Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/2065#discussion_r16754471 --- Diff: external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumePollingRunnable.scala --- @@ -0,0 +1,163 @@ +/* + * 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. + */ +package org.apache.spark.streaming.flume + +import scala.collection.JavaConversions._ +import scala.collection.mutable.ArrayBuffer + +import com.google.common.base.Throwables + +import org.apache.spark.Logging +import org.apache.spark.streaming.flume.sink._ + +private[flume] class FlumePollingRunnable(val parent: FlumePollingReceiver) extends Runnable with +Logging { + + def run(): Unit = { + while (!parent.isStopped()) { + val connection = parent.getConnections.poll() + val client = connection.client + var batchReceived = false + var seq: CharSequence = null + try { + getBatch(client) match { + case Some(eventBatch) => + batchReceived = true + seq = eventBatch.getSequenceNumber + val events = toSparkFlumeEvents(eventBatch.getEvents) + logDebug( + "Received batch of " + events.size + " events with sequence number: " + seq) + if (store(events)) { + ack(client, seq) + } else { + sendNack(batchReceived, client, seq) + } + case None => + } + } catch { + case e: Exception => + Throwables.getRootCause(e) match { + // If the cause was an InterruptedException, then check if the receiver is stopped - + // if yes, just break out of the loop. Else send a Nack and log a warning. + // In the unlikely case, the cause was not an Exception, + // then just throw it out and exit. + case interrupted: InterruptedException => + if (!parent.isStopped()) { + logWarning("Interrupted while receiving data from Flume", interrupted) + sendNack(batchReceived, client, seq) + } + case exception: Exception => + logWarning("Error while receiving data from Flume", exception) + sendNack(batchReceived, client, seq) + } + } finally { + parent.getConnections.add(connection) + } + } + } + + /** + * Gets a batch of events from the specified client. This method does not handle any exceptions + * which will be propogated to the caller. + * @param client Client to get events from + * @return [[Some]] which contains the event batch if Flume sent any events back, else [[None]] + */ + private def getBatch(client: SparkFlumeProtocol.Callback): Option[EventBatch] = { + val eventBatch = client.getEventBatch(parent.getMaxBatchSize) + if (!SparkSinkUtils.isErrorBatch(eventBatch)) { + // No error, proceed with processing data + Some(eventBatch) + } else { + logWarning( + "Did not receive events from Flume agent due to error on the Flume " + + "agent: " + eventBatch.getErrorMsg) + None + } + } + + /** + * Store the events in the buffer to Spark. This method will not propogate any exceptions, + * but will propogate any other errors. + * @param buffer The buffer to store + * @return true if the data was stored without any exception being thrown, else false + */ + private def store(buffer: ArrayBuffer[SparkFlumeEvent]): Boolean = { + try { + parent.store(buffer) + true + } catch { + case e: Exception => + logWarning("Error while attempting to store data received from Flume", e) + false + } + } + + /** + * Send an ack to the client for the sequence number. This method does not handle any exceptions + * which will be propogated to the caller. + * @param client client to send the ack to + * @param seq sequence number of the batch to be ack-ed. + * @return + */ + private def ack(client: SparkFlumeProtocol.Callback, seq: CharSequence): Unit = { + logDebug("Sending nack for sequence number: " + seq) --- End diff -- The debug statement is wrong! Its not sending nack !!!!!
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org