diff options
| -rw-r--r-- | kafka/__init__.py | 2 | ||||
| -rw-r--r-- | kafka/codec.py | 8 | ||||
| -rw-r--r-- | kafka/common.py | 45 | ||||
| -rw-r--r-- | kafka/producer.py | 4 | ||||
| -rw-r--r-- | kafka/protocol.py | 231 | ||||
| -rw-r--r-- | kafka/queue.py | 96 | ||||
| -rw-r--r-- | kafka/util.py | 51 |
7 files changed, 309 insertions, 128 deletions
diff --git a/kafka/__init__.py b/kafka/__init__.py index 5198d2f..d229169 100644 --- a/kafka/__init__.py +++ b/kafka/__init__.py @@ -4,7 +4,7 @@ __author__ = 'David Arthur' __license__ = 'Apache License 2.0' __copyright__ = 'Copyright 2012, David Arthur under Apache License, v2.0' -from kafka.client import KafkaClient +from kafka.client import KafkaClient from kafka.conn import KafkaConnection from kafka.protocol import ( create_message, create_gzip_message, create_snappy_message diff --git a/kafka/codec.py b/kafka/codec.py index 83f3c0b..c7d3992 100644 --- a/kafka/codec.py +++ b/kafka/codec.py @@ -6,10 +6,11 @@ log = logging.getLogger("kafka.codec") try: import snappy - hasSnappy=True + hasSnappy = True except ImportError: log.warn("Snappy codec not available") - hasSnappy=False + hasSnappy = False + def gzip_encode(payload): buf = StringIO() @@ -21,6 +22,7 @@ def gzip_encode(payload): buf.close() return out + def gzip_decode(payload): buf = StringIO(payload) f = gzip.GzipFile(fileobj=buf, mode='r') @@ -29,11 +31,13 @@ def gzip_decode(payload): buf.close() return out + def snappy_encode(payload): if not hasSnappy: raise NotImplementedError("Snappy codec not available") return snappy.compress(payload) + def snappy_decode(payload): if not hasSnappy: raise NotImplementedError("Snappy codec not available") diff --git a/kafka/common.py b/kafka/common.py index 447684f..9aab8fc 100644 --- a/kafka/common.py +++ b/kafka/common.py @@ -5,26 +5,49 @@ from collections import namedtuple ############### # Request payloads -ProduceRequest = namedtuple("ProduceRequest", ["topic", "partition", "messages"]) -FetchRequest = namedtuple("FetchRequest", ["topic", "partition", "offset", "max_bytes"]) -OffsetRequest = namedtuple("OffsetRequest", ["topic", "partition", "time", "max_offsets"]) -OffsetCommitRequest = namedtuple("OffsetCommitRequest", ["topic", "partition", "offset", "metadata"]) +ProduceRequest = namedtuple("ProduceRequest", + ["topic", "partition", "messages"]) + +FetchRequest = namedtuple("FetchRequest", + ["topic", "partition", "offset", "max_bytes"]) + +OffsetRequest = namedtuple("OffsetRequest", + ["topic", "partition", "time", "max_offsets"]) + +OffsetCommitRequest = namedtuple("OffsetCommitRequest", + ["topic", "partition", "offset", "metadata"]) + OffsetFetchRequest = namedtuple("OffsetFetchRequest", ["topic", "partition"]) # Response payloads -ProduceResponse = namedtuple("ProduceResponse", ["topic", "partition", "error", "offset"]) -FetchResponse = namedtuple("FetchResponse", ["topic", "partition", "error", "highwaterMark", "messages"]) -OffsetResponse = namedtuple("OffsetResponse", ["topic", "partition", "error", "offsets"]) -OffsetCommitResponse = namedtuple("OffsetCommitResponse", ["topic", "partition", "error"]) -OffsetFetchResponse = namedtuple("OffsetFetchResponse", ["topic", "partition", "offset", "metadata", "error"]) +ProduceResponse = namedtuple("ProduceResponse", + ["topic", "partition", "error", "offset"]) + +FetchResponse = namedtuple("FetchResponse", ["topic", "partition", "error", + "highwaterMark", "messages"]) + +OffsetResponse = namedtuple("OffsetResponse", + ["topic", "partition", "error", "offsets"]) + +OffsetCommitResponse = namedtuple("OffsetCommitResponse", + ["topic", "partition", "error"]) + +OffsetFetchResponse = namedtuple("OffsetFetchResponse", + ["topic", "partition", "offset", + "metadata", "error"]) + BrokerMetadata = namedtuple("BrokerMetadata", ["nodeId", "host", "port"]) -PartitionMetadata = namedtuple("PartitionMetadata", ["topic", "partition", "leader", "replicas", "isr"]) -# Other useful structs +PartitionMetadata = namedtuple("PartitionMetadata", + ["topic", "partition", "leader", + "replicas", "isr"]) + +# Other useful structs OffsetAndMessage = namedtuple("OffsetAndMessage", ["offset", "message"]) Message = namedtuple("Message", ["magic", "attributes", "key", "value"]) TopicAndPartition = namedtuple("TopicAndPartition", ["topic", "partition"]) + class ErrorMapping(object): # Many of these are not actually used by the client UNKNOWN = -1 diff --git a/kafka/producer.py b/kafka/producer.py index 47e690b..589eb11 100644 --- a/kafka/producer.py +++ b/kafka/producer.py @@ -6,6 +6,7 @@ from kafka.protocol import create_message log = logging.getLogger("kafka") + class SimpleProducer(object): """ A simple, round-robbin producer. Each message goes to exactly one partition @@ -18,6 +19,7 @@ class SimpleProducer(object): def send_messages(self, *msg): req = ProduceRequest(self.topic, self.next_partition.next(), - messages=[create_message(m) for m in msg]) + messages=[create_message(m) for m in msg]) + resp = self.client.send_produce_request([req])[0] assert resp.error == 0 diff --git a/kafka/protocol.py b/kafka/protocol.py index 94a7f2a..6bd5c73 100644 --- a/kafka/protocol.py +++ b/kafka/protocol.py @@ -18,10 +18,12 @@ from kafka.util import ( log = logging.getLogger("kafka") + class KafkaProtocol(object): """ - Class to encapsulate all of the protocol encoding/decoding. This class does not - have any state associated with it, it is purely for organization. + Class to encapsulate all of the protocol encoding/decoding. + This class does not have any state associated with it, it is purely + for organization. """ PRODUCE_KEY = 0 FETCH_KEY = 1 @@ -44,18 +46,18 @@ class KafkaProtocol(object): """ Encode the common request envelope """ - return struct.pack('>hhih%ds' % len(client_id), + return struct.pack('>hhih%ds' % len(client_id), request_key, # ApiKey 0, # ApiVersion correlation_id, # CorrelationId - len(client_id), # + len(client_id), client_id) # ClientId @classmethod def _encode_message_set(cls, messages): """ - Encode a MessageSet. Unlike other arrays in the protocol, MessageSets are - not length-prefixed + Encode a MessageSet. Unlike other arrays in the protocol, + MessageSets are not length-prefixed Format ====== @@ -66,7 +68,8 @@ class KafkaProtocol(object): message_set = "" for message in messages: encoded_message = KafkaProtocol._encode_message(message) - message_set += struct.pack('>qi%ds' % len(encoded_message), 0, len(encoded_message), encoded_message) + message_set += struct.pack('>qi%ds' % len(encoded_message), 0, + len(encoded_message), encoded_message) return message_set @classmethod @@ -74,10 +77,10 @@ class KafkaProtocol(object): """ Encode a single message. - The magic number of a message is a format version number. The only supported - magic number right now is zero + The magic number of a message is a format version number. + The only supported magic number right now is zero - Format + Format ====== Message => Crc MagicByte Attributes Key Value Crc => int32 @@ -96,24 +99,27 @@ class KafkaProtocol(object): raise Exception("Unexpected magic number: %d" % message.magic) return msg - @classmethod def _decode_message_set_iter(cls, data): """ Iteratively decode a MessageSet - Reads repeated elements of (offset, message), calling decode_message to decode a - single message. Since compressed messages contain futher MessageSets, these two methods - have been decoupled so that they may recurse easily. + Reads repeated elements of (offset, message), calling decode_message + to decode a single message. Since compressed messages contain futher + MessageSets, these two methods have been decoupled so that they may + recurse easily. """ cur = 0 while cur < len(data): try: ((offset, ), cur) = relative_unpack('>q', data, cur) (msg, cur) = read_int_string(data, cur) - for (offset, message) in KafkaProtocol._decode_message(msg, offset): + for (offset, message) in KafkaProtocol._decode_message(msg, + offset): yield