class topic4:
def __init__(self, c_hash, c_user, c_words):
self.topic_count =1
self.l1 = LRU(c_hash)
self.l2 = LRU(c_user)
def set_hashLRU(self,l):
self.set(self.l1, l)
def set_userLRU(self,l):
self.set(self.l2, l)
def set(self, lru, l):
for k in l:
v = lru.get(k,0)
lru[k]=v+1
def set_cluster(self, hashtags, users, words):
for k in hashtags:
self.l1[k]=self.l1.get(k,0)+1
for k in users:
self.l2[k]=self.l2.get(k,0)+1
self.topic_count+=1
def get_similarity(self,hashtags,users,words):
h_sum = 1
u_sum = 1
w_sum = 1
h_match =0
h_ind =0
u_ind =0
w_ind =0
c=0
h1 = self.l1.get_size()
u1 = self.l2.get_size()
for h in hashtags:
# l1_items=zip(*self.l1.items())
h_sum+= self.l1.get(h,0)
if(self.l1.has_key(h)):
ind = self.l1.keys().index(h)
h_ind+= h1 - ind
h_match+= 1 if ind<250 else 0
for u in users:
u_sum+= self.l2.get(u,0)
if(self.l2.has_key(u)):
u_ind+= u1 - self.l2.keys().index(u)
if(h_match !=0):
c = h_match -1
# print(h_ind,h1,u_ind,u1,w_ind,w1, h_sum,w_sum,)
similarity = (h_ind/(h1+1))*(h_sum/sum(self.l1.values() +[1])) + (u_ind/(u1+1))*(u_sum/sum(self.l2.values()+[1])) +c
return similarity
class GameState(object, metaclass=Singleton):
def __init__(self):
self.is_finished = False
self.active_player = None
self.other_players = LRU(10)
self.world_map = LRU(1000)
@classmethod
def get_instance(self):
return GameState()
@guard_exception(False)
@log_exception
def parse_net_frame(self, net_frame):
# parse current player
ap = PlayerState.from_dict(net_frame["active_player"])
if self.active_player is None:
self.active_player = ap
else:
self.active_player.update(ap)
# parse other aoi players
ops = net_frame["other_aoi_players"]
if len(ops) > self.other_players.get_size():
self.other_players.set_size(len(ops))
for op in ops:
op = PlayerState.from_dict(op)
if op.name not in self.other_players:
self.other_players[op.name] = op
else:
self.other_players[op.name].update(op)
# parse world map element
wm = net_frame["world_map"]
if len(wm) > self.world_map.get_size():
self.world_map.set_size(len(wm))
for item in wm:
x, y, val = item
wm[(x, y)] = val
return True
def get_update(self, net_frame):
ret = self.parse_net_frame(net_frame)
if ret:
return self
def test_capacity_set(self):
for size in SIZES:
l = LRU(size)
for i in range(size+5):
l[i] = str(i)
l.set_size(size+10)
self.assertTrue(size+10 == l.get_size())
self.assertTrue(len(l) == size)
for i in range(size+20):
l[i] = str(i)
self.assertTrue(len(l) == size+10)
l.set_size(size+10-1)
self.assertTrue(len(l) == size+10-1)
def test_capacity_set(self):
for size in SIZES:
l = LRU(size)
for i in range(size+5):
l[i] = str(i)
l.set_size(size+10)
self.assertTrue(size+10 == l.get_size())
self.assertTrue(len(l) == size)
for i in range(size+20):
l[i] = str(i)
self.assertTrue(len(l) == size+10)
l.set_size(size+10-1)
self.assertTrue(len(l) == size+10-1)
def test_capacity_get(self):
for size in SIZES:
l = LRU(size)
self.assertTrue(size == l.get_size())
def test_capacity_get(self):
for size in SIZES:
l = LRU(size)
self.assertTrue(size == l.get_size())
class FileServer(fileService_pb2_grpc.FileserviceServicer):
def __init__(self, hostname, server_port, activeNodesChecker,
shardingHandler, superNodeAddress):
self.serverPort = server_port
self.serverAddress = hostname + ":" + server_port
self.activeNodesChecker = activeNodesChecker
self.shardingHandler = shardingHandler
self.hostname = hostname
self.lru = LRU(5)
self.superNodeAddress = superNodeAddress
#
# This service gets invoked when user uploads a new file.
#
def UploadFile(self, request_iterator, context):
print("Inside Server method ---------- UploadFile")
data = bytes("", 'utf-8')
username, filename = "", ""
totalDataSize = 0
active_ip_channel_dict = self.activeNodesChecker.getActiveChannels()
# list to store the info related to file location.
metaData = []
# If the node is the leader of the cluster.
if (int(db.get("primaryStatus")) == 1):
print("Inside primary upload")
currDataSize = 0
currDataBytes = bytes("", 'utf-8')
seqNo = 1
# Step 1:
# Get 2 least loaded nodes based on the CPU stats.
# 'Node' is where the actual data goes and 'node_replica' is where replica will go.
node, node_replica = self.getLeastLoadedNode()
if (node == -1):
return fileService_pb2.ack(
success=False,
message="Error Saving File. No active nodes.")
