#指定agent的sources,sinks,channels
a1.sources = s1
a1.sinks = k1
a1.channels = c1

#配置sources属性
a1.sources.s1.type = exec
a1.sources.s1.command = tail -F /tmp/log.txt
a1.sources.s1.shell = /bin/bash -c
a1.sources.s1.channels = c1

#配置sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = 192.168.1.103
a1.sinks.k1.port = 8888
a1.sinks.k1.batch-size = 1
a1.sinks.k1.channel = c1

#配置channel类型
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/exec-memory-logger.properties --name a1 -Dflume.root.logger=INFO,console

echo "asfsafsf" >> /tmp/log.txt

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444

# 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.r1.channels = c1
a1.sinks.k1.channel = c1

flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/netcat.properties --name a1 -Dflume.root.logger=INFO,console

telnet localhost 44444

#指定agent的sources,sinks,channels
a1.sources = s1  
a1.sinks = k1  
a1.channels = c1  
   
#配置sources属性
a1.sources.s1.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.s1.channels = c1
a1.sources.s1.batchSize = 5000
a1.sources.s1.batchDurationMillis = 2000
a1.sources.s1.kafka.bootstrap.servers = 192.168.1.103:9092
a1.sources.s1.kafka.topics = test1
a1.sources.s1.kafka.consumer.group.id = custom.g.id

#将sources与channels进行绑定
a1.sources.s1.channels = c1
   
#配置sink 
a1.sinks.k1.type = logger

#将sinks与channels进行绑定  
a1.sinks.k1.channel = c1  
   
#配置channel类型
a1.channels.c1.type = memory

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

a1.sources.s1.type=exec
a1.sources.s1.command=tail -F /tmp/kafka.log
a1.sources.s1.channels=c1 

#设置Kafka接收器
a1.sinks.k1.type= org.apache.flume.sink.kafka.KafkaSink
#设置Kafka地址
a1.sinks.k1.brokerList=192.168.1.103:9092
#设置发送到Kafka上的主题
a1.sinks.k1.topic=test1
#设置序列化方式
a1.sinks.k1.serializer.class=kafka.serializer.StringEncoder
a1.sinks.k1.channel=c1     

a1.channels.c1.type=memory
a1.channels.c1.capacity=10000
a1.channels.c1.transactionCapacity=100   

flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/read-kafka.properties --name a1 -Dflume.root.logger=INFO,console

flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/write-kafka.properties --name a1 -Dflume.root.logger=INFO,console

# 创建用于测试主题
bin/kafka-topics.sh --create                     --bootstrap-server 192.168.1.103:9092                     --replication-factor 1                     --partitions 1                      --topic test1
# 启动 Producer,用于发送测试数据：
bin/kafka-console-producer.sh --broker-list 192.168.1.103:9092 --topic test1

a1.sources = r1
a1.channels = c1
a1.sources.r1.type = org.example.MySource
a1.sources.r1.channels = c1

#指定agent的sources,sinks,channels
a1.sources = s1  
a1.sinks = k1  
a1.channels = c1  
   
#配置sources属性
a1.sources.s1.type =spooldir  
a1.sources.s1.spoolDir =/tmp/log2
a1.sources.s1.basenameHeader = true
a1.sources.s1.basenameHeaderKey = fileName 
#将sources与channels进行绑定  
a1.sources.s1.channels =c1 

   
#配置sink 
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /flume/events/%y-%m-%d/%H/
a1.sinks.k1.hdfs.filePrefix = %{fileName}
#生成的文件类型，默认是Sequencefile，可用DataStream，则为普通文本
a1.sinks.k1.hdfs.fileType = DataStream  
a1.sinks.k1.hdfs.useLocalTimeStamp = true
#将sinks与channels进行绑定  
a1.sinks.k1.channel = c1
   
#配置channel类型
a1.channels.c1.type = memory

hdfs dfs -ls /flume/events/19-11-21/15

a1.channels = c1
a1.channels.c1.type = memory
a1.sinks = k1
a1.sinks.k1.type = hive
a1.sinks.k1.channel = c1
a1.sinks.k1.hive.metastore = thrift://127.0.0.1:9083
a1.sinks.k1.hive.database = logsdb
a1.sinks.k1.hive.table = weblogs
a1.sinks.k1.hive.partition = asia,%{country},%y-%m-%d-%H-%M
a1.sinks.k1.useLocalTimeStamp = false
a1.sinks.k1.round = true
a1.sinks.k1.roundValue = 10
a1.sinks.k1.roundUnit = minute
a1.sinks.k1.serializer = DELIMITED
a1.sinks.k1.serializer.delimiter = "\t"
a1.sinks.k1.serializer.serdeSeparator = ‘\t‘
a1.sinks.k1.serializer.fieldnames =id,,msg

#指定agent的sources,sinks,channels
a1.sources = s1
a1.sinks = k1
a1.channels = c1

#配置sources属性
a1.sources.s1.type = exec
a1.sources.s1.command = tail -F /tmp/log.txt
a1.sources.s1.shell = /bin/bash -c
a1.sources.s1.channels = c1

#配置sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = 192.168.1.103
a1.sinks.k1.port = 8888
a1.sinks.k1.batch-size = 1
a1.sinks.k1.channel = c1

#配置channel类型
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

#指定agent的sources,sinks,channels
a2.sources = s2
a2.sinks = k2
a2.channels = c2

#配置sources属性
a2.sources.s2.type = avro
a2.sources.s2.bind = 192.168.1.103
a2.sources.s2.port = 8888

#将sources与channels进行绑定
a2.sources.s2.channels = c2

#配置sink
a2.sinks.k2.type = logger

#将sinks与channels进行绑定
a2.sinks.k2.channel = c2

#配置channel类型
a2.channels.c2.type = memory
a2.channels.c2.capacity = 1000
a2.channels.c2.transactionCapacity = 100

