/**
* Verify that the NameNode is able to still use <tt>READ_ONLY_SHARED</tt> replicas even when the
* single NORMAL replica is offline (and the effective replication count is 0).
*/
@Test
public void testNormalReplicaOffline() throws Exception {
// Stop the datanode hosting the NORMAL replica
cluster.stopDataNode(normalDataNode.getXferAddr());
// Force NameNode to detect that the datanode is down
BlockManagerTestUtil.noticeDeadDatanode(cluster.getNameNode(), normalDataNode.getXferAddr());
// The live replica count should now be zero (since the NORMAL replica is offline)
NumberReplicas numberReplicas = blockManager.countNodes(block);
assertThat(numberReplicas.liveReplicas(), is(0));
// The block should be reported as under-replicated
BlockManagerTestUtil.updateState(blockManager);
assertThat(blockManager.getUnderReplicatedBlocksCount(), is(1L));
// The BlockManager should be able to heal the replication count back to 1
// by triggering an inter-datanode replication from one of the READ_ONLY_SHARED replicas
BlockManagerTestUtil.computeAllPendingWork(blockManager);
DFSTestUtil.waitForReplication(cluster, extendedBlock, 1, 1, 0);
// There should now be 2 *locations* for the block, and 1 *replica*
assertThat(getLocatedBlock().getLocations().length, is(2));
validateNumberReplicas(1);
}
/**
* Verify that corrupt <tt>READ_ONLY_SHARED</tt> replicas aren't counted towards the corrupt
* replicas total.
*/
@Test
public void testReadOnlyReplicaCorrupt() throws Exception {
// "Corrupt" a READ_ONLY_SHARED replica by reporting it as a bad replica
client.reportBadBlocks(
new LocatedBlock[] {
new LocatedBlock(extendedBlock, new DatanodeInfo[] {readOnlyDataNode})
});
// There should now be only 1 *location* for the block as the READ_ONLY_SHARED is corrupt
waitForLocations(1);
// However, the corrupt READ_ONLY_SHARED replica should *not* affect the overall corrupt
// replicas count
NumberReplicas numberReplicas = blockManager.countNodes(block);
assertThat(numberReplicas.corruptReplicas(), is(0));
}
private void validateNumberReplicas(int expectedReplicas) throws IOException {
NumberReplicas numberReplicas = blockManager.countNodes(block);
assertThat(numberReplicas.liveReplicas(), is(expectedReplicas));
assertThat(numberReplicas.excessReplicas(), is(0));
assertThat(numberReplicas.corruptReplicas(), is(0));
assertThat(numberReplicas.decommissionedReplicas(), is(0));
assertThat(numberReplicas.replicasOnStaleNodes(), is(0));
BlockManagerTestUtil.updateState(blockManager);
assertThat(blockManager.getUnderReplicatedBlocksCount(), is(0L));
assertThat(blockManager.getExcessBlocksCount(), is(0L));
}
@VisibleForTesting
void check(String parent, HdfsFileStatus file, Result res) throws IOException {
String path = file.getFullName(parent);
boolean isOpen = false;
if (file.isDir()) {
if (snapshottableDirs != null && snapshottableDirs.contains(path)) {
String snapshotPath =
(path.endsWith(Path.SEPARATOR) ? path : path + Path.SEPARATOR)
+ HdfsConstants.DOT_SNAPSHOT_DIR;
HdfsFileStatus snapshotFileInfo = namenode.getRpcServer().getFileInfo(snapshotPath);
check(snapshotPath, snapshotFileInfo, res);
}
byte[] lastReturnedName = HdfsFileStatus.EMPTY_NAME;
DirectoryListing thisListing;
if (showFiles) {
out.println(path + " <dir>");
}
res.totalDirs++;
do {
assert lastReturnedName != null;
thisListing = namenode.getRpcServer().getListing(path, lastReturnedName, false);
if (thisListing == null) {
return;
}
HdfsFileStatus[] files = thisListing.getPartialListing();
for (int i = 0; i < files.length; i++) {
check(path, files[i], res);
}
lastReturnedName = thisListing.getLastName();
} while (thisListing.hasMore());
return;
}
if (file.isSymlink()) {
if (showFiles) {
out.println(path + " <symlink>");
}
res.totalSymlinks++;
return;
}
long fileLen = file.getLen();
// Get block locations without updating the file access time
// and without block access tokens
LocatedBlocks blocks;
try {
blocks = namenode.getNamesystem().getBlockLocations(path, 0, fileLen, false, false, false);
