anishshri-db commented on code in PR #47445:
URL: https://github.com/apache/spark/pull/47445#discussion_r1687022712
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/metadata/StateMetadataSource.scala:
##########
@@ -188,29 +191,56 @@ class StateMetadataPartitionReader(
} else Array.empty
}
- private def allOperatorStateMetadata: Array[OperatorStateMetadata] = {
+ private[sql] def allOperatorStateMetadata: Array[(OperatorStateMetadata,
Long)] = {
val stateDir = new Path(checkpointLocation, "state")
val opIds = fileManager
.list(stateDir, pathNameCanBeParsedAsLongFilter).map(f =>
pathToLong(f.getPath)).sorted
- opIds.map { opId =>
- new OperatorStateMetadataReader(new Path(stateDir, opId.toString),
hadoopConf).read()
+ opIds.flatMap { opId =>
+ val operatorIdPath = new Path(stateDir, opId.toString)
+ // check if OperatorStateMetadataV2 path exists, if it does, read it
Review Comment:
We can already read the version here right ?
--
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]
