This is an automated email from the ASF dual-hosted git repository.
HyukjinKwon pushed a commit to branch branch-4.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.0 by this push:
new f1655fd60c2e [SPARK-57652][SS][TESTS] Deflake
snapshotStartBatchId-with-transformWithState StateDataSource test
f1655fd60c2e is described below
commit f1655fd60c2ec8e01478332d1be2ed4abf232a66
Author: Hyukjin Kwon <[email protected]>
AuthorDate: Mon Jul 6 12:41:32 2026 +0900
[SPARK-57652][SS][TESTS] Deflake
snapshotStartBatchId-with-transformWithState StateDataSource test
Replace the fixed Thread.sleep(5000) in the "snapshotStartBatchId with
transformWithState" test of
StateDataSourceTransformWithStateSuite with a deterministic eventually(...)
wait that polls until the
RocksDB snapshot files the reader needs (snapshot version 2 for the
partitions read) have actually
been uploaded by the asynchronous maintenance thread. The timeout assertion
prints the state-directory
contents so a recurrence is diagnosable. Test-only.
Backport of SPARK-57652 to branch-4.0. The fix is on master (850a41e0) and
branch-4.2/4.1 but was not
on branch-4.0, so branch-4.0 build_maven fails on the (encoding = avro)
case with
FileNotFoundException .../state/0/1/2.zip.
(cherry picked from commit 850a41e0623834c9b7eb5457692f08b61b8d770a)
Co-authored-by: Isaac
---
.../StateDataSourceTransformWithStateSuite.scala | 32 ++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTransformWithStateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTransformWithStateSuite.scala
index 7d242c7444f1..a0a617279b8c 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTransformWithStateSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceTransformWithStateSuite.scala
@@ -20,6 +20,7 @@ import java.io.File
import java.time.Duration
import org.apache.hadoop.conf.Configuration
+import org.scalatest.time.SpanSugar._
import org.apache.spark.io.CompressionCodec
import org.apache.spark.sql.{Encoders, Row}
@@ -1050,20 +1051,47 @@ class StateDataSourceTransformWithStateSuite extends
StateStoreMetricsTest
.transformWithState(new AggregationStatefulProcessor(),
TimeMode.None(),
OutputMode.Append())
+
+ // Block until the async maintenance thread has written the RocksDB
snapshot `.zip` for the
+ // given state-store `version` (matching both `<v>.zip` and
checkpoint-v2 `<v>_<uid>.zip`)
+ // on each of `partitions`. Used right after `version` is committed
(while it is the current
+ // version), since maintenance only ever snapshots the current
version. On timeout it prints
+ // the actual directory contents so a recurrence in scheduled jobs is
diagnosable.
+ def waitForStateSnapshot(version: Long, partitions: Seq[Int]):
StreamAction = Execute { _ =>
+ val opStateDir = new File(tmpDir, "state/0")
+ eventually(timeout(60.seconds), interval(100.milliseconds)) {
+ partitions.foreach { partition =>
+ val partitionDir = new File(opStateDir, partition.toString)
+ val files = Option(partitionDir.listFiles())
+ .map(_.map(_.getName).sorted.toSeq).getOrElse(Seq.empty)
+ val snapshotUploaded =
files.exists(_.matches(s"$version(_.*)?\\.zip"))
+ assert(snapshotUploaded,
+ s"Snapshot (version $version) for partition $partition was not
uploaded in time. " +
+ s"Contents of $partitionDir: ${files.mkString("[", ", ",
"]")}")
+ }
+ }
+ }
+
testStream(query)(
StartStream(checkpointLocation = tmpDir.getCanonicalPath),
AddData(inputData, (1, 1L), (2, 2L), (3, 3L), (4, 4L)),
ProcessAllAvailable(),
AddData(inputData, (5, 1L), (6, 2L), (7, 3L), (8, 4L)),
ProcessAllAvailable(),
+ // State version 2 is now the current version. The
snapshotStartBatchId=1 reader below
+ // needs the version-2 snapshot, and the asynchronous maintenance
thread only creates a
+ // snapshot for the *current* version. So block here, while version
2 is still current,
+ // until that snapshot has actually been written - this
deterministically forces it to
+ // exist. (A fixed sleep at the *end* is flaky: once later batches
advance the current
+ // version, maintenance never goes back to snapshot version 2, so it
may never appear and
+ // the reader fails with FileNotFoundException on `2.zip`.)
+ waitForStateSnapshot(version = 2, partitions = Seq(1, 4)),
AddData(inputData, (9, 1L), (10, 2L), (11, 3L), (12, 4L)),
ProcessAllAvailable(),
AddData(inputData, (13, 1L), (14, 2L), (15, 3L), (16, 4L)),
ProcessAllAvailable(),
AddData(inputData, (17, 1L), (18, 2L), (19, 3L), (20, 4L)),
ProcessAllAvailable(),
- // Ensure that we get a chance to upload created snapshots
- Execute { _ => Thread.sleep(5000) },
StopStream
)
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
