概述
Member fields.
class BlockManagerMasterEndpoint(
override val rpcEnv: RpcEnv,
val isLocal: Boolean,
conf: SparkConf,
listenerBus: LiveListenerBus)
extends ThreadSafeRpcEndpoint with Logging {
// Mapping from block manager id to the block manager's information.
private val blockManagerInfo = new mutable.HashMap[BlockManagerId, BlockManagerInfo]
// Mapping from executor ID to block manager ID.
private val blockManagerIdByExecutor = new mutable.HashMap[String, BlockManagerId]
// Mapping from block id to the set of block managers that have the block.
private val blockLocations = new JHashMap[BlockId, mutable.HashSet[BlockManagerId]]
private val askThreadPool = ThreadUtils.newDaemonCachedThreadPool("block-manager-ask-thread-pool")
private implicit val askExecutionContext = ExecutionContext.fromExecutorService(askThreadPool)
private val topologyMapper = {
val topologyMapperClassName = conf.get(
"spark.storage.replication.topologyMapper", classOf[DefaultTopologyMapper].getName)
val clazz = Utils.classForName(topologyMapperClassName)
val mapper =
clazz.getConstructor(classOf[SparkConf]).newInstance(conf).asInstanceOf[TopologyMapper]
logInfo(s"Using $topologyMapperClassName for getting topology information")
mapper
}
logInfo("BlockManagerMasterEndpoint up")
The RPC list
override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {
case RegisterBlockManager(blockManagerId, maxMemSize, slaveEndpoint) =>
context.reply(register(blockManagerId, maxMemSize, slaveEndpoint))
case _updateBlockInfo @
UpdateBlockInfo(blockManagerId, blockId, storageLevel, deserializedSize, size) =>
context.reply(updateBlockInfo(blockManagerId, blockId, storageLevel, deserializedSize, size))
listenerBus.post(SparkListenerBlockUpdated(BlockUpdatedInfo(_updateBlockInfo)))
case GetLocations(blockId) =>
context.reply(getLocations(blockId))
case GetLocationsMultipleBlockIds(blockIds) =>
context.reply(getLocationsMultipleBlockIds(blockIds))
case GetPeers(blockManagerId) =>
context.reply(getPeers(blockManagerId))
case GetExecutorEndpointRef(executorId) =>
context.reply(getExecutorEndpointRef(executorId))
case GetMemoryStatus =>
context.reply(memoryStatus)
case GetStorageStatus =>
context.reply(storageStatus)
case GetBlockStatus(blockId, askSlaves) =>
context.reply(blockStatus(blockId, askSlaves))
case GetMatchingBlockIds(filter, askSlaves) =>
context.reply(getMatchingBlockIds(filter, askSlaves))
case RemoveRdd(rddId) =>
context.reply(removeRdd(rddId))
case RemoveShuffle(shuffleId) =>
context.reply(removeShuffle(shuffleId))
case RemoveBroadcast(broadcastId, removeFromDriver) =>
context.reply(removeBroadcast(broadcastId, removeFromDriver))
case RemoveBlock(blockId) =>
removeBlockFromWorkers(blockId)
context.reply(true)
case RemoveExecutor(execId) =>
removeExecutor(execId)
context.reply(true)
case StopBlockManagerMaster =>
context.reply(true)
stop()
case BlockManagerHeartbeat(blockManagerId) =>
context.reply(heartbeatReceived(blockManagerId))
case HasCachedBlocks(executorId) =>
blockManagerIdByExecutor.get(executorId) match {
case Some(bm) =>
if (blockManagerInfo.contains(bm)) {
val bmInfo = blockManagerInfo(bm)
context.reply(bmInfo.cachedBlocks.nonEmpty)
} else {
context.reply(false)
}
case None => context.reply(false)
}
}
updateBlockInfo
private def updateBlockInfo(
blockManagerId: BlockManagerId,
blockId: BlockId,
storageLevel: StorageLevel,
memSize: Long,
diskSize: Long): Boolean = {
if (!blockManagerInfo.contains(blockManagerId)) {
if (blockManagerId.isDriver && !isLocal) {
// We intentionally do not register the master (except in local mode),
// so we should not indicate failure.
return true
} else {
return false
}
}
if (blockId == null) {
blockManagerInfo(blockManagerId).updateLastSeenMs()
return true
}
blockManagerInfo(blockManagerId).updateBlockInfo(blockId, storageLevel, memSize, diskSize)
var locations: mutable.HashSet[BlockManagerId] = null
if (blockLocations.containsKey(blockId)) {
locations = blockLocations.get(blockId)
} else {
locations = new mutable.HashSet[BlockManagerId]
blockLocations.put(blockId, locations)
}
if (storageLevel.isValid) {
locations.add(blockManagerId)
} else {
locations.remove(blockManagerId)
}
// Remove the block from master tracking if it has been removed on all slaves.
if (locations.size == 0) {
blockLocations.remove(blockId)
}
true
}
getPeers
/** Get the list of the peers of the given block manager */
private def getPeers(blockManagerId: BlockManagerId): Seq[BlockManagerId] = {
val blockManagerIds = blockManagerInfo.keySet
if (blockManagerIds.contains(blockManagerId)) {
blockManagerIds.filterNot { _.isDriver }.filterNot { _ == blockManagerId }.toSeq
} else {
Seq.empty
}
}
memoryStatus
// Return a map from the block manager id to max memory and remaining memory.
private def memoryStatus: Map[BlockManagerId, (Long, Long)] = {
blockManagerInfo.map { case(blockManagerId, info) =>
(blockManagerId, (info.maxMem, info.remainingMem))
}.toMap
}
storageStatus
private def storageStatus: Array[StorageStatus] = {
blockManagerInfo.map { case (blockManagerId, info) =>
new StorageStatus(blockManagerId, info.maxMem, info.blocks.asScala)
}.toArray
}
最后
以上就是强健草莓为你收集整理的spark 2.1 BlockManagerMasterEndpoint的全部内容,希望文章能够帮你解决spark 2.1 BlockManagerMasterEndpoint所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错,欢迎将靠谱客网站推荐给程序员好友。
本图文内容来源于网友提供,作为学习参考使用,或来自网络收集整理,版权属于原作者所有。
发表评论 取消回复