gaborgsomogyi commented on a change in pull request #27664: [SPARK-30915][SS]
FileStreamSink: Avoid reading the metadata log file when finding the latest
batch ID
URL: https://github.com/apache/spark/pull/27664#discussion_r402388241
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/FileStreamSinkLogSuite.scala
##########
@@ -240,6 +247,40 @@ class FileStreamSinkLogSuite extends SparkFunSuite with
SharedSparkSession {
))
}
+ test("getLatestBatchId") {
+ withCountOpenLocalFileSystemAsLocalFileSystem {
+ val scheme = CountOpenLocalFileSystem.scheme
+ withSQLConf(SQLConf.FILE_SINK_LOG_COMPACT_INTERVAL.key -> "3") {
+ withTempDir { file =>
+ val sinkLog = new FileStreamSinkLog(FileStreamSinkLog.VERSION, spark,
+ s"$scheme:///${file.getCanonicalPath}")
+ for (batchId <- 0 to 2) {
+ sinkLog.add(
+ batchId,
+ Array(newFakeSinkFileStatus("/a/b/" + batchId,
FileStreamSinkLog.ADD_ACTION)))
+ }
+
+ def getCountForOpenOnMetadataFile(batchId: Long): Long = {
+ val path = sinkLog.batchIdToPath(batchId).toUri.getPath
+ CountOpenLocalFileSystem.pathToNumOpenCalled
+ .get(path).map(_.get()).getOrElse(0)
+ }
+
+ val curCount = getCountForOpenOnMetadataFile(2)
+
+ assert(sinkLog.getLatestBatchId() === Some(2))
+ // getLatestBatchId doesn't open the latest metadata log file
+ assert(getCountForOpenOnMetadataFile(2L) === curCount)
Review comment:
Maybe worth to check other batches as well.
----------------------------------------------------------------
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
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
