You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "HyukjinKwon (via GitHub)" <gi...@apache.org> on 2023/07/17 23:21:09 UTC
[GitHub] [spark] HyukjinKwon commented on a diff in pull request #42035: [SPARK-42944][SS][PYTHON] Streaming ForeachBatch in Python
HyukjinKwon commented on code in PR #42035:
URL: https://github.com/apache/spark/pull/42035#discussion_r1265999659
##########
core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala:
##########
@@ -0,0 +1,88 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.api.python
+
+import java.io.{BufferedInputStream, BufferedOutputStream, DataInputStream, DataOutputStream}
+import java.net.Socket
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.SparkEnv
+import org.apache.spark.internal.Logging
+import org.apache.spark.internal.config.BUFFER_SIZE
+import org.apache.spark.internal.config.Python.{PYTHON_AUTH_SOCKET_TIMEOUT, PYTHON_USE_DAEMON}
+
+
+private[spark] object StreamingPythonRunner {
+ def apply(func: PythonFunction, connectUrl: String): StreamingPythonRunner = {
+ new StreamingPythonRunner(func, connectUrl)
+ }
+}
+
+private[spark] class StreamingPythonRunner(func: PythonFunction, connectUrl: String)
+ extends Logging {
+ private val conf = SparkEnv.get.conf
+ protected val bufferSize: Int = conf.get(BUFFER_SIZE)
+ protected val authSocketTimeout = conf.get(PYTHON_AUTH_SOCKET_TIMEOUT)
+
+ private val envVars: java.util.Map[String, String] = func.envVars
+ private val pythonExec: String = func.pythonExec
+ protected val pythonVer: String = func.pythonVer
+
+ /**
+ * Initializes the Python worker for streaming functions. Sets up Spark Connect session
+ * to be used with the functions.
+ */
+ def init(sessionId: String): (DataOutputStream, DataInputStream) = {
+ log.info(s"Initializing Python runner (session: $sessionId ,pythonExec: $pythonExec")
+
+ val env = SparkEnv.get
+
+ val localdir = env.blockManager.diskBlockManager.localDirs.map(f => f.getPath()).mkString(",")
+ envVars.put("SPARK_LOCAL_DIRS", localdir)
+
+ envVars.put("SPARK_AUTH_SOCKET_TIMEOUT", authSocketTimeout.toString)
+ envVars.put("SPARK_BUFFER_SIZE", bufferSize.toString)
+ conf.set(PYTHON_USE_DAEMON, false)
+ envVars.put("SPARK_CONNECT_LOCAL_URL", connectUrl)
+
+ val pythonWorkerFactory = new PythonWorkerFactory(pythonExec, envVars.asScala.toMap)
+ val (worker: Socket, _) = pythonWorkerFactory.createStreamingWorker()
Review Comment:
@ueshin is actually working on this in https://github.com/apache/spark/pull/41948. I believe we can reuse the same codebase.
##########
core/src/main/scala/org/apache/spark/api/python/StreamingPythonRunner.scala:
##########
@@ -0,0 +1,88 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.api.python
+
+import java.io.{BufferedInputStream, BufferedOutputStream, DataInputStream, DataOutputStream}
+import java.net.Socket
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.SparkEnv
+import org.apache.spark.internal.Logging
+import org.apache.spark.internal.config.BUFFER_SIZE
+import org.apache.spark.internal.config.Python.{PYTHON_AUTH_SOCKET_TIMEOUT, PYTHON_USE_DAEMON}
+
+
+private[spark] object StreamingPythonRunner {
+ def apply(func: PythonFunction, connectUrl: String): StreamingPythonRunner = {
+ new StreamingPythonRunner(func, connectUrl)
+ }
+}
+
+private[spark] class StreamingPythonRunner(func: PythonFunction, connectUrl: String)
+ extends Logging {
+ private val conf = SparkEnv.get.conf
+ protected val bufferSize: Int = conf.get(BUFFER_SIZE)
+ protected val authSocketTimeout = conf.get(PYTHON_AUTH_SOCKET_TIMEOUT)
+
+ private val envVars: java.util.Map[String, String] = func.envVars
+ private val pythonExec: String = func.pythonExec
+ protected val pythonVer: String = func.pythonVer
+
+ /**
+ * Initializes the Python worker for streaming functions. Sets up Spark Connect session
+ * to be used with the functions.
+ */
+ def init(sessionId: String): (DataOutputStream, DataInputStream) = {
+ log.info(s"Initializing Python runner (session: $sessionId ,pythonExec: $pythonExec")
+
+ val env = SparkEnv.get
+
+ val localdir = env.blockManager.diskBlockManager.localDirs.map(f => f.getPath()).mkString(",")
+ envVars.put("SPARK_LOCAL_DIRS", localdir)
+
+ envVars.put("SPARK_AUTH_SOCKET_TIMEOUT", authSocketTimeout.toString)
+ envVars.put("SPARK_BUFFER_SIZE", bufferSize.toString)
+ conf.set(PYTHON_USE_DAEMON, false)
+ envVars.put("SPARK_CONNECT_LOCAL_URL", connectUrl)
+
+ val pythonWorkerFactory = new PythonWorkerFactory(pythonExec, envVars.asScala.toMap)
+ val (worker: Socket, _) = pythonWorkerFactory.createStreamingWorker()
Review Comment:
The logic here and there are virtually same .. if I am not wrong.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org