聊聊storm tuple的序列化

// Every executor has an instance of this class
public class ExecutorTransfer {
    private static final Logger LOG = LoggerFactory.getLogger(ExecutorTransfer.class);

    private final WorkerState workerData;
    private final KryoTupleSerializer serializer;
    private final boolean isDebug;
    private int indexingBase = 0;
    private ArrayList<JCQueue> localReceiveQueues; // [taskId-indexingBase] => queue : List of all recvQs local to this worker
    private AtomicReferenceArray<JCQueue> queuesToFlush;
        // [taskId-indexingBase] => queue, some entries can be null. : outbound Qs for this executor instance


    public ExecutorTransfer(WorkerState workerData, Map<String, Object> topoConf) {
        this.workerData = workerData;
        this.serializer = new KryoTupleSerializer(topoConf, workerData.getWorkerTopologyContext());
        this.isDebug = ObjectReader.getBoolean(topoConf.get(Config.TOPOLOGY_DEBUG), false);
    }

    //......

    // adds addressedTuple to destination Q if it is not full. else adds to pendingEmits (if its not null)
    public boolean tryTransfer(AddressedTuple addressedTuple, Queue<AddressedTuple> pendingEmits) {
        if (isDebug) {
            LOG.info("TRANSFERRING tuple {}", addressedTuple);
        }

        JCQueue localQueue = getLocalQueue(addressedTuple);
        if (localQueue != null) {
            return tryTransferLocal(addressedTuple, localQueue, pendingEmits);
        }
        return workerData.tryTransferRemote(addressedTuple, pendingEmits, serializer);
    }

    //......
}

    /* Not a Blocking call. If cannot emit, will add 'tuple' to pendingEmits and return 'false'. 'pendingEmits' can be null */
    public boolean tryTransferRemote(AddressedTuple tuple, Queue<AddressedTuple> pendingEmits, ITupleSerializer serializer) {
        return workerTransfer.tryTransferRemote(tuple, pendingEmits, serializer);
    }

    /* Not a Blocking call. If cannot emit, will add 'tuple' to 'pendingEmits' and return 'false'. 'pendingEmits' can be null */
    public boolean tryTransferRemote(AddressedTuple addressedTuple, Queue<AddressedTuple> pendingEmits, ITupleSerializer serializer) {
        if (pendingEmits != null && !pendingEmits.isEmpty()) {
            pendingEmits.add(addressedTuple);
            return false;
        }

        if (!remoteBackPressureStatus[addressedTuple.dest].get()) {
            TaskMessage tm = new TaskMessage(addressedTuple.getDest(), serializer.serialize(addressedTuple.getTuple()));
            if (transferQueue.tryPublish(tm)) {
                return true;
            }
        } else {
            LOG.debug("Noticed Back Pressure in remote task {}", addressedTuple.dest);
        }
        if (pendingEmits != null) {
            pendingEmits.add(addressedTuple);
        }
        return false;
    }

public class KryoTupleSerializer implements ITupleSerializer {
    KryoValuesSerializer _kryo;
    SerializationFactory.IdDictionary _ids;
    Output _kryoOut;

    public KryoTupleSerializer(final Map<String, Object> conf, final GeneralTopologyContext context) {
        _kryo = new KryoValuesSerializer(conf);
        _kryoOut = new Output(2000, 2000000000);
        _ids = new SerializationFactory.IdDictionary(context.getRawTopology());
    }

    public byte[] serialize(Tuple tuple) {
        try {

            _kryoOut.clear();
            _kryoOut.writeInt(tuple.getSourceTask(), true);
            _kryoOut.writeInt(_ids.getStreamId(tuple.getSourceComponent(), tuple.getSourceStreamId()), true);
            tuple.getMessageId().serialize(_kryoOut);
            _kryo.serializeInto(tuple.getValues(), _kryoOut);
            return _kryoOut.toBytes();
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    //    public long crc32(Tuple tuple) {
    //        try {
    //            CRC32OutputStream hasher = new CRC32OutputStream();
    //            _kryo.serializeInto(tuple.getValues(), hasher);
    //            return hasher.getValue();
    //        } catch (IOException e) {
    //            throw new RuntimeException(e);
    //        }
    //    }
}

public class KryoValuesSerializer {
    Kryo _kryo;
    ListDelegate _delegate;
    Output _kryoOut;

    public KryoValuesSerializer(Map<String, Object> conf) {
        _kryo = SerializationFactory.getKryo(conf);
        _delegate = new ListDelegate();
        _kryoOut = new Output(2000, 2000000000);
    }