先
flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/avro-memory-log.properties --name a2 -Dflume.root.logger=INFO,console
后
flume-ng agent --conf conf --conf-file /usr/app/apache-flume-1.8.0-bin/exec-memory-avro.properties --name a1 -Dflume.root.logger=INFO,console

import org.apache.flume.Event;
import org.apache.flume.EventDeliveryException;
import org.apache.flume.event.EventBuilder;
import org.apache.flume.api.SecureRpcClientFactory;
import org.apache.flume.api.RpcClientConfigurationConstants;
import org.apache.flume.api.RpcClient;
import java.nio.charset.Charset;
import java.util.Properties;

public class MyApp {
  public static void main(String[] args) {
    MySecureRpcClientFacade client = new MySecureRpcClientFacade();
    // Initialize client with the remote Flume agent‘s host, port
    Properties props = new Properties();
    props.setProperty(RpcClientConfigurationConstants.CONFIG_CLIENT_TYPE, "thrift");
    props.setProperty("hosts", "h1");
    props.setProperty("hosts.h1", "client.example.org"+":"+ String.valueOf(8888));

    // Initialize client with the kerberos authentication related properties
    props.setProperty("kerberos", "true");
    props.setProperty("client-principal", "flumeclient/client.example.org@EXAMPLE.ORG");
    props.setProperty("client-keytab", "/tmp/flumeclient.keytab");
    props.setProperty("server-principal", "flume/server.example.org@EXAMPLE.ORG");
    client.init(props);

    // Send 10 events to the remote Flume agent. That agent should be
    // configured to listen with an AvroSource.
    String sampleData = "Hello Flume!";
    for (int i = 0; i < 10; i++) {
      client.sendDataToFlume(sampleData);
    }

    client.cleanUp();
  }
}

class MySecureRpcClientFacade {
  private RpcClient client;
  private Properties properties;

  public void init(Properties properties) {
    // Setup the RPC connection
    this.properties = properties;
    // Create the ThriftSecureRpcClient instance by using SecureRpcClientFactory
    this.client = SecureRpcClientFactory.getThriftInstance(properties);
  }

  public void sendDataToFlume(String data) {
    // Create a Flume Event object that encapsulates the sample data
    Event event = EventBuilder.withBody(data, Charset.forName("UTF-8"));

    // Send the event
    try {
      client.append(event);
    } catch (EventDeliveryException e) {
      // clean up and recreate the client
      client.close();
      client = null;
      client = SecureRpcClientFactory.getThriftInstance(properties);
    }
  }

  public void cleanUp() {
    // Close the RPC connection
    client.close();
  }
}

a1.channels = c1
a1.sinks = k1
a1.sinks.k1.type = elasticsearch
a1.sinks.k1.hostNames = 127.0.0.1:9200,127.0.0.2:9300
a1.sinks.k1.indexName = foo_index
a1.sinks.k1.indexType = bar_type
a1.sinks.k1.clusterName = foobar_cluster
a1.sinks.k1.batchSize = 500
a1.sinks.k1.ttl = 5d
a1.sinks.k1.serializer = org.apache.flume.sink.elasticsearch.ElasticSearchDynamicSerializer
a1.sinks.k1.channel = c1

public class MySink extends AbstractSink implements Configurable {
  private String myProp;

  @Override
  public void configure(Context context) {
    String myProp = context.getString("myProp", "defaultValue");

    // Process the myProp value (e.g. validation)

    // Store myProp for later retrieval by process() method
    this.myProp = myProp;
  }

  @Override
  public void start() {
    // Initialize the connection to the external repository (e.g. HDFS) that
    // this Sink will forward Events to ..
  }

  @Override
  public void stop () {
    // Disconnect from the external respository and do any
    // additional cleanup (e.g. releasing resources or nulling-out
    // field values) ..
  }

  @Override
  public Status process() throws EventDeliveryException {
    Status status = null;

    // Start transaction
    Channel ch = getChannel();
    Transaction txn = ch.getTransaction();
    txn.begin();
    try {
      // This try clause includes whatever Channel operations you want to do

      Event event = ch.take();

      // Send the Event to the external repository.
      // storeSomeData(e);

      txn.commit();
      status = Status.READY;
    } catch (Throwable t) {
      txn.rollback();

      // Log exception, handle individual exceptions as needed

      status = Status.BACKOFF;

      // re-throw all Errors
      if (t instanceof Error) {
        throw (Error)t;
      }
    }
    return status;
  }
}

public class MySource extends AbstractSource implements Configurable, PollableSource {
  private String myProp;

  @Override
  public void configure(Context context) {
    String myProp = context.getString("myProp", "defaultValue");

    // Process the myProp value (e.g. validation, convert to another type, ...)

    // Store myProp for later retrieval by process() method
    this.myProp = myProp;
  }

  @Override
  public void start() {
    // Initialize the connection to the external client
  }

  @Override
  public void stop () {
    // Disconnect from external client and do any additional cleanup
    // (e.g. releasing resources or nulling-out field values) ..
  }

  @Override
  public Status process() throws EventDeliveryException {
    Status status = null;

    try {
      // This try clause includes whatever Channel/Event operations you want to do

      // Receive new data
      Event e = getSomeData();

      // Store the Event into this Source‘s associated Channel(s)
      getChannelProcessor().processEvent(e);

      status = Status.READY;
    } catch (Throwable t) {
      // Log exception, handle individual exceptions as needed

      status = Status.BACKOFF;

      // re-throw all Errors
      if (t instanceof Error) {
        throw (Error)t;
      }
    } finally {
      txn.close();
    }
    return status;
  }
}