = 1
# meandelay = getMetadata('taskdelay-' + str(days), None)
# if meandelay is None:
# tasks = TaskState.objects.filter(
# tstamp__range=[timezone.now() - datetime.timedelta(days=int(days)), timezone.now()]).exclude(
# runtime=None).values_list('runtime', flat=True)
# meandelay = mean(tasks)
meandelay = 1
setMetadata('taskdelay-' + str(days), meandelay)
return HttpResponse(meandelay)
def computestr(check, host, value):
from .models import Historical
# create the db record
history = Historical(host=host,
hostcheck=check,
value=value,
timestamp=timezone.now())
setMetadata(
host.name + ':' + check.name + '::lastvalue',
getMetadata(host.name + ':' + check.name + '::value', 'No Data'))
now = int(timezone.now().timestamp())
setMetadata(host.name + ':' + check.name + '::lastcheck', now)
setMetadata(host.name + ':' + check.name + '::value', value)
metadata = {
'error': getMetadata(host.name + ':' + check.name + '::error', 'OK')
}
thiserror = 'false'
metadata['error'] = 'false'
errors = alertstr(check, host, value)
if check.colorizesla and len(errors) > 0:
thiserror = 'ok'
metadata['error'] = 'ok'
# dbg(check.name + ' is colorizesla')
# if colorizesla is true, we check if the sla is failing instead of the check
slas = check.sla.filter(enabled=True)
for sla in slas:
# dbg('checking sla ' + sla.name + '. its status is ' + sla.status)
if sla.status == 'failing':
metadata['error'] = 'crit'
thiserror = 'crit'
else:
for error in errors:
if error.get('hasError', True):
if error.get('strwarn', False):
thiserror = 'warn'
if error.get('strgood', False) or error.get('strbad', False):
thiserror = 'crit'
elif error.get('hasError', None) is False:
thiserror = 'ok'
metadata['error'] = setMetadata(host.name + ':' + check.name + '::error',
thiserror)
# save a snapshot of the metadata when the check ran
history.data = json.dumps(metadata)
history.save()
return metadata
def snmpgetint(self, host, check):
global checkname
global hostname
global res
try:
print('doing ' + check + ' on ' + host)
hostname = Hosts.objects.get(name=host)
if hostname.enabled is True:
checkname = HostChecks.objects.get(name=check)
address = hostname.address
community = hostname.community
oid = checkname.arg
# res = str(float(snmp_get(oid, hostname=address, community=community, version=1).value) * float(check.quotient))
# from pysnmp import debug
# debug.setLogger(debug.Debug('msgproc'))
# Protocol version to use
pMod = api.protoModules[api.protoVersion1]
# pMod = api.protoModules[api.protoVersion2c]
# Build PDU
reqPDU = pMod.GetRequestPDU()
pMod.apiPDU.setDefaults(reqPDU)
pMod.apiPDU.setVarBinds(reqPDU, (((oid), pMod.Null()), ))
# Build message
reqMsg = pMod.Message()
pMod.apiMessage.setDefaults(reqMsg)
pMod.apiMessage.setCommunity(reqMsg, community)
pMod.apiMessage.setPDU(reqMsg, reqPDU)
startedAt = time()
def cbTimerFun(timeNow):
if timeNow - startedAt > 3:
raise Exception("Request timed out")
# noinspection PyUnusedLocal,PyUnusedLocal
def cbRecvFun(transportDispatcher,
transportDomain,
transportAddress,
wholeMsg,
reqPDU=reqPDU):
while wholeMsg:
rspMsg, wholeMsg = decoder.decode(wholeMsg,
asn1Spec=pMod.Message())
rspPDU = pMod.apiMessage.getPDU(rspMsg)
# Match response to request
if pMod.apiPDU.getRequestID(
