val shortShuffleMgrNames = Map(
"hash" -> "org.apache.spark.shuffle.hash.HashShuffleManager",
"sort" -> "org.apache.spark.shuffle.sort.SortShuffleManager",
"tungsten-sort" -> "org.apache.spark.shuffle.sort.SortShuffleManager")
val shuffleMgrName = conf.get("spark.shuffle.manager", "sort")
val shuffleMgrClass = shortShuffleMgrNames.getOrElse(shuffleMgrName.toLowerCase, shuffleMgrName)
val shuffleManager = instantiateClass[ShuffleManager](shuffleMgrClass)
override def runTask(context: TaskContext): MapStatus = {
// Deserialize the RDD using the broadcast variable.
val deserializeStartTime = System.currentTimeMillis()
val ser = SparkEnv.get.closureSerializer.newInstance()
val (rdd, dep) = ser.deserialize[(RDD[_], ShuffleDependency[_, _, _])](
ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
_executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime
metrics = Some(context.taskMetrics)
var writer: ShuffleWriter[Any, Any] = null
try {
val manager = SparkEnv.get.shuffleManager
writer = manager.getWriter[Any, Any](dep.shuffleHandle, partitionId, context)
writer.write(rdd.iterator(partition, context).asInstanceOf[Iterator[_ <: Product2[Any, Any]]])
writer.stop(success = true).get
} catch {
case e: Exception =>
try {
if (writer != null) {
writer.stop(success = false)
}
} catch {
case e: Exception =>
log.debug("Could not stop writer", e)
}
throw e
}
}
/** Write a bunch of records to this task's output */
override def write(records: Iterator[Product2[K, V]]): Unit = {
sorter = if (dep.mapSideCombine) {
require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
new ExternalSorter[K, V, C](
context, dep.aggregator, Some(dep.partitioner), dep.keyOrdering, dep.serializer)
} else {
// In this case we pass neither an aggregator nor an ordering to the sorter, because we don't
// care whether the keys get sorted in each partition; that will be done on the reduce side
// if the operation being run is sortByKey.
new ExternalSorter[K, V, V](
context, aggregator = None, Some(dep.partitioner), ordering = None, dep.serializer)
}
sorter.insertAll(records)
// Don't bother including the time to open the merged output file in the shuffle write time,
// because it just opens a single file, so is typically too fast to measure accurately
// (see SPARK-3570).
val output = shuffleBlockResolver.getDataFile(dep.shuffleId, mapId)
val tmp = Utils.tempFileWith(output)
try {
val blockId = ShuffleBlockId(dep.shuffleId, mapId, IndexShuffleBlockResolver.NOOP_REDUCE_ID)
val partitionLengths = sorter.writePartitionedFile(blockId, tmp)
shuffleBlockResolver.writeIndexFileAndCommit(dep.shuffleId, mapId, partitionLengths, tmp)
mapStatus = MapStatus(blockManager.shuffleServerId, partitionLengths)
} finally {
if (tmp.exists() && !tmp.delete()) {
logError(s"Error while deleting temp file ${tmp.getAbsolutePath}")
}
}
}@volatile private var map = new PartitionedAppendOnlyMap[K, C]
def insertAll(records: Iterator[Product2[K, V]]): Unit = {
// TODO: stop combining if we find that the reduction factor isn't high
val shouldCombine = aggregator.isDefined
if (shouldCombine) {
// Combine values in-memory first using our AppendOnlyMap
val mergeValue = aggregator.get.mergeValue
val createCombiner = aggregator.get.createCombiner
var kv: Product2[K, V] = null
val update = (hadValue: Boolean, oldValue: C) => {
if (hadValue) mergeValue(oldValue, kv._2) else createCombiner(kv._2)
}
while (records.hasNext) {
addElementsRead()
kv = records.next()
map.changeValue((getPartition(kv._1), kv._1), update)
maybeSpillCollection(usingMap = true)
}
} else {
// Stick values into our buffer
while (records.hasNext) {
addElementsRead()
val kv = records.next()
buffer.insert(getPartition(kv._1), kv._1, kv._2.asInstanceOf[C])
maybeSpillCollection(usingMap = false)
}
}
}
/**
* Spill the current in-memory collection to disk if needed.
