SparkListener的最上层接口是SparkListenerInterface,是一个Spark调度器的事件的处理接口,大多数程序不直接实现这个接口,而应该直接扩展SparkListener或者SparkFirehoseLIstener。
/**
* Interface for listening to events from the Spark scheduler. Most applications should probably
* extend SparkListener or SparkFirehoseListener directly, rather than implementing this class.
*
* Note that this is an internal interface which might change in different Spark releases.
*/
private[spark] trait SparkListenerInterface {
/**
* Called when a stage completes successfully or fails, with information on the completed stage.
*/
def onStageCompleted(stageCompleted: SparkListenerStageCompleted): Unit
/**
* Called when a stage is submitted
*/
def onStageSubmitted(stageSubmitted: SparkListenerStageSubmitted): Unit
/**
* Called when a task starts
*/
def onTaskStart(taskStart: SparkListenerTaskStart): Unit
/**
* Called when a task begins remotely fetching its result (will not be called for tasks that do
* not need to fetch the result remotely).
*/
def onTaskGettingResult(taskGettingResult: SparkListenerTaskGettingResult): Unit
/**
* Called when a task ends
*/
def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit
/**
* Called when a job starts
*/
def onJobStart(jobStart: SparkListenerJobStart): Unit
/**
* Called when a job ends
*/
def onJobEnd(jobEnd: SparkListenerJobEnd): Unit
/**
* Called when environment properties have been updated
*/
def onEnvironmentUpdate(environmentUpdate: SparkListenerEnvironmentUpdate): Unit
/**
* Called when a new block manager has joined
*/
def onBlockManagerAdded(blockManagerAdded: SparkListenerBlockManagerAdded): Unit
/**
* Called when an existing block manager has been removed
*/
def onBlockManagerRemoved(blockManagerRemoved: SparkListenerBlockManagerRemoved): Unit
/**
* Called when an RDD is manually unpersisted by the application
*/
def onUnpersistRDD(unpersistRDD: SparkListenerUnpersistRDD): Unit
/**
* Called when the application starts
*/
def onApplicationStart(applicationStart: SparkListenerApplicationStart): Unit
/**
* Called when the application ends
*/
def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit
/**
* Called when the driver receives task metrics from an executor in a heartbeat.
*/
def onExecutorMetricsUpdate(executorMetricsUpdate: SparkListenerExecutorMetricsUpdate): Unit
/**
* Called when the driver registers a new executor.
*/
def onExecutorAdded(executorAdded: SparkListenerExecutorAdded): Unit
/**
* Called when the driver removes an executor.
*/
def onExecutorRemoved(executorRemoved: SparkListenerExecutorRemoved): Unit
/**
* Called when the driver receives a block update info.
*/
def onBlockUpdated(blockUpdated: SparkListenerBlockUpdated): Unit
/**
* Called when other events like SQL-specific events are posted.
*/
def onOtherEvent(event: SparkListenerEvent): Unit
}
SparkListener是SparkListenerInterface的一个默认实现,这个实现对所有的回调都不做任何操作。
注意这个一个内部的接口,不同的spark版本中可能变动。
/**
* :: DeveloperApi ::
* A default implementation for [[SparkListenerInterface]] that has no-op implementations for
* all callbacks.
*
* Note that this is an internal interface which might change in different Spark releases.
