spark TriggerExecutor 源码

spark TriggerExecutor 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/TriggerExecutor.scala

/*
 * 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.sql.execution.streaming

import org.apache.spark.internal.Logging
import org.apache.spark.util.{Clock, SystemClock}

trait TriggerExecutor {

  /**
   * Execute batches using `batchRunner`. If `batchRunner` runs `false`, terminate the execution.
   */
  def execute(batchRunner: () => Boolean): Unit
}

/**
 * A trigger executor that runs a single batch only, then terminates.
 */
case class SingleBatchExecutor() extends TriggerExecutor {

  /**
   * Execute a single batch using `batchRunner`.
   */
  override def execute(batchRunner: () => Boolean): Unit = batchRunner()
}

/**
 * A trigger executor that runs multiple batches then terminates.
 */
case class MultiBatchExecutor() extends TriggerExecutor {
  /**
   * Execute multiple batches using `batchRunner`
   */
  override def execute(batchRunner: () => Boolean): Unit = while (batchRunner()) {}
}

/**
 * A trigger executor that runs a batch every `intervalMs` milliseconds.
 */
case class ProcessingTimeExecutor(
    processingTimeTrigger: ProcessingTimeTrigger,
    clock: Clock = new SystemClock())
  extends TriggerExecutor with Logging {

  private val intervalMs = processingTimeTrigger.intervalMs
  require(intervalMs >= 0)

  override def execute(triggerHandler: () => Boolean): Unit = {
    while (true) {
      val triggerTimeMs = clock.getTimeMillis
      val nextTriggerTimeMs = nextBatchTime(triggerTimeMs)
      val terminated = !triggerHandler()
      if (intervalMs > 0) {
        val batchElapsedTimeMs = clock.getTimeMillis - triggerTimeMs
        if (batchElapsedTimeMs > intervalMs) {
          notifyBatchFallingBehind(batchElapsedTimeMs)
        }
        if (terminated) {
          return
        }
        clock.waitTillTime(nextTriggerTimeMs)
      } else {
        if (terminated) {
          return
        }
      }
    }
  }

  /** Called when a batch falls behind */
  def notifyBatchFallingBehind(realElapsedTimeMs: Long): Unit = {
    logWarning("Current batch is falling behind. The trigger interval is " +
      s"${intervalMs} milliseconds, but spent ${realElapsedTimeMs} milliseconds")
  }

  /**
   * Returns the start time in milliseconds for the next batch interval, given the current time.
   * Note that a batch interval is inclusive with respect to its start time, and thus calling
   * `nextBatchTime` with the result of a previous call should return the next interval. (i.e. given
   * an interval of `100 ms`, `nextBatchTime(nextBatchTime(0)) = 200` rather than `0`).
   */
  def nextBatchTime(now: Long): Long = {
    if (intervalMs == 0) now else now / intervalMs * intervalMs + intervalMs
  }
}

相关信息

spark 源码目录

相关文章

spark AvailableNowDataStreamWrapper 源码

spark AvailableNowMicroBatchStreamWrapper 源码

spark AvailableNowSourceWrapper 源码

spark CheckpointFileManager 源码

spark CommitLog 源码

spark CompactibleFileStreamLog 源码

spark ContinuousRecordEndpoint 源码

spark EventTimeWatermarkExec 源码

spark FileStreamOptions 源码

spark FileStreamSink 源码