Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/21220#discussion_r185973467
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/WatermarkTracker.scala
---
@@ -0,0 +1,75 @@
+/*
+ * 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.execution.streaming
+
+import scala.collection.mutable
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.execution.SparkPlan
+
+class WatermarkTracker extends Logging {
+ private val operatorToWatermarkMap = mutable.HashMap[Int, Long]()
+ private var watermarkMs: Long = 0
+ private var updated = false
+
+ def setWatermark(newWatermarkMs: Long): Unit = synchronized {
+ watermarkMs = newWatermarkMs
+ }
+
+ def updateWatermark(executedPlan: SparkPlan): Unit = synchronized {
+ val watermarkOperators = executedPlan.collect {
--- End diff --
I dont think we do anything that depends on ordering of
EventTimeWatermarkExec. We choose to take the minimum watermark calculated
across multiple of them independent of the order.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
