Details
-
Bug
-
Status: Resolved
-
Minor
-
Resolution: Fixed
-
2.3.0
-
None
Description
After the change in SPARK-25118, which enables spark-shell to run with default log level, test_glr_summary started failing with StackOverflow error.
Cause: ClosureCleaner calls logDebug on various objects and when it is called for GeneralizedLinearRegressionTrainingSummary, it starts a spark job which runs into infinite loop and fails with the below exception.
====================================================================== ERROR: test_glr_summary (pyspark.ml.tests.TrainingSummaryTest) ---------------------------------------------------------------------- Traceback (most recent call last): File "/home/jenkins/workspace/SparkPullRequestBuilder/python/pyspark/ml/tests.py", line 1809, in test_glr_summary self.assertTrue(isinstance(s.aic, float)) File "/home/jenkins/workspace/SparkPullRequestBuilder/python/pyspark/ml/regression.py", line 1781, in aic return self._call_java("aic") File "/home/jenkins/workspace/SparkPullRequestBuilder/python/pyspark/ml/wrapper.py", line 55, in _call_java return _java2py(sc, m(*java_args)) File "/home/jenkins/workspace/SparkPullRequestBuilder/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__ answer, self.gateway_client, self.target_id, self.name) File "/home/jenkins/workspace/SparkPullRequestBuilder/python/pyspark/sql/utils.py", line 63, in deco return f(*a, **kw) File "/home/jenkins/workspace/SparkPullRequestBuilder/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value format(target_id, ".", name), value) Py4JJavaError: An error occurred while calling o31639.aic. : java.lang.StackOverflowError at java.io.UnixFileSystem.getBooleanAttributes0(Native Method) at java.io.UnixFileSystem.getBooleanAttributes(UnixFileSystem.java:242) at java.io.File.exists(File.java:819) at sun.misc.URLClassPath$FileLoader.getResource(URLClassPath.java:1245) at sun.misc.URLClassPath$FileLoader.findResource(URLClassPath.java:1212) at sun.misc.URLClassPath.findResource(URLClassPath.java:188) at java.net.URLClassLoader$2.run(URLClassLoader.java:569) at java.net.URLClassLoader$2.run(URLClassLoader.java:567) at java.security.AccessController.doPrivileged(Native Method) at java.net.URLClassLoader.findResource(URLClassLoader.java:566) at java.lang.ClassLoader.getResource(ClassLoader.java:1093) at java.net.URLClassLoader.getResourceAsStream(URLClassLoader.java:232) at java.lang.Class.getResourceAsStream(Class.java:2223) at org.apache.spark.util.ClosureCleaner$.getClassReader(ClosureCleaner.scala:43) at org.apache.spark.util.ClosureCleaner$.getInnerClosureClasses(ClosureCleaner.scala:87) at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:269) at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162) at org.apache.spark.SparkContext.clean(SparkContext.scala:2342) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:864) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:863) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) at org.apache.spark.rdd.RDD.withScope(RDD.scala:364) at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:863) at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:613) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.DeserializeToObjectExec.doExecute(objects.scala:89) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80) at org.apache.spark.sql.Dataset.rdd$lzycompute(Dataset.scala:3038) at org.apache.spark.sql.Dataset.rdd(Dataset.scala:3036) at org.apache.spark.ml.regression.GeneralizedLinearRegressionSummary.nullDeviance$lzycompute(GeneralizedLinearRegression.scala:1342) at org.apache.spark.ml.regression.GeneralizedLinearRegressionSummary.nullDeviance(GeneralizedLinearRegression.scala:1315) at org.apache.spark.ml.regression.GeneralizedLinearRegressionTrainingSummary.toString(GeneralizedLinearRegression.scala:1556) at java.lang.String.valueOf(String.java:2994) at java.lang.StringBuilder.append(StringBuilder.java:131) at scala.StringContext.standardInterpolator(StringContext.scala:125) at scala.StringContext.s(StringContext.scala:95) at org.apache.spark.util.ClosureCleaner$$anonfun$org$apache$spark$util$ClosureCleaner$$clean$12$$anonfun$apply$6.apply(ClosureCleaner.scala:289) at org.apache.spark.util.ClosureCleaner$$anonfun$org$apache$spark$util$ClosureCleaner$$clean$12$$anonfun$apply$6.apply(ClosureCleaner.scala:289)
