[
https://issues.apache.org/jira/browse/HDFS-14768?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16964625#comment-16964625
]
Surendra Singh Lilhore edited comment on HDFS-14768 at 11/1/19 5:51 AM:
------------------------------------------------------------------------
[~gjhkael] why you think it is not a problem ?
This is major issue and we have to fix this. Will commit this tomorrow if no
comment from other guys.
was (Author: surendrasingh):
[~gjhkael] why you think it is not a problem ?
This is major issue and we have to fix this. Will commit this tomorrow if no
other comment form other guys.
> EC : Busy DN replica should be consider in live replica check.
> --------------------------------------------------------------
>
> Key: HDFS-14768
> URL: https://issues.apache.org/jira/browse/HDFS-14768
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode, erasure-coding, hdfs, namenode
> Affects Versions: 3.0.2
> Reporter: guojh
> Assignee: guojh
> Priority: Major
> Labels: patch
> Attachments: 1568275810244.jpg, 1568276338275.jpg, 1568771471942.jpg,
> HDFS-14768.000.patch, HDFS-14768.001.patch, HDFS-14768.002.patch,
> HDFS-14768.003.patch, HDFS-14768.004.patch, HDFS-14768.005.patch,
> HDFS-14768.006.patch, HDFS-14768.007.patch, HDFS-14768.008.patch,
> HDFS-14768.009.patch, HDFS-14768.010.patch, HDFS-14768.jpg,
> guojh_UT_after_deomission.txt, guojh_UT_before_deomission.txt,
> zhaoyiming_UT_after_deomission.txt, zhaoyiming_UT_beofre_deomission.txt
>
>
> Policy is RS-6-3-1024K, version is hadoop 3.0.2;
> We suppose a file's block Index is [0,1,2,3,4,5,6,7,8], And decommission
> index[3,4], increase the index 6 datanode's
> pendingReplicationWithoutTargets that make it large than
> replicationStreamsHardLimit(we set 14). Then, After the method
> chooseSourceDatanodes of BlockMananger, the liveBlockIndices is
> [0,1,2,3,4,5,7,8], Block Counter is, Live:7, Decommission:2.
> In method scheduleReconstruction of BlockManager, the additionalReplRequired
> is 9 - 7 = 2. After Namenode choose two target Datanode, will assign a
> erasureCode task to target datanode.
> When datanode get the task will build targetIndices from liveBlockIndices
> and target length. the code is blow.
> {code:java}
> // code placeholder
> targetIndices = new short[targets.length];
> private void initTargetIndices() {
> BitSet bitset = reconstructor.getLiveBitSet();
> int m = 0; hasValidTargets = false;
> for (int i = 0; i < dataBlkNum + parityBlkNum; i++) {
> if (!bitset.get) {
> if (reconstructor.getBlockLen > 0) {
> if (m < targets.length) {
> targetIndices[m++] = (short)i;
> hasValidTargets = true;
> }
> }
> }
> }
> {code}
> targetIndices[0]=6, and targetIndices[1] is aways 0 from initial value.
> The StripedReader is aways create reader from first 6 index block, and is
> [0,1,2,3,4,5]
> Use the index [0,1,2,3,4,5] to build target index[6,0] will trigger the isal
> bug. the block index6's data is corruption(all data is zero).
> I write a unit test can stabilize repreduce.
> {code:java}
> // code placeholder
> private int replicationStreamsHardLimit =
> DFSConfigKeys.DFS_NAMENODE_REPLICATION_STREAMS_HARD_LIMIT_DEFAULT;
> numDNs = dataBlocks + parityBlocks + 10;
> @Test(timeout = 240000)
> public void testFileDecommission() throws Exception {
> LOG.info("Starting test testFileDecommission");
> final Path ecFile = new Path(ecDir, "testFileDecommission");
> int writeBytes = cellSize * dataBlocks;
> writeStripedFile(dfs, ecFile, writeBytes);
> Assert.assertEquals(0, bm.numOfUnderReplicatedBlocks());
> FileChecksum fileChecksum1 = dfs.getFileChecksum(ecFile, writeBytes);
> final INodeFile fileNode = cluster.getNamesystem().getFSDirectory()
> .getINode4Write(ecFile.toString()).asFile();
> LocatedBlocks locatedBlocks =
> StripedFileTestUtil.getLocatedBlocks(ecFile, dfs);
> LocatedBlock lb = dfs.getClient().getLocatedBlocks(ecFile.toString(), 0)
> .get(0);
> DatanodeInfo[] dnLocs = lb.getLocations();
> LocatedStripedBlock lastBlock =
> (LocatedStripedBlock)locatedBlocks.getLastLocatedBlock();
> DatanodeInfo[] storageInfos = lastBlock.getLocations();
> //
> DatanodeDescriptor datanodeDescriptor =
> cluster.getNameNode().getNamesystem()
>
> .getBlockManager().getDatanodeManager().getDatanode(storageInfos[6].getDatanodeUuid());
> BlockInfo firstBlock = fileNode.getBlocks()[0];
> DatanodeStorageInfo[] dStorageInfos = bm.getStorages(firstBlock);
> // the first heartbeat will consume 3 replica tasks
> for (int i = 0; i <= replicationStreamsHardLimit + 3; i++) {
> BlockManagerTestUtil.addBlockToBeReplicated(datanodeDescriptor, new
> Block(i),
> new DatanodeStorageInfo[]{dStorageInfos[0]});
> }
> assertEquals(dataBlocks + parityBlocks, dnLocs.length);
> int[] decommNodeIndex = {3, 4};
> final List<DatanodeInfo> decommisionNodes = new ArrayList<DatanodeInfo>();
> // add the node which will be decommissioning
> decommisionNodes.add(dnLocs[decommNodeIndex[0]]);
> decommisionNodes.add(dnLocs[decommNodeIndex[1]]);
> decommissionNode(0, decommisionNodes, AdminStates.DECOMMISSIONED);
> assertEquals(decommisionNodes.size(), fsn.getNumDecomLiveDataNodes());
> bm.getDatanodeManager().removeDatanode(datanodeDescriptor);
> //assertNull(checkFile(dfs, ecFile, 9, decommisionNodes, numDNs));
> // Ensure decommissioned datanode is not automatically shutdown
> DFSClient client = getDfsClient(cluster.getNameNode(0), conf);
> assertEquals("All datanodes must be alive", numDNs,
> client.datanodeReport(DatanodeReportType.LIVE).length);
> FileChecksum fileChecksum2 = dfs.getFileChecksum(ecFile, writeBytes);
> Assert.assertTrue("Checksum mismatches!",
> fileChecksum1.equals(fileChecksum2));
> StripedFileTestUtil.checkData(dfs, ecFile, writeBytes, decommisionNodes,
> null, blockGroupSize);
> }
> {code}
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
