Logstash学习之路（五）使用Logstash抽取mysql数据到kakfa

一、Logstash对接kafka测通

说明：

　　由于我这里kafka是伪分布式，且kafka在伪分布式下，已经集成了zookeeper。

1、先将zk启动，如果是在伪分布式下，kafka已经集成了zk

[root@master zookeeperData]# nohup /mnt/kafka/bin/zookeeper-server-start.sh /mnt/kafka/config/zookeeper.properties &

2、启动broker

[root@master mnt]# nohup /mnt/kafka/bin/kafka-server-start.sh /mnt/kafka/config/server.properties &

3、创建topic

[root@master bin]# ./kafka-topics.sh --create --zookeeper 192.168.200.100:2181 --topic test --partition 1 --replication-factor 1
Created topic "test".

4、创建消费者

[root@master bin]# ./kafka-console-consumer.sh  --topic test --zookeeper localhost:2181

5、配置Logstash对接kafka的配置文件

input{
    stdin{}
}
output{
    kafka{
        topic_id => "test"
        bootstrap_servers => "192.168.200.100:9092" # kafka的地址
       # batch_size => 5
    }
    stdout{
        codec => rubydebug
    }
}

6、测试

启动日志：

[root@master bin]# ./logstash -f kafka.conf 
Sending Logstash's logs to /mnt/logstash/logs which is now configured via log4j2.properties
[2019-04-25T16:19:38,811][WARN ][logstash.config.source.multilocal] Ignoring the 'pipelines.yml' file because modules or command line options are specified
[2019-04-25T16:19:40,075][INFO ][logstash.runner          ] Starting Logstash {"logstash.version"=>"6.3.1"}
[2019-04-25T16:19:46,274][INFO ][logstash.pipeline        ] Starting pipeline {:pipeline_id=>"main", "pipeline.workers"=>2, "pipeline.batch.size"=>125, "pipeline.batch.delay"=>50}
[2019-04-25T16:19:46,583][INFO ][org.apache.kafka.clients.producer.ProducerConfig] ProducerConfig values: 
        acks = 1
        batch.size = 16384
        bootstrap.servers = [192.168.200.100:9092]
        buffer.memory = 33554432
        client.id = 
        compression.type = none
        connections.max.idle.ms = 540000
        enable.idempotence = false
        interceptor.classes = []
        key.serializer = class org.apache.kafka.common.serialization.StringSerializer
        linger.ms = 0
        max.block.ms = 60000
        max.in.flight.requests.per.connection = 5
        max.request.size = 1048576
        metadata.max.age.ms = 300000
        metric.reporters = []
        metrics.num.samples = 2
        metrics.recording.level = INFO
        metrics.sample.window.ms = 30000
        partitioner.class = class org.apache.kafka.clients.producer.internals.DefaultPartitioner
        receive.buffer.bytes = 32768
        reconnect.backoff.max.ms = 10
        reconnect.backoff.ms = 10
        request.timeout.ms = 30000
        retries = 0
        retry.backoff.ms = 100
        sasl.jaas.config = null
        sasl.kerberos.kinit.cmd = /usr/bin/kinit
        sasl.kerberos.min.time.before.relogin = 60000
        sasl.kerberos.service.name = null
        sasl.kerberos.ticket.renew.jitter = 0.05
        sasl.kerberos.ticket.renew.window.factor = 0.8
        sasl.mechanism = GSSAPI
        security.protocol = PLAINTEXT
        send.buffer.bytes = 131072
        ssl.cipher.suites = null
        ssl.enabled.protocols = [TLSv1.2, TLSv1.1, TLSv1]
        ssl.endpoint.identification.algorithm = null
        ssl.key.password = null
        ssl.keymanager.algorithm = SunX509
        ssl.keystore.location = null
        ssl.keystore.password = null
        ssl.keystore.type = JKS
        ssl.protocol = TLS
        ssl.provider = null
        ssl.secure.random.implementation = null
        ssl.trustmanager.algorithm = PKIX
        ssl.truststore.location = null
        ssl.truststore.password = null
        ssl.truststore.type = JKS
        transaction.timeout.ms = 60000
        transactional.id = null
        value.serializer = class org.apache.kafka.common.serialization.StringSerializer

[2019-04-25T16:19:46,705][INFO ][org.apache.kafka.common.utils.AppInfoParser] Kafka version : 1.1.0
[2019-04-25T16:19:46,706][INFO ][org.apache.kafka.common.utils.AppInfoParser] Kafka commitId : fdcf75ea326b8e07
[2019-04-25T16:19:46,854][INFO ][logstash.pipeline        ] Pipeline started successfully {:pipeline_id=>"main", :thread=>"#<Thread:0x11d30400 run>"}
The stdin plugin is now waiting for input:
[2019-04-25T16:19:47,009][INFO ][logstash.agent           ] Pipelines running {:count=>1, :running_pipelines=>[:main], :non_running_pipelines=>[]}
[2019-04-25T16:19:47,417][INFO ][logstash.agent           ] Successfully started Logstash API endpoint {:port=>9600}

二、使用Logstash抽取mysql数据到kafka

配置文件：

input {
        stdin {}
        jdbc {
                type => "jdbc"
                jdbc_connection_string => "jdbc:mysql://192.168.200.100:3306/yang?characterEncoding=UTF-8&autoReconnect=true"
                 # 数据库连接账号密码；
                jdbc_user => "root"
                jdbc_password => "010209"
                 # MySQL依赖包路径；
                jdbc_driver_library => "/mnt/mysql-connector-java-5.1.38.jar"
                 # the name of the driver class for mysql
                jdbc_driver_class => "com.mysql.jdbc.Driver"
                statement => "SELECT * FROM `im`"
        }
}
output {
        kafka{
                 topic_id => "test"
                 bootstrap_servers => "192.168.200.100:9092" # kafka的地址
                 batch_size => 5
        }
        stdout {
        }
}