def run(self):
logging.info("Running Source Master Manager ...")
method_name = "run()"
# Get configuration
config = Configure()
timer = config.get_config()['GeneralParams']['dataSourcesScheduling']
timeout = config.get_config(
)['GeneralParams']['dataSourcesNotReadyWaitingTime']
try:
# Monitoring interval counter
c_interval = 1
# Doing until stop request
while not self._stopped_event.isSet():
# init of the monitoring interval
t_init_interval = datetime.now()
# end of the monitoring interval
t_end_interval = t_init_interval + timedelta(seconds=timer)
# max time for waiting a source
t_max_interval = t_end_interval + timedelta(seconds=timeout)
# ts associated to the current monitoring interval
ts = dateutils.get_timestamp()
# Start a thread to manage the sources ready for the current monitoring interval
intervalSourceMonitoringThread = IntervalMonitoringSourceManagerThread(
self._sourceManager_instance, t_init_interval,
t_end_interval, t_max_interval, ts)
intervalSourceMonitoringThread.setName("IntervalThread_" +
str(c_interval))
intervalSourceMonitoringThread.start()
# Wait for the end of the interval
logging.debug("Waiting for the next interval ...")
sleep(timer)
# Monitoring interval counter
c_interval = c_interval + 1
except Exception as detail:
logging.error(
"Error in processing the data sources. Type: %s, msg: %s",
sys.exc_info()[0], detail)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
limit=5,
file=sys.stdout)
raise DataSourceError(self, detail, method_name)
def manage_data(self, data, client_address):
"""
Depending on the type of the received package this method selects the corresponding procedure to process it.
Parameters
----------
data: str
the received serialized data
client_address:
client address
"""
# Reception timestamp
ts_rec = dateutils.get_timestamp()
# Client IP
client_IP = client_address[0]
# De-serialized the received data
pack = pickle.loads(data)
logging.info(
"Data received from sensor: %s (%s) at %s. Package type: %s",
pack._header['sid'], client_IP, ts_rec, pack._type)
# Data packet
if pack._type == Packet.TYPE_D:
# Save the packet
self.save_packet(pack, client_address, ts_rec)
# Command packet
elif pack._type == Packet.TYPE_C:
# TODO fill additional package fields
# Do diagnosis
pass
else:
# Error
logging.warn("The received packet is not a valid type. Type: %s",
pack._type)
return pack
def do_dynamic_calibration(self, **kwargs):
"""
Starting point for the dynamic calibration procedure
Raises
------
SensorError, MSNMError
"""
method_name = "do_dynamic_calibration()"
logging.info("Doing dynamic calibration ...")
# Time stamp
ts = dateutils.get_timestamp()
# Get configuration
config = Configure()
model_backup_path = config.get_config()['Sensor']['model']
model_backup_file = model_backup_path + "model_" + ts + ".json"
try:
# Model calibration init
self._model.calibrate_dynamically(self._data, **kwargs)
# Get the JSON of the model
logging.debug("Saving the current model")
json_model = datautils.model2json(self._model, ts)
# Save the model
datautils.save2json(json_model, model_backup_file)
except ModelError as me:
logging.error("Error doing dynamic calibration: %s", me.get_msg())
raise SensorError(self, me.get_msg(), method_name)
except MSNMError as emsnm:
logging.error("Error doing dynamic calibration: %s",
emsnm.get_msg())
raise emsnm
logging.info("End of doing dynamic calibration...")