OffsetAndMessage(offset, message) - except BufferUnderflowError: # If we get a partial read of a message, stop + + except BufferUnderflowError: + # If we get a partial read of a message, stop raise StopIteration() @classmethod @@ -121,9 +127,10 @@ class KafkaProtocol(object): """ Decode a single Message - The only caller of this method is decode_message_set_iter. They are decoupled to - support nested messages (compressed MessageSets). The offset is actually read from - decode_message_set_iter (it is part of the MessageSet payload). + The only caller of this method is decode_message_set_iter. + They are decoupled to support nested messages (compressed MessageSets). + The offset is actually read from decode_message_set_iter (it is part + of the MessageSet payload). """ ((crc, magic, att), cur) = relative_unpack('>iBB', data, 0) if crc != zlib.crc32(data[4:]): @@ -131,23 +138,29 @@ class KafkaProtocol(object): (key, cur) = read_int_string(data, cur) (value, cur) = read_int_string(data, cur) - if att & KafkaProtocol.ATTRIBUTE_CODEC_MASK == KafkaProtocol.CODEC_NONE: + + codec = att & KafkaProtocol.ATTRIBUTE_CODEC_MASK + + if codec == KafkaProtocol.CODEC_NONE: yield (offset, Message(magic, att, key, value)) - elif att & KafkaProtocol.ATTRIBUTE_CODEC_MASK == KafkaProtocol.CODEC_GZIP: + + elif codec == KafkaProtocol.CODEC_GZIP: gz = gzip_decode(value) - for (offset, message) in KafkaProtocol._decode_message_set_iter(gz): - yield (offset, message) - elif att & KafkaProtocol.ATTRIBUTE_CODEC_MASK == KafkaProtocol.CODEC_SNAPPY: + for (offset, msg) in KafkaProtocol._decode_message_set_iter(gz): + yield (offset, msg) + + elif codec == KafkaProtocol.CODEC_SNAPPY: snp = snappy_decode(value) - for (offset, message) in KafkaProtocol._decode_message_set_iter(snp): - yield (offset, message) + for (offset, msg) in KafkaProtocol._decode_message_set_iter(snp): + yield (offset, msg) ################## # Public API # ################## @classmethod - def encode_produce_request(cls, client_id, correlation_id, payloads=[], acks=1, timeout=1000): + def encode_produce_request(cls, client_id, correlation_id, + payloads=None, acks=1, timeout=1000): """ Encode some ProduceRequest structs @@ -161,39 +174,53 @@ class KafkaProtocol(object): 1: written to disk by the leader 2+: waits for this many number of replicas to sync -1: waits for all replicas to be in sync - timeout: Maximum time the server will wait for acks from replicas. This is _not_ a socket timeout + timeout: Maximum time the server will wait for acks from replicas. + This is _not_ a socket timeout """ + payloads = [] if payloads is None else payloads grouped_payloads = group_by_topic_and_partition(payloads) - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.PRODUCE_KEY) + + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.PRODUCE_KEY) + message += struct.pack('>hii', acks, timeout, len(grouped_payloads)) + for topic, topic_payloads in grouped_payloads.items(): - message += struct.pack('>h%dsi' % len(topic), len(topic), topic, len(topic_payloads)) + message += struct.pack('>h%dsi' % len(topic), + len(topic), topic, len(topic_payloads)) + for partition, payload in topic_payloads.items(): - message_set = KafkaProtocol._encode_message_set(payload.messages) - message += struct.pack('>ii%ds' % len(message_set), partition, len(message_set), message_set) + msg_set = KafkaProtocol._encode_message_set(payload.messages) + message += struct.pack('>ii%ds' % len(msg_set), partition, + len(msg_set), msg_set) + return struct.pack('>i%ds' % len(message), len(message), message) @classmethod def decode_produce_response(cls, data): """ - Decode bytes to a ProduceResponse + Decode bytes to a ProduceResponse Params ====== data: bytes to decode """ ((correlation_id, num_topics), cur) = relative_unpack('>ii', data, 0) + for i in range(num_topics): ((strlen,), cur) = relative_unpack('>h', data, cur) - topic = data[cur:cur+strlen] + topic = data[cur:cur + strlen] cur += strlen ((num_partitions,), cur) = relative_unpack('>i', data, cur) for i in range(num_partitions): - ((partition, error, offset), cur) = relative_unpack('>ihq', data, cur) + ((partition, error, offset), cur) = relative_unpack('>ihq', + data, cur) + yield ProduceResponse(topic, partition, error, offset) @classmethod - def encode_fetch_request(cls, client_id, correlation_id, payloads=[], max_wait_time=100, min_bytes=4096): + def encode_fetch_request(cls, client_id, correlation_id, payloads=None, + max_wait_time=100, min_bytes=4096): """ Encodes some FetchRequest structs @@ -203,17 +230,27 @@ class KafkaProtocol(object): correlation_id: string payloads: list of FetchRequest max_wait_time: int, how long to block waiting on min_bytes of data - min_bytes: int, the minimum number of bytes to accumulate before returning the response + min_bytes: int, the minimum number of bytes to accumulate before + returning the response """ - + + payloads = [] if payloads is None else payloads grouped_payloads = group_by_topic_and_partition(payloads) - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.FETCH_KEY) - message += struct.pack('>iiii', -1, max_wait_time, min_bytes, len(grouped_payloads)) # -1 is the replica id + + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.FETCH_KEY) + + # -1 is the replica id + message += struct.pack('>iiii', -1, max_wait_time, min_bytes, + len(grouped_payloads)) + for topic, topic_payloads in grouped_payloads.items(): message += write_short_string(topic) message += struct.pack('>i', len(topic_payloads)) for partition, payload in topic_payloads.items(): - message += struct.pack('>iqi', partition, payload.offset, payload.max_bytes) + message += struct.pack('>iqi', partition, payload.offset, + payload.max_bytes) + return struct.pack('>i%ds' % len(message), len(message), message) @classmethod @@ -226,25 +263,41 @@ class KafkaProtocol(object): data: bytes to decode """ ((correlation_id, num_topics), cur) = relative_unpack('>ii', data, 0) + for i in range(num_topics): (topic, cur) = read_short_string(data, cur) ((num_partitions,), cur) = relative_unpack('>i', data, cur) + for i in range(num_partitions): - ((partition, error, highwater_mark_offset), cur) = relative_unpack('>ihq', data, cur) + ((partition, error, highwater_mark_offset), cur) = \ + relative_unpack('>ihq', data, cur) + (message_set, cur) = read_int_string(data, cur) - yield FetchResponse(topic, partition, error, highwater_mark_offset, + + yield FetchResponse( + topic, partition, error, + highwater_mark_offset, KafkaProtocol._decode_message_set_iter(message_set)) @classmethod - def encode_offset_request(cls, client_id, correlation_id, payloads=[]): + def encode_offset_request(cls, client_id, correlation_id, payloads=None): + payloads = [] if payloads is None else payloads grouped_payloads = group_by_topic_and_partition(payloads) - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.OFFSET_KEY) - message += struct.pack('>ii', -1, len(grouped_payloads)) # -1 is the replica id + + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.OFFSET_KEY) + + # -1 is the replica id + message += struct.pack('>ii', -1, len(grouped_payloads)) + for topic, topic_payloads in grouped_payloads.items(): message += write_short_string(topic) message += struct.pack('>i', len(topic_payloads)) + for partition, payload in topic_payloads.items(): - message += struct.pack('>iqi', partition, payload.time, payload.max_offsets) + message += struct.pack('>iqi', partition, payload.time, + payload.max_offsets) + return struct.pack('>i%ds' % len(message), len(message), message) @classmethod @@ -257,19 +310,24 @@ class KafkaProtocol(object): data: bytes to decode """ ((correlation_id, num_topics), cur) = relative_unpack('>ii', data, 0) + for i in range(num_topics): (topic, cur) = read_short_string(data, cur) ((num_partitions,), cur) = relative_unpack('>i', data, cur) + for i in range(num_partitions): - ((partition, error, num_offsets,), cur) = relative_unpack('>ihi', data, cur) + ((partition, error, num_offsets,), cur) = \ + relative_unpack('>ihi', data, cur) + offsets = [] for j in range(num_offsets): ((offset,), cur) = relative_unpack('>q', data, cur) offsets.append(offset) + yield OffsetResponse(topic, partition, error, tuple(offsets)) @classmethod - def encode_metadata_request(cls, client_id, correlation_id, topics=[]): + def encode_metadata_request(cls, client_id, correlation_id, topics=None): """ Encode a MetadataRequest @@ -279,10 +337,15 @@ class KafkaProtocol(object): correlation_id: string topics: list of strings """ - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.METADATA_KEY) + topics = [] if topics is None else topics + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.METADATA_KEY) + message += struct.pack('>i', len(topics)) + for topic in topics: message += struct.pack('>h%ds' % len(topic), len(topic), topic) + return write_int_string(message) @classmethod @@ -307,22 +370,34 @@ class KafkaProtocol(object): # Topic info ((num_topics,), cur) = relative_unpack('>i', data, cur) topicMetadata = {} + for i in range(num_topics): ((topicError,), cur) = relative_unpack('>h', data, cur) (topicName, cur) = read_short_string(data, cur) ((num_partitions,), cur) = relative_unpack('>i', data, cur) partitionMetadata = {} + for j in range(num_partitions): - ((partitionErrorCode, partition, leader, numReplicas), cur) = relative_unpack('>hiii', data, cur) - (replicas, cur) = relative_unpack('>%di' % numReplicas, data, cur) + ((partitionErrorCode, partition, leader, numReplicas), cur) = \ + relative_unpack('>hiii', data, cur) + + (replicas, cur) = relative_unpack('>%di' % numReplicas, + data, cur) + ((numIsr,), cur) = relative_unpack('>i', data, cur) (isr, cur) = relative_unpack('>%di' % numIsr, data, cur) - partitionMetadata[partition] = PartitionMetadata(topicName, partition, leader, replicas, isr) + + partitionMetadata[partition] = \ + PartitionMetadata(topicName, partition, leader, + replicas, isr) + topicMetadata[topicName] = partitionMetadata + return (brokers, topicMetadata) @classmethod - def encode_offset_commit_request(cls, client_id, correlation_id, group, payloads): + def encode_offset_commit_request(cls, client_id, correlation_id, + group, payloads): """ Encode some OffsetCommitRequest structs @@ -333,16 +408,21 @@ class KafkaProtocol(object): group: string, the consumer group you are committing offsets for payloads: list of OffsetCommitRequest """ - grouped_payloads= group_by_topic_and_partition(payloads) - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.OFFSET_COMMIT_KEY) + grouped_payloads = group_by_topic_and_partition(payloads) + + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.OFFSET_COMMIT_KEY) message += write_short_string(group) message += struct.pack('>i', len(grouped_payloads)) + for topic, topic_payloads in grouped_payloads.items(): message += write_short_string(topic) message += struct.pack('>i', len(topic_payloads)) + for partition, payload in topic_payloads.items(): message += struct.pack('>iq', partition, payload.offset) message += write_short_string(payload.metadata) + return struct.pack('>i%ds' % len(message), len(message), message) @classmethod @@ -357,15 +437,18 @@ class KafkaProtocol(object): ((correlation_id,), cur) = relative_unpack('>i', data, 0) (client_id, cur) = read_short_string(data, cur) ((num_topics,), cur) = relative_unpack('>i', data, cur) + for i in xrange(num_topics): (topic, cur) = read_short_string(data, cur) ((num_partitions,), cur) = relative_unpack('>i', data, cur) + for i in xrange(num_partitions): ((partition, error), cur) = relative_unpack('>ih', data, cur) yield OffsetCommitResponse(topic, partition, error) @classmethod - def encode_offset_fetch_request(cls, client_id, correlation_id, group, payloads): + def encode_offset_fetch_request(cls, client_id, correlation_id, + group, payloads): """ Encode some OffsetFetchRequest structs @@ -377,14 +460,19 @@ class KafkaProtocol(object): payloads: list of OffsetFetchRequest """ grouped_payloads = group_by_topic_and_partition(payloads) - message = cls._encode_message_header(client_id, correlation_id, KafkaProtocol.OFFSET_FETCH_KEY) + message = cls._encode_message_header(client_id, correlation_id, + KafkaProtocol.OFFSET_FETCH_KEY) + message += write_short_string(group) message += struct.pack('>i', len(grouped_payloads)) + for topic, topic_payloads in grouped_payloads.items(): message += write_short_string(topic) message += struct.pack('>i', len(topic_payloads)) + for partition, payload in topic_payloads.items(): message += struct.pack('>i', partition) + return struct.pack('>i%ds' % len(message), len(message), message) @classmethod @@ -400,14 +488,19 @@ class KafkaProtocol(object): ((correlation_id,), cur) = relative_unpack('>i', data, 0) (client_id, cur) = read_short_string(data, cur) ((num_topics,), cur) = relative_unpack('>i', data, cur) + for i in range(num_topics): (topic, cur) = read_short_string(data, cur) ((num_partitions,), cur) = relative_unpack('>i', data, cur) + for i in range(num_partitions): ((partition, offset), cur) = relative_unpack('>iq', data, cur) (metadata, cur) = read_short_string(data, cur) ((error,), cur) = relative_unpack('>h', data, cur) - yield OffsetFetchResponse(topic, partition, offset, metadata, error) + + yield OffsetFetchResponse(topic, partition, offset, + metadata, error) + def create_message(payload, key=None): """ @@ -420,6 +513,7 @@ def create_message(payload, key=None): """ return Message(0, 0, key, payload) + def create_gzip_message(payloads, key=None): """ Construct a Gzipped Message containing multiple Messages @@ -433,9 +527,13 @@ def create_gzip_message(payloads, key=None): key: bytes, a key used for partition routing (optional) """ message_set = KafkaProtocol._encode_message_set( - [create_message(payload) for payload in payloads]) - gzipped = gzip_encode(message_set) - return Message(0, 0x00 | (KafkaProtocol.ATTRIBUTE_CODEC_MASK & KafkaProtocol.CODEC_GZIP), key, gzipped) + [create_message(payload) for payload in payloads]) + + gzipped = gzip_encode(message_set) + codec = KafkaProtocol.ATTRIBUTE_CODEC_MASK & KafkaProtocol.CODEC_GZIP + + return Message(0, 0x00 | codec, key, gzipped) + def create_snappy_message(payloads, key=None): """ @@ -450,6 +548,9 @@ def create_snappy_message(payloads, key=None): key: bytes, a key used for partition routing (optional) """ message_set = KafkaProtocol._encode_message_set( - [create_message(payload) for payload in payloads]) - snapped = snappy_encode(message_set) - return Message(0, 0x00 | (KafkaProtocol.ATTRIBUTE_CODEC_MASK & KafkaProtocol.CODEC_SNAPPY), key, snapped) + [create_message(payload) for payload in payloads]) + + snapped = snappy_encode(message_set) + codec = KafkaProtocol.ATTRIBUTE_CODEC_MASK & KafkaProtocol.CODEC_SNAPPY + + return Message(0, 0x00 | codec, key, snapped) diff --git a/kafka/queue.py b/kafka/queue.py index 6fe9eaa..3bd7dca 100644 --- a/kafka/queue.py +++ b/kafka/queue.py @@ -10,8 +10,10 @@ log = logging.getLogger("kafka") raise NotImplementedError("Still need to refactor this class") + class KafkaConsumerProcess(Process): - def __init__(self, client, topic, partition, out_queue, barrier, consumer_fetch_size=1024, consumer_sleep=200): + def __init__(self, client, topic, partition, out_queue, barrier, + consumer_fetch_size=1024, consumer_sleep=200): self.client = copy(client) self.topic = topic self.partition = partition @@ -23,29 +25,40 @@ class KafkaConsumerProcess(Process): Process.