Standalone Worker (aka standalone slave) is a logical node in a Spark Standalone cluster.
Worker is a ThreadSafeRpcEndpoint that uses Worker for the RPC endpoint name when registered.
You can have one or many standalone workers in a standalone cluster. They can be started and stopped using management scripts.
Worker is created when…FIXME
When started, Worker…FIXME
| Name | Description |
|---|---|
Working directory of the executors that the Initialized when Used when Used when |
receive: PartialFunction[Any, Unit]|
Note
|
receive is part of RpcEndpoint Contract to process messages.
|
receive…FIXME
handleRegisterResponse(msg: RegisterWorkerResponse): UnithandleRegisterResponse…FIXME
|
Note
|
handleRegisterResponse is used when…FIXME
|
main(argStrings: Array[String]): Unitmain…FIXME
startRpcEnvAndEndpoint(
host: String,
port: Int,
webUiPort: Int,
cores: Int,
memory: Int,
masterUrls: Array[String],
workDir: String,
workerNumber: Option[Int] = None,
conf: SparkConf = new SparkConf): RpcEnvstartRpcEnvAndEndpoint…FIXME
startRpcEnvAndEndpoint creates a RpcEnv for the input host and port.
startRpcEnvAndEndpoint creates a Worker RPC endpoint (for the RPC environment and the input webUiPort, cores, memory, masterUrls, workDir and conf).
startRpcEnvAndEndpoint requests the RpcEnv to register the Worker RPC endpoint under the name Worker.
|
Note
|
|
createWorkDir(): UnitcreateWorkDir sets workDir to be either workDirPath if defined or sparkHome with work subdirectory.
In the end, createWorkDir creates workDir directory (including any necessary but nonexistent parent directories).
createWorkDir reports…FIXME
|
Note
|
createWorkDir is used exclusively when Worker RPC Endpoint is requested to start on a RPC environment.
|
onStart(): Unit|
Note
|
onStart is part of RpcEndpoint Contract to activate an endpoint and start accepting messages.
|
onStart…FIXME