use of java.io.InterruptedIOException in project hadoop by apache.
the class Shell method runCommand.
/** Run the command. */
private void runCommand() throws IOException {
ProcessBuilder builder = new ProcessBuilder(getExecString());
Timer timeOutTimer = null;
ShellTimeoutTimerTask timeoutTimerTask = null;
timedOut.set(false);
completed.set(false);
// the parent process.
if (!inheritParentEnv) {
builder.environment().clear();
}
if (environment != null) {
builder.environment().putAll(this.environment);
}
if (dir != null) {
builder.directory(this.dir);
}
builder.redirectErrorStream(redirectErrorStream);
if (Shell.WINDOWS) {
synchronized (WindowsProcessLaunchLock) {
// To workaround the race condition issue with child processes
// inheriting unintended handles during process launch that can
// lead to hangs on reading output and error streams, we
// serialize process creation. More info available at:
// http://support.microsoft.com/kb/315939
process = builder.start();
}
} else {
process = builder.start();
}
waitingThread = Thread.currentThread();
CHILD_SHELLS.put(this, null);
if (timeOutInterval > 0) {
timeOutTimer = new Timer("Shell command timeout");
timeoutTimerTask = new ShellTimeoutTimerTask(this);
//One time scheduling.
timeOutTimer.schedule(timeoutTimerTask, timeOutInterval);
}
final BufferedReader errReader = new BufferedReader(new InputStreamReader(process.getErrorStream(), Charset.defaultCharset()));
BufferedReader inReader = new BufferedReader(new InputStreamReader(process.getInputStream(), Charset.defaultCharset()));
final StringBuffer errMsg = new StringBuffer();
// read error and input streams as this would free up the buffers
// free the error stream buffer
Thread errThread = new Thread() {
@Override
public void run() {
try {
String line = errReader.readLine();
while ((line != null) && !isInterrupted()) {
errMsg.append(line);
errMsg.append(System.getProperty("line.separator"));
line = errReader.readLine();
}
} catch (IOException ioe) {
// so only log a WARN if the command didn't time out
if (!isTimedOut()) {
LOG.warn("Error reading the error stream", ioe);
} else {
LOG.debug("Error reading the error stream due to shell " + "command timeout", ioe);
}
}
}
};
try {
errThread.start();
} catch (IllegalStateException ise) {
} catch (OutOfMemoryError oe) {
LOG.error("Caught " + oe + ". One possible reason is that ulimit" + " setting of 'max user processes' is too low. If so, do" + " 'ulimit -u <largerNum>' and try again.");
throw oe;
}
try {
// parse the output
parseExecResult(inReader);
// clear the input stream buffer
String line = inReader.readLine();
while (line != null) {
line = inReader.readLine();
}
// wait for the process to finish and check the exit code
exitCode = process.waitFor();
// make sure that the error thread exits
joinThread(errThread);
completed.set(true);
//taken care in finally block
if (exitCode != 0) {
throw new ExitCodeException(exitCode, errMsg.toString());
}
} catch (InterruptedException ie) {
InterruptedIOException iie = new InterruptedIOException(ie.toString());
iie.initCause(ie);
throw iie;
} finally {
if (timeOutTimer != null) {
timeOutTimer.cancel();
}
// close the input stream
try {
// JDK 7 tries to automatically drain the input streams for us
// when the process exits, but since close is not synchronized,
// it creates a race if we close the stream first and the same
// fd is recycled. the stream draining thread will attempt to
// drain that fd!! it may block, OOM, or cause bizarre behavior
// see: https://bugs.openjdk.java.net/browse/JDK-8024521
// issue is fixed in build 7u60
InputStream stdout = process.getInputStream();
synchronized (stdout) {
inReader.close();
}
} catch (IOException ioe) {
LOG.warn("Error while closing the input stream", ioe);
}
if (!completed.get()) {
errThread.interrupt();
joinThread(errThread);
}
try {
InputStream stderr = process.getErrorStream();
synchronized (stderr) {
errReader.close();
}
} catch (IOException ioe) {
LOG.warn("Error while closing the error stream", ioe);
}
process.destroy();
waitingThread = null;
CHILD_SHELLS.remove(this);
lastTime = Time.monotonicNow();
}
}
use of java.io.InterruptedIOException in project hadoop by apache.
the class TestCopy method testInterruptedCreate.
