1. 程式人生 > >【Kafka】使用非自帶zookeeper Java API 例子

【Kafka】使用非自帶zookeeper Java API 例子

這裡沒有使用kafka自帶的zk。

1.啟動zk:

zk下載解壓至任意資料夾。新建kafka-zk-csdn資料夾。這裡啟動包含三個節點的zk偽叢集,進入kafka-zk-csdn資料夾,新建zk1,zk2和zk3資料夾。

kafka-zk-csdn:

--zk1

    --data

        --myid

    --log

    --zoo.cfg

--zk2

    --data

        --myid

    --log

    --zoo.cfg

--zk3

    --data

        --myid

    --log

    --zoo.cfg


每一個資料夾下新建data資料夾,在data資料夾下新建myid檔案,內容分別為1,2,3,表示zk節點id。新建log資料夾,並且新建zoo.cfg配置檔案。內容如下:

zk1:

initLimit=10
syncLimit=5

dataDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk1/data
dataLogDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk1/log

clientPort=2181

server.1=127.0.0.1:2222:2225
server.2=127.0.0.1:3333:3335
server.3=127.0.0.1:4444:4445

zk2:

initLimit=10
syncLimit=5

dataDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk2/data
dataLogDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk2/log

clientPort=2182

server.1=127.0.0.1:2222:2225
server.2=127.0.0.1:3333:3335
server.3=127.0.0.1:4444:4445

zk3:

initLimit=10
syncLimit=5

dataDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk3/data
dataLogDir=/Users/miracle/zookeeper/kafka-zk-csdn/zk3/log

clientPort=2183

server.1=127.0.0.1:2222:2225
server.2=127.0.0.1:3333:3335
server.3=127.0.0.1:4444:4445

前兩個配置是必須的,沒有啟動報錯。dataDir和dataLogDir目錄路徑自行修改。clientPort是客戶端訪問的埠。server.x.A.B中,x表示myid節點的id,A表示主節點和從節點通訊的埠,B表示主節點掛了選舉使用的埠。

接著使用如下命令啟動zk叢集:

./bin/zkServer.sh start ../kafka-zk-csdn/zk1/zoo.cfg
./bin/zkServer.sh start ../kafka-zk-csdn/zk2/zoo.cfg
./bin/zkServer.sh start ../kafka-zk-csdn/zk3/zoo.cfg

可以使用status命令檢視是否啟動:

./bin/zkServer.sh status ../kafka-zk-csdn/zk1/zoo.cfg
./bin/zkServer.sh status ../kafka-zk-csdn/zk2/zoo.cfg
./bin/zkServer.sh status ../kafka-zk-csdn/zk3/zoo.cfg

如上資訊表明zk叢集啟動成功。

2.啟動kafka:

這裡啟動 兩個broker,進入kafka的目錄。在config目錄下新建一個server-test-csdn目錄存放配置,進入該目錄下,新建server1.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

############################# 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://:9092
listeners=PLAINTEXT://127.0.0.1:9096
# 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 that the server uses for receiving requests from the network and sending responses to the network
num.network.threads=3

# The number of threads that the server uses for processing requests, which may include 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/kafka-logs1

# 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=2

# 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

############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state"
# For anything other than development testing, a value greater than 1 is recommended for to ensure availability such as 3.
offsets.topic.replication.factor=1
transaction.state.log.replication.factor=1
transaction.state.log.min.isr=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 unless the remaining
# segments 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=localhost:2181

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


############################# Group Coordinator Settings #############################

# The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance.
# The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms.
# The default value for this is 3 seconds.
# We override this to 0 here as it makes for a better out-of-the-box experience for development and testing.
# However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup.
group.initial.rebalance.delay.ms=0

同時新建server2.properties,內容同上,但是做如下修改:

broker.id=1
listeners=PLAINTEXT://127.0.0.1:9097
log.dirs=/tmp/kafka-logs2

執行命令啟動:

bin/kafka-server-start.sh config/server-test-csdn/server1.properties
bin/kafka-server-start.sh config/server-test-csdn/server2.properties

上述命令是阻塞式的,執行一條命令需要新開一個終端。

沒有報錯說明啟動成功。

3.JAVA Api。這裡使用的kafka 2.11版本。

上面啟動了兩個broker,且配置分割槽數目為2。

pom:

    <!-- https://mvnrepository.com/artifact/org.apache.kafka/kafka -->
    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>1.1.0</version>
    </dependency>

生產者:

package a;

import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;

import java.util.Properties;

public class Prod {
    public static String topic = "kafka-topic";

    public static void main(String[] args) {
        Properties props = new Properties();
        props.put("bootstrap.servers", "127.0.0.1:9096,127.0.0.1:9097");
        props.put("acks", "all");
        props.put("retries", 0);
        props.put("batch.size", 16384);
        props.put("linger.ms", 1);
        props.put("buffer.memory", 33554432);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        Producer<String, String> procuder = new KafkaProducer<String,String>(props);

        for (int i = 0;i < 30;i++) {
            String value = "value_" + i;
            ProducerRecord<String, String> msg = new ProducerRecord<String, String>(topic, value);
            procuder.send(msg);
            try {
                Thread.sleep(1000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }
    }
}

消費者:

package a;

import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

import java.util.*;

public class Consu {


    public static void main(String args[]){
        Properties props = new Properties();
        props.put("bootstrap.servers", "127.0.0.1:9096");
        props.put("group.id", "g2");
        props.put("zookeeper.session.timeout.ms", "400");
        props.put("zookeeper.sync.time.ms", "200");
        props.put("auto.commit.interval.ms", "1000");
        props.put("auto.offset.reset", "earliest");
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");

        KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);

        consumer.subscribe(Arrays.asList(Prod.topic));
        while (true) {
            ConsumerRecords<String, String> records = consumer.poll(100);
            for (ConsumerRecord<String, String> record : records)
                System.out.printf("partition = %d, offset = %d, key = %s, value = %s%n", record.partition(), record.offset(), record.key(), record.value());
        }
    }
}

截圖:


消費者傳送的訊息確實是傳送到了兩個分割槽中,具體規則在下一篇分割槽中總結。

Kafka的API每一版本都有更新,這裡是2.11版本的。