org.apache.spark.scheduler.AccumulableInfo Scala Examples

The following examples show how to use org.apache.spark.scheduler.AccumulableInfo. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: SQLMetrics.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.metric

import java.text.NumberFormat
import java.util.Locale

import org.apache.spark.SparkContext
import org.apache.spark.scheduler.AccumulableInfo
import org.apache.spark.util.{AccumulatorContext, AccumulatorV2, Utils}


class SQLMetric(val metricType: String, initValue: Long = 0L) extends AccumulatorV2[Long, Long] {
  // This is a workaround for SPARK-11013.
  // We may use -1 as initial value of the accumulator, if the accumulator is valid, we will
  // update it at the end of task and the value will be at least 0. Then we can filter out the -1
  // values before calculate max, min, etc.
  private[this] var _value = initValue
  private var _zeroValue = initValue

  override def copy(): SQLMetric = {
    val newAcc = new SQLMetric(metricType, _value)
    newAcc._zeroValue = initValue
    newAcc
  }

  override def reset(): Unit = _value = _zeroValue

  override def merge(other: AccumulatorV2[Long, Long]): Unit = other match {
    case o: SQLMetric => _value += o.value
    case _ => throw new UnsupportedOperationException(
      s"Cannot merge ${this.getClass.getName} with ${other.getClass.getName}")
  }

  override def isZero(): Boolean = _value == _zeroValue

  override def add(v: Long): Unit = _value += v

  def +=(v: Long): Unit = _value += v

  override def value: Long = _value

  // Provide special identifier as metadata so we can tell that this is a `SQLMetric` later
  override def toInfo(update: Option[Any], value: Option[Any]): AccumulableInfo = {
    new AccumulableInfo(
      id, name, update, value, true, true, Some(AccumulatorContext.SQL_ACCUM_IDENTIFIER))
  }
}


object SQLMetrics {
  private val SUM_METRIC = "sum"
  private val SIZE_METRIC = "size"
  private val TIMING_METRIC = "timing"

  def createMetric(sc: SparkContext, name: String): SQLMetric = {
    val acc = new SQLMetric(SUM_METRIC)
    acc.register(sc, name = Some(name), countFailedValues = false)
    acc
  }

  
  def stringValue(metricsType: String, values: Seq[Long]): String = {
    if (metricsType == SUM_METRIC) {
      val numberFormat = NumberFormat.getIntegerInstance(Locale.ENGLISH)
      numberFormat.format(values.sum)
    } else {
      val strFormat: Long => String = if (metricsType == SIZE_METRIC) {
        Utils.bytesToString
      } else if (metricsType == TIMING_METRIC) {
        Utils.msDurationToString
      } else {
        throw new IllegalStateException("unexpected metrics type: " + metricsType)
      }

      val validValues = values.filter(_ >= 0)
      val Seq(sum, min, med, max) = {
        val metric = if (validValues.isEmpty) {
          Seq.fill(4)(0L)
        } else {
          val sorted = validValues.sorted
          Seq(sorted.sum, sorted(0), sorted(validValues.length / 2), sorted(validValues.length - 1))
        }
        metric.map(strFormat)
      }
      s"\n$sum ($min, $med, $max)"
    }
  }
}
Example 2
Source File: SQLMetrics.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.metric

import java.text.NumberFormat
import java.util.Locale

import org.apache.spark.SparkContext
import org.apache.spark.scheduler.AccumulableInfo
import org.apache.spark.util.{AccumulatorContext, AccumulatorV2, Utils}


class SQLMetric(val metricType: String, initValue: Long = 0L) extends AccumulatorV2[Long, Long] {
  // This is a workaround for SPARK-11013.
  // We may use -1 as initial value of the accumulator, if the accumulator is valid, we will
  // update it at the end of task and the value will be at least 0. Then we can filter out the -1
  // values before calculate max, min, etc.
  private[this] var _value = initValue
  private var _zeroValue = initValue

  override def copy(): SQLMetric = {
    val newAcc = new SQLMetric(metricType, _value)
    newAcc._zeroValue = initValue
    newAcc
  }

  override def reset(): Unit = _value = _zeroValue

  override def merge(other: AccumulatorV2[Long, Long]): Unit = other match {
    case o: SQLMetric => _value += o.value
    case _ => throw new UnsupportedOperationException(
      s"Cannot merge ${this.getClass.getName} with ${other.getClass.getName}")
  }

  override def isZero(): Boolean = _value == _zeroValue

  override def add(v: Long): Unit = _value += v

  def +=(v: Long): Unit = _value += v

  override def value: Long = _value

  // Provide special identifier as metadata so we can tell that this is a `SQLMetric` later
  override def toInfo(update: Option[Any], value: Option[Any]): AccumulableInfo = {
    new AccumulableInfo(
      id, name, update, value, true, true, Some(AccumulatorContext.SQL_ACCUM_IDENTIFIER))
  }
}


object SQLMetrics {
  private val SUM_METRIC = "sum"
  private val SIZE_METRIC = "size"
  private val TIMING_METRIC = "timing"