# Step 2:
# Check whether file already exists, if yes then return with message 'File already exists'.
for request in request_iterator:
username, filename = request.username, request.filename
print("Key is-----------------", username + "_" + filename)
if (self.fileExists(username, filename) == 1):
print("sending neg ack")
return fileService_pb2.ack(
success=False,
message=
"File already exists for this user. Please rename or delete file first."
)
break
# Step 3:
# Make chunks of size 'UPLOAD_SHARD_SIZE' and start sending the data to the least utilized node trough gRPC streaming.
currDataSize += sys.getsizeof(request.data)
currDataBytes += request.data
for request in request_iterator:
if ((currDataSize + sys.getsizeof(request.data)) >
UPLOAD_SHARD_SIZE):
response = self.sendDataToDestination(
currDataBytes, node, node_replica, username, filename,
seqNo, active_ip_channel_dict[node])
metaData.append([node, seqNo, node_replica])
currDataBytes = request.data
currDataSize = sys.getsizeof(request.data)
seqNo += 1
node, node_replica = self.getLeastLoadedNode()
else:
currDataSize += sys.getsizeof(request.data)
currDataBytes += request.data
if (currDataSize > 0):
response = self.sendDataToDestination(
currDataBytes, node, node_replica, username, filename,
seqNo, active_ip_channel_dict[node])
metaData.append([node, seqNo, node_replica])
# Step 4:
# Save the metadata on the primary node after the completion of sharding.
if (response.success):
db.saveMetaData(username, filename, metaData)
db.saveUserFile(username, filename)
# Step 5:
# Make a gRPC call to replicate the matadata on all the other nodes.
self.saveMetadataOnAllNodes(username, filename, metaData)
return fileService_pb2.ack(success=True, message="Saved")
# If the node is not the leader.
else:
print("Saving the data on my local db")
sequenceNumberOfChunk = 0
dataToBeSaved = bytes("", 'utf-8')
# Gather all the data from gRPC stream
for request in request_iterator:
username, filename, sequenceNumberOfChunk = request.username, request.filename, request.seqNo
dataToBeSaved += request.data
key = username + "_" + filename + "_" + str(sequenceNumberOfChunk)
# Save the data in local DB.
db.setData(key, dataToBeSaved)
# After saving the chunk in the local DB, make a gRPC call to save the replica of the chunk on different
# node only if the replicaNode is present.
if (request.replicaNode != ""):
print("Sending replication to ", request.replicaNode)
replica_channel = active_ip_channel_dict[request.replicaNode]
t1 = Thread(target=self.replicateChunkData,
args=(
replica_channel,
dataToBeSaved,
username,
filename,
sequenceNumberOfChunk,
))
t1.start()
# stub = fileService_pb2_grpc.FileserviceStub(replica_channel)
# response = stub.UploadFile(self.sendDataInStream(dataToBeSaved, username, filename, sequenceNumberOfChunk, ""))
return fileService_pb2.ack(success=True, message="Saved")
def replicateChunkData(self, replica_channel, dataToBeSaved, username,
filename, sequenceNumberOfChunk):
stub = fileService_pb2_grpc.FileserviceStub(replica_channel)
response = stub.UploadFile(
self.sendDataInStream(dataToBeSaved, username, filename,
sequenceNumberOfChunk, ""))
# This helper method is responsible for sending the data to destination node through gRPC stream.
def sendDataToDestination(self, currDataBytes, node, nodeReplica, username,
filename, seqNo, channel):
if (node == self.serverAddress):
key = username + "_" + filename + "_" + str(seqNo)
db.setData(key, currDataBytes)
if (nodeReplica != ""):
print("Sending replication to ", nodeReplica)
active_ip_channel_dict = self.activeNodesChecker.getActiveChannels(
)
replica_channel = active_ip_channel_dict[nodeReplica]
stub = fileService_pb2_grpc.FileserviceStub(replica_channel)
response = stub.UploadFile(
self.sendDataInStream(currDataBytes, username, filename,
seqNo, ""))
return response
else:
print("Sending the UPLOAD_SHARD_SIZE to node :", node)
stub = fileService_pb2_grpc.FileserviceStub(channel)
response = stub.UploadFile(
self.sendDataInStream(currDataBytes, username, filename, seqNo,
nodeReplica))
print("Response from uploadFile: ", response.message)
