dongjoon-hyun commented on a change in pull request #24047: [SPARK-25196][SQL]
Extends Analyze commands for cached tables
URL: https://github.com/apache/spark/pull/24047#discussion_r265299548
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala
##########
@@ -181,6 +182,38 @@ class CacheManager extends Logging {
}
}
+ private[sql] def analyzeColumnCacheQuery(
+ query: Dataset[_],
+ column: Seq[Attribute]): Unit = writeLock {
+ val cachedData = lookupCachedData(query)
+ if (cachedData.isEmpty) {
+ logWarning("The cached data not found, so you need to cache the query
first.")
+ } else {
+ cachedData.foreach { cachedData =>
+ val relation = cachedData.cachedRepresentation
+ val (rowCount, newColStats) =
+ CommandUtils.computeColumnStats(query.sparkSession, relation, column)
+ val oldStats = relation.statsOfPlanToCache
+ val newStats = oldStats.copy(
+ rowCount = Some(rowCount),
+ attributeStats = AttributeMap((oldStats.attributeStats ++
newColStats).toSeq)
+ )
+ relation.statsOfPlanToCache = newStats
+ }
+ }
+ }
+
+ /**
+ * Analyzes column statistics in an already-cached table.
+ *
+ * @param spark The Spark session.
+ * @param tableName The identifier of a cached table.
Review comment:
`identifier` -> `name`?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
