Skip to content
  • Gmodena @gmodena ·

    Fails (permission denied) when invoking the following query:

    SELECT
  page_id,
  pageview_info['project'] as project,
  geocoded_data['country'] as country,
  actor_signature
FROM wmf.pageview_actor
WHERE
  is_pageview
  AND namespace_id = 0
  AND year = 2022
  AND month = 9
  AND day = 15
LIMIT 10
  • Gmodena @gmodena ·

    I tried to run the query from pyspark2:

    Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /__ / .__/\_,_/_/ /_/\_\   version 2.4.4
      /_/

Using Python version 3.7.3 (default, Jan 22 2021 20:04:44)
SparkSession available as 'spark'.

In [1]: pv_query = """SELECT
   ...:   page_id,
   ...:   pageview_info['project'] as project,
   ...:   geocoded_data['country'] as country,
   ...:   actor_signature
   ...: FROM wmf.pageview_actor
   ...: WHERE
   ...:   is_pageview
   ...:   AND namespace_id = 0
   ...:   AND year = 2022
   ...:   AND month = 9
   ...:   AND day = 15
   ...: LIMIT 10
   ...: """

In [2]: spark.sql(pv_query).show()
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
/usr/lib/spark2/python/pyspark/sql/utils.py in deco(*a, **kw)
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:

/usr/lib/spark2/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:

Py4JJavaError: An error occurred while calling o51.sql.
: org.apache.spark.sql.AnalysisException: java.lang.RuntimeException: java.lang.RuntimeException: java.io.IOException: Permission denied;
	at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:106)
	at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:214)
	at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
	at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
	at org.apache.spark.sql.internal.SharedState.globalTempViewManager$lzycompute(SharedState.scala:141)
	at org.apache.spark.sql.internal.SharedState.globalTempViewManager(SharedState.scala:136)
	at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
	at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
	at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager$lzycompute(SessionCatalog.scala:91)
	at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager(SessionCatalog.scala:91)
	at org.apache.spark.sql.catalyst.catalog.SessionCatalog.isTemporaryTable(SessionCatalog.scala:736)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.isRunningDirectlyOnFiles(Analyzer.scala:747)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:681)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:713)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:706)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
	at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:89)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
	at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
	at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:706)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:652)
	at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
	at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
	at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
	at scala.collection.immutable.List.foldLeft(List.scala:84)
	at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
	at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
	at scala.collection.immutable.List.foreach(List.scala:392)
	at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
	at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
	at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
	at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
	at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
	at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
	at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
	at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
	at py4j.Gateway.invoke(Gateway.java:282)
	at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
	at py4j.commands.CallCommand.execute(CallCommand.java:79)
	at py4j.GatewayConnection.run(GatewayConnection.java:238)
	at java.lang.Thread.run(Thread.java:750)
Caused by: java.lang.RuntimeException: java.lang.RuntimeException: java.io.IOException: Permission denied
	at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522)
	at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:183)
	at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:117)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
	at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
	at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:271)
	at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:384)
	at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:286)
	at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
	at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
	at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:215)
	at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:215)
	at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:215)
	at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
	... 94 more
Caused by: java.lang.RuntimeException: java.io.IOException: Permission denied
	at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:515)
	... 109 more
Caused by: java.io.IOException: Permission denied
	at java.io.UnixFileSystem.createFileExclusively(Native Method)
	at java.io.File.createTempFile(File.java:2063)
	at org.apache.hadoop.hive.ql.session.SessionState.createTempFile(SessionState.java:818)
	at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:513)
	... 109 more


During handling of the above exception, another exception occurred:

AnalysisException                         Traceback (most recent call last)
<ipython-input-2-4a8d517bdf47> in <module>()
----> 1 spark.sql(pv_query).show()

/usr/lib/spark2/python/pyspark/sql/session.py in sql(self, sqlQuery)
    765         [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
    766         """
--> 767         return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
    768 
    769     @since(2.0)

/usr/lib/spark2/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

/usr/lib/spark2/python/pyspark/sql/utils.py in deco(*a, **kw)
     67                                              e.java_exception.getStackTrace()))
     68             if s.startswith('org.apache.spark.sql.AnalysisException: '):
---> 69                 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
     70             if s.startswith('org.apache.spark.sql.catalyst.analysis'):
     71                 raise AnalysisException(s.split(': ', 1)[1], stackTrace)

AnalysisException: 'java.lang.RuntimeException: java.lang.RuntimeException: java.io.IOException: Permission denied;'
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment