像原生C/C++，序列化Java对象

你曾经希望能够将Java对象object快速地转化为字节流，就像原生语言C/C++？如果你使用标准的Java Serialization，你会对它的性能感到非常失望。Java Serialization针对不同的使用目的，而不仅仅是快速紧凑地序列化对象。

那为什么需要快速紧凑的序列化？我们遇到的大多数系统时分布式的，我们需要在处理任务之间有效地通过传递状态（state）进行交流，这个状态在我们的对象中。所碰到的许多系统，相当大的一部分代价是在byte buffers序列化状态（state）。目前已有一大批协议和机制实现了这种需求，其中的一部分协议使用简单，但是非常低效，如Java Serialisation, XML 和JSON。另一部分采用二进制协议，性能高效，但是需要深入理解其技术。

这篇文章，将会使用简单的二进制协议和Java的相关技术，达到与原生语言 C 或者 C++ 一样的性能。

三种方法：

1. Java Serialization：实现Serializable接口；
2. Binary via ByteBuffer: 使用ByteBuffer API以二进制的方式写入对象的field；这也是好的二进制编码方法的基准。
3. Binary via Unsafe：引入Unsafe类及其方法，使用direct memory。

import sun.misc.Unsafe;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
import java.io.Serializable;
import java.lang.reflect.Field;
import java.nio.ByteBuffer;
import java.util.Arrays;

@SuppressWarnings("restriction")
public final class TestSerialisationPerf {
    public static final int REPETITIONS = 1 * 1000 * 1000;

    private static ObjectToBeSerialised ITEM = new ObjectToBeSerialised(1010L, true, 777, 99,
            new double[] { 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0 },
            new long[] { 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 });

    public static void main(final String[] arg) throws Exception {
        for (final PerformanceTestCase testCase : testCases) {
            for (int i = 0; i < 5; i++) {
                testCase.performTest();

                System.out.format("%d %s\twrite=%,dns read=%,dns total=%,dns\n", i, testCase.getName(),
                        testCase.getWriteTimeNanos(), testCase.getReadTimeNanos(),
                        testCase.getWriteTimeNanos() + testCase.getReadTimeNanos());

                if (!ITEM.equals(testCase.getTestOutput())) {
                    throw new IllegalStateException("Objects do not match");
                }
                System.gc();
                Thread.sleep(3000);
            }
        }
    }

    private static final PerformanceTestCase[] testCases = {
            new PerformanceTestCase("Serialisation", REPETITIONS, ITEM) {
                ByteArrayOutputStream baos = new ByteArrayOutputStream();

                @Override
                public void testWrite(ObjectToBeSerialised item) throws Exception {
                    for (int i = 0; i < REPETITIONS; i++) {
                        baos.reset();
                        ObjectOutputStream oos = new ObjectOutputStream(baos);
                        oos.writeObject(item);
                        oos.close();
                    }
                }

                @Override
                public ObjectToBeSerialised testRead() throws Exception {
                    ObjectToBeSerialised object = null;
                    for (int i = 0; i < REPETITIONS; i++) {
                        ByteArrayInputStream bais = new ByteArrayInputStream(baos.toByteArray());
                        ObjectInputStream ois = new ObjectInputStream(bais);
                        object = (ObjectToBeSerialised) ois.readObject();
                    }
                    return object;
                }
            },

            new PerformanceTestCase("ByteBuffer", REPETITIONS, ITEM) {
                ByteBuffer byteBuffer = ByteBuffer.allocate(1024);
                @Override
                public void testWrite(ObjectToBeSerialised item) throws Exception {
                    for (int i = 0; i < REPETITIONS; i++) {
                        byteBuffer.clear();
                        item.write(byteBuffer);
                    }
                }

                @Override
                public ObjectToBeSerialised testRead() throws Exception {
                    ObjectToBeSerialised object = null;
                    for (int i = 0; i < REPETITIONS; i++) {
                        byteBuffer.flip();
                        object = ObjectToBeSerialised.read(byteBuffer);
                    }
                    return object;
                }
            },

            new PerformanceTestCase("UnsafeMemory", REPETITIONS, ITEM) {
                UnsafeMemory buffer = new UnsafeMemory(new byte[1024]);
                @Override
                public void testWrite(ObjectToBeSerialised item) throws Exception {
                    for (int i = 0; i < REPETITIONS; i++) {
                        buffer.reset();
                        item.write(buffer);
                    }
                }