return response
# This helper method actually makes chunks of less than 4MB and streams them through gRPC.
# 4 MB is the max data packet size in gRPC while sending. That's why it is necessary.
def sendDataInStream(self, dataBytes, username, filename, seqNo,
replicaNode):
chunk_size = 4000000
start, end = 0, chunk_size
while (True):
chunk = dataBytes[start:end]
if (len(chunk) == 0): break
start = end
end += chunk_size
yield fileService_pb2.FileData(username=username,
filename=filename,
data=chunk,
seqNo=seqNo,
replicaNode=replicaNode)
#
# This service gets invoked when user requests an uploaded file.
#
def DownloadFile(self, request, context):
print("Inside Download")
# If the node is the leader of the cluster.
if (int(db.get("primaryStatus")) == 1):
print("Inside primary download")
# Check if file exists
if (self.fileExists(request.username, request.filename) == 0):
print("File does not exist")
yield fileService_pb2.FileData(username=request.username,
filename=request.filename,
data=bytes("", 'utf-8'),
seqNo=0)
return
# If the file is present in cache then just fetch it and return. No need to go to individual node.
if (self.lru.has_key(request.username + "_" + request.filename)):
print("Fetching data from Cache")
CHUNK_SIZE = 4000000
fileName = request.username + "_" + request.filename
filePath = self.lru[fileName]
outfile = os.path.join(filePath, fileName)
with open(outfile, 'rb') as infile:
while True:
chunk = infile.read(CHUNK_SIZE)
if not chunk: break
yield fileService_pb2.FileData(
username=request.username,
filename=request.filename,
data=chunk,
seqNo=1)
# If the file is not present in the cache, then fetch it from the individual node.
else:
print("Fetching the metadata")
# Step 1: get metadata i.e. the location of chunks.
metaData = db.parseMetaData(request.username, request.filename)
print(metaData)
#Step 2: make gRPC calls and get the fileData from all the nodes.
downloadHelper = DownloadHelper(self.hostname, self.serverPort,
self.activeNodesChecker)
data = downloadHelper.getDataFromNodes(request.username,
request.filename,
metaData)
print("Sending the data to client")
#Step 3: send the file to supernode using gRPC streaming.
chunk_size = 4000000
start, end = 0, chunk_size
while (True):
chunk = data[start:end]
if (len(chunk) == 0): break
start = end
end += chunk_size
yield fileService_pb2.FileData(username=request.username,
filename=request.filename,
data=chunk,
seqNo=request.seqNo)
# Step 4: update the cache based on LRU(least recently used) algorithm.
self.saveInCache(request.username, request.filename, data)
# If the node is not the leader, then just fetch the fileChunk from the local db and stream it back to leader.
else:
key = request.username + "_" + request.filename + "_" + str(
request.seqNo)
print(key)
data = db.getFileData(key)
chunk_size = 4000000
start, end = 0, chunk_size
while (True):
chunk = data[start:end]
if (len(chunk) == 0): break
start = end
end += chunk_size
yield fileService_pb2.FileData(username=request.username,
filename=request.filename,
data=chunk,
seqNo=request.seqNo)
# This service is responsible fetching all the files.
def FileList(self, request, context):
print("File List Called")
userFiles = db.getUserFiles(request.username)
return fileService_pb2.FileListResponse(Filenames=str(userFiles))
# This helper method checks whether the file is present in db or not.
def fileExists(self, username, filename):
print("isFile Present", db.keyExists(username + "_" + filename))
return db.keyExists(username + "_" + filename)
# This helper method returns 2 least loaded nodes from the cluster.
def getLeastLoadedNode(self):
print("Ready to enter sharding handler")
node, node_replica = self.shardingHandler.leastUtilizedNode()
print("Least loaded node is :", node)
print("Replica node - ", node_replica)
return node, node_replica
# This helper method replicates the metadata on all nodes.
def saveMetadataOnAllNodes(self, username, filename, metadata):
print("saveMetadataOnAllNodes")
active_ip_channel_dict = self.activeNodesChecker.getActiveChannels()
uniqueFileName = username + "_" + filename
for ip, channel in active_ip_channel_dict.items():
if (self.isChannelAlive(channel)):
stub = fileService_pb2_grpc.FileserviceStub(channel)
response = stub.MetaDataInfo(
fileService_pb2.MetaData(
filename=uniqueFileName,
seqValues=str(metadata).encode('utf-8')))
print(response.message)
# This service is responsible for saving the metadata on local db.
def MetaDataInfo(self, request, context):
print("Inside Metadatainfo")
fileName = request.filename
seqValues = request.seqValues
db.saveMetaDataOnOtherNodes(fileName, seqValues)
ack_message = "Successfully saved the metadata on " + self.serverAddress
return fileService_pb2.ack(success=True, message=ack_message)
# This helper method checks whethere created channel is alive or not
def isChannelAlive(self, channel):
try:
grpc.channel_ready_future(channel).result(timeout=1)
except grpc.FutureTimeoutError:
#print("Connection timeout. Unable to connect to port ")