  def createMetric(sc: SparkContext, name: String): SQLMetric = {
    val acc = new SQLMetric(SUM_METRIC)
    acc.register(sc, name = Some(name), countFailedValues = false)
    acc
  }

  
  def stringValue(metricsType: String, values: Seq[Long]): String = {
    if (metricsType == SUM_METRIC) {
      val numberFormat = NumberFormat.getIntegerInstance(Locale.US)
      numberFormat.format(values.sum)
    } else {
      val strFormat: Long => String = if (metricsType == SIZE_METRIC) {
        Utils.bytesToString
      } else if (metricsType == TIMING_METRIC) {
        Utils.msDurationToString
      } else {
        throw new IllegalStateException("unexpected metrics type: " + metricsType)
      }

      val validValues = values.filter(_ >= 0)
      val Seq(sum, min, med, max) = {
        val metric = if (validValues.isEmpty) {
          Seq.fill(4)(0L)
        } else {
          val sorted = validValues.sorted
          Seq(sorted.sum, sorted(0), sorted(validValues.length / 2), sorted(validValues.length - 1))
        }
        metric.map(strFormat)
      }
      s"\n$sum ($min, $med, $max)"
    }
  }
}
Example 3
Source File: UIData.scala    From SparkCore   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ui.jobs

import org.apache.spark.JobExecutionStatus
import org.apache.spark.executor.TaskMetrics
import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo}
import org.apache.spark.util.collection.OpenHashSet

import scala.collection.mutable.HashMap

private[jobs] object UIData {

  class ExecutorSummary {
    var taskTime : Long = 0
    var failedTasks : Int = 0
    var succeededTasks : Int = 0
    var inputBytes : Long = 0
    var inputRecords : Long = 0
    var outputBytes : Long = 0
    var outputRecords : Long = 0
    var shuffleRead : Long = 0
    var shuffleReadRecords : Long = 0
    var shuffleWrite : Long = 0
    var shuffleWriteRecords : Long = 0
    var memoryBytesSpilled : Long = 0
    var diskBytesSpilled : Long = 0
  }

  class JobUIData(
    var jobId: Int = -1,
    var submissionTime: Option[Long] = None,
    var completionTime: Option[Long] = None,
    var stageIds: Seq[Int] = Seq.empty,
    var jobGroup: Option[String] = None,
    var status: JobExecutionStatus = JobExecutionStatus.UNKNOWN,
    
  case class TaskUIData(
      var taskInfo: TaskInfo,
      var taskMetrics: Option[TaskMetrics] = None,
      var errorMessage: Option[String] = None)
}
Example 4
Source File: SQLMetrics.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.metric

import java.text.NumberFormat
import java.util.Locale

import org.apache.spark.SparkContext
import org.apache.spark.scheduler.AccumulableInfo
import org.apache.spark.util.{AccumulatorContext, AccumulatorV2, Utils}


class SQLMetric(val metricType: String, initValue: Long = 0L) extends AccumulatorV2[Long, Long] {
  // This is a workaround for SPARK-11013.
  // We may use -1 as initial value of the accumulator, if the accumulator is valid, we will
  // update it at the end of task and the value will be at least 0. Then we can filter out the -1
  // values before calculate max, min, etc.
  private[this] var _value = initValue
  private var _zeroValue = initValue

  override def copy(): SQLMetric = {
    val newAcc = new SQLMetric(metricType, _value)
    newAcc._zeroValue = initValue
    newAcc
  }

  override def reset(): Unit = _value = _zeroValue

  override def merge(other: AccumulatorV2[Long, Long]): Unit = other match {
    case o: SQLMetric => _value += o.value
    case _ => throw new UnsupportedOperationException(
      s"Cannot merge ${this.getClass.getName} with ${other.getClass.getName}")
  }

  override def isZero(): Boolean = _value == _zeroValue

  override def add(v: Long): Unit = _value += v

  def +=(v: Long): Unit = _value += v

  override def value: Long = _value

  // Provide special identifier as metadata so we can tell that this is a `SQLMetric` later
  override def toInfo(update: Option[Any], value: Option[Any]): AccumulableInfo = {
    new AccumulableInfo(
      id, name, update, value, true, true, Some(AccumulatorContext.SQL_ACCUM_IDENTIFIER))
  }
}


object SQLMetrics {
  private val SUM_METRIC = "sum"
  private val SIZE_METRIC = "size"
  private val TIMING_METRIC = "timing"

  def createMetric(sc: SparkContext, name: String): SQLMetric = {
    val acc = new SQLMetric(SUM_METRIC)
    acc.register(sc, name = Some(name), countFailedValues = false)
    acc
  }

  
  def stringValue(metricsType: String, values: Seq[Long]): String = {
    if (metricsType == SUM_METRIC) {
      val numberFormat = NumberFormat.getIntegerInstance(Locale.US)
      numberFormat.format(values.sum)
    } else {
      val strFormat: Long => String = if (metricsType == SIZE_METRIC) {
        Utils.bytesToString
      } else if (metricsType == TIMING_METRIC) {
        Utils.msDurationToString
      } else {
        throw new IllegalStateException("unexpected metrics type: " + metricsType)
      }

