parisni commented on issue #8903:
URL: https://github.com/apache/hudi/issues/8903#issuecomment-1623204179
Hello, we encounter the same error, on EMR . Removing the EMR
`/usr/lib/hudi` did not help, so I assume this is not a dependency conflict
```
pyspark --driver-memory 1g --executor-memory 1g --conf
spark.dynamicAllocation.enabled=false --num-executors 1 --conf
spark.executor.cores=1 --jars
hudi-aws-0.13.1.jar,hudi-spark3.2-bundle_2.12-0.13.1.jar --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
```
```python
from pyspark.sql.types import StructType, StructField, StringType,
IntegerType
data = [
(1, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b21", "A", "BC", "C"),
(2, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b22", "A", "BC", "C"),
(3, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b21", "A", "BC", "C"),
(4, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b22", "A", "BC", "C"),
]
schema = StructType(
[
StructField("uuid", IntegerType(), True),
StructField("user_id", StringType(), True),
StructField("col1", StringType(), True),
StructField("ts", StringType(), True),
StructField("part", StringType(), True),
]
)
df = spark.createDataFrame(data=data, schema=schema)
bucket = ...
tableName = "test_hudi_mor"
basePath = f"s3://"+bucket+"/test/" + tableName
hudi_options = {
"hoodie.table.name": tableName,
"hoodie.datasource.write.recordkey.field": "uuid",
"hoodie.datasource.write.partitionpath.field": "part",
"hoodie.datasource.write.table.name": tableName,
"hoodie.datasource.write.operation": "insert",
"hoodie.datasource.write.table.type": "MERGE_ON_READ",
"hoodie.datasource.write.precombine.field": "ts",
"hoodie.upsert.shuffle.parallelism": 2,
"hoodie.insert.shuffle.parallelism": 2,
"hoodie.datasource.hive_sync.enable": "true",
"hoodie.datasource.hive_sync.database": "datalake_insight",
"hoodie.datasource.hive_sync.table": tableName,
"hoodie.datasource.hive_sync.mode": "jdbc",
"hoodie.meta.sync.client.tool.class":
"org.apache.hudi.aws.sync.AwsGlueCatalogSyncTool",
"hoodie.datasource.hive_sync.partition_fields": "part",
"hoodie.datasource.hive_sync.partition_extractor_class":
"org.apache.hudi.hive.MultiPartKeysValueExtractor",
}
(df.write.format("hudi").options(**hudi_options).mode("overwrite").save(basePath))
# this works fine
spark.table("datalake_insight."+tableName+"_ro").show()
# this raises an error
spark.table("datalake_insight."+tableName+"_rt").show()
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
