[SPARK-4048] Enhance and extend hadoop-provided profile.

This change does a few things to make the hadoop-provided profile more useful:

- Create new profiles for other libraries / services that might be provided by the infrastructure
- Simplify and fix the poms so that the profiles are only activated while building assemblies.
- Fix tests so that they're able to run when the profiles are activated
- Add a new env variable to be used by distributions that use these profiles to provide the runtime
  classpath for Spark jobs and daemons.

Author: Marcelo Vanzin <[email protected]>

Closes apache#2982 from vanzin/SPARK-4048 and squashes the following commits:

82eb688 [Marcelo Vanzin] Add a comment.
eb228c0 [Marcelo Vanzin] Fix borked merge.
4e38f4e [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9ef79a3 [Marcelo Vanzin] Alternative way to propagate test classpath to child processes.
371ebee [Marcelo Vanzin] Review feedback.
52f366d [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
83099fc [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
7377e7b [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
322f882 [Marcelo Vanzin] Fix merge fail.
f24e9e7 [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
8b00b6a [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9640503 [Marcelo Vanzin] Cleanup child process log message.
115fde5 [Marcelo Vanzin] Simplify a comment (and make it consistent with another pom).
e3ab2da [Marcelo Vanzin] Fix hive-thriftserver profile.
7820d58 [Marcelo Vanzin] Fix CliSuite with provided profiles.
1be73d4 [Marcelo Vanzin] Restore flume-provided profile.
d1399ed [Marcelo Vanzin] Restore jetty dependency.
82a54b9 [Marcelo Vanzin] Remove unused profile.
5c54a25 [Marcelo Vanzin] Fix HiveThriftServer2Suite with *-provided profiles.
1fc4d0b [Marcelo Vanzin] Update dependencies for hive-thriftserver.
f7b3bbe [Marcelo Vanzin] Add snappy to hadoop-provided list.
9e4e001 [Marcelo Vanzin] Remove duplicate hive profile.
d928d62 [Marcelo Vanzin] Redirect child stderr to parent's log.
4d67469 [Marcelo Vanzin] Propagate SPARK_DIST_CLASSPATH on Yarn.
417d90e [Marcelo Vanzin] Introduce "SPARK_DIST_CLASSPATH".
2f95f0d [Marcelo Vanzin] Propagate classpath to child processes during testing.
1adf91c [Marcelo Vanzin] Re-enable maven-install-plugin for a few projects.
284dda6 [Marcelo Vanzin] Rework the "hadoop-provided" profile, add new ones.

Author: Marcelo Vanzin

assembly/pom.xml

@@ -354,5 +354,25 @@
         </dependency>
       </dependencies>
     </profile>
+
+    <!-- Profiles that disable inclusion of certain dependencies. -->
+    <profile>
+      <id>hadoop-provided</id>
+      <properties>
+        <hadoop.deps.scope>provided</hadoop.deps.scope>
+      </properties>
+    </profile>
+    <profile>
+      <id>hive-provided</id>
+      <properties>
+        <hive.deps.scope>provided</hive.deps.scope>
+      </properties>
+    </profile>
+    <profile>
+      <id>parquet-provided</id>
+      <properties>
+        <parquet.deps.scope>provided</parquet.deps.scope>
+      </properties>
+    </profile>
   </profiles>
 </project>

bagel/pom.xml

@@ -40,10 +40,6 @@
       <artifactId>spark-core_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
-    <dependency>
-      <groupId>org.eclipse.jetty</groupId>
-      <artifactId>jetty-server</artifactId>
-    </dependency>
     <dependency>
       <groupId>org.scalacheck</groupId>
       <artifactId>scalacheck_${scala.binary.version}</artifactId>

bin/compute-classpath.cmd

@@ -109,6 +109,13 @@ if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
   set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
 :no_yarn_conf_dir
 
+rem To allow for distributions to append needed libraries to the classpath (e.g. when
+rem using the "hadoop-provided" profile to build Spark), check SPARK_DIST_CLASSPATH and
+rem append it to tbe final classpath.
+if not "x%$SPARK_DIST_CLASSPATH%"=="x" (
+  set CLASSPATH=%CLASSPATH%;%SPARK_DIST_CLASSPATH%
+)
+
 rem A bit of a hack to allow calling this script within run2.cmd without seeing output
 if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
 

bin/compute-classpath.sh

@@ -146,4 +146,11 @@ if [ -n "$YARN_CONF_DIR" ]; then
   CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
 fi
 
+# To allow for distributions to append needed libraries to the classpath (e.g. when
+# using the "hadoop-provided" profile to build Spark), check SPARK_DIST_CLASSPATH and
+# append it to tbe final classpath.
+if [ -n "$SPARK_DIST_CLASSPATH" ]; then
+  CLASSPATH="$CLASSPATH:$SPARK_DIST_CLASSPATH"
+fi
+
 echo "$CLASSPATH"

core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala

@@ -55,19 +55,26 @@ private[spark] class SparkDeploySchedulerBackend(
       "{{WORKER_URL}}")
     val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions")
       .map(Utils.splitCommandString).getOrElse(Seq.empty)
-    val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath").toSeq.flatMap { cp =>
-      cp.split(java.io.File.pathSeparator)
-    }
-    val libraryPathEntries =
-      sc.conf.getOption("spark.executor.extraLibraryPath").toSeq.flatMap { cp =>
-        cp.split(java.io.File.pathSeparator)
+    val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath")
+      .map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)
+    val libraryPathEntries = sc.conf.getOption("spark.executor.extraLibraryPath")
+      .map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)
+
+    // When testing, expose the parent class path to the child. This is processed by
+    // compute-classpath.{cmd,sh} and makes all needed jars available to child processes
+    // when the assembly is built with the "*-provided" profiles enabled.
+    val testingClassPath =
+      if (sys.props.contains("spark.testing")) {
+        sys.props("java.class.path").split(java.io.File.pathSeparator).toSeq
+      } else {
+        Nil
       }
 
     // Start executors with a few necessary configs for registering with the scheduler
     val sparkJavaOpts = Utils.sparkJavaOpts(conf, SparkConf.isExecutorStartupConf)
     val javaOpts = sparkJavaOpts ++ extraJavaOpts
     val command = Command("org.apache.spark.executor.CoarseGrainedExecutorBackend",
-      args, sc.executorEnvs, classPathEntries, libraryPathEntries, javaOpts)
+      args, sc.executorEnvs, classPathEntries ++ testingClassPath, libraryPathEntries, javaOpts)
     val appUIAddress = sc.ui.map(_.appUIAddress).getOrElse("")
     val appDesc = new ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
       appUIAddress, sc.eventLogDir)

core/src/main/scala/org/apache/spark/util/Utils.scala

@@ -990,11 +990,12 @@ private[spark] object Utils extends Logging {
     for ((key, value) <- extraEnvironment) {
       environment.put(key, value)
     }
+
     val process = builder.start()
     new Thread("read stderr for " + command(0)) {
       override def run() {
         for (line <- Source.fromInputStream(process.getErrorStream).getLines()) {
-          System.err.println(line)
+          logInfo(line)
         }
       }
     }.start()
@@ -1089,7 +1090,7 @@ private[spark] object Utils extends Logging {
     var firstUserLine = 0
     var insideSpark = true
     var callStack = new ArrayBuffer[String]() :+ "<unknown>"
- 
+
     Thread.currentThread.getStackTrace().foreach { ste: StackTraceElement =>
       // When running under some profilers, the current stack trace might contain some bogus
       // frames. This is intended to ensure that we don't crash in these situations by

core/src/test/scala/org/apache/spark/DriverSuite.scala

@@ -35,7 +35,7 @@ class DriverSuite extends FunSuite with Timeouts {
     forAll(masters) { (master: String) =>
       failAfter(60 seconds) {
         Utils.executeAndGetOutput(
-          Seq("./bin/spark-class", "org.apache.spark.DriverWithoutCleanup", master),
+          Seq(s"$sparkHome/bin/spark-class", "org.apache.spark.DriverWithoutCleanup", master),
           new File(sparkHome),
           Map("SPARK_TESTING" -> "1", "SPARK_HOME" -> sparkHome))
       }