} catch (FileNotFoundException fnfe) {
blocks = null;
}
if (blocks == null) { // the file is deleted
return;
}
isOpen = blocks.isUnderConstruction();
if (isOpen && !showOpenFiles) {
// We collect these stats about open files to report with default options
res.totalOpenFilesSize += fileLen;
res.totalOpenFilesBlocks += blocks.locatedBlockCount();
res.totalOpenFiles++;
return;
}
res.totalFiles++;
res.totalSize += fileLen;
res.totalBlocks += blocks.locatedBlockCount();
if (showOpenFiles && isOpen) {
out.print(
path
+ " "
+ fileLen
+ " bytes, "
+ blocks.locatedBlockCount()
+ " block(s), OPENFORWRITE: ");
} else if (showFiles) {
out.print(path + " " + fileLen + " bytes, " + blocks.locatedBlockCount() + " block(s): ");
} else {
out.print('.');
}
if (res.totalFiles % 100 == 0) {
out.println();
out.flush();
}
int missing = 0;
int corrupt = 0;
long missize = 0;
int underReplicatedPerFile = 0;
int misReplicatedPerFile = 0;
StringBuilder report = new StringBuilder();
int i = 0;
for (LocatedBlock lBlk : blocks.getLocatedBlocks()) {
ExtendedBlock block = lBlk.getBlock();
boolean isCorrupt = lBlk.isCorrupt();
String blkName = block.toString();
DatanodeInfo[] locs = lBlk.getLocations();
NumberReplicas numberReplicas =
namenode.getNamesystem().getBlockManager().countNodes(block.getLocalBlock());
int liveReplicas = numberReplicas.liveReplicas();
res.totalReplicas += liveReplicas;
short targetFileReplication = file.getReplication();
res.numExpectedReplicas += targetFileReplication;
if (liveReplicas > targetFileReplication) {
res.excessiveReplicas += (liveReplicas - targetFileReplication);
res.numOverReplicatedBlocks += 1;
}
// Check if block is Corrupt
if (isCorrupt) {
corrupt++;
res.corruptBlocks++;
out.print(
"\n"
+ path
+ ": CORRUPT blockpool "
+ block.getBlockPoolId()
+ " block "
+ block.getBlockName()
+ "\n");
}
if (liveReplicas >= minReplication) res.numMinReplicatedBlocks++;
if (liveReplicas < targetFileReplication && liveReplicas > 0) {
res.missingReplicas += (targetFileReplication - liveReplicas);
res.numUnderReplicatedBlocks += 1;
underReplicatedPerFile++;
if (!showFiles) {
out.print("\n" + path + ": ");
}
out.println(
" Under replicated "
+ block
+ ". Target Replicas is "
+ targetFileReplication
+ " but found "
+ liveReplicas
+ " replica(s).");
}
// verify block placement policy
BlockPlacementStatus blockPlacementStatus =
bpPolicy.verifyBlockPlacement(path, lBlk, targetFileReplication);
if (!blockPlacementStatus.isPlacementPolicySatisfied()) {
res.numMisReplicatedBlocks++;
misReplicatedPerFile++;
if (!showFiles) {
if (underReplicatedPerFile == 0) out.println();
out.print(path + ": ");
}
out.println(
" Replica placement policy is violated for "
+ block
+ ". "
+ blockPlacementStatus.getErrorDescription());
}
report.append(i + ". " + blkName + " len=" + block.getNumBytes());
if (liveReplicas == 0) {
report.append(" MISSING!");
res.addMissing(block.toString(), block.getNumBytes());
missing++;
missize += block.getNumBytes();
} else {
report.append(" repl=" + liveReplicas);
if (showLocations || showRacks) {
StringBuilder sb = new StringBuilder("[");
for (int j = 0; j < locs.length; j++) {
if (j > 0) {
sb.append(", ");
}
if (showRacks) sb.append(NodeBase.getPath(locs[j]));
else sb.append(locs[j]);
}
sb.append(']');
report.append(" " + sb.toString());
}
}
report.append('\n');
i++;
}
if ((missing > 0) || (corrupt > 0)) {
if (!showFiles && (missing > 0)) {
out.print(
"\n" + path + ": MISSING " + missing + " blocks of total size " + missize + " B.");
}
res.corruptFiles++;
if (isOpen) {
LOG.info("Fsck: ignoring open file " + path);
} else {
if (doMove) copyBlocksToLostFound(parent, file, blocks);
if (doDelete) deleteCorruptedFile(path);
}
}
if (showFiles) {
if (missing > 0) {
out.print(" MISSING " + missing + " blocks of total size " + missize + " B\n");
} else if (underReplicatedPerFile == 0 && misReplicatedPerFile == 0) {
out.print(" OK\n");
}
if (showBlocks) {
out.print(report.toString() + "\n");
}
}
}