详解大数据处理引擎Flink内存管理

public abstract class MemorySegment {
    /**
     * The heap byte array object relative to which we access the memory.
     *  如果为堆内存，则指向访问的内存的引用，否则若内存为非堆内存，则为null
     * 
Is non-null if the memory is on the heap, and is null, if the memory is
     * off the heap. If we have this buffer, we must never void this reference, or the memory
     * segment will point to undefined addresses outside the heap and may in out-of-order execution
     * cases cause segmentation faults.
     */
    protected final byte[] heapMemory;
    /**
     * The address to the data, relative to the heap memory byte array. If the heap memory byte
     * array is null, this becomes an absolute memory address outside the heap.
     * 字节数组对应的相对地址
     */
    protected long address;  
}

public final class HeapMemorySegment extends MemorySegment {
    /**
     * An extra reference to the heap memory, so we can let byte array checks fail by the built-in
     * checks automatically without extra checks.
     * 字节数组的引用指向该内存段
     */
    private byte[] memory;
    public void free() {
        super.free();
        this.memory = null;
    }
 
    public final void get(DataOutput out, int offset, int length) throws IOException {
        out.write(this.memory, offset, length);
    }
}

public final class HybridMemorySegment extends MemorySegment {
  @Override
    public ByteBuffer wrap(int offset, int length) {
        if (address <= addressLimit) {
            if (heapMemory != null) {
                return ByteBuffer.wrap(heapMemory, offset, length);
            }
            else {
                try {
                    ByteBuffer wrapper = offHeapBuffer.duplicate();
                    wrapper.limit(offset + length);
                    wrapper.position(offset);
                    return wrapper;
                }
                catch (IllegalArgumentException e) {
                    throw new IndexOutOfBoundsException();
                }
            }
        }
        else {
            throw new IllegalStateException("segment has been freed");
        }
    }
}

/**
 * This interface defines a view over some memory that can be used to sequentially read the contents of the memory.
 * The view is typically backed by one or more {@link org.apache.flink.core.memory.MemorySegment}.
 */
@Public
public interface DataInputView extends DataInput {
private MemorySegment[] memorySegments; // view持有的MemorySegment的引用， 该组memorysegment可以视为一个内存页，
flink可以顺序读取memorysegmet中的数据
/**
     * Reads up to {@code len} bytes of memory and stores it into {@code b} starting at offset {@code off}.
     * It returns the number of read bytes or -1 if there is no more data left.
     * @param b byte array to store the data to
     * @param off offset into byte array
     * @param len byte length to read
     * @return the number of actually read bytes of -1 if there is no more data left
     */
    int read(byte[] b, int off, int len) throws IOException;
}

/**
 * This interface defines a view over some memory that can be used to sequentially write contents to the memory.
 * The view is typically backed by one or more {@link org.apache.flink.core.memory.MemorySegment}.
 */
@Public
public interface DataOutputView extends DataOutput {
private final List memory; // memorysegment的引用
/**
     * Copies {@code numBytes} bytes from the source to this view.
     * @param source The source to copy the bytes from.
     * @param numBytes The number of bytes to copy.
    void write(DataInputView source, int numBytes) throws IOException;
}

/**
 * The memory manager governs the memory that Flink uses for sorting, hashing, caching or off-heap state backends
 * (e.g. RocksDB). Memory is represented either in {@link MemorySegment}s of equal size or in reserved chunks of certain
 * size. Operators allocate the memory either by requesting a number of memory segments or by reserving chunks.
 * Any allocated memory has to be released to be reused later.
 * 
The memory segments are represented as off-heap unsafe memory regions (both via {@link HybridMemorySegment}).
 * Releasing a memory segment will make it re-claimable by the garbage collector, but does not necessarily immediately
 * releases the underlying memory.
 */
public class MemoryManager {
 /**
     * Allocates a set of memory segments from this memory manager.
     * 
The total allocated memory will not exceed its size limit, announced in the constructor.
     * @param owner The owner to associate with the memory segment, for the fallback release.
     * @param target The list into which to put the allocated memory pages.
     * @param numberOfPages The number of pages to allocate.
     * @throws MemoryAllocationException Thrown, if this memory manager does not have the requested amount
     *                                   of memory pages any more.
     */
    public void allocatePages(
            Object owner,
            Collection target,
            int numberOfPages) throws MemoryAllocationException {
}

private static void freeSegment(MemorySegment segment, @Nullable Collection segments) {
        segment.free();
        if (segments != null) {
            segments.remove(segment);
        }
    }
/**
     * Frees this memory segment.
     * 
After this operation has been called, no further operations are possible on the memory
     * segment and will fail. The actual memory (heap or off-heap) will only be released after this
     * memory segment object has become garbage collected.
     */
    public void free() {
        // this ensures we can place no more data and trigger
        // the checks for the freed segment
        address = addressLimit + 1;
    }
}

