Github user squito commented on a diff in the pull request:
https://github.com/apache/spark/pull/22612#discussion_r227054038
--- Diff:
core/src/main/scala/org/apache/spark/executor/ProcfsBasedSystems.scala ---
@@ -0,0 +1,226 @@
+/*
+ * 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
+
+import java.io._
+import java.nio.charset.Charset
+import java.nio.file.{Files, Paths}
+import java.util.Locale
+
+import scala.collection.mutable
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.spark.{SparkEnv, SparkException}
+import org.apache.spark.internal.{config, Logging}
+import org.apache.spark.util.Utils
+
+private[spark] case class ProcfsBasedSystemsMetrics(
+ jvmVmemTotal: Long,
+ jvmRSSTotal: Long,
+ pythonVmemTotal: Long,
+ pythonRSSTotal: Long,
+ otherVmemTotal: Long,
+ otherRSSTotal: Long)
+
+// Some of the ideas here are taken from the ProcfsBasedProcessTree class
in hadoop
+// project.
+private[spark] class ProcfsBasedSystems(val procfsDir: String = "/proc/")
extends Logging {
+ val procfsStatFile = "stat"
+ val testing = sys.env.contains("SPARK_TESTING") ||
sys.props.contains("spark.testing")
+ var pageSize = computePageSize()
+ var isAvailable: Boolean = isProcfsAvailable
+ private val pid = computePid()
+ private val ptree = mutable.Map[ Int, Set[Int]]()
+
+ var allMetrics: ProcfsBasedSystemsMetrics = ProcfsBasedSystemsMetrics(0,
0, 0, 0, 0, 0)
+
+ computeProcessTree()
+
+ private def isProcfsAvailable: Boolean = {
+ if (testing) {
+ return true
+ }
+ try {
+ if (!Files.exists(Paths.get(procfsDir))) {
+ return false
+ }
+ }
+ catch {
+ case f: FileNotFoundException => return false
+ }
+ val shouldLogStageExecutorMetrics =
+ SparkEnv.get.conf.get(config.EVENT_LOG_STAGE_EXECUTOR_METRICS)
+ val shouldLogStageExecutorProcessTreeMetrics =
+ SparkEnv.get.conf.get(config.EVENT_LOG_PROCESS_TREE_METRICS)
+ shouldLogStageExecutorProcessTreeMetrics &&
shouldLogStageExecutorMetrics
+ }
+
+ private def computePid(): Int = {
+ if (!isAvailable || testing) {
+ return -1;
+ }
+ try {
+ // This can be simplified in java9:
+ //
https://docs.oracle.com/javase/9/docs/api/java/lang/ProcessHandle.html
+ val cmd = Array("bash", "-c", "echo $PPID")
+ val length = 10
+ val out2 = Utils.executeAndGetOutput(cmd)
+ val pid = Integer.parseInt(out2.split("\n")(0))
+ return pid;
+ }
+ catch {
+ case e: SparkException => logDebug("IO Exception when trying to
compute process tree." +
--- End diff --
well, executeAndGetOutput might throw a SparkException ... but are you sure
nothing else will get thrown? Eg. what if you get some weird output and then
the `Integer.parseInt` failse? Is there some reason you wouldn't want the same
error handling for any exception here?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
