HeartSaVioR commented on a change in pull request #31495:
URL: https://github.com/apache/spark/pull/31495#discussion_r571523237
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala
##########
@@ -46,6 +47,23 @@ import org.apache.spark.sql.connector.read.streaming.{Offset
=> OffsetV2}
class OffsetSeqLog(sparkSession: SparkSession, path: String)
extends HDFSMetadataLog[OffsetSeq](sparkSession, path) {
+ private val cachedMetadata = new ju.TreeMap[Long, OffsetSeq]()
+
+ override def add(batchId: Long, metadata: OffsetSeq): Boolean = {
+ val added = super.add(batchId, metadata)
+ if (added) {
+ // cache metadata as it will be read again
+ cachedMetadata.put(batchId, metadata)
+ // we don't access metadata for (batchId - 2) batches; evict them
Review comment:
TreeMap approach is pretty much intuitive compared to this, and the
overhead should be pretty much trivial compared to FS ops. Let's not do
over-engineering.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
