Github user cenyuhai commented on a diff in the pull request:
https://github.com/apache/spark/pull/18193#discussion_r123903846
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala ---
@@ -139,6 +138,54 @@ class DetermineTableStats(session: SparkSession)
extends Rule[LogicalPlan] {
}
}
+case class DeterminePartitionedTableStats(
+ session: SparkSession) extends Rule[LogicalPlan] with PredicateHelper {
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown {
+ case filter @ Filter(condition, relation: CatalogRelation)
+ if DDLUtils.isHiveTable(relation.tableMeta) &&
relation.isPartitioned =>
+ val predicates = splitConjunctivePredicates(condition)
+ val normalizedFilters = predicates.map { e =>
+ e transform {
+ case a: AttributeReference =>
+ a.withName(relation.output.find(_.semanticEquals(a)).get.name)
+ }
+ }
+ val partitionSet = AttributeSet(relation.partitionCols)
+ val pruningPredicates = normalizedFilters.filter { predicate =>
+ !predicate.references.isEmpty &&
+ predicate.references.subsetOf(partitionSet)
+ }
+ if (pruningPredicates.nonEmpty &&
session.sessionState.conf.fallBackToHdfsForStatsEnabled &&
+ session.sessionState.conf.metastorePartitionPruning) {
+ val prunedPartitions =
session.sharedState.externalCatalog.listPartitionsByFilter(
+ relation.tableMeta.database,
+ relation.tableMeta.identifier.table,
+ pruningPredicates,
+ session.sessionState.conf.sessionLocalTimeZone)
+ val hiveTable = HiveClientImpl.toHiveTable(relation.tableMeta)
+ val partitions =
prunedPartitions.map(HiveClientImpl.toHivePartition(_, hiveTable))
+ val sizeInBytes = try {
+ val hadoopConf = session.sessionState.newHadoopConf()
+ partitions.map { partition =>
+ val fs: FileSystem =
partition.getDataLocation.getFileSystem(hadoopConf)
+ fs.getContentSummary(partition.getDataLocation).getLength
+ }.sum
--- End diff --
if there are too many partitions, it will be very slow.
can you add a check that whether the sum is larger than threshold, if true
then break.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
