cloud-fan commented on a change in pull request #34684:
URL: https://github.com/apache/spark/pull/34684#discussion_r759942207
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala
##########
@@ -237,7 +238,23 @@ case class CachedRDDBuilder(
}
def isCachedColumnBuffersLoaded: Boolean = {
- _cachedColumnBuffers != null
+ _cachedColumnBuffers != null && isCachedRDDLoaded
+ }
+
+ def isCachedRDDLoaded: Boolean = {
+ if (_cachedColumnBuffersAreLoaded) {
+ _cachedColumnBuffersAreLoaded
+ } else {
+ val rddLoaded = _cachedColumnBuffers.partitions.forall { partition =>
+ SparkEnv.get.blockManager.master
+ .getBlockStatus(RDDBlockId(_cachedColumnBuffers.id,
partition.index), false)
+ .exists { case(_, blockStatus) => blockStatus.isCached }
+ }
+ if (rddLoaded) {
+ _cachedColumnBuffersAreLoaded = rddLoaded
+ }
+ rddLoaded
+ }
Review comment:
```suggestion
_cachedColumnBuffersAreLoaded || {
val bmMaster = SparkEnv.get.blockManager.master
val rddLoaded = _cachedColumnBuffers.partitions.forall { partition =>
bmMaster.getBlockStatus(RDDBlockId(_cachedColumnBuffers.id,
partition.index), false)
.exists { case(_, blockStatus) => blockStatus.isCached }
}
_cachedColumnBuffersAreLoaded = rddLoaded
_cachedColumnBuffersAreLoaded
}
```
--
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]
