Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/15089#discussion_r81234675
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/RowQueue.scala ---
@@ -0,0 +1,277 @@
+/*
+* 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.python
+
+import java.io._
+
+import com.google.common.io.Closeables
+
+import org.apache.spark.SparkException
+import org.apache.spark.memory.{MemoryConsumer, TaskMemoryManager}
+import org.apache.spark.sql.catalyst.expressions.UnsafeRow
+import org.apache.spark.unsafe.Platform
+import org.apache.spark.unsafe.memory.MemoryBlock
+
+/**
+ * A RowQueue is an FIFO queue for UnsafeRow.
+ *
+ * This RowQueue is ONLY designed and used for Python UDF, which has only
one writer and only one
+ * reader, the reader ALWAYS ran behind the writer. See the doc of class
[[BatchEvalPythonExec]]
+ * on how it works.
+ */
+private[python] trait RowQueue {
+
+ /**
+ * Add a row to the end of it, returns true iff the row has added into
it.
+ */
+ def add(row: UnsafeRow): Boolean
+
+ /**
+ * Retrieve and remove the first row, returns null if it's empty.
+ *
+ * It can only be called after add is called.
+ */
+ def remove(): UnsafeRow
+
+ /**
+ * Cleanup all the resources.
+ */
+ def close(): Unit
+}
+
+/**
+ * A RowQueue that is based on in-memory page. UnsafeRows are appended
into it until it's full.
+ * Another thread could read from it at the same time (behind the writer).
+ *
+ * The format of UnsafeRow in page:
+ * [4 bytes to hold length of record (N)] [N bytes to hold record] [...]
+ */
+private[python] abstract class InMemoryRowQueue(val page: MemoryBlock,
numFields: Int)
--- End diff --
can we add more asserts everywhere to guard the invariant readOffset <=
writeOffset?
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