return False
return True
# This helper method is responsible for updating the cache for faster lookup.
def saveInCache(self, username, filename, data):
if (len(self.lru.items()) >= self.lru.get_size()):
fileToDel, path = self.lru.peek_last_item()
os.remove(path + "/" + fileToDel)
self.lru[username + "_" + filename] = "cache"
filePath = os.path.join('cache', username + "_" + filename)
saveFile = open(filePath, 'wb')
saveFile.write(data)
saveFile.close()
# This service is responsible for sending the whole cluster stats to superNode
def getClusterStats(self, request, context):
print("Inside getClusterStats")
active_ip_channel_dict = self.activeNodesChecker.getActiveChannels()
total_cpu_usage, total_disk_space, total_used_mem = 0.0, 0.0, 0.0
total_nodes = 0
for ip, channel in active_ip_channel_dict.items():
if (self.isChannelAlive(channel)):
stub = heartbeat_pb2_grpc.HearBeatStub(channel)
stats = stub.isAlive(heartbeat_pb2.NodeInfo(ip="", port=""))
total_cpu_usage = float(stats.cpu_usage)
total_disk_space = float(stats.disk_space)
total_used_mem = float(stats.used_mem)
total_nodes += 1
if (total_nodes == 0):
return fileService_pb2.ClusterStats(cpu_usage=str(100.00),
disk_space=str(100.00),
used_mem=str(100.00))
return fileService_pb2.ClusterStats(
cpu_usage=str(total_cpu_usage / total_nodes),
disk_space=str(total_disk_space / total_nodes),
used_mem=str(total_used_mem / total_nodes))
# This service is responsible for sending the leader info to superNode as soon as leader changes.
def getLeaderInfo(self, request, context):
channel = grpc.insecure_channel('{}'.format(self.superNodeAddress))
stub = fileService_pb2_grpc.FileserviceStub(channel)
response = stub.getLeaderInfo(
fileService_pb2.ClusterInfo(ip=self.hostname,
port=self.serverPort,
clusterName="team1"))
print(response.message)
#
# This service gets invoked when user deletes a file.
#
def FileDelete(self, request, data):
username = request.username
filename = request.filename
if (int(db.get("primaryStatus")) == 1):
if (self.fileExists(username, filename) == 0):
print("File does not exist")
return fileService_pb2.ack(success=False,
message="File does not exist")
print("Fetching metadata from leader")
metadata = db.parseMetaData(request.username, request.filename)
print("Successfully retrieved metadata from leader")
deleteHelper = DeleteHelper(self.hostname, self.serverPort,
self.activeNodesChecker)
deleteHelper.deleteFileChunksAndMetaFromNodes(
username, filename, metadata)
return fileService_pb2.ack(
success=True,
message="Successfully deleted file from the cluster")
else:
seqNo = -1
try:
seqNo = request.seqNo
except:
return fileService_pb2.ack(success=False,
message="Internal Error")
metaDataKey = username + "_" + filename
dataChunkKey = username + "_" + filename + "_" + str(seqNo)
if (db.keyExists(metaDataKey) == 1):
print("FileDelete: Deleting the metadataEntry from local db :")
db.deleteEntry(metaDataKey)
if (db.keyExists(dataChunkKey)):
print("FileDelete: Deleting the data chunk from local db: ")
db.deleteEntry(dataChunkKey)
return fileService_pb2.ack(
success=True,
message="Successfully deleted file from the cluster")
#
# This service gets invoked when user wants to check if the file is present.
#
def FileSearch(self, request, data):
username, filename = request.username, request.filename
if (self.fileExists(username, filename) == 1):
return fileService_pb2.ack(success=True,
message="File exists in the cluster.")
else:
return fileService_pb2.ack(
success=False, message="File does not exist in the cluster.")
#
# This service gets invoked when user wants to update a file.
#
def UpdateFile(self, request_iterator, context):
username, filename = "", ""
fileData = bytes("", 'utf-8')
for request in request_iterator:
fileData += request.data
username, filename = request.username, request.filename
def getFileChunks(fileData):
# Maximum chunk size that can be sent
CHUNK_SIZE = 4000000
outfile = os.path.join('files', fileName)
sTime = time.time()
while True:
chunk = fileData.read(CHUNK_SIZE)
if not chunk: break
yield fileService_pb2.FileData(username=username,
filename=fileName,
data=chunk,
seqNo=1)
print("Time for upload= ", time.time() - sTime)
if (int(db.get("primaryStatus")) == 1):
channel = grpc.insecure_channel('{}'.format(self.serverAddress))
stub = fileService_pb2_grpc.FileserviceStub(channel)
response1 = stub.FileDelete(
fileService_pb2.FileInfo(username=userName, filename=fileName))
if (response1.success):
response2 = stub.UploadFile(getFileChunks(fileData))
if (response2.success):
return fileService_pb2.ack(
success=True, message="File suceessfully updated.")