__init__(self) def __str__(self): - return "[KafkaConsumerProcess: topic=%s, partition=%s, sleep=%s]" % ( - self.topic, self.partition, self.consumer_sleep) + return "[KafkaConsumerProcess: topic=%s, partition=%s, sleep=%s]" % \ + (self.topic, self.partition, self.consumer_sleep) def run(self): self.barrier.wait() log.info("Starting %s" % self) - fetchRequest = FetchRequest(self.topic, self.partition, offset=0, size=self.consumer_fetch_size) + fetchRequest = FetchRequest(self.topic, self.partition, + offset=0, size=self.consumer_fetch_size) + while True: - if self.barrier.is_set() == False: + if self.barrier.is_set() is False: log.info("Shutdown %s" % self) self.client.close() break + lastOffset = fetchRequest.offset (messages, fetchRequest) = self.client.get_message_set(fetchRequest) + if fetchRequest.offset == lastOffset: - log.debug("No more data for this partition, sleeping a bit (200ms)") + log.debug("No more data for this partition, " + "sleeping a bit (200ms)") time.sleep(self.consumer_sleep) continue + for message in messages: self.out_queue.put(message) + class KafkaProducerProcess(Process): - def __init__(self, client, topic, in_queue, barrier, producer_flush_buffer=500, producer_flush_timeout=2000, producer_timeout=100): + def __init__(self, client, topic, in_queue, barrier, + producer_flush_buffer=500, + producer_flush_timeout=2000, + producer_timeout=100): + self.client = copy(client) self.topic = topic self.in_queue = in_queue @@ -57,8 +70,10 @@ class KafkaProducerProcess(Process): Process.__init__(self) def __str__(self): - return "[KafkaProducerProcess: topic=%s, flush_buffer=%s, flush_timeout=%s, timeout=%s]" % ( - self.topic, self.producer_flush_buffer, self.producer_flush_timeout, self.producer_timeout) + return "[KafkaProducerProcess: topic=%s, flush_buffer=%s, \ + flush_timeout=%s, timeout=%s]" % ( + self.topic, self.producer_flush_buffer, + self.producer_flush_timeout, self.producer_timeout) def run(self): self.barrier.wait() @@ -67,36 +82,47 @@ class KafkaProducerProcess(Process): last_produce = time.time() def flush(messages): - self.client.send_message_set(ProduceRequest(self.topic, -1, messages)) + self.client.send_message_set(ProduceRequest(self.topic, -1, + messages)) del messages[:] while True: - if self.barrier.is_set() == False: + if self.barrier.is_set() is False: log.info("Shutdown %s, flushing messages" % self) flush(messages) self.client.close() break + if len(messages) > self.producer_flush_buffer: - log.debug("Message count threashold reached. Flushing messages") + log.debug("Message count threshold reached. Flushing messages") flush(messages) last_produce = time.time() + elif (time.time() - last_produce) > self.producer_flush_timeout: log.debug("Producer timeout reached. Flushing messages") flush(messages) last_produce = time.time() + try: - messages.append(KafkaClient.create_message(self.in_queue.get(True, self.producer_timeout))) + msg = KafkaClient.create_message(self.in_queue.get(True, + self.producer_timeout)) + messages.append(msg) + except Empty: continue + class KafkaQueue(object): - def __init__(self, client, topic, partitions, producer_config={}, consumer_config={}): + def __init__(self, client, topic, partitions, + producer_config=None, consumer_config=None): """ - KafkaQueue a Queue-like object backed by a Kafka producer and some number of consumers + KafkaQueue a Queue-like object backed by a Kafka producer and some + number of consumers - Messages are eagerly loaded by the consumer in batches of size consumer_fetch_size. - Messages are buffered in the producer thread until producer_flush_timeout or - producer_flush_buffer is reached. + Messages are eagerly loaded by the consumer in batches of size + consumer_fetch_size. + Messages are buffered in the producer thread until + producer_flush_timeout or producer_flush_buffer is reached. Params ====== @@ -108,21 +134,26 @@ class KafkaQueue(object): Consumer Config =============== - consumer_fetch_size: int, number of bytes to fetch in one call to Kafka. Default - is 1024 - consumer_sleep: int, time in milliseconds a consumer should sleep when it reaches - the end of a partition. Default is 200 + consumer_fetch_size: int, number of bytes to fetch in one call + to Kafka. Default is 1024 + consumer_sleep: int, time in milliseconds a consumer should sleep + when it reaches the end of a partition. Default is 200 Producer Config =============== - producer_timeout: int, time in milliseconds a producer