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_r402386522
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/FileStreamSinkLogSuite.scala
##########
@@ -267,4 +308,38 @@ class FileStreamSinkLogSuite extends SparkFunSuite with
SharedSparkSession {
val log = new FileStreamSinkLog(FileStreamSinkLog.VERSION, spark,
input.toString)
log.allFiles()
}
+
+ private def withCountOpenLocalFileSystemAsLocalFileSystem(body: => Unit):
Unit = {
+ val optionKey = s"fs.${CountOpenLocalFileSystem.scheme}.impl"
+ val originClassForLocalFileSystem = spark.conf.getOption(optionKey)
+ try {
+ spark.conf.set(optionKey, classOf[CountOpenLocalFileSystem].getName)
+ body
+ } finally {
+ originClassForLocalFileSystem match {
+ case Some(fsClazz) => spark.conf.set(optionKey, fsClazz)
+ case _ => spark.conf.unset(optionKey)
+ }
+ }
+ }
+}
+
+class CountOpenLocalFileSystem extends RawLocalFileSystem {
+ import CountOpenLocalFileSystem._
+
+ override def getUri: URI = {
+ URI.create(s"$scheme:///")
+ }
+
+ override def open(f: Path, bufferSize: Int): FSDataInputStream = {
+ val path = f.toUri.getPath
+ val curVal = pathToNumOpenCalled.getOrElseUpdate(path, new AtomicLong(0))
+ curVal.incrementAndGet()
+ super.open(f, bufferSize)
+ }
+}
+
+object CountOpenLocalFileSystem {
+ val scheme = s"FileStreamSinkLogSuite${math.abs(Random.nextInt)}fs"
+ val pathToNumOpenCalled = new mutable.HashMap[String, AtomicLong]
Review comment:
Some reset functionality would be good to make it re-usable. This would also
make `curCount` disappear.
----------------------------------------------------------------
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