*/
@DeveloperApi
abstract class SparkListener extends SparkListenerInterface {
override def onStageCompleted(stageCompleted: SparkListenerStageCompleted): Unit = { }
override def onStageSubmitted(stageSubmitted: SparkListenerStageSubmitted): Unit = { }
override def onTaskStart(taskStart: SparkListenerTaskStart): Unit = { }
override def onTaskGettingResult(taskGettingResult: SparkListenerTaskGettingResult): Unit = { }
override def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit = { }
override def onJobStart(jobStart: SparkListenerJobStart): Unit = { }
override def onJobEnd(jobEnd: SparkListenerJobEnd): Unit = { }
override def onEnvironmentUpdate(environmentUpdate: SparkListenerEnvironmentUpdate): Unit = { }
override def onBlockManagerAdded(blockManagerAdded: SparkListenerBlockManagerAdded): Unit = { }
override def onBlockManagerRemoved(
blockManagerRemoved: SparkListenerBlockManagerRemoved): Unit = { }
override def onUnpersistRDD(unpersistRDD: SparkListenerUnpersistRDD): Unit = { }
override def onApplicationStart(applicationStart: SparkListenerApplicationStart): Unit = { }
override def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit = { }
override def onExecutorMetricsUpdate(
executorMetricsUpdate: SparkListenerExecutorMetricsUpdate): Unit = { }
override def onExecutorAdded(executorAdded: SparkListenerExecutorAdded): Unit = { }
override def onExecutorRemoved(executorRemoved: SparkListenerExecutorRemoved): Unit = { }
override def onBlockUpdated(blockUpdated: SparkListenerBlockUpdated): Unit = { }
override def onOtherEvent(event: SparkListenerEvent): Unit = { }
}
SparkFirehoseListener允许用户接收所有的SparkListener事件,用户应该重写onEvent方法。
这个是一个具体的Java类,为了确保当在SparkListener中增加方法时我们不忘记更新此类,如果忘记则会导致编译错误。
/**
* Class that allows users to receive all SparkListener events.
* Users should override the onEvent method.
*
* This is a concrete Java class in order to ensure that we don't forget to update it when adding
* new methods to SparkListener: forgetting to add a method will result in a compilation error (if
* this was a concrete Scala class, default implementations of new event handlers would be inherited
* from the SparkListener trait).
*/
public class SparkFirehoseListener implements SparkListenerInterface {
public void onEvent(SparkListenerEvent event) { }
@Override
public final void onStageCompleted(SparkListenerStageCompleted stageCompleted) {
onEvent(stageCompleted);
}
@Override
public final void onStageSubmitted(SparkListenerStageSubmitted stageSubmitted) {
onEvent(stageSubmitted);
}
@Override
public final void onTaskStart(SparkListenerTaskStart taskStart) {
onEvent(taskStart);
}
@Override
public final void onTaskGettingResult(SparkListenerTaskGettingResult taskGettingResult) {
onEvent(taskGettingResult);
}
@Override
public final void onTaskEnd(SparkListenerTaskEnd taskEnd) {
onEvent(taskEnd);
}
@Override
public final void onJobStart(SparkListenerJobStart jobStart) {
onEvent(jobStart);
}
@Override
public final void onJobEnd(SparkListenerJobEnd jobEnd) {
onEvent(jobEnd);
}
@Override
public final void onEnvironmentUpdate(SparkListenerEnvironmentUpdate environmentUpdate) {
onEvent(environmentUpdate);
}
@Override
public final void onBlockManagerAdded(SparkListenerBlockManagerAdded blockManagerAdded) {
onEvent(blockManagerAdded);
}
@Override
public final void onBlockManagerRemoved(SparkListenerBlockManagerRemoved blockManagerRemoved) {
onEvent(blockManagerRemoved);
}
@Override
public final void onUnpersistRDD(SparkListenerUnpersistRDD unpersistRDD) {
onEvent(unpersistRDD);
}
@Override
public final void onApplicationStart(SparkListenerApplicationStart applicationStart) {
onEvent(applicationStart);
}
@Override
public final void onApplicationEnd(SparkListenerApplicationEnd applicationEnd) {
onEvent(applicationEnd);
}
@Override
public final void onExecutorMetricsUpdate(
SparkListenerExecutorMetricsUpdate executorMetricsUpdate) {
onEvent(executorMetricsUpdate);
}
@Override
public final void onExecutorAdded(SparkListenerExecutorAdded executorAdded) {
onEvent(executorAdded);
}
@Override
public final void onExecutorRemoved(SparkListenerExecutorRemoved executorRemoved) {
onEvent(executorRemoved);
}
@Override
public void onBlockUpdated(SparkListenerBlockUpdated blockUpdated) {
onEvent(blockUpdated);
}
@Override
public void onOtherEvent(SparkListenerEvent event) {
onEvent(event);
}
}