@Test
public void testInterruptedCreate() throws Exception {
whenFsCreate().thenThrow(new InterruptedIOException());
when(mockFs.getFileStatus(eq(tmpPath))).thenReturn(fileStat);
FSDataInputStream in = mock(FSDataInputStream.class);
tryCopyStream(in, false);
verify(mockFs).delete(eq(tmpPath), anyBoolean());
verify(mockFs, never()).rename(any(Path.class), any(Path.class));
verify(mockFs, never()).delete(eq(path), anyBoolean());
verify(mockFs, never()).close();
}
use of java.io.InterruptedIOException in project hadoop by apache.
the class DataXceiver method run.
/**
* Read/write data from/to the DataXceiverServer.
*/
@Override
public void run() {
int opsProcessed = 0;
Op op = null;
try {
synchronized (this) {
xceiver = Thread.currentThread();
}
dataXceiverServer.addPeer(peer, Thread.currentThread(), this);
peer.setWriteTimeout(datanode.getDnConf().socketWriteTimeout);
InputStream input = socketIn;
try {
IOStreamPair saslStreams = datanode.saslServer.receive(peer, socketOut, socketIn, datanode.getXferAddress().getPort(), datanode.getDatanodeId());
input = new BufferedInputStream(saslStreams.in, smallBufferSize);
socketOut = saslStreams.out;
} catch (InvalidMagicNumberException imne) {
if (imne.isHandshake4Encryption()) {
LOG.info("Failed to read expected encryption handshake from client " + "at " + peer.getRemoteAddressString() + ". Perhaps the client " + "is running an older version of Hadoop which does not support " + "encryption");
} else {
LOG.info("Failed to read expected SASL data transfer protection " + "handshake from client at " + peer.getRemoteAddressString() + ". Perhaps the client is running an older version of Hadoop " + "which does not support SASL data transfer protection");
}
return;
}
super.initialize(new DataInputStream(input));
// Setting keepalive timeout to 0 disable this behavior.
do {
updateCurrentThreadName("Waiting for operation #" + (opsProcessed + 1));
try {
if (opsProcessed != 0) {
assert dnConf.socketKeepaliveTimeout > 0;
peer.setReadTimeout(dnConf.socketKeepaliveTimeout);
} else {
peer.setReadTimeout(dnConf.socketTimeout);
}
op = readOp();
} catch (InterruptedIOException ignored) {
// Time out while we wait for client rpc
break;
} catch (EOFException | ClosedChannelException e) {
// Since we optimistically expect the next op, it's quite normal to
// get EOF here.
LOG.debug("Cached {} closing after {} ops. " + "This message is usually benign.", peer, opsProcessed);
break;
} catch (IOException err) {
incrDatanodeNetworkErrors();
throw err;
}
// restore normal timeout
if (opsProcessed != 0) {
peer.setReadTimeout(dnConf.socketTimeout);
}
opStartTime = monotonicNow();
processOp(op);
++opsProcessed;
} while ((peer != null) && (!peer.isClosed() && dnConf.socketKeepaliveTimeout > 0));
} catch (Throwable t) {
String s = datanode.getDisplayName() + ":DataXceiver error processing " + ((op == null) ? "unknown" : op.name()) + " operation " + " src: " + remoteAddress + " dst: " + localAddress;
if (op == Op.WRITE_BLOCK && t instanceof ReplicaAlreadyExistsException) {
// at the same time.
if (LOG.isTraceEnabled()) {
LOG.trace(s, t);
} else {
LOG.info(s + "; " + t);
}
} else if (op == Op.READ_BLOCK && t instanceof SocketTimeoutException) {
String s1 = "Likely the client has stopped reading, disconnecting it";
s1 += " (" + s + ")";
if (LOG.isTraceEnabled()) {
LOG.trace(s1, t);
} else {
LOG.info(s1 + "; " + t);
}
} else if (t instanceof InvalidToken) {
// checkAccess() method and this is not a server error.