reqPDU) == pMod.apiPDU.getRequestID(rspPDU):
# Check for SNMP errors reported
errorStatus = pMod.apiPDU.getErrorStatus(rspPDU)
if errorStatus:
print(errorStatus.prettyPrint())
else:
for oid, val in pMod.apiPDU.getVarBinds(rspPDU):
# print('%s = %s' % (oid.prettyPrint(), val.prettyPrint()))
# res = str(float(val.prettyPrint() * float(check.quotient)))
global checkname
global hostname
global res
res = str(
float(val * float(checkname.quotient)))
computeint(checkname, hostname, res)
transportDispatcher.jobFinished(1)
return wholeMsg
transportDispatcher = AsyncoreDispatcher()
transportDispatcher.registerRecvCbFun(cbRecvFun)
# transportDispatcher.registerTimerCbFun(cbTimerFun)
# UDP/IPv4
transportDispatcher.registerTransport(
udp.domainName,
udp.UdpSocketTransport().openClientMode())
# Pass message to dispatcher
transportDispatcher.sendMessage(encoder.encode(reqMsg),
udp.domainName, (address, 161))
transportDispatcher.jobStarted(1)
## UDP/IPv6 (second copy of the same PDU will be sent)
# transportDispatcher.registerTransport(
# udp6.domainName, udp6.Udp6SocketTransport().openClientMode()
# )
# Pass message to dispatcher
# transportDispatcher.sendMessage(
# encoder.encode(reqMsg), udp6.domainName, ('::1', 161)
# )
# transportDispatcher.jobStarted(1)
## Local domain socket
# transportDispatcher.registerTransport(
# unix.domainName, unix.UnixSocketTransport().openClientMode()
# )
#
# Pass message to dispatcher
# transportDispatcher.sendMessage(
# encoder.encode(reqMsg), unix.domainName, '/tmp/snmp-agent'
# )
# transportDispatcher.jobStarted(1)
# Dispatcher will finish as job#1 counter reaches zero
transportDispatcher.runDispatcher()
transportDispatcher.closeDispatcher()
# print(transportDispatcher)
del transportDispatcher
del pMod
del reqPDU
del reqMsg
del startedAt
del cbTimerFun
del cbRecvFun
# computeint(check, host, res)
# print(oid + ' on ' + address + ' equals ' + res)
except Exception as e:
print('doing ' + checkname.name + ' on ' + hostname.name + ' failed')
print(traceback.format_exc())
# update the error count
setMetadata(hostname.name + ':' + checkname.name + '::lasterror',
str(timezone.now()))
setMetadata(
hostname.name + ':' + checkname.name + '::nberror',
int(
getMetadata(hostname.name + ':' + checkname.name + '::nberror',
0)) + 1)
# Log the error to the database.
ErrorLog(hostcheck=checkname,
host=hostname,
event=e.__class__.__name__,
error=str(e),
value=res).save()
return res
def computeint(check, host, value):
# we process the value we get from the check
from .models import Historical
# create the db record
history = Historical(host=host,
hostcheck=check,
value=value,
timestamp=timezone.now())
setMetadata(
host.name + ':' + check.name + '::lastvalue',
getMetadata(host.name + ':' + check.name + '::value', 'No Data'))
now = int(timezone.now().timestamp())
setMetadata(host.name + ':' + check.name + '::lastcheck', now)
setMetadata(host.name + ':' + check.name + '::value', value)
metadata = {
'min': getMetadata(host.name + ':' + check.name + '::min', 'No Data'),
'max': getMetadata(host.name + ':' + check.name + '::max', 'No Data'),
'avg': getMetadata(host.name + ':' + check.name + '::avg', 'No Data'),
'error': getMetadata(host.name + ':' + check.name + '::error', 'OK')
