Re: [PR] [SPARK-46094] Support Executor JVM Profiling [spark]

["dongjoon-hyun (via GitHub)" <gi...@apache.org>]

dongjoon-hyun commented on code in PR #44021:
URL: https://github.com/apache/spark/pull/44021#discussion_r1450185201


##########
connector/profiler/src/main/scala/org/apache/spark/executor/profiler/ExecutorJVMProfiler.scala:
##########
@@ -0,0 +1,183 @@
+/*
+ * 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.executor.profiler
+
+import java.io.{BufferedInputStream, FileInputStream, InputStream, IOException}
+import java.net.URI
+import java.util.concurrent.{ScheduledExecutorService, TimeUnit}
+
+import one.profiler.{AsyncProfiler, AsyncProfilerLoader}
+import org.apache.hadoop.fs.{FileSystem, FSDataOutputStream, Path}
+
+import org.apache.spark.SparkConf
+import org.apache.spark.deploy.SparkHadoopUtil
+import org.apache.spark.internal.Logging
+import org.apache.spark.util.ThreadUtils
+
+
+/**
+ * A class that enables the async JVM code profiler
+ */
+private[spark] class ExecutorJVMProfiler(conf: SparkConf, executorId: String) extends Logging {
+
+  private var running = false
+  private val enableProfiler = conf.get(EXECUTOR_PROFILING_ENABLED)
+  private val profilerOptions = conf.get(EXECUTOR_PROFILING_OPTIONS)
+  private val profilerDfsDir = conf.get(EXECUTOR_PROFILING_DFS_DIR)
+  private val profilerLocalDir = conf.get(EXECUTOR_PROFILING_LOCAL_DIR)
+  private val writeInterval = conf.get(EXECUTOR_PROFILING_WRITE_INTERVAL)
+
+  private val startcmd = s"start,$profilerOptions,file=$profilerLocalDir/profile.jfr"
+  private val stopcmd = s"stop,$profilerOptions,file=$profilerLocalDir/profile.jfr"
+  private val dumpcmd = s"dump,$profilerOptions,file=$profilerLocalDir/profile.jfr"
+  private val resumecmd = s"resume,$profilerOptions,file=$profilerLocalDir/profile.jfr"
+
+  private val UPLOAD_SIZE = 8 * 1024 * 1024 // 8 MB
+  private var outputStream: FSDataOutputStream = _
+  private var inputStream: InputStream = _
+  private val dataBuffer = new Array[Byte](UPLOAD_SIZE)
+  private var threadpool: ScheduledExecutorService = _
+  private var writing: Boolean = false
+
+  val profiler: Option[AsyncProfiler] = {
+    Option(
+      if (enableProfiler && AsyncProfilerLoader.isSupported) AsyncProfilerLoader.load() else null
+    )
+  }
+
+  def start(): Unit = {
+    if (!running) {
+      try {
+        profiler.foreach(p => {
+          p.execute(startcmd)
+          logInfo("Executor JVM profiling started.")
+          running = true
+          startWriting()
+        }
+        )

Review Comment:
   nit. Let's merge line 71 into 70.



-- 
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