jojochuang commented on a change in pull request #919: HADOOP-16158. DistCp to support checksum validation when copy blocks in parallel URL: https://github.com/apache/hadoop/pull/919#discussion_r314540809
########## File path: hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/DistCpUtils.java ########## @@ -583,6 +583,66 @@ public static boolean checksumsAreEqual(FileSystem sourceFS, Path source, sourceChecksum.equals(targetChecksum)); } + /** + * Utility to compare file lengths and checksums for source and target. + * + * @param sourceFS FileSystem for the source path. + * @param source The source path. + * @param sourceChecksum The checksum of the source file. If it is null we + * still need to retrieve it through sourceFS. + * @param targetFS FileSystem for the target path. + * @param target The target path. + * @param skipCrc The flag to indicate whether to skip checksums. + * @throws IOException if there's a mismatch in file lengths or checksums. + */ + public static void compareFileLengthsAndChecksums( + FileSystem sourceFS, Path source, FileChecksum sourceChecksum, + FileSystem targetFS, Path target, boolean skipCrc) throws IOException { + long srcLen = sourceFS.getFileStatus(source).getLen(); + long tgtLen = targetFS.getFileStatus(target).getLen(); + if (srcLen != tgtLen) { + throw new IOException( + "Mismatch in length of source:" + source + " (" + srcLen + + ") and target:" + target + " (" + tgtLen + ")"); + } + + //At this point, src & dest lengths are same. if length==0, we skip checksum + if ((srcLen != 0) && (!skipCrc)) { + if (!checksumsAreEqual(sourceFS, source, sourceChecksum, + targetFS, target)) { + StringBuilder errorMessage = + new StringBuilder("Checksum mismatch between ") + .append(source).append(" and ").append(target).append("."); + boolean addSkipHint = false; + String srcScheme = sourceFS.getScheme(); + String targetScheme = targetFS.getScheme(); + if (!srcScheme.equals(targetScheme)) { + // the filesystems are different and they aren't both hdfs connectors + errorMessage.append("Source and destination filesystems are of" + + " different types\n") + .append("Their checksum algorithms may be incompatible"); + addSkipHint = true; + } else if (sourceFS.getFileStatus(source).getBlockSize() != + targetFS.getFileStatus(target).getBlockSize()) { + errorMessage.append(" Source and target differ in block-size.\n") + .append(" Use -pb to preserve block-sizes during copy."); + addSkipHint = true; + } + if (addSkipHint) { + errorMessage + .append(" You can choose file-level checksum validation via " + + "-Ddfs.checksum.combine.mode=COMPOSITE_CRC when block-sizes" + + " or filesystems are different.") + .append(" Or you can skip checksum-checks altogether " + + " with -skipcrccheck.\n") + .append(" (NOTE: By skipping checksums, one runs the risk of " + + "masking data-corruption during file-transfer.)\n"); + } + throw new IOException(errorMessage.toString()); Review comment: I'm sorry I didn't make this clear. When dfs.checksum.combine.mode=COMPOSITE_CRC, you should tolerate different file systems and different block sizes, and it should not fail. ---------------------------------------------------------------- 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