}
# disable avg calculation for now. will do it out of band to avoid running late of checks
# if (now - metadata.get('laststats', 0)) > check.statsinterval:
# try:
# castedata = []
# # This is the query that is loading the database, need to think about this.
# data = Historical.objects.filter(host=host, hostcheck=check).values_list('value')
# for i in data:
# castedata.append(float(i[0]))
# metadata['avg'] = mean(castedata)
# except:
# dbg('Could not compute avg of int')
# metadata['avg'] = 0
# metadata['laststats'] = now
# setMetadata(host.name + ':' + check.name + ':avg', str(metadata['avg']))
# setMetadata(host.name + ':' + check.name + ':laststats', now)
# Update min if we are under
# print(metadata)
mdmin = metadata['min']
if mdmin == 'No Data' or float(value) < float(mdmin):
metadata['min'] = setMetadata(host.name + ':' + check.name + '::min',
str(value))
# Update max if we are over
mdmax = metadata['max']
if mdmax == 'No Data' or float(value) > float(mdmax):
metadata['max'] = setMetadata(host.name + ':' + check.name + '::max',
str(value))
# process any alerts that could arise
errors = alertint(check, host, value)
thiserror = 'false'
metadata['error'] = 'false'
if check.colorizesla and len(errors) > 0:
thiserror = 'ok'
metadata['error'] = 'ok'
# if colorizesla is true, we check if the sla is failing instead of the check
slas = check.sla.filter(enabled=True)
for sla in slas:
if sla.status == 'failing':
metadata['error'] = 'crit'
thiserror = 'crit'
else:
for error in errors:
if error.get('hasError', False):
if error.get('lowcrit', False) or error.get('highcrit', False):
thiserror = 'crit'
elif error.get('lowwarn', False) or error.get(
'highwarn', False):
thiserror = 'warn'
elif error.get('hasError', None) is False:
thiserror = 'ok'
metadata['error'] = setMetadata(host.name + ':' + check.name + '::error',
str(thiserror))
# save a snapshot of the metadata when the check ran
history.data = json.dumps(metadata)
history.save()
return metadata
def computebool(check, host, value):
value = booltoint(strtobool(value))
# we process the value we get from the check
from .models import Historical
# create the db record
history = Historical(host=host,
hostcheck=check,
value=value,
timestamp=timezone.now())
setMetadata(
host.name + ':' + check.name + '::lastvalue',
getMetadata(host.name + ':' + check.name + '::value', 'No Data'))
now = int(timezone.now().timestamp())
setMetadata(host.name + ':' + check.name + '::lastcheck', now)
setMetadata(host.name + ':' + check.name + '::value', value)
metadata = {
'nbtrue':
getMetadata(host.name + ':' + check.name + '::nbtrue', '0'),
'nbfalse':
getMetadata(host.name + ':' + check.name + '::nbfalse', '0'),
'lasttrue':
getMetadata(host.name + ':' + check.name + '::lasttrue', 'No Data'),
'lastfalse':
getMetadata(host.name + ':' + check.name + '::lastfalse', 'No Data'),
'error':
getMetadata(host.name + ':' + check.name + '::error', 'OK')
}
# Update the metadata
if value == 0:
metadata['nbfalse'] = setMetadata(
host.name + ':' + check.name + '::nbfalse',
int(metadata['nbfalse']) + 1)
metadata['lastfalse'] = setMetadata(
host.name + ':' + check.name + '::lastfalse',
timezone.now().strftime("%m/%d/%Y %H:%M:%S"))
elif value == 1:
metadata['nbtrue'] = setMetadata(
host.name + ':' + check.name + '::nbtrue',
int(metadata['nbtrue']) + 1)
metadata['lasttrue'] = setMetadata(
host.name + ':' + check.name + '::lasttrue',
timezone.now().strftime("%m/%d/%Y %H:%M:%S"))
thiserror = 'false'
metadata['error'] = 'false'
errors = alertbool(check, host, value)
if check.colorizesla and len(errors) > 0:
thiserror = 'ok'
metadata['error'] = 'ok'
# dbg(check.name + ' is colorizesla')
# if colorizesla is true, we check if the sla is failing instead of the check
slas = check.sla.filter(enabled=True)
for sla in slas:
# dbg('checking sla ' + sla.name + '. its status is ' + sla.status)
if sla.status == 'failing':
metadata['error'] = 'crit'
thiserror = 'crit'
else:
for error in errors:
if error.get('hasError', True):
if error.get('boolgood', False) or error.get('boolbad', False):
thiserror = 'crit'
elif error.get('hasError', None) is False:
thiserror = 'ok'
metadata['error'] = setMetadata(host.name + ':' + check.name + '::error',
thiserror)
# save a snapshot of the metadata when the check ran
history.data = json.dumps(metadata)
history.save()
return metadata