Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/5473#discussion_r29319001
--- Diff:
streaming/src/main/scala/org/apache/spark/streaming/ui/BatchUIData.scala ---
@@ -0,0 +1,96 @@
+/*
+ * 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.streaming.ui
+
+import org.apache.spark.streaming.Time
+import org.apache.spark.streaming.scheduler.BatchInfo
+import org.apache.spark.streaming.ui.StreamingJobProgressListener._
+
+private[ui] case class OutputOpIdAndSparkJobId(outputOpId: OutputOpId,
sparkJobId: SparkJobId)
+
+private[ui] class BatchUIData(
+ val batchTime: Time,
+ val receiverNumRecords: Map[Int, Long],
+ val submissionTime: Long,
+ val processingStartTime: Option[Long],
+ val processingEndTime: Option[Long]) {
+
+ var outputOpIdSparkJobIdPairs: Seq[OutputOpIdAndSparkJobId] = Seq.empty
+
+ /**
+ * Time taken for the first job of this batch to start processing from
the time this batch
+ * was submitted to the streaming scheduler. Essentially, it is
+ * `processingStartTime` - `submissionTime`.
+ */
+ def schedulingDelay: Option[Long] = processingStartTime.map(_ -
submissionTime)
+
+ /**
+ * Time taken for the all jobs of this batch to finish processing from
the time they started
+ * processing. Essentially, it is `processingEndTime` -
`processingStartTime`.
+ */
+ def processingDelay: Option[Long] = {
+ for (start <- processingStartTime;
+ end <- processingEndTime)
+ yield end - start
+ }
+
+ /**
+ * Time taken for all the jobs of this batch to finish processing from
the time they
+ * were submitted. Essentially, it is `processingDelay` +
`schedulingDelay`.
+ */
+ def totalDelay: Option[Long] = processingEndTime.map(_ - submissionTime)
+
+ /**
+ * The number of recorders received by the receivers in this batch.
+ */
+ def numRecords: Long = receiverNumRecords.map(_._2).sum
+
+ def canEqual(other: Any): Boolean = other.isInstanceOf[BatchUIData]
+
+ override def equals(other: Any): Boolean = other match {
--- End diff --
What is `equals` and `hashCode` useful for? Unit tests? If so, then could
this be a case class?
---
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]
