srielau commented on code in PR #58317:
URL: https://github.com/apache/spark/pull/58317#discussion_r3994269255
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala:
##########
@@ -348,6 +349,45 @@ class CacheManager extends Logging with
AdaptiveSparkPlanHelper {
recacheByCondition(spark, _.plan.exists(_.sameResult(normalized)))
}
+ /**
+ * Re-caches every entry whose plan contains a [[LogicalRelation]] for
`relation`.
+ * Unlike [[recacheByPlan]], this ignores CHAR/VARCHAR scan-mode identity so
a V1 write
+ * invalidates preserve-only, standard, and unbound cache entries for that
BaseRelation.
+ */
+ def recacheByV1Relation(spark: SparkSession, relation: BaseRelation): Unit =
{
+ recacheByCondition(spark, cd => cd.plan.exists {
+ case logical: LogicalRelation => logical.relation == relation
+ case _ => false
+ })
+ }
+
+ /**
+ * Re-caches every entry whose plan contains the given catalog-less
[[DataSourceV2Relation]].
+ * The scan mode is ignored only for this mutation-specific match so an
unbound write target
+ * invalidates preserve-native and standard cache entries without weakening
normal cache identity.
+ */
+ def recacheByV2Relation(spark: SparkSession, relation:
DataSourceV2Relation): Unit = {
+ val unboundRelation = relation.copy(charVarcharScanMode = None)
+ recacheByCondition(spark, cd => cd.plan.exists {
+ case cached: DataSourceV2Relation =>
+ cached.copy(charVarcharScanMode = None).sameResult(unboundRelation)
+ case _ => false
+ })
+ }
+
+ /**
+ * Looks up a cache entry for a V2 table mutation while ignoring only its
analyzed CHAR/VARCHAR
+ * scan mode. Normal cache substitution remains mode-sensitive.
+ */
+ def lookupCachedDataByV2Relation(relation: DataSourceV2Relation):
Option[CachedData] = {
+ val unboundRelation = relation.copy(charVarcharScanMode = None)
+ cachedData.find(_.plan.exists {
Review Comment:
Fixed in 4854ae0cf89. The mutation-specific lookup now compares only the
complete cache-key root after eliminating aliases and clearing the scan mode,
so dependent query caches are excluded. It returns every direct mode variant,
and rename restores each variant with its original storage level. Tests cover
dependent-only caching and simultaneous PreserveNative/SparkStandard caches.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
