SparkEnv
源码版本2.4.7
SparkContext有一核心属性_env即SparkEnv,持有所有spark运行实例的环境对象,序列化、RPCEnv、块管理、MapOutputTracker(shuffle输出相关的记录)等等
首先看看其基本属性
class SparkEnv (
val executorId: String,
private[spark] val rpcEnv: RpcEnv,
val serializer: Serializer,
val closureSerializer: Serializer,
val serializerManager: SerializerManager,
val mapOutputTracker: MapOutputTracker,
val shuffleManager: ShuffleManager,
val broadcastManager: BroadcastManager,
val blockManager: BlockManager,
val securityManager: SecurityManager,
val metricsSystem: MetricsSystem,
val memoryManager: MemoryManager,
val outputCommitCoordinator: OutputCommitCoordinator,
val conf: SparkConf)
RpcEnv 各个组件之间通信的执行环境
SerializerManager 对象在通用网络传输或者写入序列化
MapOutputTracker 用于跟踪Map阶段任务的输出状态，此状态便于Reduce阶段任务获取地址及中间结果
ShuffleManager 负责管理本地及远程的Block数据的shuffle操作
BroadcastManager 将配置信息和序列化后的RDD、Job以及ShuffleDependency等信息在本地存储
BlockManager 负责对Block的管理，管理整个Spark运行时的数据读写的
SecurityManager 主要对账户、权限及身份认证进行设置与管理。
MemoryManager 一个抽象的内存管理器，用于执行内存如何在执行和存储之间共享。
MetricsSystem 各种指标的度量系统
sparkenv创建过程
/**
* Helper method to create a SparkEnv for a driver or an executor.
*/
private def create(
conf: SparkConf,
executorId: String,
bindAddress: String,
advertiseAddress: String,
port: Option[Int],
isLocal: Boolean,
numUsableCores: Int,
ioEncryptionKey: Option[Array[Byte]],
listenerBus: LiveListenerBus = null,
mockOutputCommitCoordinator: Option[OutputCommitCoordinator] = None): SparkEnv = {
val isDriver = executorId == SparkContext.DRIVER_IDENTIFIER
// Listener bus is only used on the driver
if (isDriver) {
assert(listenerBus != null, "Attempted to create driver SparkEnv with null listener bus!")
}
val securityManager = new SecurityManager(conf, ioEncryptionKey)
if (isDriver) {
securityManager.initializeAuth()
}
ioEncryptionKey.foreach { _ =>
if (!securityManager.isEncryptionEnabled()) {
logWarning("I/O encryption enabled without RPC encryption: keys will be visible on the " +
"wire.")
}
}
val systemName = if (isDriver) driverSystemName else executorSystemName
val rpcEnv = RpcEnv.create(systemName, bindAddress, advertiseAddress, port.getOrElse(-1), conf,
securityManager, numUsableCores, !isDriver)
// Figure out which port RpcEnv actually bound to in case the original port is 0 or occupied.
if (isDriver) {
conf.set("spark.driver.port", rpcEnv.address.port.toString)
}
// Create an instance of the class with the given name, possibly initializing it with our conf
def instantiateClass[T](className: String): T = {
val cls = Utils.classForName(className)
// Look for a constructor taking a SparkConf and a boolean isDriver, then one taking just
// SparkConf, then one taking no arguments
try {
cls.getConstructor(classOf[SparkConf], java.lang.Boolean.TYPE)
.newInstance(conf, new java.lang.Boolean(isDriver))
.asInstanceOf[T]
} catch {
case _: NoSuchMethodException =>
try {
cls.getConstructor(classOf[SparkConf]).newInstance(conf).asInstanceOf[T]
} catch {
case _: NoSuchMethodException =>
cls.getConstructor().newInstance().asInstanceOf[T]
}
}
}
// Create an instance of the class named by the given SparkConf property, or defaultClassName
// if the property is not set, possibly initializing it with our conf
def instantiateClassFromConf[T](propertyName: String, defaultClassName: String): T = {
instantiateClass[T](conf.get(propertyName, defaultClassName))
}
val serializer = instantiateClassFromConf[Serializer](
"spark.serializer", "org.apache.spark.serializer.JavaSerializer")
logDebug(s"Using serializer: ${serializer.getClass}")
val serializerManager = new SerializerManager(serializer, conf, ioEncryptionKey)
val closureSerializer = new JavaSerializer(conf)
def registerOrLookupEndpoint(
name: String, endpointCreator: => RpcEndpoint):
RpcEndpointRef = {
if (isDriver) {
logInfo("Registering " + name)
rpcEnv.setupEndpoint(name, endpointCreator)
} else {
RpcUtils.makeDriverRef(name, conf, rpcEnv)
}
}
val broadcastManager = new BroadcastManager(isDriver, conf, securityManager)
val mapOutputTracker = if (isDriver) {
new MapOutputTrackerMaster(conf, broadcastManager, isLocal)
} else {
new MapOutputTrackerWorker(conf)
}
// Have to assign trackerEndpoint after initialization as MapOutputTrackerEndpoint
// requires the MapOutputTracker itself