def do_calibration(self, **kwargs):
"""
Starting point of the calibration procedure
Raises
------
SensorError, MSNMError
"""
method_name = "do_calibration()"
# Time stamp
ts = dateutils.get_timestamp()
# Get configuration
config = Configure()
# Get root path for creating data files
rootDataPath = config.get_config()['GeneralParams']['rootPath']
model_backup_path = config.get_config()['Sensor']['model']
model_backup_file = rootDataPath + model_backup_path + "model_" + ts + ".json"
try:
# Model calibration init
self._model.calibrate(self._data, **kwargs)
# Get the JSON of the model
json_model = datautils.model2json(self._model, ts)
# Save the model
datautils.save2json(json_model, model_backup_file)
except ModelError as eme:
raise SensorError(self, eme.msg, method_name)
except MSNMError as emsnm:
raise emsnm
def send_response(self, request, msg):
"""
Sending the response to the client
Parameters
----------
request:
client request
msg: str
response msg
"""
# Sensor ID. The current sensor ID that sends the response
config = Configure()
sid = config.get_config()['Sensor']['sid']
# sent timestamp
ts = dateutils.get_timestamp()
# build a response message
pack_resp = ResponsePacket()
pack_resp.fill_header({
'id': self._packet_sent,
'sid': sid,
'ts': ts,
'type': Packet.TYPE_R
})
pack_resp.fill_body({'resp': msg})
# Response packet
p_serialized = pickle.dumps(pack_resp, 2)
request.send(p_serialized)
# increment the number of packets sent
self._packet_sent = self._packet_sent + 1
def run(self):
method_name = "run()"
iptables_log = self.config.get_config()['DataSources'][
self._iptables_instance._type][
self._iptables_instance.__class__.__name__]['captures']
iptables_log_raw_folder = self.rootDataPath + self.config.get_config(
)['DataSources'][self._iptables_instance._type][
self._iptables_instance.__class__.__name__]['raw']
iptables_log_processed_folder = self.rootDataPath + self.config.get_config(
)['DataSources'][self._iptables_instance._type][
self._iptables_instance.__class__.__name__]['processed']
iptables_log_parsed_folder = self.rootDataPath + self.config.get_config(
)['DataSources'][self._iptables_instance._type][
self._iptables_instance.__class__.__name__]['parsed']
iptables_flow_parser_config_file = self.config.get_config(
)['DataSources'][self._iptables_instance._type][
self._iptables_instance.__class__.__name__]['parserConfig']
# Parser configuration file for iptables
timer = self.config.get_config(
)['GeneralParams']['dataSourcesScheduling']
try:
# Doing until stop request
while not self._stopped_event.isSet():
logging.info("Running iptables thread ...")
logging.debug("Getting lines from file %s during %s seconds.",
iptables_log, timer)
# Get the iptables logs
log_lines = self._iptables_instance.get_file_to_parse_time(
iptables_log, timer)
# Time stamp
ts = dateutils.get_timestamp()
# Path for the backup
iptables_raw_log_file = iptables_log_raw_folder + "iptables_" + ts + ".log"
self._iptables_instance.save_file(log_lines,
iptables_raw_log_file)
# Parse it in *.csv format
logging.debug("Parsing file %s", iptables_raw_log_file)
iptables_log_processed_file = iptables_log_processed_folder + "iptables_" + ts + ".csv"
self._iptables_instance.parse(iptables_raw_log_file,
iptables_log_processed_file)
# Copy CSV file to parsed folder to be parsed by the flow parsed
iptables_log_parsed_file = iptables_log_parsed_folder + "iptables_" + ts + ".csv"
logging.debug("Copying file %s to %s ",
iptables_log_processed_file,
iptables_log_parsed_file)
shutil.copyfile(iptables_log_processed_file,
iptables_log_parsed_file)
# Flow parser
logging.debug("Running flow parser for %s file config.",
iptables_flow_parser_config_file)
self._iptables_instance.launch_flow_parser(
iptables_flow_parser_config_file)
# Add the *.dat output from parser to the dict of generated files
self._iptables_instance._files_generated[
ts] = iptables_log_parsed_folder + "output-iptables_" + ts + ".dat"
# Remove CSV file once it is parsed successfully
logging.debug("Deleting file %s", iptables_log_parsed_file)
os.remove(iptables_log_parsed_file)
except DataSourceError as edse:
logging.error("Error processing iptables source: %s",
edse.get_msg())
raise edse
except IOError as ioe:
logging.error("Error processing iptables source: %s",
ioe.get_msg())
raise DataSourceError(self, sys.exc_info()[0], method_name)
def run(self):
