steveloughran commented on a change in pull request #1404: HDFS-13660 Copy file till the source file length during distcp URL: https://github.com/apache/hadoop/pull/1404#discussion_r322699792
########## File path: hadoop-tools/hadoop-distcp/src/test/java/org/apache/hadoop/tools/mapred/TestCopyMapper.java ########## @@ -444,6 +449,54 @@ private void testCopyingExistingFiles(FileSystem fs, CopyMapper copyMapper, } } + @Test + public void testCopyWhileAppend() throws Exception { + deleteState(); + mkdirs(SOURCE_PATH + "/1"); + touchFile(SOURCE_PATH + "/1/3"); + CopyMapper copyMapper = new CopyMapper(); + StubContext stubContext = new StubContext(getConfiguration(), null, 0); + Mapper<Text, CopyListingFileStatus, Text, Text>.Context context = + stubContext.getContext(); + copyMapper.setup(context); + final Path path = new Path(SOURCE_PATH + "/1/3"); + int manyBytes = 100000000; + appendFile(path, manyBytes); + ScheduledExecutorService scheduledExecutorService = Executors.newSingleThreadScheduledExecutor(); + Runnable task = new Runnable() { + public void run() { + try { + int maxAppendAttempts = 20; + int appendCount = 0; + while (appendCount < maxAppendAttempts) { + appendFile(path, 1000); + Thread.sleep(200); + appendCount++; + } + } catch (IOException | InterruptedException e) { + e.printStackTrace(); + } + } + }; + scheduledExecutorService.schedule(task, 10, TimeUnit.MILLISECONDS); + boolean isFileMismatchErrorPresent = false; + try { + copyMapper.map(new Text(DistCpUtils.getRelativePath(new Path(SOURCE_PATH), path)), + new CopyListingFileStatus(cluster.getFileSystem().getFileStatus( + path)), context); + } catch (Exception ex) { + StringWriter sw = new StringWriter(); + ex.printStackTrace(new PrintWriter(sw)); + String exceptionAsString = sw.toString(); + if (exceptionAsString.contains("Mismatch in length of source") || + exceptionAsString.contains("Checksum mismatch")) { + isFileMismatchErrorPresent = true; + } + } + Assert.assertFalse(isFileMismatchErrorPresent); + scheduledExecutorService.shutdown(); Review comment: finally clause ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org