1.Hadoop集群搭建的配置
主机（kafka zookeeper 三台同时安装启动）
master: 192.168.28.129
slave0: 192.168.28.130
slave1: 192.168.28.131
1.1搭建步骤如下链接:
https://blog.csdn.net/qq_31987649/article/details/85037833
1.2 启动hadoop
只需要启动Master 主节点上的hadoop
hadoop安装路径: / hadoop-2.6.5 /sbin
./start-all.sh 启动
./stop-all.sh 关闭
启动成功如下:
Master:
slave0:
slave1:
2.下载并解压 flume
apache-flume-1.7.0-bin.tar.gz
2.1 解压目录入下 命令 tar -zxvf /app/soft/apache-flume-1.7.0-bin.tar.gz -C /app/install/
2.2修改配置文件 进入conf目录下
mv flume-env.sh.template flume-env.sh
vi flume-env.sh
2.3 在conf目录下创建 hdfs-avro.conf 配置文件
命令: vi flume-kafka-hdfs.conf 增加内容:
a1.sources = r1
#数据沉淀，可以多个，中间用空格分隔
a1.sinks = k1
#传输管道，一般只有一个，可以多个
a1.channels = c1
#配置source 消息生产者
#exec可以通过指定的操作对日志进行读取,使用exec时需要指定shell命令,对日志进行读取
#a1.sources.r1.type = exec
#a1.sources.r1.command = tail -F /app/logs/webProvider.log
a1.sources.r1.channels = memoryChannel
a1.sources.r1.type=org.apache.flume.source.kafka.KafkaSource
a1.sources.r1.zookeeperConnect=192.168.28.130:2181
a1.sources.r1.topic=log4j-topic
#a1.sources.r1.groupId=flume
a1.sources.r1.kafka.consumer.timeout.ms=100
# 配置channel,将buffer事件放在内存中,相当于数据缓冲区，接收source数据发送给sink
#传输管道的参数，类型是内存传输
a1.channels.c1.type = memory
#存储在通道中的最大事件数。
a1.channels.c1.capacity = 1000
#收集端的sink会在收集到了1000条以后再去提交事务（即发送到下一个目的地）
a1.channels.c1.transactionCapacity = 100
# 配置sink 接收器
#沉淀的方式是控制台打印，还可以有其他方式，如上传到hdfs。
a1.sinks.k1.type = hdfs
#设置hdfs接收器
a1.sinks.k1.hdfs.path = hdfs://192.168.28.129:9000/flume/testLog.log
#设置
a1.sinks.k1.hdfs.filePrefix = test
#a1.sinks.k1.hdfs.fileSuffix = .log
a1.sinks.k1.hdfs.fileType=DataStream
# 把source和sink绑定在channel上
#指定传输管道，
a1.sources.r1.channels = c1
#设置数据沉淀接收的管道
a1.sinks.k1.channel = c1
2.下载并解压 Kafka
（kafka 三台同时安装启动）
kafka_2.11-2.0.0.tgz
解压目录
3.下载并解压 zookeeper
zookeeper-3.4.11.tar.gz
（zookeeper 三台同时安装启动）
解压目录
4.集群搭建
4.1zookeeper集群搭建
进入zookeeper conf目录(三台服务器都要修改)
复制zoo_sample.cfg 重命名为 zoo.conf 修改如下:
分别在三台服务器上新建 myid
cd /app/data/zookeeper/myid
master:
slave0:
slave1:
4.2 kafka集群搭建(三台服务器都要修改)
进入kafka config 目录
修改server.properties 如下:
# 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://192.168.28.129:9092
# 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
advertised.listeners=PLAINTEXT://192.168.28.129:9092
# 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 separated list of directories under which to store log files
log.dirs=/app/data/kafka/kafka-logs
# 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=1
# 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 excessive 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=192.168.28.129:2181,192.168.28.130:2181,192.168.28.131:2181
zookeeper.connect=master:2181,slave0:2181,slave1:2181
# 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
5.项目构建
5.1 pom依赖
<!-- 单元测试 -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
<scope>test</scope>
</dependency>
<!-- 导入servlet支持包 -->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>javax.servlet-api</artifactId>
<version>4.0.0-b01</version>
</dependency>
<!-- 导入日志支持包 -->
<!-- <dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
</dependency> -->
<!-- 日志系统支持(slf4j-log4j12:链接slf4j-api和log4j中间的适配器。它实现了slf4j-apiz中StaticLoggerBinder接口，
从而使得在编译时绑定的是slf4j-log4j12的getSingleton()方法) -->
<!-- <dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.21</version>
</dependency> -->
<!-- spring4相关jar包导入 -->
<!-- 提供在基础IOC(控制反转)功能上的扩展服务，此外还提供许多企业级服务的支持，有邮件服务、