    public void serializeInto(List<Object> values, Output out) {
        // this ensures that list of values is always written the same way, regardless
        // of whether it's a java collection or one of clojure's persistent collections 
        // (which have different serializers)
        // Doing this lets us deserialize as ArrayList and avoid writing the class here
        _delegate.setDelegate(values);
        _kryo.writeObject(out, _delegate);
    }

    public byte[] serialize(List<Object> values) {
        _kryoOut.clear();
        serializeInto(values, _kryoOut);
        return _kryoOut.toBytes();
    }

    public byte[] serializeObject(Object obj) {
        _kryoOut.clear();
        _kryo.writeClassAndObject(_kryoOut, obj);
        return _kryoOut.toBytes();
    }
}

    public static Kryo getKryo(Map<String, Object> conf) {
        IKryoFactory kryoFactory = (IKryoFactory) ReflectionUtils.newInstance((String) conf.get(Config.TOPOLOGY_KRYO_FACTORY));
        Kryo k = kryoFactory.getKryo(conf);
        k.register(byte[].class);

        /* tuple payload serializer is specified via configuration */
        String payloadSerializerName = (String) conf.get(Config.TOPOLOGY_TUPLE_SERIALIZER);
        try {
            Class serializerClass = Class.forName(payloadSerializerName);
            Serializer serializer = resolveSerializerInstance(k, ListDelegate.class, serializerClass, conf);
            k.register(ListDelegate.class, serializer);
        } catch (ClassNotFoundException ex) {
            throw new RuntimeException(ex);
        }

        k.register(ArrayList.class, new ArrayListSerializer());
        k.register(HashMap.class, new HashMapSerializer());
        k.register(HashSet.class, new HashSetSerializer());
        k.register(BigInteger.class, new BigIntegerSerializer());
        k.register(TransactionAttempt.class);
        k.register(Values.class);
        k.register(org.apache.storm.metric.api.IMetricsConsumer.DataPoint.class);
        k.register(org.apache.storm.metric.api.IMetricsConsumer.TaskInfo.class);
        k.register(ConsList.class);
        k.register(BackPressureStatus.class);

        synchronized (loader) {
            for (SerializationRegister sr : loader) {
                try {
                    sr.register(k);
                } catch (Exception e) {
                    throw new RuntimeException(e);
                }
            }
        }

        kryoFactory.preRegister(k, conf);

        boolean skipMissing = (Boolean) conf.get(Config.TOPOLOGY_SKIP_MISSING_KRYO_REGISTRATIONS);

        register(k, conf.get(Config.TOPOLOGY_KRYO_REGISTER), conf, skipMissing);

        kryoFactory.postRegister(k, conf);

        if (conf.get(Config.TOPOLOGY_KRYO_DECORATORS) != null) {
            for (String klassName : (List<String>) conf.get(Config.TOPOLOGY_KRYO_DECORATORS)) {
                try {
                    Class klass = Class.forName(klassName);
                    IKryoDecorator decorator = (IKryoDecorator) klass.newInstance();
                    decorator.decorate(k);
                } catch (ClassNotFoundException e) {
                    if (skipMissing) {
                        LOG.info("Could not find kryo decorator named " + klassName + ". Skipping registration...");
                    } else {
                        throw new RuntimeException(e);
                    }
                } catch (InstantiationException e) {
                    throw new RuntimeException(e);
                } catch (IllegalAccessException e) {
                    throw new RuntimeException(e);
                }
            }
        }

        kryoFactory.postDecorate(k, conf);

        return k;
    }

    public static void register(Kryo k, Object kryoRegistrations, Map<String, Object> conf, boolean skipMissing) {
        Map<String, String> registrations = normalizeKryoRegister(kryoRegistrations);
        for (Map.Entry<String, String> entry : registrations.entrySet()) {
            String serializerClassName = entry.getValue();
            try {
                Class klass = Class.forName(entry.getKey());
                Class serializerClass = null;
                if (serializerClassName != null) {
                    serializerClass = Class.forName(serializerClassName);
                }
                if (serializerClass == null) {
                    k.register(klass);
                } else {
                    k.register(klass, resolveSerializerInstance(k, klass, serializerClass, conf));
                }
            } catch (ClassNotFoundException e) {
                if (skipMissing) {
                    LOG.info("Could not find serialization or class for " + serializerClassName + ". Skipping registration...");
                } else {
                    throw new RuntimeException(e);
                }
            }
        }
    }

public class DefaultKryoFactory implements IKryoFactory {

    @Override
    public Kryo getKryo(Map<String, Object> conf) {
        KryoSerializableDefault k = new KryoSerializableDefault();
        k.setRegistrationRequired(!((Boolean) conf.get(Config.TOPOLOGY_FALL_BACK_ON_JAVA_SERIALIZATION)));
        k.setReferences(false);
        return k;
    }