*
* @param usingMap whether we're using a map or buffer as our current in-memory collection
*/
private def maybeSpillCollection(usingMap: Boolean): Unit = {
var estimatedSize = 0L
if (usingMap) {
estimatedSize = map.estimateSize()
if (maybeSpill(map, estimatedSize)) {
map = new PartitionedAppendOnlyMap[K, C]
}
} else {
estimatedSize = buffer.estimateSize()
if (maybeSpill(buffer, estimatedSize)) {
buffer = new PartitionedPairBuffer[K, C]
}
}
if (estimatedSize > _peakMemoryUsedBytes) {
_peakMemoryUsedBytes = estimatedSize
}
}
/**
* Spills the current in-memory collection to disk if needed. Attempts to acquire more
* memory before spilling.
*
* @param collection collection to spill to disk
* @param currentMemory estimated size of the collection in bytes
* @return true if `collection` was spilled to disk; false otherwise
*/
protected def maybeSpill(collection: C, currentMemory: Long): Boolean = {
var shouldSpill = false
if (elementsRead % 32 == 0 && currentMemory >= myMemoryThreshold) {
// Claim up to double our current memory from the shuffle memory pool
val amountToRequest = 2 * currentMemory - myMemoryThreshold
val granted = acquireOnHeapMemory(amountToRequest)
myMemoryThreshold += granted
// If we were granted too little memory to grow further (either tryToAcquire returned 0,
// or we already had more memory than myMemoryThreshold), spill the current collection
shouldSpill = currentMemory >= myMemoryThreshold
}
shouldSpill = shouldSpill || _elementsRead > numElementsForceSpillThreshold
// Actually spill
if (shouldSpill) {
_spillCount += 1
logSpillage(currentMemory)
spill(collection)
_elementsRead = 0
_memoryBytesSpilled += currentMemory
releaseMemory()
}
shouldSpill
}
/**
* Spill our in-memory collection to a sorted file that we can merge later.
* We add this file into `spilledFiles` to find it later.
*
* @param collection whichever collection we're using (map or buffer)
*/
override protected[this] def spill(collection: WritablePartitionedPairCollection[K, C]): Unit = {
val inMemoryIterator = collection.destructiveSortedWritablePartitionedIterator(comparator)
val spillFile = spillMemoryIteratorToDisk(inMemoryIterator)
spills.append(spillFile)
}/**
* Implementation of WritablePartitionedPairCollection that wraps a map in which the keys are tuples
* of (partition ID, K)
*/
private[spark] class PartitionedAppendOnlyMap[K, V]
extends SizeTrackingAppendOnlyMap[(Int, K), V] with WritablePartitionedPairCollection[K, V] {
def partitionedDestructiveSortedIterator(keyComparator: Option[Comparator[K]])
: Iterator[((Int, K), V)] = {
val comparator = keyComparator.map(partitionKeyComparator).getOrElse(partitionComparator)
destructiveSortedIterator(comparator)
}
def insert(partition: Int, key: K, value: V): Unit = {
update((partition, key), value)
}
}
/**
* A comparator for (Int, K) pairs that orders them both by their partition ID and a key ordering.
*/
def partitionKeyComparator[K](keyComparator: Comparator[K]): Comparator[(Int, K)] = {
new Comparator[(Int, K)] {
override def compare(a: (Int, K), b: (Int, K)): Int = {
val partitionDiff = a._1 - b._1
if (partitionDiff != 0) {
partitionDiff
} else {
keyComparator.compare(a._2, b._2)
}
}
}
}
}/**
* Spill contents of in-memory iterator to a temporary file on disk.
*/
private[this] def spillMemoryIteratorToDisk(inMemoryIterator: WritablePartitionedIterator)
: SpilledFile = {
// Because these files may be read during shuffle, their compression must be controlled by
// spark.shuffle.compress instead of spark.shuffle.spill.compress, so we need to use
// createTempShuffleBlock here; see SPARK-3426 for more context.
val (blockId, file) = diskBlockManager.createTempShuffleBlock()
// These variables are reset after each flush
var objectsWritten: Long = 0
var spillMetrics: ShuffleWriteMetrics = null
var writer: DiskBlockObjectWriter = null
def openWriter(): Unit = {
assert (writer == null && spillMetrics == null)
spillMetrics = new ShuffleWriteMetrics
writer = blockManager.getDiskWriter(blockId, file, serInstance, fileBufferSize, spillMetrics)
}
openWriter()
// List of batch sizes (bytes) in the order they are written to disk
val batchSizes = new ArrayBuffer[Long]
// How many elements we have in each partition
val elementsPerPartition = new Array[Long](numPartitions)
// Flush the disk writer's contents to disk, and update relevant variables.
