org.apache.spark.rdd.RDDOperationScope Scala Examples
The following examples show how to use org.apache.spark.rdd.RDDOperationScope.
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: RDDInfo.scala From drizzle-spark with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDD, RDDOperationScope} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, var name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val callSite: String = "", val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.creationSite.shortForm, rdd.scope) } }
Example 2
Source File: RDDInfo.scala From sparkoscope with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDD, RDDOperationScope} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, var name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val callSite: String = "", val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.creationSite.shortForm, rdd.scope) } }
Example 3
Source File: RDDInfo.scala From multi-tenancy-spark with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDD, RDDOperationScope} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, var name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val callSite: String = "", val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.creationSite.shortForm, rdd.scope) } }
Example 4
Source File: RDDInfo.scala From iolap with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDDOperationScope, RDD} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, val name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize + externalBlockStoreSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; ExternalBlockStoreSize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(externalBlockStoreSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.scope) } }
Example 5
Source File: RDDInfo.scala From spark1.52 with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDDOperationScope, RDD} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, val name: String, val numPartitions: Int,//分区数 var storageLevel: StorageLevel,//存储级别 val parentIds: Seq[Int],//父RDD列表 val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0//缓存分区数 var memSize = 0L//内存大小 var diskSize = 0L//硬盘大小 var externalBlockStoreSize = 0L//扩展块存储大小 //是否缓存, def isCached: Boolean = (memSize + diskSize + externalBlockStoreSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; ExternalBlockStoreSize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(externalBlockStoreSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id)//返回RDD依赖的父列表 new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.scope) } }
Example 6
Source File: RDDInfo.scala From Spark-2.3.1 with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDD, RDDOperationScope} import org.apache.spark.util.Utils @DeveloperApi class RDDInfo( val id: Int, var name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val callSite: String = "", val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.creationSite.shortForm, rdd.scope) } }
Example 7
Source File: RDDInfo.scala From BigDatalog with Apache License 2.0 | 5 votes |
package org.apache.spark.storage import org.apache.spark.annotation.DeveloperApi import org.apache.spark.rdd.{RDDOperationScope, RDD} import org.apache.spark.util.{CallSite, Utils} @DeveloperApi class RDDInfo( val id: Int, val name: String, val numPartitions: Int, var storageLevel: StorageLevel, val parentIds: Seq[Int], val callSite: String = "", val scope: Option[RDDOperationScope] = None) extends Ordered[RDDInfo] { var numCachedPartitions = 0 var memSize = 0L var diskSize = 0L var externalBlockStoreSize = 0L def isCached: Boolean = (memSize + diskSize + externalBlockStoreSize > 0) && numCachedPartitions > 0 override def toString: String = { import Utils.bytesToString ("RDD \"%s\" (%d) StorageLevel: %s; CachedPartitions: %d; TotalPartitions: %d; " + "MemorySize: %s; ExternalBlockStoreSize: %s; DiskSize: %s").format( name, id, storageLevel.toString, numCachedPartitions, numPartitions, bytesToString(memSize), bytesToString(externalBlockStoreSize), bytesToString(diskSize)) } override def compare(that: RDDInfo): Int = { this.id - that.id } } private[spark] object RDDInfo { def fromRdd(rdd: RDD[_]): RDDInfo = { val rddName = Option(rdd.name).getOrElse(Utils.getFormattedClassName(rdd)) val parentIds = rdd.dependencies.map(_.rdd.id) new RDDInfo(rdd.id, rddName, rdd.partitions.length, rdd.getStorageLevel, parentIds, rdd.creationSite.shortForm, rdd.scope) } }