/**
* Kick off a new sub-procedure on the listener with the data stored in the passed znode.
*
* <p>Will attempt to create the same procedure multiple times if an procedure znode with the same
* name is created. It is left up the coordinator to ensure this doesn't occur.
*
* @param path full path to the znode for the procedure to start
*/
private synchronized void startNewSubprocedure(String path) {
LOG.debug("Found procedure znode: " + path);
String opName = ZKUtil.getNodeName(path);
// start watching for an abort notification for the procedure
String abortZNode = zkController.getAbortZNode(opName);
try {
if (ZKUtil.watchAndCheckExists(zkController.getWatcher(), abortZNode)) {
LOG.debug("Not starting:" + opName + " because we already have an abort notification.");
return;
}
} catch (KeeperException e) {
member.controllerConnectionFailure(
"Failed to get the abort znode (" + abortZNode + ") for procedure :" + opName, e, opName);
return;
}
// get the data for the procedure
Subprocedure subproc = null;
try {
byte[] data = ZKUtil.getData(zkController.getWatcher(), path);
if (!ProtobufUtil.isPBMagicPrefix(data)) {
String msg =
"Data in for starting procuedure "
+ opName
+ " is illegally formatted (no pb magic). "
+ "Killing the procedure: "
+ Bytes.toString(data);
LOG.error(msg);
throw new IllegalArgumentException(msg);
}
LOG.debug("start proc data length is " + data.length);
data = Arrays.copyOfRange(data, ProtobufUtil.lengthOfPBMagic(), data.length);
LOG.debug("Found data for znode:" + path);
subproc = member.createSubprocedure(opName, data);
member.submitSubprocedure(subproc);
} catch (IllegalArgumentException iae) {
LOG.error("Illegal argument exception", iae);
sendMemberAborted(subproc, new ForeignException(getMemberName(), iae));
} catch (IllegalStateException ise) {
LOG.error("Illegal state exception ", ise);
sendMemberAborted(subproc, new ForeignException(getMemberName(), ise));
} catch (KeeperException e) {
member.controllerConnectionFailure(
"Failed to get data for new procedure:" + opName, e, opName);
} catch (InterruptedException e) {
member.controllerConnectionFailure(
"Failed to get data for new procedure:" + opName, e, opName);
Thread.currentThread().interrupt();
}
}
/**
* This should be called by the member and should write a serialized root cause exception as to
* the abort znode.
*/
@Override
public void sendMemberAborted(Subprocedure sub, ForeignException ee) {
if (sub == null) {
LOG.error("Failed due to null subprocedure", ee);
return;
}
String procName = sub.getName();
LOG.debug("Aborting procedure (" + procName + ") in zk");
String procAbortZNode = zkController.getAbortZNode(procName);
try {
String source = (ee.getSource() == null) ? memberName : ee.getSource();
byte[] errorInfo = ProtobufUtil.prependPBMagic(ForeignException.serialize(source, ee));
ZKUtil.createAndFailSilent(zkController.getWatcher(), procAbortZNode, errorInfo);
LOG.debug("Finished creating abort znode:" + procAbortZNode);
} catch (KeeperException e) {
// possible that we get this error for the procedure if we already reset the zk state, but in
// that case we should still get an error for that procedure anyways
zkController.logZKTree(zkController.getBaseZnode());
member.controllerConnectionFailure(
"Failed to post zk node:" + procAbortZNode + " to abort procedure", e, procName);
}
}