任务调度、JNDI定位，EJB集成、远程访问、缓存以及多种视图层框架的支持。 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- spring核心工具包,其它包依赖此包 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-core</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- spring对jdbc的简单封闭包 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-jdbc</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- spring用于支持web开发时所需的Spring框架的核心类，包括自动载入WebApplicationContext特性的类、
Struts与JSF集成类、文件上传的支持类、Filter类和大量工具辅助类。 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-web</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- 用于对spring AOP(面向切面)的支持jar包 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-aop</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- 扩展包:spring context 的扩展支持,用于MVC方面-->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-context-support</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- spring bean管理包(包括配置文件的访问和创建bean管理bean)是Spring IOC的基础实现-->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-beans</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- spring提供对事物的支持,事务的相关处理以及实现类就在这个jar包中 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-tx</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- 提供对AspectJ的支持，以便可以方便的将面向方面的功能集成进IDE中，比如Eclipse AJDT。
外部依赖。 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-aspects</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!-- springMvc4对json的支持 -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>2.5.0</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.5.0</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.5.0</version>
</dependency>
<!-- 这个jar 文件包含Spring MVC 框架相关的所有类。
包括框架的Servlets，Web MVC框架，控制器和视图支持。当然，如果你的应用使用了独立的MVC 框架，则无需这个JAR 文件里的任何类。
外部依赖spring-web, (spring-support，Tiles，iText，POI)。 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-webmvc</artifactId>
<version>4.3.2.RELEASE</version>
</dependency>
<!--Spring数据库访问中另外一大模块就是ORM，ORM即对象/关系映射。
Spring支持大多数ORM框架，比如Hibernate，JPA，JDO，TopLink和iBatis
（Spring2支持iBatis2，现MyBatis3的Spring支持由MyBatis社区开发，并非Spring）。 -->
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-orm</artifactId>
<version>4.0.2.RELEASE</version>
</dependency>
<dependency>
<groupId>org.springframework.security</groupId>
<artifactId>spring-security-config</artifactId>
<version>4.0.2.RELEASE</version>
</dependency>
<dependency>
<groupId>org.springframework.security</groupId>
<artifactId>spring-security-web</artifactId>
<version>4.0.2.RELEASE</version>
</dependency>
<dependency>
<groupId>org.springframework.security</groupId>
<artifactId>spring-security-core</artifactId>
<version>4.0.2.RELEASE</version>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-test</artifactId>
<version>4.1.6.RELEASE</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.sun.mail</groupId>
<artifactId>javax.mail</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.aspectj</groupId>
<artifactId>aspectjweaver</artifactId>
<version>1.8.7</version>
</dependency>
<dependency>
<groupId>org.apache.tomcat</groupId>
<artifactId>tomcat-servlet-api</artifactId>
<version>8.0.26</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.cxf</groupId>
<artifactId>cxf-rt-frontend-jaxrs</artifactId>
<version>3.1.2</version>
</dependency>
<dependency>
<groupId>org.codehaus.jackson</groupId>
<artifactId>jackson-jaxrs</artifactId>
<version>1.9.2</version>
</dependency>
<dependency>
<groupId>commons-net</groupId>
<artifactId>commons-net</artifactId>
<version>1.4.1</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.0</version>
</dependency>
