diff options
author | Sean Owen <sowen@cloudera.com> | 2014-05-12 14:16:19 -0700 |
---|---|---|
committer | Patrick Wendell <pwendell@gmail.com> | 2014-05-12 14:16:33 -0700 |
commit | 14515b416e9a00cb3a77c2645984265b30b05882 (patch) | |
tree | 09bb1756961915015ed9b64ccc3e27199ea13343 /streaming/src/test | |
parent | 722ecaa0195674be1b69c2f0a50fe21f3cf62ffc (diff) | |
download | spark-14515b416e9a00cb3a77c2645984265b30b05882.tar.gz spark-14515b416e9a00cb3a77c2645984265b30b05882.tar.bz2 spark-14515b416e9a00cb3a77c2645984265b30b05882.zip |
SPARK-1798. Tests should clean up temp files
Three issues related to temp files that tests generate – these should be touched up for hygiene but are not urgent.
Modules have a log4j.properties which directs the unit-test.log output file to a directory like `[module]/target/unit-test.log`. But this ends up creating `[module]/[module]/target/unit-test.log` instead of former.
The `work/` directory is not deleted by "mvn clean", in the parent and in modules. Neither is the `checkpoint/` directory created under the various external modules.
Many tests create a temp directory, which is not usually deleted. This can be largely resolved by calling `deleteOnExit()` at creation and trying to call `Utils.deleteRecursively` consistently to clean up, sometimes in an `@After` method.
_If anyone seconds the motion, I can create a more significant change that introduces a new test trait along the lines of `LocalSparkContext`, which provides management of temp directories for subclasses to take advantage of._
Author: Sean Owen <sowen@cloudera.com>
Closes #732 from srowen/SPARK-1798 and squashes the following commits:
5af578e [Sean Owen] Try to consistently delete test temp dirs and files, and set deleteOnExit() for each
b21b356 [Sean Owen] Remove work/ and checkpoint/ dirs with mvn clean
bdd0f41 [Sean Owen] Remove duplicate module dir in log4j.properties output path for tests
(cherry picked from commit 7120a2979d0a9f0f54a88b2416be7ca10e74f409)
Signed-off-by: Patrick Wendell <pwendell@gmail.com>
Diffstat (limited to 'streaming/src/test')
4 files changed, 8 insertions, 2 deletions
diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java index f9bfb9b744..ce58cb12a4 100644 --- a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java +++ b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java @@ -17,7 +17,6 @@ package org.apache.spark.streaming; -import org.apache.spark.streaming.api.java.*; import scala.Tuple2; import org.junit.Assert; @@ -37,6 +36,8 @@ import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.*; import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.api.java.*; +import org.apache.spark.util.Utils; // The test suite itself is Serializable so that anonymous Function implementations can be // serialized, as an alternative to converting these anonymous classes to static inner classes; @@ -1606,6 +1607,7 @@ public class JavaAPISuite extends LocalJavaStreamingContext implements Serializa Arrays.asList(8,7)); File tempDir = Files.createTempDir(); + tempDir.deleteOnExit(); ssc.checkpoint(tempDir.getAbsolutePath()); JavaDStream<String> stream = JavaCheckpointTestUtils.attachTestInputStream(ssc, inputData, 1); @@ -1627,6 +1629,7 @@ public class JavaAPISuite extends LocalJavaStreamingContext implements Serializa // will be re-processed after recovery List<List<Integer>> finalResult = JavaCheckpointTestUtils.runStreams(ssc, 2, 3); assertOrderInvariantEquals(expectedFinal, finalResult.subList(1, 3)); + Utils.deleteRecursively(tempDir); } diff --git a/streaming/src/test/resources/log4j.properties b/streaming/src/test/resources/log4j.properties index 063529a9cb..45d2ec676d 100644 --- a/streaming/src/test/resources/log4j.properties +++ b/streaming/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala index 25739956cb..d20a7b728c 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala @@ -232,6 +232,7 @@ class CheckpointSuite extends TestSuiteBase { test("recovery with file input stream") { // Set up the streaming context and input streams val testDir = Files.createTempDir() + testDir.deleteOnExit() var ssc = new StreamingContext(master, framework, Seconds(1)) ssc.checkpoint(checkpointDir) val fileStream = ssc.textFileStream(testDir.toString) @@ -326,6 +327,7 @@ class CheckpointSuite extends TestSuiteBase { ) // To ensure that all the inputs were received correctly assert(expectedOutput.last === output.last) + Utils.deleteRecursively(testDir) } diff --git a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala index 3fa254065c..cd0aa4d0dc 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala @@ -98,6 +98,7 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { // Set up the streaming context and input streams val testDir = Files.createTempDir() + testDir.deleteOnExit() val ssc = new StreamingContext(conf, batchDuration) val fileStream = ssc.textFileStream(testDir.toString) val outputBuffer = new ArrayBuffer[Seq[String]] with SynchronizedBuffer[Seq[String]] |