Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/2516#discussion_r18002822
--- Diff:
core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala ---
@@ -406,22 +413,166 @@ private[spark] class SparkSubmitArguments(args:
Seq[String]) {
}
}
+
object SparkSubmitArguments {
- /** Load properties present in the given file. */
- def getPropertiesFromFile(file: File): Seq[(String, String)] = {
- require(file.exists(), s"Properties file $file does not exist")
- require(file.isFile(), s"Properties file $file is not a normal file")
- val inputStream = new FileInputStream(file)
- try {
- val properties = new Properties()
- properties.load(inputStream)
- properties.stringPropertyNames().toSeq.map(k => (k,
properties(k).trim))
- } catch {
- case e: IOException =>
- val message = s"Failed when loading Spark properties file $file"
- throw new SparkException(message, e)
- } finally {
- inputStream.close()
+ /**
+ * Resolves Configuration sources in order of highest to lowest
+ * 1. Each map passed in as additionalConfig from first to last
+ * 2. Environment variables (including legacy variable mappings)
+ * 3. System config variables (eg by using -Dspark.var.name)
+ * 4 SPARK_DEFAULT_CONF/spark-defaults.conf or
SPARK_HOME/conf/spark-defaults.conf
+ * 5. hard coded defaults in class path at spark-submit-defaults.prop
+ *
+ * A property file specified by one of the means listed above gets read
in and the properties are
+ * considered to be at the priority of the method that specified the
files.
+ * A property specified in a property file will not override an existing
+ * config value at that same level
+ *
+ * @param additionalConfigs additional Map[ConfigName->ConfigValue] in
order of highest
+ * priority to lowest
+ * @return Map[propName->propFile] containing values merged from all
sources in order of priority
+ */
+ def mergeSparkProperties(additionalConfigs: Vector[Map[String,String]])
= {
+
+ // Configuration read in from spark-submit-defaults.prop file found on
the classpath
+ val is = Option(Thread.currentThread().getContextClassLoader()
+ .getResourceAsStream(SparkSubmitDefaults))
+
+ val hardCodedDefaultConfig = is.flatMap{x =>
+ Some(SparkSubmitArguments.getPropertyValuesFromStream(x))}
+
+ if (hardCodedDefaultConfig.isEmpty || (hardCodedDefaultConfig.get.size
== 0)) {
+ throw new IllegalStateException(s"Default values not found at
classpath $SparkSubmitDefaults")
+ }
+
+ // Configuration read in from defaults file if it exists
+ var sparkDefaultConfig = SparkSubmitArguments.getSparkDefaultFileConfig
+
+ if (sparkDefaultConfig.isDefinedAt(SparkPropertiesFile))
+ {
+ SparkSubmitArguments.getPropertyValuesFromFile(
+ sparkDefaultConfig.get(SparkPropertiesFile).get)
+ } else {
+ Map.empty
+ }
+
+ // Configuration from java system properties
+ val systemPropertyConfig =
SparkSubmitArguments.getPropertyMap(System.getProperties)
+
+ // Configuration variables from the environment
+ // support legacy variables
+ val environmentConfig = System.getenv().asScala
+
+ val legacyEnvVars = List("MASTER"->SparkMaster,
"DEPLOY_MODE"->SparkDeployMode,
+ "SPARK_DRIVER_MEMORY"->SparkDriverMemory,
"SPARK_EXECUTOR_MEMORY"->SparkExecutorMemory)
+
+
+ // legacy variables act at the priority of a system property
+ systemPropertyConfig ++ legacyEnvVars
+ .map( {case(varName, propName) => (environmentConfig.get(varName),
propName) })
+ .filter( {case(varVariable, _) => varVariable.isDefined &&
!varVariable.get.isEmpty} )
+ .map{case(varVariable, propName) => (propName, varVariable.get)}
+
+ val ConfigSources = additionalConfigs ++ Vector (
+ environmentConfig,
+ systemPropertyConfig,
+ sparkDefaultConfig,
+ hardCodedDefaultConfig.get
+ )
+
+ // Load properties file at priority level of source that specified the
property file
+ // loaded property file configs will not override existing configs at
the priority
+ // level the property file was specified at
+ val processedConfigSource = ConfigSources
+ .map( configMap => getFileBasedPropertiesIfSpecified(configMap) ++
configMap)
+
+ val test = MergedPropertyMap.mergePropertyMaps(processedConfigSource)
+
+ test
+ }
+
+ /**
+ * Returns a map of config values from a property file if
+ * the passed configMap has a SparkPropertiesFile defined pointing to a
file
+ * @param configMap Map of config values to check for file path from
+ * @return Map of config values if map holds a valid
SparkPropertiesFile, Map.Empty otherwise
+ */
+ def getFileBasedPropertiesIfSpecified(configMap: Map[String, String])= {
+ if (configMap.isDefinedAt(SparkPropertiesFile))
+ {
+
SparkSubmitArguments.getPropertyValuesFromFile(configMap.get(SparkPropertiesFile).get)
+ } else {
+ Map.empty
+ }
+ }
+
+ /**
+ * Returns a loaded property file
+ */
+ def loadPropFile(propFile: File): Properties = {
+ val prop = new Properties()
+ prop.load(new FileInputStream(propFile))
+ prop
+ }
+
+ /**
+ * Gets configuration from reading SPARK_CONF_DIR/spark-defaults.conf if
it exists
+ * otherwise reads SPARK_HOME/conf/spark-defaults.conf if it exists
+ * otherwise returns an empty config structure
+ * @return Map[PropName->PropValue]
+ */
+ def getSparkDefaultFileConfig: Map[String, String] = {
+ val baseConfDir: Option[String] = sys.env.get(SparkHome).map(_ +
File.separator + SparkConfDir)
+ val altConfDir: Option[String] = sys.env.get(AltSparkConfPath)
+ val confDir: Option[String] = altConfDir.orElse(baseConfDir)
+
+ confDir.flatMap(path => Some(path + File.separator +
SparkDefaultsConfFile))
+ .flatMap(path => Some(new File(path)))
--- End diff --
This is equivalent to `.map { path => new File(path) }`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
