siying commented on code in PR #48355:
URL: https://github.com/apache/spark/pull/48355#discussion_r1868173630
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala:
##########
@@ -299,20 +313,33 @@ class RocksDBFileManager(
}
// Get latest snapshot version <= version
- def getLatestSnapshotVersion(version: Long): Long = {
+ def getLatestSnapshotVersionAndUniqueId(
+ version: Long, checkpointUniqueId: Option[String] = None): Array[(Long,
Option[String])] = {
val path = new Path(dfsRootDir)
if (fm.exists(path)) {
// If the latest version snapshot exists, we avoid listing.
- if (fm.exists(dfsBatchZipFile(version))) {
- return version
+ if (fm.exists(dfsBatchZipFile(version, checkpointUniqueId))) {
+ return Array((version, checkpointUniqueId))
+ } else if (fm.exists(dfsBatchZipFile(version))) {
+ // This is possible when the state was previously ran under checkpoint
format v1
+ // and restarted with v2. Then even if there is checkpointUniqueId
passed in, the file
+ // does not have that uniqueId in the filename.
+ return Array((version, None))
}
- fm.list(path, onlyZipFiles)
- .map(_.getPath.getName.stripSuffix(".zip"))
- .map(_.toLong)
- .filter(_ <= version)
- .foldLeft(0L)(math.max)
+ val versionAndUniqueIds = fm.list(path, onlyZipFiles)
+ .map(_.getPath.getName.stripSuffix(".zip").split("_"))
+ .filter {
+ case Array(ver, _) => ver.toLong <= version
+ case Array(ver) => ver.toLong <= version
+ }
+ .map {
+ case Array(version, uniqueId) => (version.toLong, Option(uniqueId))
+ case Array(version) => (version.toLong, None)
+ }
+ val maxVersion = versionAndUniqueIds.map(_._1).foldLeft(0L)(math.max)
+ versionAndUniqueIds.filter(_._1 == maxVersion)
Review Comment:
@WweiL I feel like I've been repeating it. Yes, the logic currently is where
you pointed to, but it should be moved to where I pointed to. The code as it is
written now is problematic, as `latestSnapshotVersionsAndUniqueIds` may not
contain the correct snapshot we look for.
--
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]
