soumilshah1995 opened a new issue, #7879:
URL: https://github.com/apache/hudi/issues/7879
### Hello We were using AWS Market place connector and this morning i was
preparing some hudi labs thats when this error started to show up
# Code
```
try:
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job
from pyspark.sql.session import SparkSession
from awsglue.dynamicframe import DynamicFrame
from pyspark.sql.functions import col, to_timestamp,
monotonically_increasing_id, to_date, when
from pyspark.sql.functions import *
from awsglue.utils import getResolvedOptions
from pyspark.sql.types import *
from datetime import datetime
import boto3
from functools import reduce
import uuid
from faker import Faker
except Exception as e:
pass
spark = SparkSession.builder.config('spark.serializer',
'org.apache.spark.serializer.KryoSerializer') \
.config('spark.sql.hive.convertMetastoreParquet', 'false') \
.config('spark.sql.legacy.pathOptionBehavior.enabled', 'true') \
.getOrCreate()
sc = spark.sparkContext
glueContext = GlueContext(sc)
job = Job(glueContext)
logger = glueContext.get_logger()
db_name = "hudidb"
table_name = "sample"
recordkey = 'emp_id'
path = "s3://soumilshah-hudi-demos/tmp/"
groupSize = "1048576"
method = 'upsert'
table_type = "COPY_ON_WRITE"
connection_options = {
"path": path,
"connectionName": "hudi-connection",
"hoodie.datasource.write.storage.type": table_type,
'className': 'org.apache.hudi',
'hoodie.table.name': table_name,
'hoodie.datasource.write.recordkey.field': recordkey,
'hoodie.datasource.write.table.name': table_name,
'hoodie.datasource.write.operation': method,
'hoodie.datasource.hive_sync.enable': 'true',
"hoodie.datasource.hive_sync.mode": "hms",
'hoodie.datasource.hive_sync.sync_as_datasource': 'false',
'hoodie.datasource.hive_sync.database': db_name,
'hoodie.datasource.hive_sync.table': table_name,
'hoodie.datasource.hive_sync.use_jdbc': 'false',
'hoodie.datasource.hive_sync.partition_extractor_class':
'org.apache.hudi.hive.MultiPartKeysValueExtractor',
'hoodie.datasource.write.hive_style_partitioning': 'true',
}
global faker
faker = Faker()
class DataGenerator(object):
@staticmethod
def get_data():
return [
(
uuid.uuid4().__str__(),
faker.name(),
faker.random_element(elements=('IT', 'HR', 'Sales',
'Marketing')),
faker.random_element(elements=('CA', 'NY', 'TX', 'FL', 'IL',
'RJ')),
str(faker.random_int(min=10000, max=150000)),
str(faker.random_int(min=18, max=60)),
str(faker.random_int(min=0, max=100000)),
str(faker.unix_time()),
faker.email(),
faker.credit_card_number(card_type='amex')
) for x in range(20)
]
data = DataGenerator.get_data()
columns = ["emp_id", "employee_name", "department", "state", "salary",
"age", "bonus", "ts", "email", "credit_card"]
spark_df = spark.createDataFrame(data=data, schema=columns)
WriteDF = (
glueContext.write_dynamic_frame.from_options(
frame=DynamicFrame.fromDF(spark_df, glueContext, "glue_df"),
connection_type="marketplace.spark",
connection_options=connection_options,
transformation_ctx="glue_df",
)
)
job.commit()
```
### Error Message
```
Py4JJavaError: An error occurred while calling o111.pyWriteDynamicFrame.