    @Override
    public void preRegister(Kryo k, Map<String, Object> conf) {
    }

    public void postRegister(Kryo k, Map<String, Object> conf) {
        ((KryoSerializableDefault) k).overrideDefault(true);
    }

    @Override
    public void postDecorate(Kryo k, Map<String, Object> conf) {
    }

    public static class KryoSerializableDefault extends Kryo {
        boolean _override = false;

        public void overrideDefault(boolean value) {
            _override = value;
        }

        @Override
        public Serializer getDefaultSerializer(Class type) {
            if (_override) {
                return new SerializableSerializer();
            } else {
                return super.getDefaultSerializer(type);
            }
        }
    }
}

    /** If the class is not registered and {@link Kryo#setRegistrationRequired(boolean)} is false, it is automatically registered
     * using the {@link Kryo#addDefaultSerializer(Class, Class) default serializer}.
     * @throws IllegalArgumentException if the class is not registered and {@link Kryo#setRegistrationRequired(boolean)} is true.
     * @see ClassResolver#getRegistration(Class) */
    public Registration getRegistration (Class type) {
        if (type == null) throw new IllegalArgumentException("type cannot be null.");

        Registration registration = classResolver.getRegistration(type);
        if (registration == null) {
            if (Proxy.isProxyClass(type)) {
                // If a Proxy class, treat it like an InvocationHandler because the concrete class for a proxy is generated.
                registration = getRegistration(InvocationHandler.class);
            } else if (!type.isEnum() && Enum.class.isAssignableFrom(type) && !Enum.class.equals(type)) {
                // This handles an enum value that is an inner class. Eg: enum A {b{}};
                registration = getRegistration(type.getEnclosingClass());
            } else if (EnumSet.class.isAssignableFrom(type)) {
                registration = classResolver.getRegistration(EnumSet.class);
            } else if (isClosure(type)) {
                registration = classResolver.getRegistration(ClosureSerializer.Closure.class);
            }
            if (registration == null) {
                if (registrationRequired) {
                    throw new IllegalArgumentException(unregisteredClassMessage(type));
                }
                if (warnUnregisteredClasses) {
                    warn(unregisteredClassMessage(type));
                }
                registration = classResolver.registerImplicit(type);
            }
        }
        return registration;
    }

    /** Registers the class using the lowest, next available integer ID and the {@link Kryo#getDefaultSerializer(Class) default
     * serializer}. If the class is already registered, no change will be made and the existing registration will be returned.
     * Registering a primitive also affects the corresponding primitive wrapper.
     * <p>
     * Because the ID assigned is affected by the IDs registered before it, the order classes are registered is important when
     * using this method. The order must be the same at deserialization as it was for serialization. */
    public Registration register (Class type) {
        Registration registration = classResolver.getRegistration(type);
        if (registration != null) return registration;
        return register(type, getDefaultSerializer(type));
    }

    /** Returns the best matching serializer for a class. This method can be overridden to implement custom logic to choose a
     * serializer. */
    public Serializer getDefaultSerializer (Class type) {
        if (type == null) throw new IllegalArgumentException("type cannot be null.");

        final Serializer serializerForAnnotation = getDefaultSerializerForAnnotatedType(type);
        if (serializerForAnnotation != null) return serializerForAnnotation;

        for (int i = 0, n = defaultSerializers.size(); i < n; i++) {
            DefaultSerializerEntry entry = defaultSerializers.get(i);
            if (entry.type.isAssignableFrom(type)) {
                Serializer defaultSerializer = entry.serializerFactory.makeSerializer(this, type);
                return defaultSerializer;
            }
        }

        return newDefaultSerializer(type);
    }

    /** Called by {@link #getDefaultSerializer(Class)} when no default serializers matched the type. Subclasses can override this
     * method to customize behavior. The default implementation calls {@link SerializerFactory#makeSerializer(Kryo, Class)} using
     * the {@link #setDefaultSerializer(Class) default serializer}. */
    protected Serializer newDefaultSerializer (Class type) {
        return defaultSerializer.makeSerializer(this, type);
    }

    /** Registers the class using the lowest, next available integer ID and the specified serializer. If the class is already
     * registered, the existing entry is updated with the new serializer. Registering a primitive also affects the corresponding
     * primitive wrapper.
     * <p>
     * Because the ID assigned is affected by the IDs registered before it, the order classes are registered is important when
     * using this method. The order must be the same at deserialization as it was for serialization. */
    public Registration register (Class type, Serializer serializer) {
        Registration registration = classResolver.getRegistration(type);
        if (registration != null) {
            registration.setSerializer(serializer);
            return registration;
        }
        return classResolver.register(new Registration(type, serializer, getNextRegistrationId()));
    }

