Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/11897#discussion_r57089301
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStressSuite.scala ---
@@ -0,0 +1,128 @@
+/*
+ * 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 java.util.UUID
+
+import scala.util.Random
+import scala.util.control.NonFatal
+
+import org.apache.spark.sql.{ContinuousQuery, ContinuousQueryException,
StreamTest}
+import org.apache.spark.sql.catalyst.util._
+import org.apache.spark.sql.test.SharedSQLContext
+import org.apache.spark.util.Utils
+
+/**
+ * A stress test for streamign queries that read and write files. This
test constists of
+ * two threads:
+ * - one that writes out `numRecords` distinct integers to files of
random sizes (the total
+ * number of records is fixed but each files size / creation time is
random).
+ * - another that continually restarts a buggy streaming query (i.e.
fails with 5% probability on
+ * any partition).
+ *
+ * At the end, the resulting files are loaded and the answer is checked.
+ */
+class FileStressSuite extends StreamTest with SharedSQLContext {
+ import testImplicits._
+
+ test("fault tolerance stress test") {
+ val numRecords = 10000
+ val inputDir = Utils.createTempDir("stream.input").getCanonicalPath
+ val stagingDir = Utils.createTempDir("stream.staging").getCanonicalPath
+ val outputDir = Utils.createTempDir("stream.output").getCanonicalPath
+ val checkpoint =
Utils.createTempDir("stream.checkpoint").getCanonicalPath
+
+ @volatile
+ var continue = true
+ var stream: ContinuousQuery = null
--- End diff --
nit: stream should be volatile
---
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]
