Yohahaha commented on code in PR #3260:
URL: https://github.com/apache/fluss/pull/3260#discussion_r3233562433
##########
fluss-spark/fluss-spark-common/src/main/scala/org/apache/fluss/spark/read/FlussBatch.scala:
##########
@@ -91,26 +92,64 @@ class FlussAppendBatch(
}
override def planInputPartitions(): Array[InputPartition] = {
- val bucketOffsetsRetrieverImpl = new BucketOffsetsRetrieverImpl(admin,
tablePath)
+ val maxRecordsPerPartition: Option[Long] = {
+ val opt =
flussConfig.getOptional(SparkFlussConf.SCAN_MAX_RECORDS_PER_PARTITION)
+ if (opt.isPresent) Some(opt.get().longValue()) else None
+ }
+
+ val bucketOffsetsRetrieverImpl = maxRecordsPerPartition match {
+ case Some(_) => new BucketOffsetsRetrieverImpl(admin, tablePath, true)
+ case None => new BucketOffsetsRetrieverImpl(admin, tablePath)
+ }
val buckets = (0 until tableInfo.getNumBuckets).toSeq
+ def splitOffsetRange(
+ tableBucket: TableBucket,
+ startOffset: Long,
+ stopOffset: Long,
+ maxRecords: Long): Seq[InputPartition] = {
+ if (
+ startOffset < 0 || stopOffset <= startOffset || stopOffset <=
(startOffset + maxRecords)
Review Comment:
The startup mode is designed for streaming scenarios. It will not be used in
batch. I will refactor it in a future PR.
--
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]
