def __build_consumer(
self, strategy_factory: ProcessingStrategyFactory[KafkaPayload]
) -> StreamProcessor[KafkaPayload]:
storage_key = self.storage.get_storage_key()
configuration = build_kafka_consumer_configuration(
storage_key,
bootstrap_servers=self.bootstrap_servers,
group_id=self.group_id,
auto_offset_reset=self.auto_offset_reset,
queued_max_messages_kbytes=self.queued_max_messages_kbytes,
queued_min_messages=self.queued_min_messages,
)
if self.commit_log_topic is None:
consumer = KafkaConsumer(
configuration, commit_retry_policy=self.__commit_retry_policy,
)
else:
consumer = KafkaConsumerWithCommitLog(
configuration,
producer=self.producer,
commit_log_topic=self.commit_log_topic,
commit_retry_policy=self.__commit_retry_policy,
)
return StreamProcessor(
consumer,
self.raw_topic,
strategy_factory,
metrics=self.metrics,
recoverable_errors=[TransportError],
)
def replacer(
*,
replacements_topic: Optional[str],
consumer_group: str,
bootstrap_server: Sequence[str],
storage_name: str,
max_batch_size: int,
max_batch_time_ms: int,
auto_offset_reset: str,
queued_max_messages_kbytes: int,
queued_min_messages: int,
log_level: Optional[str] = None,
) -> None:
from snuba.replacer import ReplacerWorker
from snuba.utils.streams import Topic
from snuba.utils.streams.backends.kafka import (
KafkaConsumer,
TransportError,
build_kafka_consumer_configuration,
)
from snuba.utils.streams.processing import StreamProcessor
from snuba.utils.streams.processing.strategies.batching import (
BatchProcessingStrategyFactory, )
setup_logging(log_level)
setup_sentry()
storage_key = StorageKey(storage_name)
storage = get_writable_storage(storage_key)
metrics_tags = {"group": consumer_group, "storage": storage_name}
stream_loader = storage.get_table_writer().get_stream_loader()
default_replacement_topic_spec = stream_loader.get_replacement_topic_spec()
assert (
default_replacement_topic_spec is not None
), f"Storage {storage.get_storage_key().value} does not have a replacement topic."
replacements_topic = replacements_topic or default_replacement_topic_spec.topic_name
metrics = MetricsWrapper(
environment.metrics,
"replacer",
tags=metrics_tags,
)
replacer = StreamProcessor(
KafkaConsumer(
build_kafka_consumer_configuration(
bootstrap_servers=bootstrap_server,
group_id=consumer_group,
auto_offset_reset=auto_offset_reset,
queued_max_messages_kbytes=queued_max_messages_kbytes,
queued_min_messages=queued_min_messages,
), ),
Topic(replacements_topic),
BatchProcessingStrategyFactory(
worker=ReplacerWorker(storage, metrics=metrics),
max_batch_size=max_batch_size,
max_batch_time=max_batch_time_ms,
metrics=metrics,
),
metrics=metrics,
recoverable_errors=[TransportError],
)
def handler(signum: int, frame: Any) -> None:
replacer.signal_shutdown()
signal.signal(signal.SIGINT, handler)
signal.signal(signal.SIGTERM, handler)
replacer.run()
def subscriptions(
*,
dataset_name: str,
topic: Optional[str],
partitions: Optional[int],
commit_log_topic: Optional[str],
commit_log_groups: Sequence[str],
consumer_group: str,
auto_offset_reset: str,
bootstrap_servers: Sequence[str],
max_batch_size: int,
max_batch_time_ms: int,
max_query_workers: Optional[int],
schedule_ttl: int,
result_topic: Optional[str],
log_level: Optional[str],
delay_seconds: Optional[int],
) -> None:
"""Evaluates subscribed queries for a dataset."""
assert result_topic is not None
setup_logging(log_level)
setup_sentry()
dataset = get_dataset(dataset_name)
if not bootstrap_servers:
storage = dataset.get_default_entity().get_writable_storage()
assert storage is not None
storage_key = storage.get_storage_key().value
bootstrap_servers = settings.DEFAULT_STORAGE_BROKERS.get(
storage_key, settings.DEFAULT_BROKERS)
loader = enforce_table_writer(dataset).get_stream_loader()
metrics = MetricsWrapper(
environment.metrics,
"subscriptions",
tags={
"group": consumer_group,
"dataset": dataset_name
},
)
consumer = TickConsumer(
SynchronizedConsumer(
KafkaConsumer(
build_kafka_consumer_configuration(
bootstrap_servers,
consumer_group,
auto_offset_reset=auto_offset_reset,
), ),
KafkaConsumer(
build_kafka_consumer_configuration(
bootstrap_servers,
f"subscriptions-commit-log-{uuid.uuid1().hex}",
auto_offset_reset="earliest",
), ),
(Topic(commit_log_topic) if commit_log_topic is not None else
Topic(loader.get_commit_log_topic_spec().topic_name)),
set(commit_log_groups),
),
time_shift=(timedelta(seconds=delay_seconds *
-1) if delay_seconds is not None else None),
)
producer = ProducerEncodingWrapper(
KafkaProducer({
"bootstrap.servers": ",".join(bootstrap_servers),
"partitioner": "consistent",
"message.max.bytes": 50000000, # 50MB, default is 1MB
}),
SubscriptionTaskResultEncoder(),
)
executor = ThreadPoolExecutor(max_workers=max_query_workers)
logger.debug("Starting %r with %s workers...", executor,
executor._max_workers)
metrics.gauge("executor.workers", executor._max_workers)
with closing(consumer), executor, closing(producer):
batching_consumer = StreamProcessor(
consumer,
(Topic(topic) if topic is not None else Topic(
loader.get_default_topic_spec().topic_name)),
BatchProcessingStrategyFactory(
SubscriptionWorker(
dataset,
executor,
{
index: SubscriptionScheduler(
RedisSubscriptionDataStore(redis_client, dataset,
PartitionId(index)),
PartitionId(index),
cache_ttl=timedelta(seconds=schedule_ttl),
metrics=metrics,
)
for index in
range(partitions if partitions is not None else loader.
