原始碼-spark執行流程分析
阿新 • • 發佈：2019-02-18
private def createTaskScheduler(
sc: SparkContext,
master: String): (SchedulerBackend, TaskScheduler) = {
import SparkMasterRegex._
// When running locally, don't try to re-execute tasks on failure.
val MAX_LOCAL_TASK_FAILURES = 1
master match {
case "local" =>
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, 1)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_REGEX(threads) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
val threadCount = if (threads == "*") localCpuCount else threads.toInt
if (threadCount <= 0) {
throw new SparkException(s"Asked to run locally with $threadCount threads")
}
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*, M] means the number of cores on the computer with M failures
// local[N, M] means exactly N threads with M failures
val threadCount = if (threads == "*") localCpuCount else threads.toInt
val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case SPARK_REGEX(sparkUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
// Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
val memoryPerSlaveInt = memoryPerSlave.toInt
if (sc.executorMemory > memoryPerSlaveInt) {
throw new SparkException(
"Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
memoryPerSlaveInt, sc.executorMemory))
}
val scheduler = new TaskSchedulerImpl(sc)
val localCluster = new LocalSparkCluster(
numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt, sc.conf)
val masterUrls = localCluster.start()
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
backend.shutdownCallback = (backend: SparkDeploySchedulerBackend) => {
localCluster.stop()
}
(backend, scheduler)
case "yarn-standalone" | "yarn-cluster" =>
if (master == "yarn-standalone") {
logWarning(
"\"yarn-standalone\" is deprecated as of Spark 1.0. Use \"yarn-cluster\" instead.")
}
val scheduler = try {
val clazz = Utils.classForName("org.apache.spark.scheduler.cluster.YarnClusterScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
// TODO: Enumerate the exact reasons why it can fail
// But irrespective of it, it means we cannot proceed !
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
val backend = try {
val clazz =
Utils.classForName("org.apache.spark.scheduler.cluster.YarnClusterSchedulerBackend")
val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
scheduler.initialize(backend)
(backend, scheduler)
case "yarn-client" =>
val scheduler = try {
val clazz = Utils.classForName("org.apache.spark.scheduler.cluster.YarnScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
val backend = try {
val clazz =
Utils.classForName("org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend")
val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
scheduler.initialize(backend)
(backend, scheduler)
case MESOS_REGEX(mesosUrl) =>
MesosNativeLibrary.load()
val scheduler = new TaskSchedulerImpl(sc)
val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", defaultValue = true)
val backend = if (coarseGrained) {
new CoarseMesosSchedulerBackend(scheduler, sc, mesosUrl, sc.env.securityManager)
} else {
new MesosSchedulerBackend(scheduler, sc, mesosUrl)
}
scheduler.initialize(backend)
(backend, scheduler)
case SIMR_REGEX(simrUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val backend = new SimrSchedulerBackend(scheduler, sc, simrUrl)
scheduler.initialize(backend)
(backend, scheduler)
case zkUrl if zkUrl.startsWith("zk://") =>
logWarning("Master URL for a multi-master Mesos cluster managed by ZooKeeper should be " +
"in the form mesos://zk://host:port. Current Master URL will stop working in Spark 2.0.")
createTaskScheduler(sc, "mesos://" + zkUrl)
case _ =>
throw new SparkException("Could not parse Master URL: '" + master + "'")
}
}
}
sc: SparkContext,
master: String): (SchedulerBackend, TaskScheduler) = {
import SparkMasterRegex._
// When running locally, don't try to re-execute tasks on failure.
val MAX_LOCAL_TASK_FAILURES = 1
master match {
case "local" =>
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, 1)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_REGEX(threads) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
val threadCount = if (threads == "*") localCpuCount else threads.toInt
if (threadCount <= 0) {
throw new SparkException(s"Asked to run locally with $threadCount threads")
}
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
// local[*, M] means the number of cores on the computer with M failures
// local[N, M] means exactly N threads with M failures
val threadCount = if (threads == "*") localCpuCount else threads.toInt
val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
val backend = new LocalBackend(sc.getConf, scheduler, threadCount)
scheduler.initialize(backend)
(backend, scheduler)
case SPARK_REGEX(sparkUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
(backend, scheduler)
case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
// Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
val memoryPerSlaveInt = memoryPerSlave.toInt
if (sc.executorMemory > memoryPerSlaveInt) {
throw new SparkException(
"Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
memoryPerSlaveInt, sc.executorMemory))
}
val scheduler = new TaskSchedulerImpl(sc)
val localCluster = new LocalSparkCluster(
numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt, sc.conf)
val masterUrls = localCluster.start()
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
backend.shutdownCallback = (backend: SparkDeploySchedulerBackend) => {
localCluster.stop()
}
(backend, scheduler)
case "yarn-standalone" | "yarn-cluster" =>
if (master == "yarn-standalone") {
logWarning(
"\"yarn-standalone\" is deprecated as of Spark 1.0. Use \"yarn-cluster\" instead.")
}
val scheduler = try {
val clazz = Utils.classForName("org.apache.spark.scheduler.cluster.YarnClusterScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
// TODO: Enumerate the exact reasons why it can fail
// But irrespective of it, it means we cannot proceed !
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
val backend = try {
val clazz =
Utils.classForName("org.apache.spark.scheduler.cluster.YarnClusterSchedulerBackend")
val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
scheduler.initialize(backend)
(backend, scheduler)
case "yarn-client" =>
val scheduler = try {
val clazz = Utils.classForName("org.apache.spark.scheduler.cluster.YarnScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
val backend = try {
val clazz =
Utils.classForName("org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend")
val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
} catch {
case e: Exception => {
throw new SparkException("YARN mode not available ?", e)
}
}
scheduler.initialize(backend)
(backend, scheduler)
case MESOS_REGEX(mesosUrl) =>
MesosNativeLibrary.load()
val scheduler = new TaskSchedulerImpl(sc)
val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", defaultValue = true)
val backend = if (coarseGrained) {
new CoarseMesosSchedulerBackend(scheduler, sc, mesosUrl, sc.env.securityManager)
} else {
new MesosSchedulerBackend(scheduler, sc, mesosUrl)
}
scheduler.initialize(backend)
(backend, scheduler)
case SIMR_REGEX(simrUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val backend = new SimrSchedulerBackend(scheduler, sc, simrUrl)
scheduler.initialize(backend)
(backend, scheduler)
case zkUrl if zkUrl.startsWith("zk://") =>
logWarning("Master URL for a multi-master Mesos cluster managed by ZooKeeper should be " +
"in the form mesos://zk://host:port. Current Master URL will stop working in Spark 2.0.")
createTaskScheduler(sc, "mesos://" + zkUrl)
case _ =>
throw new SparkException("Could not parse Master URL: '" + master + "'")
}
}
}