重写配置文件，指定一个更完整的参数选择，就成功了。本例将在10公里记录或10分钟后写入，以先到者为准。此外，我将内存通道改为文件通道，以提高数据流的可靠性。

agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1

# Describe/configure source1

agent1.sources.source1.type = exec
agent1.sources.source1.command = tail -f /home/cloudera/LogCreator/fortune_log.log

# Describe sink1

agent1.sinks.sink1.type = hdfs
agent1.sinks.sink1.hdfs.path = hdfs://localhost/flume/logtest/
agent1.sinks.sink1.hdfs.filePrefix = LogCreateTest

# Number of seconds to wait before rolling current file (0 = never roll based on time interval)

agent1.sinks.sink1.hdfs.rollInterval = 600

# File size to trigger roll, in bytes (0: never roll based on file size)

agent1.sinks.sink1.hdfs.rollSize = 0

# Number of events written to file before it rolled (0 = never roll based on number of events)

agent1.sinks.sink1.hdfs.rollCount = 10000

# number of events written to file before it flushed to HDFS

agent1.sinks.sink1.hdfs.batchSize = 10000
agent1.sinks.sink1.hdfs.txnEventMax = 40000

# -- Compression codec. one of following : gzip, bzip2, lzo, snappy

# hdfs.codeC = gzip

# format: currently SequenceFile, DataStream or CompressedStream

# (1)DataStream will not compress output file and please don't set codeC

# (2)CompressedStream requires set hdfs.codeC with an available codeC

agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.maxOpenFiles=50

# -- "Text" or "Writable"

# hdfs.writeFormat

agent1.sinks.sink1.hdfs.appendTimeout = 10000
agent1.sinks.sink1.hdfs.callTimeout = 10000

# Number of threads per HDFS sink for HDFS IO ops (open, write, etc.)

agent1.sinks.sink1.hdfs.threadsPoolSize=100

# Number of threads per HDFS sink for scheduling timed file rolling

agent1.sinks.sink1.hdfs.rollTimerPoolSize = 1

# hdfs.kerberosPrin--cipal Kerberos user principal for accessing secure HDFS

# hdfs.kerberosKey--tab Kerberos keytab for accessing secure HDFS

# hdfs.round false Should the timestamp be rounded down (if true, affects all time based escape sequences except %t)

# hdfs.roundValue1 Rounded down to the highest multiple of this (in the unit configured using

# hdfs.roundUnit), less than current time.

# hdfs.roundUnit second The unit of the round down value - second, minute or hour.

# serializer TEXT Other possible options include AVRO_EVENT or the fully-qualified class name of an implementation of the EventSerializer.Builder interface.

# serializer.*

# Use a channel which buffers events to a file

# -- The component type name, needs to be FILE.

agent1.channels.channel1.type = FILE

# checkpointDir ~/.flume/file-channel/checkpoint The directory where checkpoint file will be stored

# dataDirs ~/.flume/file-channel/data The directory where log files will be stored

# The maximum size of transaction supported by the channel

agent1.channels.channel1.transactionCapacity = 1000000

# Amount of time (in millis) between checkpoints

agent1.channels.channel1.checkpointInterval 30000

# Max size (in bytes) of a single log file

agent1.channels.channel1.maxFileSize = 2146435071

# Maximum capacity of the channel

agent1.channels.channel1.capacity 10000000

# keep-alive 3 Amount of time (in sec) to wait for a put operation

# write-timeout 3 Amount of time (in sec) to wait for a write operation

# Bind the source and sink to the channel

agent1.sources.source1.channels = channel1
agent1.sinks.sink1.channel = channel1

根据org.apache.flume.sink.hdfs.bucketwriter的源代码：

/**
 * Internal API intended for HDFSSink use.
 * This class does file rolling and handles file formats and serialization.
 * Only the public methods in this class are thread safe.
 */
class BucketWriter {
  ...
  /**
   * open() is called by append()
   * @throws IOException
   * @throws InterruptedException
   */
  private void open() throws IOException, InterruptedException {
    ...
    // if time-based rolling is enabled, schedule the roll
    if (rollInterval > 0) {
      Callable<Void> action = new Callable<Void>() {
        public Void call() throws Exception {
          LOG.debug("Rolling file ({}): Roll scheduled after {} sec elapsed.",
              bucketPath, rollInterval);
          try {
            // Roll the file and remove reference from sfWriters map.
            close(true);
          } catch(Throwable t) {
            LOG.error("Unexpected error", t);
          }
          return null;
        }
      };
      timedRollFuture = timedRollerPool.schedule(action, rollInterval,
          TimeUnit.SECONDS);
    }
    ...
  }
  ...
   /**
   * check if time to rotate the file
   */
  private boolean shouldRotate() {
    boolean doRotate = false;

    if (writer.isUnderReplicated()) {
      this.isUnderReplicated = true;
      doRotate = true;
    } else {
      this.isUnderReplicated = false;
    }

    if ((rollCount > 0) && (rollCount <= eventCounter)) {
      LOG.debug("rolling: rollCount: {}, events: {}", rollCount, eventCounter);
      doRotate = true;
    }

    if ((rollSize > 0) && (rollSize <= processSize)) {
      LOG.debug("rolling: rollSize: {}, bytes: {}", rollSize, processSize);
      doRotate = true;
    }

    return doRotate;
  }
...
}

以及org.apache.flume.sink.hdfs.abstracthdfswriter

public abstract class AbstractHDFSWriter implements HDFSWriter {
...
  @Override
  public boolean isUnderReplicated() {
    try {
      int numBlocks = getNumCurrentReplicas();
      if (numBlocks == -1) {
        return false;
      }
      int desiredBlocks;
      if (configuredMinReplicas != null) {
        desiredBlocks = configuredMinReplicas;
      } else {
        desiredBlocks = getFsDesiredReplication();
      }
      return numBlocks < desiredBlocks;
    } catch (IllegalAccessException e) {
      logger.error("Unexpected error while checking replication factor", e);
    } catch (InvocationTargetException e) {
      logger.error("Unexpected error while checking replication factor", e);
    } catch (IllegalArgumentException e) {
      logger.error("Unexpected error while checking replication factor", e);
    }
    return false;
  }
...
}

hdfs文件的滚动由4个条件控制：
hdfs.rollsize文件
hdfs.rollcount卷数
minblockreplicas（最高优先级，但通常不是导致滚动小文件的原因）
hdfs.roll间隔
根据bucketwriter.class中的这些if段更改值