# Get configuration
config = Configure()
# Load local data sources running in static Mode
local_dict = {}
try:
src_local = config.get_config()['DataSources']['local']
logging.debug("Loading %s local sources %s.",len(src_local),src_local.keys())
for i in src_local.keys():
if src_local[i]['staticMode']:
logging.debug("Local source %s is running in static mode.",i)
local_dict[i] = src_local[i]
except KeyError as ke:
logging.warning("There are no local sources configured: %s", ke)
#Test observations per source
obsBySource = {}
# Get external files
for i in local_dict.keys():
if i == 'Netflow':
# Get all parsed *.dat files from a specific folder
staticFiles = local_dict[i]['staticParsedFilesPath']
# Get the name of the files ordered
filesOrdered = np.sort(os.listdir(staticFiles))
logging.debug("Got %s files from source %s ",len(filesOrdered),i)
# Remove auxiliar files weights.dat and stats.log
filesOrdered = filesOrdered[np.logical_not('stats.log' == filesOrdered)]
filesOrdered = filesOrdered[np.logical_not('weights.dat' == filesOrdered)]
logging.debug("Removed unuseless files from source %s. Total files to process: %s ",i,len(filesOrdered))
# Generate a dataframe containing all *.dat (all observations)
# Date range as index
dstart = filesOrdered[0][7:][0:-4]# get initial timestamp from the first file name, e.g., output-20160209t1249.dat
dend = filesOrdered[-1][7:][0:-4]# get ending timestamp from the first file name, e.g., output-20160209t1249.dat
d_range = pd.date_range(dstart,dend,freq='1min')
dfAllObs = pd.DataFrame(filesOrdered,d_range,columns=['obs'])
logging.debug("Got all obs from %s to %s",dstart,dend)
# Get the test date range
date_range_start = local_dict[i]['staticObsRangeStart']
date_range_end = local_dict[i]['staticObsRangeEnd']
obsBySource[i] = dfAllObs[date_range_start:date_range_end]
logging.debug("%s observations filtered from %s to %s",len(obsBySource[i]),date_range_start,date_range_end)
else:
logging.debug("TODO: managing %s local sources",i)
# dataSourcesScheduling
schedulingTimer = config.get_config()['GeneralParams']['dataSourcesScheduling']
nfcapdTimeFormat = config.get_config()['GeneralParams']['dateFormatNfcapdFiles']
netflow_parsed_folder = config.get_config()['DataSources']['local']['Netflow']['parsed']
netflow_dat_manual_folder = config.get_config()['DataSources']['local']['Netflow']['staticParsedFilesPath']
netflow_captures = config.get_config()['DataSources']['local']['Netflow']['captures']
# flag to finish the simulation
end = False
# Observations counter
obsCounter = 0
# list of observations
obsList = list(obsBySource['Netflow']['obs'])
while not end and not self._stopped_event.isSet():
try:
# Process the observation
obsToProcess = obsList[obsCounter]
logging.debug("Observation to process: %s",obsToProcess)
# ts from obs file
tsFile = obsToProcess[7:][0:-4]
# ts from the current host
ts = dateutils.get_timestamp()
# TODO ts for nfcap file
tsdatetime = parser.parse(ts)
tsdatetimeFile = parser.parse(tsFile)
tsFormatted = tsdatetime.strftime(nfcapdTimeFormat)
tsFormattedFile = tsdatetimeFile.strftime(nfcapdTimeFormat)
logging.debug("Creating nfcapd.current.%s", tsFormatted)
# Generate nfcapd synthetic current filefile with equal timestamp as the observation
nfcapdCurrent = netflow_captures + os.sep + "nfcapd.current." + tsFormatted
with open(nfcapdCurrent,'w') as f:
f.write("Dummy nfcapd for static mode current ")
# Move current nfcapd file to emulate on_moved event in netflow source
#In static mode the emulated nfcapd files has the name like nfcapd.201701302000_2016001182312, where last ts after '_' is the ts of the statid *.dat
# file
nfcapdDummy = netflow_captures + os.sep + "nfcapd." + tsFormatted + "_" + tsFormattedFile
logging.debug("Renaming %s to %s",nfcapdCurrent,nfcapdDummy)
shutil.move(nfcapdCurrent, nfcapdDummy)
# Copy *.dat file to 'parsed' folder
netflow_dat_manual_file = netflow_dat_manual_folder + obsToProcess
netflow_parsed_file = netflow_parsed_folder + "output-netflow_" + tsFormattedFile + ".dat"
logging.debug("Copying netflow manually generated file %s to %s ",netflow_dat_manual_file, netflow_parsed_file)
shutil.copyfile(netflow_dat_manual_file, netflow_parsed_file)
logging.debug("Waiting for %s s ...",schedulingTimer)
sleep(schedulingTimer)
obsCounter = obsCounter + 1
except KeyboardInterrupt:
logging.info("KeyboardInterrupt received. Exiting ...")