                @Override
                public ObjectToBeSerialised testRead() throws Exception {
                    ObjectToBeSerialised object = null;
                    for (int i = 0; i < REPETITIONS; i++) {
                        buffer.reset();
                        object = ObjectToBeSerialised.read(buffer);
                    }

                    return object;
                }
            }
        };
}

abstract class PerformanceTestCase {
    private final String name;
    private final int repetitions;
    private final ObjectToBeSerialised testInput;
    private ObjectToBeSerialised testOutput;
    private long writeTimeNanos;
    private long readTimeNanos;

    public PerformanceTestCase(final String name, final int repetitions, final ObjectToBeSerialised testInput) {
        this.name = name;
        this.repetitions = repetitions;
        this.testInput = testInput;
    }

    public String getName() {
        return name;
    }

    public ObjectToBeSerialised getTestOutput() {
        return testOutput;
    }

    public long getWriteTimeNanos() {
        return writeTimeNanos;
    }

    public long getReadTimeNanos() {
        return readTimeNanos;
    }

    public void performTest() throws Exception {
        final long startWriteNanos = System.nanoTime();
        testWrite(testInput);
        writeTimeNanos = (System.nanoTime() - startWriteNanos) / repetitions;

        final long startReadNanos = System.nanoTime();
        testOutput = testRead();
        readTimeNanos = (System.nanoTime() - startReadNanos) / repetitions;
    }

    public abstract void testWrite(ObjectToBeSerialised item) throws Exception;

    public abstract ObjectToBeSerialised testRead() throws Exception;
}

class ObjectToBeSerialised implements Serializable {
    private static final long serialVersionUID = 10275539472837495L;

    private final long sourceId;
    private final boolean special;
    private final int orderCode;
    private final int priority;
    private final double[] prices;
    private final long[] quantities;

    public ObjectToBeSerialised(final long sourceId, final boolean special, final int orderCode, final int priority,
            final double[] prices, final long[] quantities) {
        this.sourceId = sourceId;
        this.special = special;
        this.orderCode = orderCode;
        this.priority = priority;
        this.prices = prices;
        this.quantities = quantities;
    }

    public void write(final ByteBuffer byteBuffer) {
        byteBuffer.putLong(sourceId);
        byteBuffer.put((byte) (special ? 1 : 0));
        byteBuffer.putInt(orderCode);
        byteBuffer.putInt(priority);

        byteBuffer.putInt(prices.length);
        for (final double price : prices) {
            byteBuffer.putDouble(price);
        }

        byteBuffer.putInt(quantities.length);
        for (final long quantity : quantities) {
            byteBuffer.putLong(quantity);
        }
    }

    public static ObjectToBeSerialised read(final ByteBuffer byteBuffer) {
        final long sourceId = byteBuffer.getLong();
        final boolean special = 0 != byteBuffer.get();
        final int orderCode = byteBuffer.getInt();
        final int priority = byteBuffer.getInt();

        final int pricesSize = byteBuffer.getInt();
        final double[] prices = new double[pricesSize];
        for (int i = 0; i < pricesSize; i++) {
            prices[i] = byteBuffer.getDouble();
        }

        final int quantitiesSize = byteBuffer.getInt();
        final long[] quantities = new long[quantitiesSize];
        for (int i = 0; i < quantitiesSize; i++) {
            quantities[i] = byteBuffer.getLong();
        }

        return new ObjectToBeSerialised(sourceId, special, orderCode, priority, prices, quantities);
    }

    public void write(final UnsafeMemory buffer) {
        buffer.putLong(sourceId);
        buffer.putBoolean(special);
        buffer.putInt(orderCode);
        buffer.putInt(priority);
        buffer.putDoubleArray(prices);
        buffer.putLongArray(quantities);
    }

    public static ObjectToBeSerialised read(final UnsafeMemory buffer) {
        final long sourceId = buffer.getLong();
        final boolean special = buffer.getBoolean();
        final int orderCode = buffer.getInt();
        final int priority = buffer.getInt();
        final double[] prices = buffer.getDoubleArray();
        final long[] quantities = buffer.getLongArray();

        return new ObjectToBeSerialised(sourceId, special, orderCode, priority, prices, quantities);
    }

    @Override
    public boolean equals(final Object o) {
        if (this == o) {
            return true;
        }
        if (o == null || getClass() != o.getClass()) {
            return false;
        }

        final ObjectToBeSerialised that = (ObjectToBeSerialised) o;

        if (orderCode != that.orderCode) {
            return false;
        }
        if (priority != that.priority) {
            return false;
        }
        if (sourceId != that.sourceId) {
            return false;
        }
        if (special != that.special) {
            return false;
        }
        if (!Arrays.equals(prices, that.prices)) {
            return false;
        }
        if (!Arrays.equals(quantities, that.quantities)) {
            return false;
        }

        return true;
    }
}

@SuppressWarnings("restriction")
class UnsafeMemory {

    private static final Unsafe unsafe;

    static {
        try {
            Field field = Unsafe.class.getDeclaredField("theUnsafe");
            field.setAccessible(true);
            unsafe = (Unsafe) field.get(null);
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }

    private static final long byteArrayOffset = unsafe.arrayBaseOffset(byte[].class);
    private static final long longArrayOffset = unsafe.arrayBaseOffset(long[].class);
    private static final long doubleArrayOffset = unsafe.arrayBaseOffset(double[].class);