else:
return fileService_pb2.ack(success=False,
message="Internal error.")
else:
return fileService_pb2.ack(success=False,
message="Internal error.")
class topic4:
def __init__(self, c_hash, c_user, c_words):
self.topic_count =1
# self.time = (self.first,self.last)
self.l1 = LRU(c_hash)
self.first =""
self.last=""
self.lats=[]
self.longs=[]
self.l2 = LRU(c_user)
self.l3 = LRU(c_words)
self.l4 = LRU(400)
def set_hashLRU(self,l):
self.set(self.l1, l)
def set_userLRU(self,l):
self.set(self.l2, l)
def set_wordLRU(self,l):
self.set(self.l3, l)
def set(self, lru, l):
for k in l:
v = lru.get(k,0)
lru[k]=v+1
def set_cluster(self, hashtags, users, words,links, cords):
for k in hashtags:
self.l1[k]=self.l1.get(k,0)+1
for k in users:
self.l2[k]=self.l2.get(k,0)+1
for k in words:
self.l3[k]=self.l3.get(k,0)+1
for k in links:
self.l4[k]=self.l4.get(k,0)+1
if(cords is not None):
self.lats.append(cords["coordinates"][1])
self.longs.append(cords["coordinates"][0])
self.topic_count+=1
def get_similarity(self,hashtags,users,words):
h_sum = 1
u_sum = 1
w_sum = 1
h_match =0
h_ind =0
u_ind =0
w_ind =0
c=0
h1 = self.l1.get_size()
u1 = self.l2.get_size()
w1 = self.l3.get_size()
for h in hashtags:
# l1_items=zip(*self.l1.items())
h_sum+= self.l1.get(h,0)
if(self.l1.has_key(h)):
ind = self.l1.keys().index(h)
h_ind+= h1 - ind
h_match+= 1 if ind<250 else 0
for u in users:
u_sum+= self.l2.get(u,0)
if(self.l2.has_key(u)):
u_ind+= u1 - self.l2.keys().index(u)
for w in words:
w_sum+= self.l3.get(w,0)
if(self.l3.has_key(w)):
w_ind+= w1 - self.l3.keys().index(w)
if(h_match !=0):
c = h_match -1
# print(h_ind,h1,u_ind,u1,w_ind,w1, h_sum,w_sum,)
similarity = (h_ind/(h1+1))*(h_sum/sum(self.l1.values() +[1])) + (u_ind/(u1+1))*(u_sum/sum(self.l2.values()+[1])) + (w_ind/(w1+1))*(w_sum/sum(self.l3.values()+[1])) +c
return similarity
def flush1(self, cache, size):
if(len(cache.keys())>5):
tokens = reversed(cache.keys()[5])
cache.clear()
for i in tokens:
cache[i]=1
def flush(self):
self.flush1(self.l1,500)
self.flush1(self.l2, 500)
self.flush1(self.l3,3500)
self.topic_count=1
print(l.items()) # Would print [(5, '5'), (4, '4'), (3, '3'), (2, '2'), (1, '1')] l[3] # Accessing an item would make it MRU print(l.items()) # Would print [(3, '3'), (5, '5'), (4, '4'), (2, '2'), (1, '1')] # Now 3 is in front l.keys() # Can get keys alone in MRU order # Would print [3, 5, 4, 2, 1] del l[4] # Delete an item print(l.items()) # Would print [(3, '3'), (5, '5'), (2, '2'), (1, '1')] print(l.get_size()) # Would print 5 l.set_size(3) print(l.items()) # Would print [(3, '3'), (5, '5'), (2, '2')] print(l.get_size()) # Would print 3 print(l.has_key(5)) # Would print True print(2 in l) # Would print True l.get_stats() # Would print (1, 0)
class Cache:
"""Class representing D3N."""
