示例：Log4j日志模拟数据整合 Flume+Kafka+Spark Streaming

1.Log4j日志==>Flume==>Kafka
flume_kafka.conf

agent1.sources = avro-source
agent1.channels = logger-channel
agent1.sinks = kafka-sink


# define source
agent1.sources.avro-source.type=avro
agent1.sources.avro-source.bind=0.0.0.0
agent1.sources.avro-source.port=41414


# define channel
agent1.channels.logger-channel.type=memory


# define sink
agent1.sinks.kafka-sink.type=org.apache.flume.sink.kafka.KafkaSink
agent1.sinks.kafka-sink.kafka.topic = kafka_streaming_topic
agent1.sinks.kafka-sink.kafka.bootstrap.servers = hadoop01:9092
agent1.sinks.kafka-sink.kafka.flumeBatchSize = 20
agent1.sinks.kafka-sink.kafka.producer.acks = 1


agent1.sources.avro-source.channels=logger-channel
agent1.sinks.kafka-sink.channel=logger-channel

参考官网：https://flume.apache.org/releases/content/1.9.0/FlumeUserGuide.html#kafka-sink
2. log4j.properties

log4j.rootLogger=INFO,stdout,flume

log4j.appender.stdout = org.apache.log4j.ConsoleAppender
log4j.appender.stdout.target = System.out
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 = hadoop01
log4j.appender.flume.Port = 41414
log4j.appender.flume.UnsafeMode = true

参考官网：https://flume.apache.org/releases/content/1.9.0/FlumeUserGuide.html#load-balancing-log4j-appender
3. 编写简单代码打印log4j日志

import org.apache.log4j.Logger;

public class test {
    private static Logger logger = Logger.getLogger(test.class);

    public static void main(String[] args) throws Exception {
        int i = 0;
        while (true) {
            Thread.sleep(1000);
            logger.info(i++);
        }

    }
}

4. 启动Zookeeper

zkServer.sh start

5. 启动Kafka

kafka-server-start.sh  -daemon  $KAFKA_HOME/config/server.properties &

6. 启动flume

flume-ng agent \
--name agent1 \
--conf  $FLUME_HOME/conf \
--conf-file $FLUME_HOME/conf/flume_kafka.conf \
-Dflume.root.logger=INFO,console

7. 开启消费者

kafka-console-consumer.sh \
--zookeeper hadoop01:2181 \
--topic kafka_streaming_topic

8. 编写Spark-Streaming消费者并运行

import org.apache.log4j.{Level, Logger}
import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

object kafka_streaming {
  Logger.getLogger("org").setLevel(Level.ERROR)

  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("kafka_streaming").setMaster("local[*]").set("spark.port.maxRetries","100")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    val messages = KafkaUtils.createStream(ssc, "hadoop01:2181", "test", Map("kafka_streaming_topic" -> 1))
    messages.map(_._2).count().print()

    ssc.start()
    ssc.awaitTermination()

  }
}