<!-- 导入servlet支持包 -->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>javax.servlet-api</artifactId>
<version>3.0.1</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>javax.servlet.jsp</groupId>
<artifactId>jsp-api</artifactId>
<version>2.1</version>
<scope>provided</scope>
</dependency>
<!-- 导入jstl支持包 -->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>jstl</artifactId>
<version>1.2</version>
</dependency>
<!-- kafka客户端支持包 -->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>0.11.0.1</version>
</dependency>
<!-- spring支持kafka -->
<dependency>
<groupId>org.springframework.kafka</groupId>
<artifactId>spring-kafka</artifactId>
<version>2.0.4.RELEASE</version>
</dependency>
<!-- kafka 集成 log4j 日志包 -->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-log4j-appender</artifactId>
<version>1.1.0</version>
</dependency>
<!--spring 集成 redis -->
<!-- <dependency>
<groupId>org.springframework.data</groupId>
<artifactId>spring-data-redis</artifactId>
<version>2.0.7.RELEASE</version>
</dependency> -->
<!-- <dependency>
<groupId>org.springframework.data</groupId>
<artifactId>spring-data-redis</artifactId>
<version>1.6.0.RELEASE</version>
</dependency> -->
<!-- jedis 操作 redis 客户端 -->
<!-- <dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.9.1</version>
</dependency>
-->
<!-- <dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.7.3</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-pool2</artifactId>
<version>2.0</version>
</dependency>
-->
<!-- redis -->
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.springframework.data</groupId>
<artifactId>spring-data-redis</artifactId>
<version>1.7.2.RELEASE</version>
</dependency>5.2 application-kafka.xml
<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:p="http://www.springframework.org/schema/p"
xmlns:aop="http://www.springframework.org/schema/aop"
xmlns:context="http://www.springframework.org/schema/context"
xmlns:jee="http://www.springframework.org/schema/jee"
xmlns:tx="http://www.springframework.org/schema/tx"
xmlns:task="http://www.springframework.org/schema/task"
xmlns:mvc="http://www.springframework.org/schema/mvc"
xmlns:rabbit="http://www.springframework.org/schema/rabbit"
xsi:schemaLocation="
http://www.springframework.org/schema/aop http://www.springframework.org/schema/aop/spring-aop-4.0.xsd
http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-4.0.xsd
http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context-4.0.xsd
http://www.springframework.org/schema/jee http://www.springframework.org/schema/jee/spring-jee-4.0.xsd
http://www.springframework.org/schema/tx http://www.springframework.org/schema/tx/spring-tx-4.0.xsd
http://www.springframework.org/schema/task http://www.springframework.org/schema/task/spring-task-4.1.xsd
http://www.springframework.org/schema/mvc http://www.springframework.org/schema/mvc/spring-mvc.xsd
http://www.springframework.org/schema/rabbit http://www.springframework.org/schema/rabbit/spring-rabbit-2.1.xsd
">
<!-- 加载配置文件 -->
<context:property-placeholder ignore-unresolvable="false" location="classpath:properties/config.properties"/>
<context:component-scan base-package="com.java.kafka.service" />
<!-- 激活annotation功能 -->
<context:annotation-config />
<!-- 生产者 -->
<bean id="producerFactory" class="org.springframework.kafka.core.DefaultKafkaProducerFactory">
<constructor-arg>
<map>
<entry key="bootstrap.servers" value="${kafka.servers}"></entry>