    /** Returns the lowest, next available integer ID. */
    public int getNextRegistrationId () {
        while (nextRegisterID != -2) {
            if (classResolver.getRegistration(nextRegisterID) == null) return nextRegisterID;
            nextRegisterID++;
        }
        throw new KryoException("No registration IDs are available.");
    }

    static public final byte NAME = -1;

    protected final IntMap<Registration> idToRegistration = new IntMap();
    protected final ObjectMap<Class, Registration> classToRegistration = new ObjectMap();
    protected IdentityObjectIntMap<Class> classToNameId;

    public Registration registerImplicit (Class type) {
        return register(new Registration(type, kryo.getDefaultSerializer(type), NAME));
    }

    public Registration register (Registration registration) {
        if (registration == null) throw new IllegalArgumentException("registration cannot be null.");
        if (registration.getId() != NAME) {
            if (TRACE) {
                trace("kryo", "Register class ID " + registration.getId() + ": " + className(registration.getType()) + " ("
                    + registration.getSerializer().getClass().getName() + ")");
            }
            idToRegistration.put(registration.getId(), registration);
        } else if (TRACE) {
            trace("kryo", "Register class name: " + className(registration.getType()) + " ("
                + registration.getSerializer().getClass().getName() + ")");
        }
        classToRegistration.put(registration.getType(), registration);
        if (registration.getType().isPrimitive()) classToRegistration.put(getWrapperClass(registration.getType()), registration);
        return registration;
    }

    public Registration writeClass (Output output, Class type) {
        if (type == null) {
            if (TRACE || (DEBUG && kryo.getDepth() == 1)) log("Write", null);
            output.writeVarInt(Kryo.NULL, true);
            return null;
        }
        Registration registration = kryo.getRegistration(type);
        if (registration.getId() == NAME)
            writeName(output, type, registration);
        else {
            if (TRACE) trace("kryo", "Write class " + registration.getId() + ": " + className(type));
            output.writeVarInt(registration.getId() + 2, true);
        }
        return registration;
    }

    protected void writeName (Output output, Class type, Registration registration) {
        output.writeVarInt(NAME + 2, true);
        if (classToNameId != null) {
            int nameId = classToNameId.get(type, -1);
            if (nameId != -1) {
                if (TRACE) trace("kryo", "Write class name reference " + nameId + ": " + className(type));
                output.writeVarInt(nameId, true);
                return;
            }
        }
        // Only write the class name the first time encountered in object graph.
        if (TRACE) trace("kryo", "Write class name: " + className(type));
        int nameId = nextNameId++;
        if (classToNameId == null) classToNameId = new IdentityObjectIntMap();
        classToNameId.put(type, nameId);
        output.writeVarInt(nameId, true);
        output.writeString(type.getName());
    }

    public void reset () {
        if (!kryo.isRegistrationRequired()) {
            if (classToNameId != null) classToNameId.clear(2048);
            if (nameIdToClass != null) nameIdToClass.clear();
            nextNameId = 0;
        }
    }

    /** Writes an object using the registered serializer. */
    public void writeObject (Output output, Object object) {
        if (output == null) throw new IllegalArgumentException("output cannot be null.");
        if (object == null) throw new IllegalArgumentException("object cannot be null.");
        beginObject();
        try {
            if (references && writeReferenceOrNull(output, object, false)) {
                getRegistration(object.getClass()).getSerializer().setGenerics(this, null);
                return;
            }
            if (TRACE || (DEBUG && depth == 1)) log("Write", object);
            getRegistration(object.getClass()).getSerializer().write(this, output, object);
        } finally {
            if (--depth == 0 && autoReset) reset();
        }
    }

    /** Resets unregistered class names, references to previously serialized or deserialized objects, and the
     * {@link #getGraphContext() graph context}. If {@link #setAutoReset(boolean) auto reset} is true, this method is called
     * automatically when an object graph has been completely serialized or deserialized. If overridden, the super method must be
     * called. */
    public void reset () {
        depth = 0;
        if (graphContext != null) graphContext.clear();
        classResolver.reset();
        if (references) {
            referenceResolver.reset();
            readObject = null;
        }

        copyDepth = 0;
        if (originalToCopy != null) originalToCopy.clear(2048);

        if (TRACE) trace("kryo", "Object graph complete.");
    }