[
https://issues.apache.org/jira/browse/HUDI-1747?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17473277#comment-17473277
]
sivabalan narayanan commented on HUDI-1747:
-------------------------------------------
[~vino] : Can you help w/ more info on reproducing this.
> Deltastreamer incremental read is not working on the MOR table
> --------------------------------------------------------------
>
> Key: HUDI-1747
> URL: https://issues.apache.org/jira/browse/HUDI-1747
> Project: Apache Hudi
> Issue Type: Bug
> Components: Common Core
> Reporter: Vinoth Govindarajan
> Assignee: sivabalan narayanan
> Priority: Critical
> Labels: core-flow-ds, sev:high
>
> I was trying to read the MOR HUDI table incrementally using delta streamer,
> while doing that I ran into this issue where it says:
> {code:java}
> Found recursive reference in Avro schema, which can not be processed by
> Spark:{code}
> Spark Version: 2.4
> Hudi Version: 0.7.0-SNAPSHOT or the latest master
>
> Full Stack Trace:
> {code:java}
> Found recursive reference in Avro schema, which can not be processed by Spark:
> {
> "type" : "record",
> "name" : "meta",
> "fields" : [ {
> "name" : "verified",
> "type" : [ "null", "boolean" ],
> "default" : null
> }, {
> "name" : "zip",
> "type" : [ "null", "string" ],
> "default" : null
> }, {
> "name" : "lname",
> "type" : [ "null", "string" ],
> "default" : null
> }]
> }
>
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:75)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:105)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:82)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:81)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.Iterator$class.foreach(Iterator.scala:891)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:81)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:105)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:82)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:81)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.Iterator$class.foreach(Iterator.scala:891)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:81)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:95)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:105)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:82)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:81)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.Iterator$class.foreach(Iterator.scala:891)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:81)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:105)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:82)
> at
> org.apache.spark.sql.avro.SchemaConverters$$anonfun$1.apply(SchemaConverters.scala:81)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.Iterator$class.foreach(Iterator.scala:891)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlTypeHelper(SchemaConverters.scala:81)
> at
> org.apache.spark.sql.avro.SchemaConverters$.toSqlType(SchemaConverters.scala:46)
> at
> org.apache.hudi.AvroConversionUtils$.convertAvroSchemaToStructType(AvroConversionUtils.scala:56)
> at
> org.apache.hudi.MergeOnReadIncrementalRelation.<init>(MergeOnReadIncrementalRelation.scala:77)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:109)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:63)
> at
> org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:318)
> at
> org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
> at
> org.apache.hudi.utilities.sources.HoodieIncrSource.fetchNextBatch(HoodieIncrSource.java:122)
> at
> org.apache.hudi.utilities.sources.RowSource.fetchNewData(RowSource.java:43)
> at org.apache.hudi.utilities.sources.Source.fetchNext(Source.java:75)
> at
> org.apache.hudi.utilities.deltastreamer.SourceFormatAdapter.fetchNewDataInRowFormat(SourceFormatAdapter.java:94)
> at
> org.apache.hudi.utilities.deltastreamer.DeltaSync.readFromSource(DeltaSync.java:350)
> at
> org.apache.hudi.utilities.deltastreamer.DeltaSync.syncOnce(DeltaSync.java:259)
> at
> org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer.lambda$sync$2(HoodieDeltaStreamer.java:170)
> at org.apache.hudi.common.util.Option.ifPresent(Option.java:96)
> at
> org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer.sync(HoodieDeltaStreamer.java:168)
> at
> org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer.main(HoodieDeltaStreamer.java:470)
> 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
> org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:690)
> )
> {code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
