diff options
author | Nezih Yigitbasi <nyigitbasi@netflix.com> | 2016-06-16 18:19:29 -0700 |
---|---|---|
committer | Marcelo Vanzin <vanzin@cloudera.com> | 2016-06-16 18:20:16 -0700 |
commit | 63470afc997fb9d6b6f8a911c25964743556c9cc (patch) | |
tree | 02588d1187e7e3ff855edf3f55f0d3a5aa10d39f /core/src | |
parent | f1bf0d2f3a61d81686f36763e83d3be89c98435f (diff) | |
download | spark-63470afc997fb9d6b6f8a911c25964743556c9cc.tar.gz spark-63470afc997fb9d6b6f8a911c25964743556c9cc.tar.bz2 spark-63470afc997fb9d6b6f8a911c25964743556c9cc.zip |
[SPARK-15782][YARN] Fix spark.jars and spark.yarn.dist.jars handling
When `--packages` is specified with spark-shell the classes from those packages cannot be found, which I think is due to some of the changes in SPARK-12343.
Tested manually with both scala 2.10 and 2.11 repls.
vanzin davies can you guys please review?
Author: Marcelo Vanzin <vanzin@cloudera.com>
Author: Nezih Yigitbasi <nyigitbasi@netflix.com>
Closes #13709 from nezihyigitbasi/SPARK-15782.
Diffstat (limited to 'core/src')
3 files changed, 38 insertions, 1 deletions
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index d56946e932..d8701812eb 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -391,7 +391,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli _conf.set("spark.executor.id", SparkContext.DRIVER_IDENTIFIER) - _jars = _conf.getOption("spark.jars").map(_.split(",")).map(_.filter(_.nonEmpty)).toSeq.flatten + _jars = Utils.getUserJars(_conf) _files = _conf.getOption("spark.files").map(_.split(",")).map(_.filter(_.nonEmpty)) .toSeq.flatten diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index f9d05409e1..17d193b773 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -2352,6 +2352,31 @@ private[spark] object Utils extends Logging { log.info(s"Started daemon with process name: ${Utils.getProcessName()}") SignalUtils.registerLogger(log) } + + /** + * Unions two comma-separated lists of files and filters out empty strings. + */ + def unionFileLists(leftList: Option[String], rightList: Option[String]): Set[String] = { + var allFiles = Set[String]() + leftList.foreach { value => allFiles ++= value.split(",") } + rightList.foreach { value => allFiles ++= value.split(",") } + allFiles.filter { _.nonEmpty } + } + + /** + * In YARN mode this method returns a union of the jar files pointed by "spark.jars" and the + * "spark.yarn.dist.jars" properties, while in other modes it returns the jar files pointed by + * only the "spark.jars" property. + */ + def getUserJars(conf: SparkConf): Seq[String] = { + val sparkJars = conf.getOption("spark.jars") + if (conf.get("spark.master") == "yarn") { + val yarnJars = conf.getOption("spark.yarn.dist.jars") + unionFileLists(sparkJars, yarnJars).toSeq + } else { + sparkJars.map(_.split(",")).map(_.filter(_.nonEmpty)).toSeq.flatten + } + } } /** diff --git a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala index 2718976992..0b020592b0 100644 --- a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala @@ -570,6 +570,18 @@ class SparkSubmitSuite appArgs.executorMemory should be ("2.3g") } } + + test("comma separated list of files are unioned correctly") { + val left = Option("/tmp/a.jar,/tmp/b.jar") + val right = Option("/tmp/c.jar,/tmp/a.jar") + val emptyString = Option("") + Utils.unionFileLists(left, right) should be (Set("/tmp/a.jar", "/tmp/b.jar", "/tmp/c.jar")) + Utils.unionFileLists(emptyString, emptyString) should be (Set.empty) + Utils.unionFileLists(Option("/tmp/a.jar"), emptyString) should be (Set("/tmp/a.jar")) + Utils.unionFileLists(emptyString, Option("/tmp/a.jar")) should be (Set("/tmp/a.jar")) + Utils.unionFileLists(None, Option("/tmp/a.jar")) should be (Set("/tmp/a.jar")) + Utils.unionFileLists(Option("/tmp/a.jar"), None) should be (Set("/tmp/a.jar")) + } // scalastyle:on println // NOTE: This is an expensive operation in terms of time (10 seconds+). Use sparingly. |