    private static final int SIZE_OF_BOOLEAN = 1;
    private static final int SIZE_OF_INT = 4;
    private static final int SIZE_OF_LONG = 8;

    private int pos = 0;
    private final byte[] buffer;

    public UnsafeMemory(final byte[] buffer) {
        if (null == buffer) {
            throw new NullPointerException("buffer cannot be null");
        }

        this.buffer = buffer;
    }

    public void reset() {
        this.pos = 0;
    }

    public void putBoolean(final boolean value) {
        unsafe.putBoolean(buffer, byteArrayOffset + pos, value);
        pos += SIZE_OF_BOOLEAN;
    }

    public boolean getBoolean() {
        boolean value = unsafe.getBoolean(buffer, byteArrayOffset + pos);
        pos += SIZE_OF_BOOLEAN;
        return value;
    }

    public void putInt(final int value) {
        unsafe.putInt(buffer, byteArrayOffset + pos, value);
        pos += SIZE_OF_INT;
    }

    public int getInt() {
        int value = unsafe.getInt(buffer, byteArrayOffset + pos);
        pos += SIZE_OF_INT;
        return value;
    }

    public void putLong(final long value) {
        unsafe.putLong(buffer, byteArrayOffset + pos, value);
        pos += SIZE_OF_LONG;
    }

    public long getLong() {
        long value = unsafe.getLong(buffer, byteArrayOffset + pos);
        pos += SIZE_OF_LONG;
        return value;
    }

    public void putLongArray(final long[] values) {
        putInt(values.length);
        long bytesToCopy = values.length << 3;
        unsafe.copyMemory(values, longArrayOffset, buffer, byteArrayOffset + pos, bytesToCopy);
        pos += bytesToCopy;
    }

    public long[] getLongArray() {
        int arraySize = getInt();
        long[] values = new long[arraySize];
        long bytesToCopy = values.length << 3;
        unsafe.copyMemory(buffer, byteArrayOffset + pos, values, longArrayOffset, bytesToCopy);
        pos += bytesToCopy;

        return values;
    }

    public void putDoubleArray(final double[] values) {
        putInt(values.length);
        long bytesToCopy = values.length << 3;
        unsafe.copyMemory(values, doubleArrayOffset, buffer, byteArrayOffset + pos, bytesToCopy);
        pos += bytesToCopy;
    }

    public double[] getDoubleArray() {
        int arraySize = getInt();
        double[] values = new double[arraySize];

        long bytesToCopy = values.length << 3;
        unsafe.copyMemory(buffer, byteArrayOffset + pos, values, doubleArrayOffset, bytesToCopy);
        pos += bytesToCopy;

        return values;
    }
}

结果：

0 Serialisation write=3,131ns read=9,111ns total=12,242ns
1 Serialisation write=4,081ns read=12,723ns total=16,804ns
2 Serialisation write=4,337ns read=16,147ns total=20,484ns
3 Serialisation write=4,274ns read=11,520ns total=15,794ns
4 Serialisation write=4,392ns read=12,414ns total=16,806ns
0 ByteBuffer write=525ns read=564ns total=1,089ns
1 ByteBuffer write=459ns read=642ns total=1,101ns
2 ByteBuffer write=436ns read=638ns total=1,074ns
3 ByteBuffer write=435ns read=649ns total=1,084ns
4 ByteBuffer write=429ns read=637ns total=1,066ns
0 UnsafeMemory write=96ns read=220ns total=316ns
1 UnsafeMemory write=74ns read=217ns total=291ns
2 UnsafeMemory write=78ns read=216ns total=294ns
3 UnsafeMemory write=79ns read=213ns total=292ns
4 UnsafeMemory write=77ns read=214ns total=291ns

分析

使用Java Serialization写入和读取单个相对比较小的对象需要花费大约15,000ns，然而使用Unsafe能够下降到300ns。有许多原因可以解释为什么Java Serialisation代价高昂，如每个对象写入类的全名和版本信息，而且ObjectOutputStream保留了一系列写入对象，当调用close() 方法才进行合并。对每个样本对象，Java Serialisation需要340字节，而使用二进制的方式只需要185字节。Java Serialisation的格式细节参考这里。如果在样本的绝大多数不使用数组，那么序列化后的对象会远大于Java Serialisation，因为字段名称。

使用Unsafe的方法获取了性能的提升，因为在Hotspot和其他的JVMs中，优化器对待这些操作作为指令，替换成汇编指令调用执行内存的操作。

结论

Java序列化实现像原生C/C++一样的性能是有可能的。上面的UnsafeMemory已提供基本框架的实现，可以进行扩充封装这种行为，这样就可以使用这种锋利的工具解决一些潜在的问题。

原文：Native C/C++ Like Performance For Java Object Serialization