// The writer is closed at the end of this process, and cannot be reused.
def flush(): Unit = {
val w = writer
writer = null
w.commitAndClose()
_diskBytesSpilled += spillMetrics.shuffleBytesWritten
batchSizes.append(spillMetrics.shuffleBytesWritten)
spillMetrics = null
objectsWritten = 0
}
var success = false
try {
while (inMemoryIterator.hasNext) {
val partitionId = inMemoryIterator.nextPartition()
require(partitionId >= 0 && partitionId < numPartitions,
s"partition Id: ${partitionId} should be in the range [0, ${numPartitions})")
inMemoryIterator.writeNext(writer)
elementsPerPartition(partitionId) += 1
objectsWritten += 1
if (objectsWritten == serializerBatchSize) {
flush()
openWriter()
}
}
if (objectsWritten > 0) {
flush()
} else if (writer != null) {
val w = writer
writer = null
w.revertPartialWritesAndClose()
}
success = true
} finally {
if (!success) {
// This code path only happens if an exception was thrown above before we set success;
// close our stuff and let the exception be thrown further
if (writer != null) {
writer.revertPartialWritesAndClose()
}
if (file.exists()) {
if (!file.delete()) {
logWarning(s"Error deleting ${file}")
}
}
}
}
SpilledFile(file, blockId, batchSizes.toArray, elementsPerPartition)
}
/** Write a bunch of records to this task's output */
override def write(records: Iterator[Product2[K, V]]): Unit = {
sorter = if (dep.mapSideCombine) {
require(dep.aggregator.isDefined, "Map-side combine without Aggregator specified!")
new ExternalSorter[K, V, C](
context, dep.aggregator, Some(dep.partitioner), dep.keyOrdering, dep.serializer)
} else {
// In this case we pass neither an aggregator nor an ordering to the sorter, because we don't
// care whether the keys get sorted in each partition; that will be done on the reduce side
// if the operation being run is sortByKey.
new ExternalSorter[K, V, V](
context, aggregator = None, Some(dep.partitioner), ordering = None, dep.serializer)
}
sorter.insertAll(records)
// Don't bother including the time to open the merged output file in the shuffle write time,
// because it just opens a single file, so is typically too fast to measure accurately
// (see SPARK-3570).
val output = shuffleBlockResolver.getDataFile(dep.shuffleId, mapId)
val tmp = Utils.tempFileWith(output)
try {
val blockId = ShuffleBlockId(dep.shuffleId, mapId, IndexShuffleBlockResolver.NOOP_REDUCE_ID)
val partitionLengths = sorter.writePartitionedFile(blockId, tmp)
shuffleBlockResolver.writeIndexFileAndCommit(dep.shuffleId, mapId, partitionLengths, tmp)
mapStatus = MapStatus(blockManager.shuffleServerId, partitionLengths)
} finally {
if (tmp.exists() && !tmp.delete()) {
logError(s"Error while deleting temp file ${tmp.getAbsolutePath}")
}
}
}
/**
* Write all the data added into this ExternalSorter into a file in the disk store. This is
* called by the SortShuffleWriter.
*
* @param blockId block ID to write to. The index file will be blockId.name + ".index".
* @return array of lengths, in bytes, of each partition of the file (used by map output tracker)
*/
def writePartitionedFile(
blockId: BlockId,
outputFile: File): Array[Long] = {
// Track location of each range in the output file
val lengths = new Array[Long](numPartitions)
if (spills.isEmpty) {
// Case where we only have in-memory data
val collection = if (aggregator.isDefined) map else buffer
val it = collection.destructiveSortedWritablePartitionedIterator(comparator)
while (it.hasNext) {
val writer = blockManager.getDiskWriter(blockId, outputFile, serInstance, fileBufferSize,
context.taskMetrics.shuffleWriteMetrics.get)
val partitionId = it.nextPartition()
while (it.hasNext && it.nextPartition() == partitionId) {
it.writeNext(writer)
}
writer.commitAndClose()
val segment = writer.fileSegment()
lengths(partitionId) = segment.length
}
} else {
// We must perform merge-sort; get an iterator by partition and write everything directly.
