Skip to content

[SPARK-54501][SQL] Improve error handling for Hive metastore partition filter failures #53212

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ganeshashree wants to merge 1 commit into from
Closed

[SPARK-54501][SQL] Improve error handling for Hive metastore partition filter failures #53212

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions common/utils/src/main/resources/error/error-conditions.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2436,6 +2436,14 @@
],
"sqlState" : "XX000"
},
"INTERNAL_ERROR_HIVE_METASTORE_PARTITION_FILTER" : {
"message" : [
"Failed to get partition metadata by filter from Hive metastore.",
"To work around this issue, set '<hiveMetastorePartitionPruningFallbackOnException>' to true. Note that this may result in degraded performance as Spark will fetch all partition metadata instead of filtering at the metastore level.",
"To report this issue, visit: https://issues.apache.org/jira/browse/SPARK"
],
"sqlState" : "XX000"
},
"INTERNAL_ERROR_MEMORY" : {
"message" : [
"<message>"
Expand Down Expand Up @@ -9028,11 +9036,6 @@
"Partition filter cannot have both `\"` and `'` characters."
]
},
"_LEGACY_ERROR_TEMP_2193" : {
"message" : [
"Caught Hive MetaException attempting to get partition metadata by filter from Hive. You can set the Spark configuration setting <hiveMetastorePartitionPruningFallbackOnException> to true to work around this problem, however this will result in degraded performance. Please report a bug: https://issues.apache.org/jira/browse/SPARK."
]
},
"_LEGACY_ERROR_TEMP_2194" : {
"message" : [
"Unsupported Hive Metastore version <version>. Please set <key> with a valid version."
Expand Down
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1667,7 +1667,7 @@ private[sql] object QueryExecutionErrors extends QueryErrorsBase with ExecutionE

def getPartitionMetadataByFilterError(e: Exception): SparkRuntimeException = {
new SparkRuntimeException(
errorClass = "_LEGACY_ERROR_TEMP_2193",
errorClass = "INTERNAL_ERROR_HIVE_METASTORE_PARTITION_FILTER",
messageParameters = Map(
"hiveMetastorePartitionPruningFallbackOnException" ->
SQLConf.HIVE_METASTORE_PARTITION_PRUNING_FALLBACK_ON_EXCEPTION.key),
Expand Down
2 changes: 1 addition & 1 deletion sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -573,7 +573,7 @@ abstract class ExternalCatalogSuite extends SparkFunSuite {
// then be caught and converted to a RuntimeException with a descriptive message.
case ex: RuntimeException if ex.getMessage.contains("MetaException") =>
throw new AnalysisException(
errorClass = "_LEGACY_ERROR_TEMP_2193",
errorClass = "INTERNAL_ERROR_HIVE_METASTORE_PARTITION_FILTER",
messageParameters = Map(
"hiveMetastorePartitionPruningFallbackOnException" ->
SQLConf.HIVE_METASTORE_PARTITION_PRUNING_FALLBACK_ON_EXCEPTION.key))
Expand Down
14 changes: 9 additions & 5 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe
import org.apache.hadoop.mapred.TextInputFormat
import org.scalatest.BeforeAndAfterAll

import org.apache.spark.SparkRuntimeException
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.catalog._
import org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils.DEFAULT_PARTITION_NAME
Expand Down Expand Up @@ -142,11 +143,14 @@ class HivePartitionFilteringSuite(version: String)

test(s"getPartitionsByFilter should fail when $fallbackKey=false") {
withSQLConf(fallbackKey -> "false") {
val e = intercept[RuntimeException](
clientWithoutDirectSql.getPartitionsByFilter(
clientWithoutDirectSql.getRawHiveTable("default", "test"),
Seq(attr("ds") === 20170101)))
assert(e.getMessage.contains("Caught Hive MetaException"))
checkError(
exception = intercept[SparkRuntimeException](
clientWithoutDirectSql.getPartitionsByFilter(
clientWithoutDirectSql.getRawHiveTable("default", "test"),
Seq(attr("ds") === 20170101))),
condition = "INTERNAL_ERROR_HIVE_METASTORE_PARTITION_FILTER",
parameters = Map("hiveMetastorePartitionPruningFallbackOnException" ->
SQLConf.HIVE_METASTORE_PARTITION_PRUNING_FALLBACK_ON_EXCEPTION.key))
}
}

Expand Down