/**
 * A buffer pool used to manage a number of {@link Buffer} instances from the
 * {@link NetworkBufferPool}.
 * 
Buffer requests are mediated to the network buffer pool to ensure dead-lock
 * free operation of the network stack by limiting the number of buffers per
 * local buffer pool. It also implements the default mechanism for buffer
 * recycling, which ensures that every buffer is ultimately returned to the
 * network buffer pool.
 * 
The size of this pool can be dynamically changed at runtime ({@link #setNumBuffers(int)}. It
 * will then lazily return the required number of buffers to the {@link NetworkBufferPool} to
 * match its new size.
 */
class LocalBufferPool implements BufferPool {
@Nullable
    private MemorySegment requestMemorySegment(int targetChannel) throws IOException {
        MemorySegment segment = null;
        synchronized (availableMemorySegments) {
            returnExcessMemorySegments();

            if (availableMemorySegments.isEmpty()) {
                segment = requestMemorySegmentFromGlobal();
            }
            // segment may have been released by buffer pool owner
            if (segment == null) {
                segment = availableMemorySegments.poll();
            }
            if (segment == null) {
                availabilityHelper.resetUnavailable();
            }
            if (segment != null && targetChannel != UNKNOWN_CHANNEL) {
                if (subpartitionBuffersCount[targetChannel]++ == maxBuffersPerChannel) {
                    unavailableSubpartitionsCount++;
                    availabilityHelper.resetUnavailable();
                }
            }
        }
        return segment;
    }
    ｝
    /**
 * A result partition for data produced by a single task.
 *
 * 
This class is the runtime part of a logical {@link IntermediateResultPartition}. Essentially,
 * a result partition is a collection of {@link Buffer} instances. The buffers are organized in one
 * or more {@link ResultSubpartition} instances, which further partition the data depending on the
 * number of consuming tasks and the data {@link DistributionPattern}.
 * 
Tasks, which consume a result partition have to request one of its subpartitions. The request
 * happens either remotely (see {@link RemoteInputChannel}) or locally (see {@link LocalInputChannel})
  The life-cycle of each result partition has three (possibly overlapping) phases:
    Produce  Consume  Release  Buffer management State management
 */
public abstract class ResultPartition implements ResultPartitionWriter, BufferPoolOwner {
      @Override
    public BufferBuilder getBufferBuilder(int targetChannel) throws IOException, InterruptedException {
        checkInProduceState();
        return bufferPool.requestBufferBuilderBlocking(targetChannel);
    }
    ｝
}

/**
     * Creates a serializer for the type. The serializer may use the ExecutionConfig
     * for parameterization.
     * 创建出对应类型的序列化器
     * @param config The config used to parameterize the serializer.
     * @return A serializer for this type.
     */
    @PublicEvolving
    public abstract TypeSerializer createSerializer(ExecutionConfig config);
/**
 * A utility for reflection analysis on classes, to determine the return type of implementations of transformation
 * functions.
 */
@Public
public class TypeExtractor {
/**
 * Creates a {@link TypeInformation} from the given parameters.
     * If the given {@code instance} implements {@link ResultTypeQueryable}, its information
     * is used to determine the type information. Otherwise, the type information is derived
     * based on the given class information.
     * @param instance            instance to determine type information for
     * @param baseClass            base class of {@code instance}
     * @param clazz                class of {@code instance}
     * @param returnParamPos    index of the return type in the type arguments of {@code clazz}
     * @param                 output type
     * @return type information
     */
    @SuppressWarnings("unchecked")
    @PublicEvolving
    public static  TypeInformation createTypeInfo(Object instance, Class<?> baseClass, Class<?> clazz,
 int returnParamPos) {
        if (instance instanceof ResultTypeQueryable) {
            return ((ResultTypeQueryable) instance).getProducedType();
        } else {
            return createTypeInfo(baseClass, clazz, returnParamPos, null, null);
        }
    }
}