for ((id, elements) <- this.partitionedIterator) {
if (elements.hasNext) {
val writer = blockManager.getDiskWriter(blockId, outputFile, serInstance, fileBufferSize,
context.taskMetrics.shuffleWriteMetrics.get)
for (elem <- elements) {
writer.write(elem._1, elem._2)
}
writer.commitAndClose()
val segment = writer.fileSegment()
lengths(id) = segment.length
}
}
}
context.taskMetrics().incMemoryBytesSpilled(memoryBytesSpilled)
context.taskMetrics().incDiskBytesSpilled(diskBytesSpilled)
context.internalMetricsToAccumulators(
InternalAccumulator.PEAK_EXECUTION_MEMORY).add(peakMemoryUsedBytes)
lengths
}
/**
* Return an iterator over all the data written to this object, grouped by partition and
* aggregated by the requested aggregator. For each partition we then have an iterator over its
* contents, and these are expected to be accessed in order (you can't "skip ahead" to one
* partition without reading the previous one). Guaranteed to return a key-value pair for each
* partition, in order of partition ID.
*
* For now, we just merge all the spilled files in once pass, but this can be modified to
* support hierarchical merging.
* Exposed for testing.
*/
def partitionedIterator: Iterator[(Int, Iterator[Product2[K, C]])] = {
val usingMap = aggregator.isDefined
val collection: WritablePartitionedPairCollection[K, C] = if (usingMap) map else buffer
if (spills.isEmpty) {
// Special case: if we have only in-memory data, we don't need to merge streams, and perhaps
// we don't even need to sort by anything other than partition ID
if (!ordering.isDefined) {
// The user hasn't requested sorted keys, so only sort by partition ID, not key
groupByPartition(destructiveIterator(collection.partitionedDestructiveSortedIterator(None)))
} else {
// We do need to sort by both partition ID and key
groupByPartition(destructiveIterator(
collection.partitionedDestructiveSortedIterator(Some(keyComparator))))
}
} else {
// Merge spilled and in-memory data
merge(spills, destructiveIterator(
collection.partitionedDestructiveSortedIterator(comparator)))
}
}
/**
* Merge a sequence of sorted files, giving an iterator over partitions and then over elements
* inside each partition. This can be used to either write out a new file or return data to
* the user.
*
* Returns an iterator over all the data written to this object, grouped by partition. For each
* partition we then have an iterator over its contents, and these are expected to be accessed
* in order (you can't "skip ahead" to one partition without reading the previous one).
* Guaranteed to return a key-value pair for each partition, in order of partition ID.
*/
private def merge(spills: Seq[SpilledFile], inMemory: Iterator[((Int, K), C)])
: Iterator[(Int, Iterator[Product2[K, C]])] = {
val readers = spills.map(new SpillReader(_))
val inMemBuffered = inMemory.buffered
(0 until numPartitions).iterator.map { p =>
val inMemIterator = new IteratorForPartition(p, inMemBuffered)
val iterators = readers.map(_.readNextPartition()) ++ Seq(inMemIterator)
if (aggregator.isDefined) {
// Perform partial aggregation across partitions
(p, mergeWithAggregation(
iterators, aggregator.get.mergeCombiners, keyComparator, ordering.isDefined))
} else if (ordering.isDefined) {
// No aggregator given, but we have an ordering (e.g. used by reduce tasks in sortByKey);
// sort the elements without trying to merge them
(p, mergeSort(iterators, ordering.get))
} else {
(p, iterators.iterator.flatten)
}
}
}
def readNextPartition(): Iterator[Product2[K, C]] = new Iterator[Product2[K, C]] {
val myPartition = nextPartitionToRead
nextPartitionToRead += 1
override def hasNext: Boolean = {
if (nextItem == null) {
nextItem = readNextItem()
if (nextItem == null) {
return false
}
}
assert(lastPartitionId >= myPartition)
// Check that we're still in the right partition; note that readNextItem will have returned
// null at EOF above so we would've returned false there
lastPartitionId == myPartition
}
override def next(): Product2[K, C] = {
if (!hasNext) {
throw new NoSuchElementException
}
val item = nextItem
nextItem = null
item
}
}
/**
* Return the next (K, C) pair from the deserialization stream and update partitionId,
* indexInPartition, indexInBatch and such to match its location.
