Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/15949#discussion_r89894205
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamExecutionMetadataSuite.scala
---
@@ -0,0 +1,109 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.streaming
+
+import java.io.File
+
+import org.scalatest.concurrent.Eventually
+import org.scalatest.concurrent.PatienceConfiguration.Timeout
+import org.scalatest.time.SpanSugar._
+
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.execution.streaming.{MemoryStream,
StreamExecutionMetadata}
+import org.apache.spark.sql.functions._
+import org.apache.spark.util.{SystemClock, Utils}
+
+class StreamExecutionMetadataSuite extends StreamTest {
+
+ private def newMetadataDir =
+ Utils.createTempDir(namePrefix = "streaming.metadata").getCanonicalPath
+
+ test("stream execution metadata") {
+ assert(StreamExecutionMetadata(0, 0) ===
+ StreamExecutionMetadata("""{}"""))
+ assert(StreamExecutionMetadata(1, 0) ===
+ StreamExecutionMetadata("""{"batchWatermarkMs":1}"""))
+ assert(StreamExecutionMetadata(0, 2) ===
+ StreamExecutionMetadata("""{"batchTimestampMs":2}"""))
+ assert(StreamExecutionMetadata(1, 2) ===
+ StreamExecutionMetadata(
+ """{"batchWatermarkMs":1,"batchTimestampMs":2}"""))
+ }
+
+ test("metadata is recovered from log when query is restarted") {
--- End diff --
I just tried to write a det test using manual lock:
```
test("metadata is recovered from log when query is restarted") {
import testImplicits._
val clock = new StreamManualClock()
val inputData = MemoryStream[Long]
val df = inputData.toDF()
.select(current_timestamp().cast("long").as[Long])
testStream(df)(
StartStream(trigger = ProcessingTime("1 second"), triggerClock =
clock),
AssertOnQuery { _ =>
// Make sure the clock is waiting. Otherwise, the batch time may be
0 or 1.
eventually(timeout(streamingTimeout)) {
assert(clock.isStreamWaitingAt(0L))
}
true
},
AddData(inputData, 1L), // Trigger one output row
AdvanceManualClock(1000L),
CheckLastBatch(1L),
AddData(inputData, 1L), // Trigger one output row
AdvanceManualClock(1000L),
CheckLastBatch(2L),
StopStream,
AssertOnQuery { q => // clear the sink
q.sink.asInstanceOf[MemorySink].clear()
true
},
StartStream(trigger = ProcessingTime("1 second"), triggerClock =
clock),
CheckLastBatch(2L),
AddData(inputData, 1L), // Trigger one output row
AdvanceManualClock(1000L),
CheckLastBatch(3L)
)
}
```
You can use it to replace yours.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