end = True
except Exception:
logging.warning("Probably we have reached the end of the observations. ERROR: %s", sys.exc_info()[1])
end = True
def launch_monitoring(self, ts):
"""
Once the parsing (flow parser) procedure is done, this method is in charge of to start the monitoring
process
Raises
------
MSNMError
"""
method_name = "launch_monitoring()"
# Configuration
config = Configure()
# Get root path for creating data files
rootDataPath = config.get_config()['GeneralParams']['rootPath']
obs_generated_path = rootDataPath + config.get_config()['Sensor'][
'observation'] # path to save the complete observation joining all data sources
batch_obs = config.get_config()['Sensor']['dynamiCalibration'][
'B'] # number of observation in a batch for EWMA calibration
lambda_param = config.get_config()['Sensor']['dynamiCalibration'][
'lambda'] # fogetting parameter for EWMA calibration
dyn_cal_enabled = config.get_config()['Sensor']['dynamiCalibration'][
'enabled'] # is the dynamic calibration activated?
output_generated_path = rootDataPath + config.get_config()['Sensor'][
'output'] # path to save the Q and T statistics obtained from the previous observation
missingDataMethods = config.get_config()['Sensor']['missingData'][
'missingDataMethods'] # Missing data available methods
missingDataSelectedMethod = config.get_config()['Sensor'][
'missingData']['selected'] # Get the selected missing data method
missingDataModule = config.get_config()['Sensor']['missingData'][
'missingDataModule'] # Missing data available methods
valuesFormat = config.get_config()['GeneralParams'][
'valuesFormat'] # how the variables of the complete observation are saved
logging.debug("Launch monitoring for %s ", ts)
try:
logging.debug("Building the observation at %s for %s sources.", ts,
self._sources.keys())
# Build the observation for monitoring
test = []
for i in self._sources.keys():
# Get the number of variables of source i
i_variables = self.get_number_source_variables(
self._sources[i], i)
logging.debug("Source %s has %s variables.", i, i_variables)
# Get the source output parsed file for the current
i_parsed_file = self._sources[i]._files_generated[ts]
logging.debug("File generated of source %s at %s: %s", i, ts,
i_parsed_file)
if i_parsed_file:
# Load the file
if self._sources[i]._type == Source.TYPE_L:
# static mode?
# TODO: next version
#staticMode = config.get_config()['DataSources'][self._sources[i]._type][i]['staticMode'];
staticMode = False
if not staticMode: # online or dynamic mode
i_test = np.loadtxt(i_parsed_file,
comments="#",
delimiter=",")
else: # offline or static mode
# TODO it is just a patch to remove in_npackets_verylow e in_nbytes_verylow like in matlab experiment and just for Netflow!!!
# look for a more smart way to do this e.g., by configuration params
i_test = np.loadtxt(i_parsed_file,
comments="#",
delimiter=",",
usecols=range(
1, i_variables + 1 + 2))
logging.debug(
"Offline mode for source %s. Observation size of %s",
i, i_test.shape)
mask = np.ones(i_test.shape, dtype=bool)
# in_npackets_verylow index in matlab is 119 --> 119 in numpy
# in_nbytes_verylow index in matlab is 129 --> 129 in numpy
mask[118] = False
mask[128] = False
i_test = i_test[mask]
logging.debug(
"Offline mode for source %s. Observation size of %s after removing unuseless variables.",
i, i_test.shape)
elif self._sources[i]._type == Source.TYPE_R:
i_test = np.loadtxt(i_parsed_file,
comments="#",
delimiter=",")
else:
logging.warn(
"Source %s does not has a valid type. Type: %s", i,
self._sources[i]._type)
else:
# Missing values are replaced with NaN values
i_test = np.empty(i_variables)
i_test[:] = np.nan
# Test observation
test = np.concatenate((test, i_test), axis=0)
# 1xM array
test = test.reshape((1, test.size))
# Dynamic invocation of the selected data imputation method if needed
if np.isnan(test).any():
missingDataMethod = getattr(
importlib.import_module(missingDataModule),
missingDataMethods[missingDataSelectedMethod])
logging.debug(
"Invoking %s method for data imputation for observation at %s",
missingDataMethod.func_name, ts)
# Calling the corresponding method
test = missingDataMethod(obs=test, model=self._sensor._model)
obs_generate_file = obs_generated_path + "obs_" + ts + ".dat"
np.savetxt(obs_generate_file,
test,
fmt=valuesFormat,
delimiter=",",
header=str(datautils.getAllVarNames()),
comments="#")
logging.debug("Observation generated of %s variables at %s.",
test.size, ts)