if (LOG.isTraceEnabled()) {
LOG.trace(s, t);
}
} else {
LOG.error(s, t);
}
} finally {
collectThreadLocalStates();
if (LOG.isDebugEnabled()) {
LOG.debug(datanode.getDisplayName() + ":Number of active connections is: " + datanode.getXceiverCount());
}
updateCurrentThreadName("Cleaning up");
if (peer != null) {
dataXceiverServer.closePeer(peer);
IOUtils.closeStream(in);
}
}
}
use of java.io.InterruptedIOException in project hadoop by apache.
the class TestCopy method testInterruptedRename.
@Test
public void testInterruptedRename() throws Exception {
FSDataOutputStream out = mock(FSDataOutputStream.class);
whenFsCreate().thenReturn(out);
when(mockFs.getFileStatus(eq(tmpPath))).thenReturn(fileStat);
when(mockFs.rename(eq(tmpPath), eq(path))).thenThrow(new InterruptedIOException());
FSInputStream in = mock(FSInputStream.class);
when(in.read(any(byte[].class), anyInt(), anyInt())).thenReturn(-1);
tryCopyStream(in, false);
verify(mockFs).delete(eq(tmpPath), anyBoolean());
verify(mockFs).rename(eq(tmpPath), eq(path));
verify(mockFs, never()).delete(eq(path), anyBoolean());
verify(mockFs, never()).close();
}
use of java.io.InterruptedIOException in project hadoop by apache.
the class DFSInputStream method chooseDataNode.
private DNAddrPair chooseDataNode(LocatedBlock block, Collection<DatanodeInfo> ignoredNodes) throws IOException {
while (true) {
DNAddrPair result = getBestNodeDNAddrPair(block, ignoredNodes);
if (result != null) {
return result;
} else {
String errMsg = getBestNodeDNAddrPairErrorString(block.getLocations(), deadNodes, ignoredNodes);
String blockInfo = block.getBlock() + " file=" + src;
if (failures >= dfsClient.getConf().getMaxBlockAcquireFailures()) {
String description = "Could not obtain block: " + blockInfo;
DFSClient.LOG.warn(description + errMsg + ". Throwing a BlockMissingException");
throw new BlockMissingException(src, description, block.getStartOffset());
}
DatanodeInfo[] nodes = block.getLocations();
if (nodes == null || nodes.length == 0) {
DFSClient.LOG.info("No node available for " + blockInfo);
}
DFSClient.LOG.info("Could not obtain " + block.getBlock() + " from any node: " + errMsg + ". Will get new block locations from namenode and retry...");
try {
// Introducing a random factor to the wait time before another retry.
// The wait time is dependent on # of failures and a random factor.
// At the first time of getting a BlockMissingException, the wait time
// is a random number between 0..3000 ms. If the first retry
// still fails, we will wait 3000 ms grace period before the 2nd retry.
// Also at the second retry, the waiting window is expanded to 6000 ms
// alleviating the request rate from the server. Similarly the 3rd retry
// will wait 6000ms grace period before retry and the waiting window is
// expanded to 9000ms.
final int timeWindow = dfsClient.getConf().getTimeWindow();
double waitTime = // grace period for the last round of attempt
timeWindow * failures + // expanding time window for each failure
timeWindow * (failures + 1) * ThreadLocalRandom.current().nextDouble();
DFSClient.LOG.warn("DFS chooseDataNode: got # " + (failures + 1) + " IOException, will wait for " + waitTime + " msec.");
Thread.sleep((long) waitTime);
} catch (InterruptedException e) {
Thread.currentThread().interrupt();
throw new InterruptedIOException("Interrupted while choosing DataNode for read.");
}
//2nd option is to remove only nodes[blockId]
deadNodes.clear();
openInfo(true);
block = refreshLocatedBlock(block);
failures++;
}
}
}
Aggregations