Kafka

Required files:

• test_plan.py
• server_template.properties
• zoo_template.cfg

test_plan.py

#!/usr/bin/env python
"""
Demostrates Kafka driver usage from within the testcases.
"""

import os
import sys
import uuid

from testplan import test_plan
from testplan.testing.multitest import MultiTest

try:
    from confluent_kafka import Producer, Consumer
except ImportError:
    print("Cannot import confluent_kafka!")
    sys.exit()

from testplan.testing.multitest.driver.zookeeper import (
    ZookeeperStandalone,
    ZK_SERVER,
)
from testplan.testing.multitest.driver.kafka import (
    KafkaStandalone,
    KAFKA_START,
)
from testplan.testing.multitest import testsuite, testcase
from testplan.report.testing.styles import Style, StyleEnum


OUTPUT_STYLE = Style(StyleEnum.ASSERTION_DETAIL, StyleEnum.ASSERTION_DETAIL)


@testsuite
class KafkaTest:
    """Suite that contains testcases that perform kafka operation."""

    @testcase
    def test_send_receive(self, env, result):
        producer = Producer(
            {
                "bootstrap.servers": "localhost:{}".format(env.kafka.port),
                "max.in.flight": 1,
            }
        )
        consumer = Consumer(
            {
                "bootstrap.servers": "localhost:{}".format(env.kafka.port),
                "group.id": uuid.uuid4(),
                "default.topic.config": {"auto.offset.reset": "smallest"},
                "enable.auto.commit": True,
            }
        )

        topic = "testplan"
        message = str(uuid.uuid4()).encode("utf-8")
        producer.produce(topic=topic, value=message)
        producer.flush()
        consumer.subscribe([topic])
        msg = consumer.poll(10)
        result.equal(message, msg.value(), "Test producer and consumer")


# Hard-coding `pdf_path`, 'stdout_style' and 'pdf_style' so that the
# downloadable example gives meaningful and presentable output.
# NOTE: this programmatic arguments passing approach will cause Testplan
# to ignore any command line arguments related to that functionality.
@test_plan(
    name="KafkaExample",
    stdout_style=OUTPUT_STYLE,
    pdf_style=OUTPUT_STYLE,
    pdf_path="report.pdf",
)
def main(plan):
    """
    Testplan decorated main function to add and execute MultiTests.

    :return: Testplan result object.
    :rtype:  ``testplan.base.TestplanResult``
    """
    current_path = os.path.dirname(os.path.abspath(__file__))
    zookeeper_template = os.path.join(current_path, "zoo_template.cfg")
    kafka_template = os.path.join(current_path, "server_template.properties")

    plan.add(
        MultiTest(
            name="KafkaTest",
            suites=[KafkaTest()],
            environment=[
                ZookeeperStandalone(
                    name="zk", cfg_template=zookeeper_template
                ),
                KafkaStandalone(name="kafka", cfg_template=kafka_template),
            ],
        )
    )


if __name__ == "__main__":
    if os.path.exists(ZK_SERVER) and os.path.exists(KAFKA_START):
        sys.exit(not main())
    else:
        print("Zookeeper doesn't exist in this server.")

server_template.properties

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# see kafka.server.KafkaConfig for additional details and defaults

############################# Server Basics #############################

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=0

# Switch to enable topic deletion or not, default value is false
delete.topic.enable=true

############################# Socket Server Settings #############################

# The address the socket server listens on. It will get the value returned from 
# java.net.InetAddress.getCanonicalHostName() if not configured.
#   FORMAT:
#     listeners = listener_name://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092

listeners=PLAINTEXT://localhost:{{port}}

# Hostname and port the broker will advertise to producers and consumers. If not set, 
# it uses the value for "listeners" if configured.  Otherwise, it will use the value
# returned from java.net.InetAddress.getCanonicalHostName().
#advertised.listeners=PLAINTEXT://your.host.name:9092

# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
#listener.security.protocol.map=PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL

# The number of threads handling network requests
num.network.threads=3

# The number of threads doing disk I/O
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
#log.dirs=/tmp/jiaweil/kafka-vista-9098
log.dirs={{log_path}}

# The default number of log partitions per topic. More partitions allow greater
# parallelism for consumption, but this will also result in more files across
# the brokers.
num.partitions=3

# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# This value is recommended to be increased for installations with data dirs located in RAID array.
num.recovery.threads.per.data.dir=1

############################# Log Flush Policy #############################

# Messages are immediately written to the filesystem but by default we only fsync() to sync
# the OS cache lazily. The following configurations control the flush of data to disk.
# There are a few important trade-offs here:
#    1. Durability: Unflushed data may be lost if you are not using replication.
#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
# The settings below allow one to configure the flush policy to flush data after a period of time or
# every N messages (or both). This can be done globally and overridden on a per-topic basis.

# The number of messages to accept before forcing a flush of data to disk
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms=1000

############################# Log Retention Policy #############################

# The following configurations control the disposal of log segments. The policy can
# be set to delete segments after a period of time, or after a given size has accumulated.
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.

# The minimum age of a log file to be eligible for deletion due to age
log.retention.hours=168

# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
# segments don't drop below log.retention.bytes. Functions independently of log.retention.hours.
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
log.retention.check.interval.ms=300000

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect={{context['zk'].connection_str}}

# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=6000

offsets.topic.replication.factor=1

zoo_template.cfg

# limits the number of active connections from a host,
# specified by IP address, to a single ZooKeeper server.
maxClientCnxns=100

# The basic time unit in milliseconds used by ZooKeeper.
# It is used to do heartbeats and the minimum session timeout will be twice the tickTime.
tickTime=2000

# Timeouts ZooKeeper uses to limit the length of time the ZooKeeper
# servers in quorum have to connect to a leader.
initLimit=10

# Limits how far out of date a server can be from a leader.
syncLimit=5

# Enable admin server.
admin.enableServer=false

# The localtion to store the in-memory database snapshots and, unless specified otherwise,
# the transaction log of updates to the database.
dataDir={{zkdata_path}}

# The port to listen for client connections.
clientPort={{port}}