get_default_topic_spec().partitions_number)
},
producer,
Topic(result_topic),
metrics,
),
max_batch_size,
max_batch_time_ms,
metrics,
),
metrics=metrics,
)
def handler(signum, frame) -> None:
batching_consumer.signal_shutdown()
signal.signal(signal.SIGINT, handler)
signal.signal(signal.SIGTERM, handler)
batching_consumer.run()
def multistorage_consumer(
storage_names: Sequence[str],
consumer_group: str,
max_batch_size: int,
max_batch_time_ms: int,
auto_offset_reset: str,
queued_max_messages_kbytes: int,
queued_min_messages: int,
processes: int,
input_block_size: int,
output_block_size: int,
log_level: Optional[str] = None,
) -> None:
setup_logging(log_level)
setup_sentry()
storages = {
key: get_writable_storage(key)
for key in (getattr(StorageKey, name.upper())
for name in storage_names)
}
topics = {
storage.get_table_writer().get_stream_loader().get_default_topic_spec(
).topic_name
for storage in storages.values()
}
# XXX: The ``StreamProcessor`` only supports a single topic at this time,
# but is easily modified. The topic routing in the processing strategy is a
# bit trickier (but also shouldn't be too bad.)
topic = Topic(topics.pop())
if topics:
raise ValueError("only one topic is supported")
# XXX: The ``CommitLogConsumer`` also only supports a single topic at this
# time. (It is less easily modified.) This also assumes the commit log
# topic is on the same Kafka cluster as the input topic.
commit_log_topics = {
spec.topic_name
for spec in (storage.get_table_writer().get_stream_loader(
).get_commit_log_topic_spec() for storage in storages.values())
if spec is not None
}
commit_log_topic: Optional[Topic]
if commit_log_topics:
commit_log_topic = Topic(commit_log_topics.pop())
else:
commit_log_topic = None
if commit_log_topics:
raise ValueError("only one commit log topic is supported")
# XXX: This requires that all storages are associated with the same Kafka
# cluster so that they can be consumed by the same consumer instance.
# Unfortunately, we don't have the concept of independently configurable
# Kafka clusters in settings, only consumer configurations that are
# associated with storages and/or global default configurations. To avoid
# implementing yet another method of configuring Kafka clusters, this just
# piggybacks on the existing configuration method(s), with the assumption
# that most deployments are going to be using the default configuration.
storage_keys = [*storages.keys()]
consumer_configuration = build_kafka_consumer_configuration(
storage_keys[0],
consumer_group,
auto_offset_reset=auto_offset_reset,
queued_max_messages_kbytes=queued_max_messages_kbytes,
queued_min_messages=queued_min_messages,
)
for storage_key in storage_keys[1:]:
if (build_kafka_consumer_configuration(
storage_key, consumer_group)["bootstrap.servers"] !=
consumer_configuration["bootstrap.servers"]):
raise ValueError(
"storages cannot be located on different Kafka clusters")
if commit_log_topic is None:
consumer = KafkaConsumer(consumer_configuration)
else:
# XXX: This relies on the assumptions that a.) the Kafka cluster where
# the commit log topic is located is the same as the input topic (there
# is no way to specify otherwise, at writing) and b.) all storages are
# located on the same Kafka cluster (validated above.)
producer = ConfluentKafkaProducer(
build_kafka_producer_configuration(storage_keys[0]))
consumer = KafkaConsumerWithCommitLog(
consumer_configuration,
producer=producer,
commit_log_topic=commit_log_topic,
)
metrics = MetricsWrapper(environment.metrics, "consumer")
processor = StreamProcessor(
consumer,
topic,
MultistorageConsumerProcessingStrategyFactory(
[*storages.values()],
max_batch_size,
max_batch_time_ms / 1000.0,
processes=processes,
input_block_size=input_block_size,
output_block_size=output_block_size,
metrics=metrics,
),
metrics=metrics,
)
def handler(signum: int, frame: Any) -> None:
processor.signal_shutdown()
signal.signal(signal.SIGINT, handler)
signal.signal(signal.SIGTERM, handler)
processor.run()