*
* If the current batch is drained, construct a stream for the next batch and read from it.
* If no more pairs are left, return null.
*/
private def readNextItem(): (K, C) = {
if (finished || deserializeStream == null) {
return null
}
val k = deserializeStream.readKey().asInstanceOf[K]
val c = deserializeStream.readValue().asInstanceOf[C]
lastPartitionId = partitionId
// Start reading the next batch if we're done with this one
indexInBatch += 1
if (indexInBatch == serializerBatchSize) {
indexInBatch = 0
deserializeStream = nextBatchStream()
}
// Update the partition location of the element we're reading
indexInPartition += 1
skipToNextPartition()
// If we've finished reading the last partition, remember that we're done
if (partitionId == numPartitions) {
finished = true
if (deserializeStream != null) {
deserializeStream.close()
}
}
(k, c)
}
/** Construct a stream that only reads from the next batch */
def nextBatchStream(): DeserializationStream = {
// Note that batchOffsets.length = numBatches + 1 since we did a scan above; check whether
// we're still in a valid batch.
if (batchId < batchOffsets.length - 1) {
if (deserializeStream != null) {
deserializeStream.close()
fileStream.close()
deserializeStream = null
fileStream = null
}
val start = batchOffsets(batchId)
fileStream = new FileInputStream(spill.file)
fileStream.getChannel.position(start)
batchId += 1
val end = batchOffsets(batchId)
assert(end >= start, "start = " + start + ", end = " + end +
", batchOffsets = " + batchOffsets.mkString("[", ", ", "]"))
val bufferedStream = new BufferedInputStream(ByteStreams.limit(fileStream, end - start))
val sparkConf = SparkEnv.get.conf
val stream = blockManager.wrapForCompression(spill.blockId,
CryptoStreamUtils.wrapForEncryption(bufferedStream, sparkConf))
serInstance.deserializeStream(stream)
} else {
// No more batches left
cleanup()
null
}
}end
end
微信关注我们
转载内容版权归作者及来源网站所有！
低调大师中文资讯倾力打造互联网数据资讯、行业资源、电子商务、移动互联网、网络营销平台。持续更新报道IT业界、互联网、市场资讯、驱动更新,是最及时权威的产业资讯及硬件资讯报道平台。
马里奥是站在游戏界顶峰的超人气多面角色。马里奥靠吃蘑菇成长，特征是大鼻子、头戴帽子、身穿背带裤，还留着胡子。与他的双胞胎兄弟路易基一起，长年担任任天堂的招牌角色。
Spring框架（Spring Framework）是由Rod Johnson于2002年提出的开源Java企业级应用框架，旨在通过使用JavaBean替代传统EJB实现方式降低企业级编程开发的复杂性。该框架基于简单性、可测试性和松耦合性设计理念，提供核心容器、应用上下文、数据访问集成等模块，支持整合Hibernate、Struts等第三方框架，其适用范围不仅限于服务器端开发，绝大多数Java应用均可从中受益。
Rocky Linux（中文名：洛基）是由Gregory Kurtzer于2020年12月发起的企业级Linux发行版，作为CentOS稳定版停止维护后与RHEL（Red Hat Enterprise Linux）完全兼容的开源替代方案，由社区拥有并管理，支持x86_64、aarch64等架构。其通过重新编译RHEL源代码提供长期稳定性，采用模块化包装和SELinux安全架构，默认包含GNOME桌面环境及XFS文件系统，支持十年生命周期更新。
Sublime Text具有漂亮的用户界面和强大的功能，例如代码缩略图，Python的插件，代码段等。还可自定义键绑定，菜单和工具栏。Sublime Text 的主要功能包括：拼写检查，书签，完整的 Python API ， Goto 功能，即时项目切换，多选择，多窗口等等。Sublime Text 是一个跨平台的编辑器，同时支持Windows、Linux、Mac OS X等操作系统。
扫码在手机上查看文章
扫描二维码，手机阅读更方便
有任何问题或合作意向欢迎联系我们
Email: 99873273@qq.com
QQ: 99873273