ericm-db commented on code in PR #56018:
URL: https://github.com/apache/spark/pull/56018#discussion_r3326377459
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/OfflineStateRepartitionRunner.scala:
##########
@@ -294,7 +294,10 @@ class OfflineStateRepartitionRunner(
lastCommittedBatchId: Long,
opIdToStateStoreCkptInfo: Option[Map[Long, Array[Array[String]]]]): Unit
= {
val latestCommit =
checkpointMetadata.commitLog.get(lastCommittedBatchId).get
- val commitMetadata = latestCommit.copy(stateUniqueIds =
opIdToStateStoreCkptInfo)
+ val commitMetadata = checkpointMetadata.commitLog.createMetadata(
Review Comment:
The reason it wasn't .copy() is that latestCommit is now statically a
CommitMetadataBase (the trait), which has no copy, so I just added a new method
that should be more explicit about this.
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/checkpointing/CommitLog.scala:
##########
@@ -50,39 +51,99 @@ class CommitLog(
sparkSession: SparkSession,
path: String,
readOnly: Boolean = false)
- extends HDFSMetadataLog[CommitMetadata](sparkSession, path, readOnly) {
+ extends HDFSMetadataLog[CommitMetadataBase](sparkSession, path, readOnly) {
import CommitLog._
- private val VERSION: Int = sparkSession.conf.get(
+ // The configured commit log format version. Used as the default version
when callers
+ // construct metadata through [[createMetadata]].
+ private[sql] val VERSION: Int = sparkSession.conf.get(
Review Comment:
Done
--
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]