# if the dynamic calibration enabled?
if dyn_cal_enabled:
# Increments the number of observation
self._current_batch_obs = self._current_batch_obs + 1
logging.debug("obs %s added to the batch as number %s.", ts,
self._current_batch_obs)
# Add the observation
self._batch[ts] = {}
self._batch[ts]['file'] = obs_generate_file
self._batch[ts]['data'] = test
# Once we reached the number of batch observations, we can do the dynamic calibration
if self._current_batch_obs == batch_obs:
# data for calibration
x = np.array([])
x = x.reshape((0, test.size))
# Build the [NxM] data for the calibration
#print(self._batch.keys())
for i in self._batch.keys():
logging.debug("batch at %s -> %s", i,
self._batch[i]['data'].shape)
x = np.vstack((x, self._batch[i]['data']))
#print(x)
#print(type(x))
# Build the model
self._sensor.set_data(x)
self._sensor.do_dynamic_calibration(phase=2,
lv=3,
lamda=lambda_param)
# Reset the counter
self._current_batch_obs = 0
# Removing all batch observations
self._batch.clear()
# Do monitoring
Qst, Dst = self._sensor.do_monitoring(test)
except SensorError as ese:
raise MSNMError(self, ese.get_msg(), method_name)
except MSNMError as emsnme:
raise emsnme
logging.debug("MONITORING --> UCLd: %s | Dst: %s",
self._sensor.get_model().get_mspc().getUCLD(),
self._sensor.get_mspc().getDst())
logging.debug("MONITORING --> UCLq: %s | Qst: %s",
self._sensor.get_model().get_mspc().getUCLQ(),
self._sensor.get_mspc().getQst())
# Save the generated statistics
output_generated_file = output_generated_path + "output_" + ts + ".dat"
header = "UCLq:" + str(
self._sensor.get_model().get_mspc().getUCLQ()) + ", UCLd:" + str(
self._sensor.get_model().get_mspc().getUCLD())
list_array = [
self._sensor.get_mspc().getQst(),
self._sensor.get_mspc().getDst()
]
statistics = np.array(list_array)
statistics = statistics.reshape((1, statistics.size))
np.savetxt(output_generated_file,
statistics,
fmt=valuesFormat,
delimiter=",",
header=header,
comments="#")
# Gets the remote sensor addressed to send the packet
remote_addresses = config.get_config()['Sensor']['remote_addresses']
# Send packets is there are someone for sending it!
if remote_addresses:
# Send the data packet to the corresponding sensor.
dataPacket = DataPacket()
# Packet sent counter increments
self._packet_sent = self._packet_sent + 1
dataPacket.fill_header({
'id': self._packet_sent,
'sid': config.get_config()['Sensor']['sid'],
'ts': dateutils.get_timestamp(),
'type': Packet.TYPE_D
})
dataPacket.fill_body({
'Q': self._sensor.get_mspc().getQst(),
'D': self._sensor.get_mspc().getDst()
})
logging.debug("Remote sources to send the packet #%s: %s",
self._packet_sent, remote_addresses)
for i in remote_addresses.keys():
ip = remote_addresses[i]['ip']
port = remote_addresses[i]['port']
tcpClient = TCPClient()
tcpClient.set_server_address((ip, port))
tcpClient.set_packet_to_send(dataPacket)
TCPClientThread(tcpClient).start()
return test, Qst, Dst