: org.apache.hudi.hive.HoodieHiveSyncException: Got runtime exception when
hive syncing
at org.apache.hudi.hive.HiveSyncTool.<init>(HiveSyncTool.java:83)
at
org.apache.hudi.HoodieSparkSqlWriter$.syncHive(HoodieSparkSqlWriter.scala:539)
at
org.apache.hudi.HoodieSparkSqlWriter$.$anonfun$metaSync$2(HoodieSparkSqlWriter.scala:595)
at
org.apache.hudi.HoodieSparkSqlWriter$.$anonfun$metaSync$2$adapted(HoodieSparkSqlWriter.scala:591)
at scala.collection.mutable.HashSet.foreach(HashSet.scala:77)
at
org.apache.hudi.HoodieSparkSqlWriter$.metaSync(HoodieSparkSqlWriter.scala:591)
at
org.apache.hudi.HoodieSparkSqlWriter$.commitAndPerformPostOperations(HoodieSparkSqlWriter.scala:665)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:286)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:164)
at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:90)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133)
at
org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
at
org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438)
at
org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301)
at
com.amazonaws.services.glue.marketplace.connector.SparkCustomDataSink.writeDynamicFrame(CustomDataSink.scala:45)
at
com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:71)
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: org.apache.hudi.hive.HoodieHiveSyncException: Failed to create
HiveMetaStoreClient
at
org.apache.hudi.hive.HoodieHiveClient.<init>(HoodieHiveClient.java:92)
at org.apache.hudi.hive.HiveSyncTool.<init>(HiveSyncTool.java:78)
... 48 more
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException:
org.apache.hadoop.hive.ql.metadata.HiveException: MetaException(message:Unable
to verify existence of default database:
com.amazonaws.services.glue.model.AccessDeniedException: Insufficient Lake
Formation permission(s) on default (Service: AWSGlue; Status Code: 400; Error
Code: AccessDeniedException; Request ID: 02e6bfa7-f5c0-4f18-b223-112bb28bf480;
Proxy: null))
at
org.apache.hadoop.hive.ql.metadata.Hive.registerAllFunctionsOnce(Hive.java:239)
at org.apache.hadoop.hive.ql.metadata.Hive.<init>(Hive.java:402)
at org.apache.hadoop.hive.ql.metadata.Hive.create(Hive.java:335)
at org.apache.hadoop.hive.ql.metadata.Hive.getInternal(Hive.java:315)
at org.apache.hadoop.hive.ql.metadata.Hive.get(Hive.java:291)
at
org.apache.hudi.hive.ddl.HMSDDLExecutor.<init>(HMSDDLExecutor.java:68)
at
org.apache.hudi.hive.HoodieHiveClient.<init>(HoodieHiveClient.java:76)
... 49 more
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException:
MetaException(message:Unable to verify existence of default database:
com.amazonaws.services.glue.model.AccessDeniedException: Insufficient Lake
Formation permission(s) on default (Service: AWSGlue; Status Code: 400; Error
Code: AccessDeniedException; Request ID: 02e6bfa7-f5c0-4f18-b223-112bb28bf480;
Proxy: null))
at
org.apache.hadoop.hive.ql.metadata.Hive.getAllFunctions(Hive.java:3991)
at
org.apache.hadoop.hive.ql.metadata.Hive.reloadFunctions(Hive.java:251)
at
org.apache.hadoop.hive.ql.metadata.Hive.registerAllFunctionsOnce(Hive.java:234)
... 55 more
Caused by: MetaException(message:Unable to verify existence of default
database: com.amazonaws.services.glue.model.AccessDeniedException: Insufficient
Lake Formation permission(s) on default (Service: AWSGlue; Status Code: 400;
Error Code: AccessDeniedException; Request ID:
02e6bfa7-f5c0-4f18-b223-112bb28bf480; Proxy: null))
at
com.amazonaws.glue.catalog.metastore.AWSCatalogMetastoreClient.doesDefaultDBExist(AWSCatalogMetastoreClient.java:244)
at
com.amazonaws.glue.catalog.metastore.AWSCatalogMetastoreClient.<init>(AWSCatalogMetastoreClient.java:152)
at
com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory.createMetaStoreClient(AWSGlueDataCatalogHiveClientFactory.java:20)
at
org.apache.hadoop.hive.ql.metadata.HiveUtils.createMetaStoreClient(HiveUtils.java:507)
at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3746)
at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3726)
at
org.apache.hadoop.hive.ql.metadata.Hive.getAllFunctions(Hive.java:3988)
... 57 more
```
### Connector Version
#### Note : i have tried this labs before and it was all fine until this
morning when it started to throw hive sync error
--
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]
