[GitHub] [spark] srowen commented on a change in pull request #24374: [SPARK-27366][CORE] Support GPU Resources in Spark job scheduling

[GitBox <gi...@apache.org>]

srowen commented on a change in pull request #24374: [SPARK-27366][CORE] Support GPU Resources in Spark job scheduling
URL: https://github.com/apache/spark/pull/24374#discussion_r275371510
 
 

 ##########
 File path: core/src/main/scala/org/apache/spark/ResourceDiscoverer.scala
 ##########
 @@ -0,0 +1,72 @@
+/*
+ * 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
+
+import java.io.File
+
+import org.apache.spark.{ResourceInformation, SparkConf, SparkException}
+import org.apache.spark.internal.Logging
+import org.apache.spark.internal.config._
+import org.apache.spark.util.Utils.executeAndGetOutput
+
+/**
+ * Discovers resources (gpu/fpgas/etc) available to an executor. Currently this just
+ * knows about gpus but could easily be extended.
+ */
+private[spark] object ResourceDiscoverer extends Logging {
+
+  def findResources(sparkconf: SparkConf, isDriver: Boolean): Map[String, ResourceInformation] = {
+    val gpus = getGPUResources(sparkconf, isDriver)
+    if (gpus.isEmpty) {
+      Map()
+    } else {
+      Map(ResourceInformation.GPU ->
+        new ResourceInformation(ResourceInformation.GPU, "", gpus.size, gpus))
+    }
+  }
+
+  private def getGPUResources(sparkconf: SparkConf, isDriver: Boolean): Array[String] = {
+    val discoveryConf = if (isDriver) DRIVER_GPU_DISCOVERY_SCRIPT else EXECUTOR_GPU_DISCOVERY_SCRIPT
+    val script = sparkconf.get(discoveryConf)
+    val result = if (script.nonEmpty) {
+      val scriptFile = new File(script.get)
+      // check that script exists and try to execute
+      if (scriptFile.exists()) {
+        try {
+          val output = executeAndGetOutput(Seq(script.get), new File("."))
+          // sanity check output is a comma separate list of ints
+          val gpu_ids = output.split(",").map(_.trim())
+          for (gpu <- gpu_ids) {
+            Integer.parseInt(gpu)
+          }
+          gpu_ids
+        } catch {
+          case e @ (_: SparkException | _: NumberFormatException) =>
+            throw new SparkException("The gpu discover script threw exception, assuming no gpu's",
+              e)
+        }
+      } else {
+        throw new SparkException(s"Gpu script: $scriptFile to discover gpu's doesn't exist!")
 
 Review comment:
   Nit: "GPU" in all cases where it's referring to the hardware

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org