      val validValues = values.filter(_ >= 0)
      val Seq(sum, min, med, max) = {
        val metric = if (validValues.isEmpty) {
          Seq.fill(4)(0L)
        } else {
          val sorted = validValues.sorted
          Seq(sorted.sum, sorted(0), sorted(validValues.length / 2), sorted(validValues.length - 1))
        }
        metric.map(strFormat)
      }
      s"\n$sum ($min, $med, $max)"
    }
  }
}
Example 5
Source File: UIData.scala    From iolap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ui.jobs

import org.apache.spark.JobExecutionStatus
import org.apache.spark.executor.TaskMetrics
import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo}
import org.apache.spark.util.collection.OpenHashSet

import scala.collection.mutable.HashMap

private[spark] object UIData {

  class ExecutorSummary {
    var taskTime : Long = 0
    var failedTasks : Int = 0
    var succeededTasks : Int = 0
    var inputBytes : Long = 0
    var inputRecords : Long = 0
    var outputBytes : Long = 0
    var outputRecords : Long = 0
    var shuffleRead : Long = 0
    var shuffleReadRecords : Long = 0
    var shuffleWrite : Long = 0
    var shuffleWriteRecords : Long = 0
    var memoryBytesSpilled : Long = 0
    var diskBytesSpilled : Long = 0
  }

  class JobUIData(
    var jobId: Int = -1,
    var submissionTime: Option[Long] = None,
    var completionTime: Option[Long] = None,
    var stageIds: Seq[Int] = Seq.empty,
    var jobGroup: Option[String] = None,
    var status: JobExecutionStatus = JobExecutionStatus.UNKNOWN,
    
  case class TaskUIData(
      var taskInfo: TaskInfo,
      var taskMetrics: Option[TaskMetrics] = None,
      var errorMessage: Option[String] = None)

  case class ExecutorUIData(
      val startTime: Long,
      var finishTime: Option[Long] = None,
      var finishReason: Option[String] = None)
}
Example 6
Source File: UIData.scala    From spark1.52   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ui.jobs

import org.apache.spark.JobExecutionStatus
import org.apache.spark.executor.TaskMetrics
import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo}
import org.apache.spark.util.collection.OpenHashSet

import scala.collection.mutable
import scala.collection.mutable.HashMap

private[spark] object UIData {

  class ExecutorSummary {
    var taskTime : Long = 0//任务时间
    var failedTasks : Int = 0//失败任务数
    var succeededTasks : Int = 0//完成任务数
    var inputBytes : Long = 0
    var inputRecords : Long = 0
    var outputBytes : Long = 0
    var outputRecords : Long = 0
    var shuffleRead : Long = 0
    var shuffleReadRecords : Long = 0
    var shuffleWrite : Long = 0
    var shuffleWriteRecords : Long = 0
    var memoryBytesSpilled : Long = 0
    var diskBytesSpilled : Long = 0
  }

  class JobUIData(
    var jobId: Int = -1,
    var submissionTime: Option[Long] = None,//提交时间
    var completionTime: Option[Long] = None,//完成时间
    var stageIds: Seq[Int] = Seq.empty,
    var jobGroup: Option[String] = None,
    var status: JobExecutionStatus = JobExecutionStatus.UNKNOWN,
    
  case class TaskUIData(
      var taskInfo: TaskInfo,
      var taskMetrics: Option[TaskMetrics] = None,
      var errorMessage: Option[String] = None)

  case class ExecutorUIData(
      val startTime: Long,
      var finishTime: Option[Long] = None,
      var finishReason: Option[String] = None)
}
Example 7
Source File: UIData.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ui.jobs

import org.apache.spark.JobExecutionStatus
import org.apache.spark.executor.TaskMetrics
import org.apache.spark.scheduler.{AccumulableInfo, TaskInfo}
import org.apache.spark.util.collection.OpenHashSet

import scala.collection.mutable
import scala.collection.mutable.HashMap

private[spark] object UIData {

  class ExecutorSummary {
    var taskTime : Long = 0
    var failedTasks : Int = 0
    var succeededTasks : Int = 0
    var inputBytes : Long = 0
    var inputRecords : Long = 0
    var outputBytes : Long = 0
    var outputRecords : Long = 0
    var shuffleRead : Long = 0
    var shuffleReadRecords : Long = 0
    var shuffleWrite : Long = 0
    var shuffleWriteRecords : Long = 0
    var memoryBytesSpilled : Long = 0
    var diskBytesSpilled : Long = 0
  }

  class JobUIData(
    var jobId: Int = -1,
    var submissionTime: Option[Long] = None,
    var completionTime: Option[Long] = None,
    var stageIds: Seq[Int] = Seq.empty,
    var jobGroup: Option[String] = None,
    var status: JobExecutionStatus = JobExecutionStatus.UNKNOWN,
    
  case class TaskUIData(
      var taskInfo: TaskInfo,
      var taskMetrics: Option[TaskMetrics] = None,
      var errorMessage: Option[String] = None)

  case class ExecutorUIData(
      val startTime: Long,
      var finishTime: Option[Long] = None,
      var finishReason: Option[String] = None)
}