<entry key="key.serializer" value="org.apache.kafka.common.serialization.StringSerializer"></entry>
<entry key="value.serializer" value="org.apache.kafka.common.serialization.StringSerializer"></entry>
<entry key="key.deserializer" value="org.apache.kafka.common.serialization.StringDeserializer"></entry>
<entry key="value.deserializer" value="org.apache.kafka.common.serialization.StringDeserializer"></entry>
</map>
</constructor-arg>
</bean>
<!-- 用于发送消息的模板 kafkaTemplate-->
<bean id="kafkaTemplate" class="org.springframework.kafka.core.KafkaTemplate">
<constructor-arg ref="producerFactory"></constructor-arg>
<constructor-arg name="autoFlush" value="true"></constructor-arg>
</bean>
<!-- 创建消费者 -->
<bean id="consumerFactory" class="org.springframework.kafka.core.DefaultKafkaConsumerFactory">
<constructor-arg>
<map>
<entry key="bootstrap.servers" value="${kafka.servers}"></entry>
<entry key="group.id" value="${kafka.report_data_container}"></entry>
<entry key="key.deserializer" value="org.apache.kafka.common.serialization.StringDeserializer"></entry>
<entry key="value.deserializer" value="org.apache.kafka.common.serialization.StringDeserializer"></entry>
</map>
</constructor-arg>
</bean>
<!-- 消息消费者监听器 用于在接收到消息时执行相关的业务代码 (自行定义的类 用户于处理相应的业务操作)-->
<bean id="consumerListener" class="com.java.kafka.listener.KafkaConsumerListener"/>
<!-- 页面page监听器 -->
<bean id="reportDataListener" class="com.java.kafka.listener.ReportDataListener"></bean>
<!-- 商品业务处理监听类 -->
<bean id="commodityInfoListener" class="com.java.kafka.listener.CommodityInfoListener"></bean>
<!-- 用于将监听器和个某个主题绑定在一起 -->
<bean id="containerProperties_example" class="org.springframework.kafka.listener.config.ContainerProperties">
<!-- <constructor-arg value="test-topic"></constructor-arg>
<property name="messageListener" ref="consumerListener"></property> -->
<property name="messageListener" ref="reportDataListener"/>
<!-- <property name="messageListener" ref="commodityInfoListener"/> -->
<constructor-arg>
<list>
<value>${kafka.topic_page}</value>
<!-- <value>${kafka.topic_click}</value> -->
<!-- <value>${kafka.topic_commod}</value> -->
</list>
</constructor-arg>
</bean>
<!-- 用于将消息监听器与消息消费者工厂绑定在一起 -->
<bean id="messageListtenerContainer_example" class="org.springframework.kafka.listener.KafkaMessageListenerContainer">
<constructor-arg ref="containerProperties_example"></constructor-arg>
<constructor-arg ref="consumerFactory"></constructor-arg>
</bean>
<!-- redis -->
<bean id="poolConfig" class="redis.clients.jedis.JedisPoolConfig">
<!-- pool 最大空闲数 -->
<property name="maxIdle" value="8"></property>
<!-- 控制一个pool可分配多少个jedis实例 -->
<property name="maxTotal" value="10"></property>
<!-- 最大建立连接等待时间。如果超过此时间将接到异常。设为-1表示无限制。 -->
<property name="maxWaitMillis" value="1000"></property>
<!-- 是否在从池中取出连接前进行检验,如果检验失败,则从池中去除连接并尝试取出另一个 -->
<property name="testOnBorrow" value="true"></property>
</bean>
<!--
depends-on用来指定Bean初始化及销毁时的顺序。
depends-on用来表示一个Bean的实例化依靠另一个Bean先实例化。
如果在一个bean A上定义了depend-on B那么就表示：A 实例化前先实例化 B。
-->
<!-- <bean id="jedisPool" class="redis.clients.jedis.JedisPool" destroy-method="destroy" depends-on="poolConfig">
<constructor-arg name="poolConfig" ref="poolConfig"/>
<constructor-arg name="host" value="localhost"/>
<constructor-arg name="port" value="6379"/>
</bean> -->
<!-- 配置连接工厂 -->
<bean class="org.springframework.data.redis.connection.jedis.JedisConnectionFactory" id="connectionFactory"
p:pool-config-ref="poolConfig" p:password="${redis.password}" p:port="${redis.port}" p:host-name="${redis.host}"/>
