tgravescs commented on a change in pull request #24406: [SPARK-27024] Executor interface for cluster managers to support GPU and other resources URL: https://github.com/apache/spark/pull/24406#discussion_r282607955
########## File path: core/src/main/scala/org/apache/spark/ResourceDiscoverer.scala ########## @@ -0,0 +1,89 @@ +/* + * 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 com.fasterxml.jackson.core.JsonParseException +import org.json4s.{DefaultFormats, MappingException} +import org.json4s.jackson.JsonMethods._ + +import org.apache.spark.internal.Logging +import org.apache.spark.internal.config._ +import org.apache.spark.util.Utils.executeAndGetOutput + +/** + * Discovers resources (GPUs/FPGAs/etc). + * This class find resources by running and parses the output of the user specified script + * from the config spark.{driver/executor}.resource.{resourceType}.discoveryScript. + * The output of the script it runs is expected to be JSON in the format of the + * ResourceInformation class, with addresses being optional. + * + * For example: {"name": "gpu","count":2, "units":"", "addresses": ["0","1"]} + */ +private[spark] object ResourceDiscoverer extends Logging { + + private implicit val formats = DefaultFormats + + def findResources(sparkconf: SparkConf, isDriver: Boolean): Map[String, ResourceInformation] = { + val prefix = if (isDriver) { + SPARK_DRIVER_RESOURCE_PREFIX + } else { + SPARK_EXECUTOR_RESOURCE_PREFIX + } + // get unique resource types by grabbing first part config with multiple periods, + // ie resourceType.count, grab resourceType part + val resourceTypes = sparkconf.getAllWithPrefix(prefix).map { case (k, _) => + k.split('.').head + }.toSet + resourceTypes.map { rtype => { + val rInfo = getResourceInfoForType(sparkconf, prefix, rtype) + (rtype -> rInfo) + }}.toMap + } + + private def getResourceInfoForType( + sparkconf: SparkConf, Review comment: done ---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
