1.环境

CDH 5.16.1
Spark 2.3.0 cloudera4
Kafka 2.1.0+kafka4.0.0

2.Log4j——>Flume

2.1 Log4j 产生日志

import org.apache.log4j.Logger;

/**
 * @ClassName LoggerGenerator
 * @Author wuning
 * @Date: 2020/2/3 10:54
 * @Description: 模拟日志输出
 */
public class LoggerGenerator {

    private static Logger logger = Logger.getLogger(LoggerGenerator.class.getName());

    public static void main(String[] args) throws InterruptedException {

        int index = 0;

        while (true) {
            Thread.sleep(1000);
            logger.info("value : " + index++);
        }
    }
}

#log4j.rootLogger=debug,stdout,info,debug,warn,error
log4j.rootLogger=info,stdout,flume

#console
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern= %d{yyyy-MM-dd HH:mm:ss,SSS} [%t] [%c] [%p] -%m%n

log4j.appender.flume = org.apache.flume.clients.log4jappender.Log4jAppender
log4j.appender.flume.Hostname = cdh03
log4j.appender.flume.Port = 9876
log4j.appender.flume.UnsafeMode = true

注意：需要引入flume-ng-log4jappender jar包

<dependency>
    <groupId>org.apache.flume.flume-ng-clients</groupId>
    <artifactId>flume-ng-log4jappender</artifactId>
    <version>1.6.0</version>
</dependency>

2.2 Flume采集日志

地址：http://flume.apache.org/releases/content/1.6.0/FlumeUserGuide.html#flume-sources

a1.sources = s1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.s1.type = avro
a1.sources.s1.bind = cdh03
a1.sources.s1.port = 9876

# Describe the sink
a1.sinks.k1.type = logger

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.s1.channels = c1
a1.sinks.k1.channel = c1

原文地址：https://www.cnblogs.com/wuning/p/12258033.html