<!-- 操作redis -->
<bean class="org.springframework.data.redis.core.StringRedisTemplate" id="redisTemplate">
<property name="connectionFactory" ref="connectionFactory"/>
<property name="keySerializer">
<bean
class="org.springframework.data.redis.serializer.StringRedisSerializer" />
</property>
<property name="hashKeySerializer">
<bean
class="org.springframework.data.redis.serializer.StringRedisSerializer" />
</property>
<property name="valueSerializer">
<bean
class="org.springframework.data.redis.serializer.JdkSerializationRedisSerializer" />
</property>
<property name="hashValueSerializer">
<bean
class="org.springframework.data.redis.serializer.JdkSerializationRedisSerializer" />
</property>
</bean>
<!-- springMvc4 用于将对象转换为 JSON -->
<bean id="stringConverter"
class="org.springframework.http.converter.StringHttpMessageConverter">
<property name="supportedMediaTypes">
<list>
<value>text/plain;charset=UTF-8</value>
</list>
</property>
</bean>
<bean id="jsonConverter"
class="org.springframework.http.converter.json.MappingJackson2HttpMessageConverter"></bean>
<bean
class="org.springframework.web.servlet.mvc.annotation.AnnotationMethodHandlerAdapter">
<property name="messageConverters">
<list>
<ref bean="stringConverter" />
<ref bean="jsonConverter" />
</list>
</property>
</bean>
</beans> 5.3 log4j.properties
#log4j.rootLogger=DEBUG,INFO, Console
log4j.rootLogger=INFO,Console,KAFKA
#Console 配置日志输出目的地 控制台输出
log4j.appender.Console=org.apache.log4j.ConsoleAppender
log4j.appender.Console.target=System.out
log4j.appender.Console.encoding=UTF-8
#配置日志信息的格式
log4j.appender.Console.layout=org.apache.log4j.PatternLayout
log4j.appender.Console.layout.ConversionPattern=%d [%t] %-5p [%c] - %m%n
#配置日志信息输出目的地 为 kafka (将kafka作为日志输出目的地)
log4j.appender.KAFKA=org.apache.kafka.log4jappender.KafkaLog4jAppender
#将日志数据发送到Kafka时的具体主题名
log4j.appender.KAFKA.topic=log4j-topic
#配置kafka服务器的地址,如果是群集则用逗号分隔
log4j.appender.KAFKA.brokerList=192.168.28.129:9092,192.168.28.130:9092,192.168.28.131:9092
#日志信息是否压缩
log4j.appender.KAFKA.compressionType=none
#表示是否同步发送
log4j.appender.KAFKA.syncSend=true
#将日志输出到Kafka时格式化
log4j.appender.KAFKA.layout=org.apache.log4j.PatternLayout
log4j.appender.kafka.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p %c{1}:%L - %m%n
#log4j.logger.java.sql.ResultSet=INFO
#log4j.logger.org.apache=INFO
#log4j.logger.java.sql.Connection=DEBUG
#log4j.logger.java.sql.Statement=DEBUG
#log4j.logger.java.sql.PreparedStatement=DEBUG
#log4j.logger.advertisement =TRACE
6.测试
6.1启动 hdfs 如上
6.2 启动Kafka 需要同时启动三台
进入kafka bin目录执行命令：./kafka-server-start.sh -daemon ../config/server.properties &
进程如下：
master:
slave0:
slave1:
启动zookeeper 需要同时启动三台
进入zookeeper bin目录 执行命令: ./zkServer.sh start
6.3 在( 192.168.28.131)启动flume
启动命令：./flume-ng agent -c ../conf -f ../conf/flume-kafka-hdfs.conf -n a1 -Dflume.root.logger=INFO,console
6.3 创建java测试类 KafkaLog4jTest2
package com.java.kafka.test;
import org.apache.log4j.Logger;
public class KafkaLog4jTest2 {
private static Logger logger = Logger.getLogger(KafkaLog4jTest2.class);
public static void main(String[] args) throws InterruptedException {
// TODO Auto-generated method stub
for (int i = 0; i < 5; i++) {
logger.info("这是从 KafkaLog4jTest2 产生的消息 【"+i+"】...");
Thread.sleep(1000);
}
}
}1.运行测试类:(kafka 作为从Log4j中获取数据)
2. hdfs 中存入的消息如下(flume 数据从kafka中获取)：
执行命令 hadoop fs -cat /flume/testLog.log/*
324
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