# Replacement policies
LRU = "LRU"
LFU = "LFU"
LRU_S = "LRU_S"
FIFO = "FIFO"
RAND = "RAND"
# Write policies
WRITE_BACK = "WB"
WRITE_THROUGH = "WT"
# Layer
L1 = "L1"
L2 = "L2"
consistent = "consistent"
rendezvous = "rendezvous"
rr = "rr"
def __init__(self, layer, size, replace_pol, write_pol, hash_ring,
hash_type, obj_size, full_size, logger):
self._replace_pol = replace_pol # Replacement policy
self._write_pol = write_pol # Write policy
self._layer = layer # Layer info
self._size = size # Cache size
self.spaceLeft = size # Cache size
self._logger = logger
self.hashmap = {} # Mapping
self.hash_ring = hash_ring
self._hash_type = hash_type
self._obj_size = obj_size
if (self._size == 0):
self.zerosize = True
self._size = 1
else:
self.zerosize = False
if (self._replace_pol == Cache.LRU):
self.cache = LRU(self._size)
elif (self._replace_pol == Cache.FIFO):
self.cache = deque()
elif (self._replace_pol == Cache.LRU_S):
self.cache = LRU(self._size)
self.shadow = LRU(full_size)
self.hist = []
for i in range(full_size):
self.hist.append(0)
# Statistics
self._hit_count = 0
self._miss_count = 0
self._backend_bw = 0
self._crossrack_bw = 0
self._intrarack_bw = 0
self.miss_lat = 0
self.lat_count = 0
def _insert1(self, key, size):
# No eviction
if not self.zerosize:
if (self._replace_pol == Cache.LRU_S):
self.shadow[key] = 1
if (int(size) <= self.spaceLeft):
if (self._replace_pol == Cache.LRU):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.LRU_S):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.FIFO):
self.cache.append(key)
self.hashmap[key] = int(size)
self.spaceLeft -= int(size)
else:
while (int(size) > self.spaceLeft):
self._evict()
if (self._replace_pol == Cache.LRU):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.LRU_S):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.FIFO):
self.cache.append(key)
self.hashmap[key] = int(size)
self.spaceLeft -= int(size)
def _insert(self, key, size):
# No eviction
if not self.zerosize:
if (self._replace_pol == Cache.LRU_S):
self.cache[key] = int(size)
self.shadow[key] = int(size)
elif (self._replace_pol == Cache.LRU):
self.cache[key] = int(size)
else:
if (int(size) <= self.spaceLeft):
if (self._replace_pol == Cache.LRU):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.LRU_S):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.FIFO):
self.cache.append(key)
self.hashmap[key] = int(size)
self.spaceLeft -= int(size)
else:
while (int(size) > self.spaceLeft):
self._evict()
if (self._replace_pol == Cache.LRU):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.LRU_S):
self.cache[key] = int(size)
elif (self._replace_pol == Cache.FIFO):
self.cache.append(key)
self.hashmap[key] = int(size)
self.spaceLeft -= int(size)
def read1(self, key, size):
if self._layer == "BE":
return 1
if self.zerosize == True:
return None
"""Read a object from the cache."""
r = None
if (self._replace_pol == Cache.LRU_S):
if self.shadow.has_key(key):
count = 0
for i in self.shadow.keys():
if i == key:
self.hist[count] += 1
break
count += 1
self.shadow[key] = 1
if key in self.hashmap:
if (self._replace_pol == Cache.LRU):
self._update_use(key)
elif (self._replace_pol == Cache.LRU_S):
self._update_use(key)
self._hit_count += 1
r = 1
else:
self._miss_count += 1
return r
def read(self, key, size):
if self._layer == "BE":
return 1
if self.zerosize == True:
return None
"""Read a object from the cache."""
r = None
if (self._replace_pol == Cache.LRU_S):
if self.cache.has_key(key):
self._hit_count += 1
self.cache[key] = self.cache[key]
r = 1
else:
self._miss_count += 1
if self.shadow.has_key(key):
count = 0
for i in self.shadow.keys():
if i == key:
self.hist[count] += 1
break
count += 1
self.shadow[key] = 1
else:
if key in self.hashmap:
if (self._replace_pol == Cache.LRU):
self._update_use(key)
elif (self._replace_pol == Cache.LRU_S):
self._update_use(key)
self._hit_count += 1
r = 1
else:
self._miss_count += 1
return r
def checkKey(self, key):
if self._layer == "BE":
return 1
if self.zerosize == True:
return 0
"""Read a object from the cache."""
r = 0
if (self._replace_pol == Cache.LRU_S) or (self._replace_pol
== Cache.LRU):
if self.cache.has_key(key):
r = 1
else:
r = 0
return r
def _evict(self):
if (self._replace_pol == Cache.LRU):
id = self.cache.peek_last_item()[0]
del self.cache[id]
elif (self._replace_pol == Cache.LRU_S):
id = self.cache.peek_last_item()[0]
del self.cache[id]
elif (self._replace_pol == Cache.FIFO):
id = self.cache.popleft()
self.spaceLeft += int(self.hashmap[id])
del self.hashmap[id]
def _update_use(self, key):
"""Update the use of a cache."""
