Spark2.4.0 SparkEnv 源码分析
更多资源
时序图
前置条件
- Hadoop版本: hadoop-2.9.2
- Spark版本: spark-2.4.0-bin-hadoop2.7
- JDK.1.8.0_191
- scala2.11.12
主要内容描述
- SparkEnv对象构建
- SparkEnv类中做如下操作
- ).new SecurityManager()
- ).new NettyRpcEnvFactory()
- ).创建NettyRpcEnv
- ).Utils.startServiceOnPort(启动sparkDriver)
- ). new BroadcastManager
- ).注册端点MapOutputTracker
- ).ShuffleManager:SortShuffleManager
- ).默认内存管理器:UnifiedMemoryManager
- ).注册端点MapOutputTracker
- ).SortShuffleManager
- ).UnifiedMemoryManager
- ).注册端点BlockManagerMaster
- ).new BlockManager
- ).注册端点OutputCommitCoordinator
SparkContext
SparkContext 类构造中调用createSparkEnv
private var _env: SparkEnv = _
// Create the Spark execution environment (cache, map output tracker, etc)
_env = createSparkEnv(_conf, isLocal, listenerBus)
SparkContext.createSparkEnv()
- 调用SparkEnv.createDriverEnv函数,创建SparkEnv对象
// This function allows components created by SparkEnv to be mocked in unit tests:
private[spark] def createSparkEnv(
conf: SparkConf,
isLocal: Boolean,
listenerBus: LiveListenerBus): SparkEnv = {
SparkEnv.createDriverEnv(conf, isLocal, listenerBus, SparkContext.numDriverCores(master, conf))
}
SparkEnv
SparkEnv.createDriverEnv()
- 调用create()方法
/**
* Create a SparkEnv for the driver.
*/
private[spark] def createDriverEnv(
conf: SparkConf,
isLocal: Boolean,
listenerBus: LiveListenerBus,
numCores: Int,
mockOutputCommitCoordinator: Option[OutputCommitCoordinator] = None): SparkEnv = {
assert(conf.contains(DRIVER_HOST_ADDRESS),
s"${DRIVER_HOST_ADDRESS.key} is not set on the driver!")
assert(conf.contains("spark.driver.port"), "spark.driver.port is not set on the driver!")
val bindAddress = conf.get(DRIVER_BIND_ADDRESS)
val advertiseAddress = conf.get(DRIVER_HOST_ADDRESS)
val port = conf.get("spark.driver.port").toInt
val ioEncryptionKey = if (conf.get(IO_ENCRYPTION_ENABLED)) {
Some(CryptoStreamUtils.createKey(conf))
} else {
None
}
create(
conf,
SparkContext.DRIVER_IDENTIFIER,
bindAddress,
advertiseAddress,
Option(port),
isLocal,
numCores,
ioEncryptionKey,
listenerBus = listenerBus,
mockOutputCommitCoordinator = mockOutputCommitCoordinator
)
}
SparkEnv.create()
- ).这个是最重要的方法
- ).SparkEnv对象是在这个方法中构造的
- ).new SecurityManager()
- ).new NettyRpcEnvFactory()
- ).创建NettyRpcEnv
- ).Utils.startServiceOnPort(启动sparkDriver)
- ). new BroadcastManager
- ).注册端点MapOutputTracker
- ).ShuffleManager:SortShuffleManager
- ).默认内存管理器:UnifiedMemoryManager
- ).注册端点MapOutputTracker
- ).SortShuffleManager
- ).UnifiedMemoryManager
- ).注册端点BlockManagerMaster
- ).new BlockManager
- ).注册端点OutputCommitCoordinator
/**
* 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
}
end