mapOutputTracker.trackerEndpoint = registerOrLookupEndpoint(MapOutputTracker.ENDPOINT_NAME,
new MapOutputTrackerMasterEndpoint(
rpcEnv, mapOutputTracker.asInstanceOf[MapOutputTrackerMaster], conf))
// Let the user specify short names for shuffle managers
val shortShuffleMgrNames = Map(
"sort" -> classOf[org.apache.spark.shuffle.sort.SortShuffleManager].getName,
"tungsten-sort" -> classOf[org.apache.spark.shuffle.sort.SortShuffleManager].getName)
val shuffleMgrName = conf.get("spark.shuffle.manager", "sort")
val shuffleMgrClass =
shortShuffleMgrNames.getOrElse(shuffleMgrName.toLowerCase(Locale.ROOT), shuffleMgrName)
val shuffleManager = instantiateClass[ShuffleManager](shuffleMgrClass)
val useLegacyMemoryManager = conf.getBoolean("spark.memory.useLegacyMode", false)
val memoryManager: MemoryManager =
if (useLegacyMemoryManager) {
new StaticMemoryManager(conf, numUsableCores)
} else {
UnifiedMemoryManager(conf, numUsableCores)
}
val blockManagerPort = if (isDriver) {
conf.get(DRIVER_BLOCK_MANAGER_PORT)
} else {
conf.get(BLOCK_MANAGER_PORT)
}
val blockTransferService =
new NettyBlockTransferService(conf, securityManager, bindAddress, advertiseAddress,
blockManagerPort, numUsableCores)
val blockManagerMaster = new BlockManagerMaster(registerOrLookupEndpoint(
BlockManagerMaster.DRIVER_ENDPOINT_NAME,
new BlockManagerMasterEndpoint(rpcEnv, isLocal, conf, listenerBus)),
conf, isDriver)
// NB: blockManager is not valid until initialize() is called later.
val blockManager = new BlockManager(executorId, rpcEnv, blockManagerMaster,
serializerManager, conf, memoryManager, mapOutputTracker, shuffleManager,
blockTransferService, securityManager, numUsableCores)
val metricsSystem = if (isDriver) {
// Don't start metrics system right now for Driver.
// We need to wait for the task scheduler to give us an app ID.
// Then we can start the metrics system.
MetricsSystem.createMetricsSystem("driver", conf, securityManager)
} else {
// We need to set the executor ID before the MetricsSystem is created because sources and
// sinks specified in the metrics configuration file will want to incorporate this executor's
// ID into the metrics they report.
conf.set("spark.executor.id", executorId)
val ms = MetricsSystem.createMetricsSystem("executor", conf, securityManager)
ms.start()
ms
}
val outputCommitCoordinator = mockOutputCommitCoordinator.getOrElse {
new OutputCommitCoordinator(conf, isDriver)
}
val outputCommitCoordinatorRef = registerOrLookupEndpoint("OutputCommitCoordinator",
new OutputCommitCoordinatorEndpoint(rpcEnv, outputCommitCoordinator))
outputCommitCoordinator.coordinatorRef = Some(outputCommitCoordinatorRef)
val envInstance = new SparkEnv(
executorId,
rpcEnv,
serializer,
closureSerializer,
serializerManager,
mapOutputTracker,
shuffleManager,
broadcastManager,
blockManager,
securityManager,
metricsSystem,
memoryManager,
outputCommitCoordinator,
conf)
// Add a reference to tmp dir created by driver, we will delete this tmp dir when stop() is
// called, and we only need to do it for driver. Because driver may run as a service, and if we
// don't delete this tmp dir when sc is stopped, then will create too many tmp dirs.
if (isDriver) {
val sparkFilesDir = Utils.createTempDir(Utils.getLocalDir(conf), "userFiles").getAbsolutePath
envInstance.driverTmpDir = Some(sparkFilesDir)
}
envInstance
}
优先关注BlockManager,看看其如何管理存储
// NB: blockManager is not valid until initialize() is called later.
val blockManager = new BlockManager(executorId, rpcEnv, blockManagerMaster,
serializerManager, conf, memoryManager, mapOutputTracker, shuffleManager,
blockTransferService, securityManager, numUsableCores)
存储分为内存、磁盘,内存又依赖于memoryManager,磁盘则由diskBlockManager管控,继续看memoryManager的构成
// Actual storage of where blocks are kept
private[spark] val memoryStore =
new MemoryStore(conf, blockInfoManager, serializerManager, memoryManager, this)
private[spark] val diskStore = new DiskStore(conf, diskBlockManager, securityManager)
memoryManager.setMemoryStore(memoryStore)
UnifiedMemoryManager,默认预留300MB内存
用来存储内存= ((系统内存-预留内存)x0.6)x0.5
堆内、对外内存公共组成memorystore
object UnifiedMemoryManager {
// Set aside a fixed amount of memory for non-storage, non-execution purposes.