if (self._replace_pol == Cache.LRU):
self.cache[key] = self.hashmap[key]
if (self._replace_pol == Cache.LRU_S):
self.cache[key] = self.hashmap[key]
def set_cache_size(self, size):
new_size = self.cache.get_size() + int(size)
self.cache.set_size(int(new_size))
def set_backend_bw(self, value):
self._backend_bw += value
def set_crossrack_bw(self, value):
self._crossrack_bw += value
def set_intrarack_bw(self, value):
self._intrarack_bw += value
def get_backend_bw(self):
return self._backend_bw
def get_crossrack_bw(self):
return self._crossrack_bw
def get_intrarack_bw(self):
return self._intrarack_bw
def get_replace_pol(self):
return self._replace_pol
def get_hit_count(self):
return self._hit_count
def get_miss_count(self):
return self._miss_count
def get_available_space(self):
return self.spaceLeft
def get_replace_poll(self):
return self._replace_pol
def reset_shadow_cache():
self.shadow.clear()
def print_cache(self):
print self.cache
def get_l2_address(self, key):
if (self._hash_type == Cache.consistent):
return self.hash_ring.get_node(key)
elif (self._hash_type == Cache.rendezvous):
return self.hash_ring.find_node(key)
elif (self._hash_type == Cache.rr):
val = key.split("_")[1]
res = int(val) % int(self.hash_ring)
return res
class Streamer:
""" streamer for flows management """
num_streamers = 0
def __init__(self,
source=None,
capacity=128000,
active_timeout=120,
inactive_timeout=60,
user_metrics=None,
user_classifiers=None,
enable_ndpi=True):
Streamer.num_streamers += 1
self.__exports = []
self.source = source
self.__flows = LRU(capacity, callback=emergency_callback) # LRU cache
self._capacity = self.__flows.get_size(
) # Streamer capacity (default: 128000)
self.active_timeout = active_timeout # expiration active timeout
self.inactive_timeout = inactive_timeout # expiration inactive timeout
self.current_flows = 0 # counter for stored flows
self.flows_number = 0
self.current_tick = 0 # current timestamp
self.processed_packets = 0 # current timestamp
# Python dictionaries to hold current and archived flow records
self.flow_cache = OrderedDict()
self.user_classifiers = {}
if user_classifiers is not None:
try:
classifier_iterator = iter(user_classifiers)
for classifier in classifier_iterator:
if isinstance(classifier, NFStreamClassifier):
self.user_classifiers[classifier.name] = classifier
except TypeError:
self.user_classifiers[user_classifiers.name] = user_classifiers
self.user_metrics = {}
if enable_ndpi:
ndpi_classifier = NDPIClassifier('ndpi')
self.user_classifiers[ndpi_classifier.name] = ndpi_classifier
if user_metrics is not None:
self.user_metrics = user_metrics
def _get_capacity(self):
""" getter for capacity attribute """
return self.__flows.get_size()
def _set_capacity(self, new_size):
""" setter for capacity size attribute """
return self.__flows.set_size(new_size)
capacity = property(_get_capacity, _set_capacity)
def terminate(self):
""" terminate all entries in Streamer """
remaining_flows = True
while remaining_flows:
try:
key, value = self.__flows.peek_last_item()
value.export_reason = 2
self.exporter(value)
except TypeError:
remaining_flows = False
for classifier_name, classifier in self.user_classifiers.items():
self.user_classifiers[classifier_name].on_exit()
def exporter(self, flow):
""" export method for a flow trigger_type:0(inactive), 1(active), 2(flush) """
# Look for the flow in the created classifiers
for classifier_name, classifier in self.user_classifiers.items():
# Terminate the flow in the respective classifiers
self.user_classifiers[classifier_name].on_flow_terminate(flow)
# Delete the flow register from the active flows collection
del self.__flows[flow.key]
# Decrease the number of active flows by 1
self.current_flows -= 1
# Add the expired flow register to the final flows collection
self.__exports.append(flow)
def inactive_watcher(self):
""" inactive expiration management """
remaining_inactives = True
# While there are inactive flow registers
while remaining_inactives:
try:
# Obtain the last flow register (Least Recently Used - LRU) in the variable value using its key
key, value = self.__flows.peek_last_item()
# Has the flow exceeded the inactive timeout (1 minute)?
if (self.current_tick -
value.end_time) >= (self.inactive_timeout * 1000):
# Set export reason to 0 (inactive) in the flow
value.export_reason = 0
# Export the flow to the final flows collection
self.exporter(value)
# There are no flows that can be declared inactive yet
else:
# Stop the inactive watcher until it is called again
remaining_inactives = False
except TypeError:
remaining_inactives = False
def consume(self, pkt_info):
""" consume a packet and update Streamer status """
self.processed_packets += 1 # increment total processed packet counter
# Obtain a flow hash key for identification of the flow
key = get_flow_key(pkt_info)
print("\nCONSUMING PACKET FROM FLOW:", key)
# Is this packet from a registered flow?
if key in self.__flows:
print("FLOW FOUND - UPDATING STATISTICS")
# Checking current status of the flow that the packet belongs to
# -1 active flow - 0 inactive flow - 1 active flow timeout expired - 2 flush remaining flows in LRU
# 3 FIN flag detected - 4 RST flag detected
flow_status = self.__flows[key].update_and_check_flow_status(
pkt_info, self.active_timeout, self.user_classifiers,
self.user_metrics)
#Has the active timeout of the flow register expired (2 minutes)?
