[SPARK-47833][SQL][CORE] Supply caller stackstrace for checkAndGlobPathIfNecessary AnalysisException

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

@@ -231,7 +231,7 @@ private[spark] object ThreadUtils {
   /**
    * Run a piece of code in a new thread and return the result. Exception in the new thread is
    * thrown in the caller thread with an adjusted stack trace that removes references to this
-   * method for clarity. The exception stack traces will be like the following
+   * method for clarity. The exception stack traces will be like the following:
    *
    * SomeException: exception-message
    *   at CallerClass.body-method (sourcefile.scala)
@@ -261,31 +261,51 @@ private[spark] object ThreadUtils {
 
     exception match {
       case Some(realException) =>
-        // Remove the part of the stack that shows method calls into this helper method
-        // This means drop everything from the top until the stack element
-        // ThreadUtils.runInNewThread(), and then drop that as well (hence the `drop(1)`).
-        val baseStackTrace = Thread.currentThread().getStackTrace().dropWhile(
-          ! _.getClassName.contains(this.getClass.getSimpleName)).drop(1)
-
-        // Remove the part of the new thread stack that shows methods call from this helper method
-        val extraStackTrace = realException.getStackTrace.takeWhile(
-          ! _.getClassName.contains(this.getClass.getSimpleName))
-
-        // Combine the two stack traces, with a place holder just specifying that there
-        // was a helper method used, without any further details of the helper
-        val placeHolderStackElem = new StackTraceElement(
-          s"... run in separate thread using ${ThreadUtils.getClass.getName.stripSuffix("$")} ..",
-          " ", "", -1)
-        val finalStackTrace = extraStackTrace ++ Seq(placeHolderStackElem) ++ baseStackTrace
-
-        // Update the stack trace and rethrow the exception in the caller thread
-        realException.setStackTrace(finalStackTrace)
-        throw realException
+        throw wrapCallerStacktrace(realException, dropStacks = 2)
       case None =>
         result
     }
   }
 
+  /**
+   * Adjust exception stack stace to wrap with caller side thread stack trace.
+   * The exception stack traces will be like the following:
+   *
+   * SomeException: exception-message
+   *   at CallerClass.body-method (sourcefile.scala)
+   *   at ... run in separate thread using org.apache.spark.util.ThreadUtils ... ()
+   *   at CallerClass.caller-method (sourcefile.scala)
+   *   ...
+   */
+  def wrapCallerStacktrace[T <: Throwable](
+       realException: T,
+       combineMessage: String =
+         s"run in separate thread using ${ThreadUtils.getClass.getName.stripSuffix("$")}",
+       dropStacks: Int = 1): T = {
+    require(dropStacks >= 0, "dropStacks must be zero or positive")
+    val simpleName = this.getClass.getSimpleName
+    // Remove the part of the stack that shows method calls into this helper method
+    // This means drop everything from the top until the stack element
+    // ThreadUtils.wrapCallerStack(), and then drop that as well (hence the `drop(1)`).
+    // Large dropStacks allows caller to drop more stacks.
+    val baseStackTrace = Thread.currentThread().getStackTrace
+      .dropWhile(!_.getClassName.contains(simpleName))
+      .drop(dropStacks)
+
+    // Remove the part of the new thread stack that shows methods call from this helper method
+    val extraStackTrace = realException.getStackTrace
+      .takeWhile(!_.getClassName.contains(simpleName))
+
+    // Combine the two stack traces, with a place holder just specifying that there
+    // was a helper method used, without any further details of the helper
+    val placeHolderStackElem = new StackTraceElement(s"... $combineMessage ..", " ", "", -1)
+    val finalStackTrace = extraStackTrace ++ Seq(placeHolderStackElem) ++ baseStackTrace
+
+    // Update the stack trace and rethrow the exception in the caller thread
+    realException.setStackTrace(finalStackTrace)
+    realException
+  }
+
   /**
    * Construct a new ForkJoinPool with a specified max parallelism and name prefix.
    */

core/src/test/scala/org/apache/spark/util/ThreadUtilsSuite.scala

@@ -128,6 +128,42 @@ class ThreadUtilsSuite extends SparkFunSuite {
     )
   }
 
+  test("wrapCallerStacktrace") {
+    var runnerThreadName: String = null
+    var exception: Throwable = null
+    val t = new Thread() {
+      override def run(): Unit = {
+        runnerThreadName = Thread.currentThread().getName
+        internalMethod()
+      }
+      private def internalMethod(): Unit = {
+        throw new RuntimeException(s"Error occurred on $runnerThreadName")
+      }
+    }
+    t.setDaemon(true)
+    t.setUncaughtExceptionHandler { case (_, e) => exception = e }
+    t.start()
+    t.join()
+
+    ThreadUtils.wrapCallerStacktrace(exception, s"run in separate thread: $runnerThreadName")
+
+    assert(exception.getStackTrace.mkString("\n").contains(
+      "internalMethod"),
+      "stack trace does not contain real exception stack trace"
+    )
+    assert(exception.getStackTrace.mkString("\n").contains(
+      s"... run in separate thread: $runnerThreadName ..."),
+      "stack trace does not contain expected place holder"
+    )
+    assert(exception.getStackTrace.mkString("\n").contains(
+      "org.scalatest.Suite.run"),
+      "stack trace does not contain caller stack trace"
+    )
+    assert(exception.getStackTrace.mkString("\n").contains("ThreadUtils.scala") === false,
+      "stack trace contains unexpected references to ThreadUtils"
+    )
+  }
+
   test("parmap should be interruptible") {
     val t = new Thread() {
       setDaemon(true)

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala

@@ -784,7 +784,7 @@ object DataSource extends Logging {
           globResult
         }.flatten
       } catch {
-        case e: SparkException => throw e.getCause
+        case e: SparkException => throw ThreadUtils.wrapCallerStacktrace(e.getCause)
       }
 
     if (checkFilesExist) {
@@ -796,7 +796,7 @@ object DataSource extends Logging {
           }
         }
       } catch {
-        case e: SparkException => throw e.getCause
+        case e: SparkException => throw ThreadUtils.wrapCallerStacktrace(e.getCause)
       }
     }