should wait for messages to - enqueue for producing. Default is 100 - producer_flush_timeout: int, time in milliseconds a producer should allow messages - to accumulate before sending to Kafka. Default is 2000 - producer_flush_buffer: int, number of messages a producer should allow to accumulate. - Default is 500 - + producer_timeout: int, time in milliseconds a producer should + wait for messages to enqueue for producing. + Default is 100 + producer_flush_timeout: int, time in milliseconds a producer + should allow messages to accumulate before + sending to Kafka. Default is 2000 + producer_flush_buffer: int, number of messages a producer should + allow to accumulate. Default is 500 + """ + producer_config = {} if producer_config is None else producer_config + consumer_config = {} if consumer_config is None else consumer_config + self.in_queue = Queue() self.out_queue = Queue() self.consumers = [] @@ -130,12 +161,15 @@ class KafkaQueue(object): # Initialize and start consumer threads for partition in partitions: - consumer = KafkaConsumerProcess(client, topic, partition, self.in_queue, self.barrier, **consumer_config) + consumer = KafkaConsumerProcess(client, topic, partition, + self.in_queue, self.barrier, + **consumer_config) consumer.start() self.consumers.append(consumer) # Initialize and start producer thread - self.producer = KafkaProducerProcess(client, topic, self.out_queue, self.barrier, **producer_config) + self.producer = KafkaProducerProcess(client, topic, self.out_queue, + self.barrier, **producer_config) self.producer.start() # Trigger everything to start diff --git a/kafka/util.py b/kafka/util.py index 8c02cb2..10bf838 100644 --- a/kafka/util.py +++ b/kafka/util.py @@ -3,64 +3,81 @@ from itertools import groupby import struct from threading import Timer + def write_int_string(s): if s is None: return struct.pack('>i', -1) else: return struct.pack('>i%ds' % len(s), len(s), s) + def write_short_string(s): if s is None: return struct.pack('>h', -1) else: return struct.pack('>h%ds' % len(s), len(s), s) + def read_short_string(data, cur): - if len(data) < cur+2: + if len(data) < cur + 2: raise BufferUnderflowError("Not enough data left") - (strLen,) = struct.unpack('>h', data[cur:cur+2]) + + (strLen,) = struct.unpack('>h', data[cur:cur + 2]) if strLen == -1: - return (None, cur+2) + return (None, cur + 2) + cur += 2 - if len(data) < cur+strLen: + if len(data) < cur + strLen: raise BufferUnderflowError("Not enough data left") - out = data[cur:cur+strLen] - return (out, cur+strLen) + + out = data[cur:cur + strLen] + return (out, cur + strLen) + def read_int_string(data, cur): - if len(data) < cur+4: + if len(data) < cur + 4: raise BufferUnderflowError("Not enough data left") - (strLen,) = struct.unpack('>i', data[cur:cur+4]) + + (strLen,) = struct.unpack('>i', data[cur:cur + 4]) if strLen == -1: - return (None, cur+4) + return (None, cur + 4) + cur += 4 - if len(data) < cur+strLen: + if len(data) < cur + strLen: raise BufferUnderflowError("Not enough data left") - out = data[cur:cur+strLen] - return (out, cur+strLen) + + out = data[cur:cur + strLen] + return (out, cur + strLen) + def relative_unpack(fmt, data, cur): size = struct.calcsize(fmt) - if len(data) < cur+size: + if len(data) < cur + size: raise BufferUnderflowError("Not enough data left") - out = struct.unpack(fmt, data[cur:cur+size]) - return (out, cur+size) + + out = struct.unpack(fmt, data[cur:cur + size]) + return (out, cur + size) + def group_by_topic_and_partition(tuples): out = defaultdict(dict) for t in tuples: out[t.topic][t.partition] = t - return out + return out + class BufferUnderflowError(Exception): pass + class ChecksumError(Exception): pass + class ReentrantTimer(object): """ - A timer that can be restarted, unlike threading.Timer (although this uses threading.Timer) + A timer that can be restarted, unlike threading.Timer + (although this uses threading.Timer) t: timer interval in milliseconds fn: a callable to invoke |