You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by GitBox <gi...@apache.org> on 2022/12/23 19:17:12 UTC
[GitHub] [hadoop] ayushtkn commented on a diff in pull request #5251: HADOOP-18582. skip unnecessary cleanup logic in distcp
ayushtkn commented on code in PR #5251:
URL: https://github.com/apache/hadoop/pull/5251#discussion_r1056612556
##########
hadoop-tools/hadoop-distcp/src/test/java/org/apache/hadoop/tools/mapred/TestCopyCommitter.java:
##########
@@ -580,6 +580,72 @@ fs, new Path(sourceBase + srcFilename), null,
}
}
+ @Test
+ public void testCommitWithCleanupTempFiles() throws IOException {
+ testCommitWithCleanup(true,false);
+ testCommitWithCleanup(false,true);
+ testCommitWithCleanup(true,true);
+ testCommitWithCleanup(false,false);
+ }
+
+ private void testCommitWithCleanup(boolean append, boolean directWrite)throws IOException {
+ TaskAttemptContext taskAttemptContext = getTaskAttemptContext(config);
+ JobID jobID = taskAttemptContext.getTaskAttemptID().getJobID();
+ JobContext jobContext = new JobContextImpl(
+ taskAttemptContext.getConfiguration(),
+ jobID);
+ Configuration conf = jobContext.getConfiguration();
+
+ String sourceBase;
+ String targetBase;
+ FileSystem fs = null;
+ try {
+ fs = FileSystem.get(conf);
+ sourceBase = "/tmp1/" + String.valueOf(rand.nextLong());
+ targetBase = "/tmp1/" + String.valueOf(rand.nextLong());
Review Comment:
``String.valueOf`` isn't required
##########
hadoop-tools/hadoop-distcp/src/test/java/org/apache/hadoop/tools/mapred/TestCopyCommitter.java:
##########
@@ -580,6 +580,72 @@ fs, new Path(sourceBase + srcFilename), null,
}
}
+ @Test
+ public void testCommitWithCleanupTempFiles() throws IOException {
+ testCommitWithCleanup(true,false);
+ testCommitWithCleanup(false,true);
+ testCommitWithCleanup(true,true);
+ testCommitWithCleanup(false,false);
+ }
+
+ private void testCommitWithCleanup(boolean append, boolean directWrite)throws IOException {
+ TaskAttemptContext taskAttemptContext = getTaskAttemptContext(config);
+ JobID jobID = taskAttemptContext.getTaskAttemptID().getJobID();
+ JobContext jobContext = new JobContextImpl(
+ taskAttemptContext.getConfiguration(),
+ jobID);
+ Configuration conf = jobContext.getConfiguration();
+
+ String sourceBase;
+ String targetBase;
+ FileSystem fs = null;
+ try {
+ fs = FileSystem.get(conf);
+ sourceBase = "/tmp1/" + String.valueOf(rand.nextLong());
+ targetBase = "/tmp1/" + String.valueOf(rand.nextLong());
+
+ DistCpOptions options = new DistCpOptions.Builder(
+ Collections.singletonList(new Path(sourceBase)),
+ new Path("/out"))
+ .withAppend(append)
+ .withSyncFolder(true)
+ .withDirectWrite(directWrite)
+ .build();
+ options.appendToConf(conf);
+
+ DistCpContext context = new DistCpContext(options);
+ context.setTargetPathExists(false);
+
+
+ conf.set(CONF_LABEL_TARGET_WORK_PATH, targetBase);
+ conf.set(CONF_LABEL_TARGET_FINAL_PATH, targetBase);
+
+ Path tempFilePath = getTempFile(targetBase, taskAttemptContext);
+ createDirectory(fs, tempFilePath);
+
+ OutputCommitter committer = new CopyCommitter(
+ null, taskAttemptContext);
+ committer.commitJob(jobContext);
+
+ if (append || directWrite) {
+ Assert.assertTrue(fs.exists(tempFilePath));
+ }else {
+ Assert.assertFalse(fs.exists(tempFilePath));
+ }
+ } finally {
+ TestDistCpUtils.delete(fs, "/tmp1");
+ TestDistCpUtils.delete(fs, "/meta");
+ }
+ }
+
+ private Path getTempFile(String targetWorkPath, TaskAttemptContext taskAttemptContext) {
+ Path tempFile = new Path(targetWorkPath, ".distcp.tmp." +
+ taskAttemptContext.getTaskAttemptID().toString() +
+ "." + String.valueOf(System.currentTimeMillis()));
Review Comment:
``String.valueOf(`` not required
##########
hadoop-tools/hadoop-distcp/src/test/java/org/apache/hadoop/tools/mapred/TestCopyCommitter.java:
##########
@@ -580,6 +580,72 @@ fs, new Path(sourceBase + srcFilename), null,
}
}
+ @Test
+ public void testCommitWithCleanupTempFiles() throws IOException {
+ testCommitWithCleanup(true,false);
+ testCommitWithCleanup(false,true);
+ testCommitWithCleanup(true,true);
+ testCommitWithCleanup(false,false);
+ }
+
+ private void testCommitWithCleanup(boolean append, boolean directWrite)throws IOException {
+ TaskAttemptContext taskAttemptContext = getTaskAttemptContext(config);
+ JobID jobID = taskAttemptContext.getTaskAttemptID().getJobID();
+ JobContext jobContext = new JobContextImpl(
+ taskAttemptContext.getConfiguration(),
+ jobID);
+ Configuration conf = jobContext.getConfiguration();
+
+ String sourceBase;
+ String targetBase;
+ FileSystem fs = null;
+ try {
+ fs = FileSystem.get(conf);
+ sourceBase = "/tmp1/" + String.valueOf(rand.nextLong());
+ targetBase = "/tmp1/" + String.valueOf(rand.nextLong());
+
+ DistCpOptions options = new DistCpOptions.Builder(
+ Collections.singletonList(new Path(sourceBase)),
+ new Path("/out"))
+ .withAppend(append)
+ .withSyncFolder(true)
+ .withDirectWrite(directWrite)
+ .build();
+ options.appendToConf(conf);
+
+ DistCpContext context = new DistCpContext(options);
+ context.setTargetPathExists(false);
+
+
+ conf.set(CONF_LABEL_TARGET_WORK_PATH, targetBase);
+ conf.set(CONF_LABEL_TARGET_FINAL_PATH, targetBase);
+
+ Path tempFilePath = getTempFile(targetBase, taskAttemptContext);
+ createDirectory(fs, tempFilePath);
+
+ OutputCommitter committer = new CopyCommitter(
+ null, taskAttemptContext);
+ committer.commitJob(jobContext);
+
+ if (append || directWrite) {
+ Assert.assertTrue(fs.exists(tempFilePath));
+ }else {
Review Comment:
space after }
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org