if (flow_status == 1):
# Export the old flow register to the final collection and terminate this flow process on the specified classifier
self.exporter(self.__flows[key])
# Create a new flow register for the current packet
flow = Flow(pkt_info, self.user_classifiers, self.user_metrics,
self.flow_cache)
# Add the new flow to the active flows collection using the same Hash key
self.__flows[flow.key] = flow
# Create the entry on the flow_cache with the flow key
del self.flow_cache[flow.key]
self.flow_cache[flow.key] = {}
# Update the flow status on the collection
flow.create_new_flow_record(pkt_info, self.user_classifiers,
self.user_metrics)
if (flow_status == 3
): # FIN FLAG DETECTED IN BOTH DIRECTIONS - EXPORTING FLOW
self.exporter(self.__flows[key])
if (
flow_status == 4
): # RST FLAG FOUND - UPDATING BIDIRECTIONAL STATISTICS - EXPORTING FLOW
self.exporter(self.__flows[key])
if (flow_status == 5): # FIN FLAG TIMER EXPIRED
self.exporter(self.__flows[key])
print("****FLOW EXPORTED")
"""
expired_flow = self.__flows[key]
print("****STARTING TCP TIMER")
threading.Timer(20, self.export_incomplete_flow(expired_flow))
"""
# This packet belongs to a new flow
else:
# Increase the count of current active flows
print("FLOW NOT FOUND - CREATING NEW FLOW REGISTER")
# Update flow counters
self.current_flows += 1
self.flows_number += 1
# Create the new flow object
flow = Flow(pkt_info, self.user_classifiers, self.user_metrics,
self.flow_cache)
# Add this new flow register to the LRU
self.__flows[flow.key] = flow
# Create the entry on the flow_cache with the flow key
self.flow_cache[flow.key] = {}
# Create the new bidirectional flow record
flow.create_new_flow_record(pkt_info, self.user_classifiers,
self.user_metrics)
# Set the current start time on the streamer timer to keep control of the inactive flows
self.current_tick = flow.start_time
# Remove the Least Recently Used (LRU) flow record from the active flows collection
# and export it to the final flows collection if its inactive timeout has been exceeded
self.inactive_watcher()
print(
"*******************PACKET CONSUMED - MOVING TO NEXT*********************************"
)
"""
def export_incomplete_flow(self, expired_flow):
print("##############################---TCP TIMER EXPIRED--#######################")
# Look for the flow in the created classifiers
self.flows_number += 1
for classifier_name, classifier in self.user_classifiers.items():
# Terminate the flow in the respective classifiers
self.user_classifiers[classifier_name].on_flow_terminate(expired_flow)
self.__exports.append(expired_flow)
print("##############################---EXPIRED FLOW EXPORTED-----###############################")
"""
def __iter__(self):
# Create the packet information generator
pkt_info_gen = Observer(source=self.source)
# Extract each packet information from the network interface or pcap file
for pkt_info in pkt_info_gen:
if pkt_info is not None:
# Check if the packet belongs to an existent flow or create a new one
self.consume(pkt_info)
for export in self.__exports:
yield export
self.__exports = []
# Terminate the streamer
self.terminate()
for export in self.__exports:
yield export
self.__exports = []
conn = sqlite3.connect('terms.db')
c = conn.cursor()
c.execute(
'''CREATE TABLE IF NOT EXISTS rejected (word TEXT PRIMARY KEY, reason TEXT)'''
)
conn.commit()
c.execute('''SELECT COUNT(*) FROM rejected''')
print("\tthere are", c.fetchone()[0], "words blocked in database")
c.execute('''SELECT reason, COUNT(*) FROM rejected GROUP BY reason''')
for row in c.fetchall():
print('\t\t', row[0], ':\t', row[1])
cache_rejected = LRU(50000)
# fill in the cache with entries
c.execute('''SELECT * FROM rejected ORDER BY RANDOM() LIMIT ?''',
(int(cache_rejected.get_size() * 2 / 3), ))
for row in c:
cache_rejected[row[0]] = row[1]
print("\tloaded", len(cache_rejected), "items in cache")
def is_word_rejected_db(token):
global c
global stats
global cache_rejected
# first try the cache
if token.lemma_ in cache_rejected:
stats['words rejected db (cache)'] = stats[
'words rejected db (cache)'] + 1
return cache_rejected[token.lemma_]