// This serves a function similar to `spark.memory.fraction`, but guarantees that we reserve
// sufficient memory for the system even for small heaps. E.g. if we have a 1GB JVM, then
// the memory used for execution and storage will be (1024 - 300) * 0.6 = 434MB by default.
//默认预留300MB
private val RESERVED_SYSTEM_MEMORY_BYTES = 300 * 1024 * 1024
def apply(conf: SparkConf, numCores: Int): UnifiedMemoryManager = {
val maxMemory = getMaxMemory(conf)
new UnifiedMemoryManager(
conf,
maxHeapMemory = maxMemory,
// 存储可使用的内存是 getMaxMemory(计算和存储总内存的)百分之五十
onHeapStorageRegionSize =
(maxMemory * conf.getDouble("spark.memory.storageFraction", 0.5)).toLong,
numCores = numCores)
}
/**
* Return the total amount of memory shared between execution and storage, in bytes.
*/
private def getMaxMemory(conf: SparkConf): Long = {
//Xmx
val systemMemory = conf.getLong("spark.testing.memory", Runtime.getRuntime.maxMemory)
val reservedMemory = conf.getLong("spark.testing.reservedMemory",
if (conf.contains("spark.testing")) 0 else RESERVED_SYSTEM_MEMORY_BYTES)
val minSystemMemory = (reservedMemory * 1.5).ceil.toLong
//开辟内存小于450MB，进程不能启动
if (systemMemory < minSystemMemory) {
throw new IllegalArgumentException(s"System memory $systemMemory must " +
s"be at least $minSystemMemory. Please increase heap size using the --driver-memory " +
s"option or spark.driver.memory in Spark configuration.")
}
// SPARK-12759 Check executor memory to fail fast if memory is insufficient
if (conf.contains("spark.executor.memory")) {
val executorMemory = conf.getSizeAsBytes("spark.executor.memory")
if (executorMemory < minSystemMemory) {
throw new IllegalArgumentException(s"Executor memory $executorMemory must be at least " +
s"$minSystemMemory. Please increase executor memory using the " +
s"--executor-memory option or spark.executor.memory in Spark configuration.")
}
}
//开辟内存 减去 预留内存 = 可用内存
val usableMemory = systemMemory - reservedMemory
val memoryFraction = conf.getDouble("spark.memory.fraction", 0.6)
// 用来计算和存储的内存总共占可用内存的百分之六十
(usableMemory * memoryFraction).toLong
}
}
BlockManagerMaster的作用是对存在于Executor或Driver上的BlockManager进行统一管理
Executor与Driver关于BlockManager的交互都依赖于BlockManagerMaster
无论是Driver还是Executor，它们的BlockManagerMaster的driverEndpoint属性都将持有BlockManagerMasterEndpoint的RpcEndpiointRef
无论是Driver还是Executor，每个BlockManager都拥有自己的BlockManagerSlaveEndpoint，且BlockManager的slaveEndpoint属性保存着各自BlockManagerSlaveEndpoint的RpcEndpointRef
val blockManagerMaster = new BlockManagerMaster(registerOrLookupEndpoint(
BlockManagerMaster.DRIVER_ENDPOINT_NAME,
//重点:此处的new没有被执行,而是取决于registerOrLookupEndpoint方法内部的判断,只有isDrver=true时才new BlockManagerMasterEndpoint
new BlockManagerMasterEndpoint(rpcEnv, isLocal, conf, listenerBus)),
conf, isDriver)
// 根据isDriver注册blockMasterEndpoint还是EndpointRef
def registerOrLookupEndpoint(
name: String, endpointCreator: => RpcEndpoint):
RpcEndpointRef = {
if (isDriver) {
logInfo("Registering " + name)
rpcEnv.setupEndpoint(name, endpointCreator)
} else {
RpcUtils.makeDriverRef(name, conf, rpcEnv)
}
}
// NB: blockManager is not valid until initialize() is called later.
val blockManager = new BlockManager(executorId, rpcEnv, blockManagerMaster,
serializerManager, conf, memoryManager, mapOutputTracker, shuffleManager,
blockTransferService, securityManager, numUsableCores)
//blockManager成员属性
private val slaveEndpoint = rpcEnv.setupEndpoint(
"BlockManagerEndpoint" + BlockManager.ID_GENERATOR.next,
new BlockManagerSlaveEndpoint(rpcEnv, this, mapOutputTracker))
版权声明：本文为wangxilong1991原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。