JAVA拾遗 - ConcurrentHashMap源码阅读<实在续不动>

说实话在这段时间的编程里，多线程用的少，但是这是JAVA里面非常重要的一个部分，所以找了个机会看了点书。但是看完书后觉得还不够，书里面也就讲了它主要的对外接口，所以就想进入源码里面看看，顺便复习一下。

继承

ConcurrentHashMap继承于AbstractMap，实现了Map\Serializable这几个接口。

public class ConcurrentHashMap<K,V> extends AbstractMap<K,V>
    implements ConcurrentMap<K,V>, Serializable {
    ···
    }

然后我们可以看到Doug Lea大神写的doc

/*
     * Overview:
     *
     * The primary design goal of this hash table is to maintain
     * concurrent readability (typically method get(), but also
     * iterators and related methods) while minimizing update
     * contention. Secondary goals are to keep space consumption about
     * the same or better than java.util.HashMap, and to support high
     * initial insertion rates on an empty table by many threads.
     * 
     *···
     *
     * Also, solely for compatibility with previous versions of this
     * class, it extends AbstractMap, even though all of its methods
     * are overridden, so it is just useless baggage.
     *
     * This file is organized to make things a little easier to follow
     * while reading than they might otherwise: First the main static
     * declarations and utilities, then fields, then main public
     * methods (with a few factorings of multiple public methods into
     * internal ones), then sizing methods, trees, traversers, and
     * bulk operations.
     */

大致说明了下阅读次序以及实现的功能。

常量

/**
     * The largest possible table capacity.  This value must be
     * exactly 1<<30 to stay within Java array allocation and indexing
     * bounds for power of two table sizes, and is further required
     * because the top two bits of 32bit hash fields are used for
     * control purposes.
     */
    private static final int MAXIMUM_CAPACITY = 1 << 30;//定义了这个table 的最大容纳额，由于int32里的前两位需要用来进行控制，所以最大容纳额是1<<30(2^30)
/**
     * The default initial table capacity.  Must be a power of 2
     * (i.e., at least 1) and at most MAXIMUM_CAPACITY.
     */
    private static final int DEFAULT_CAPACITY = 16;

    /**
     * The largest possible (non-power of two) array size.
     * Needed by toArray and related methods.
     */
    static final int MAX_ARRAY_SIZE = Integer.MAX_VALUE - 8;

    /**
     * The default concurrency level for this table. Unused but
     * defined for compatibility with previous versions of this class.
     */
    private static final int DEFAULT_CONCURRENCY_LEVEL = 16; //设置了并发的等级为16，在JAVA核心技术里说是并发线程的估计数目

    /**
     * The load factor for this table. Overrides of this value in
     * constructors affect only the initial table capacity.  The
     * actual floating point value isn't normally used -- it is
     * simpler to use expressions such as {@code n - (n >>> 2)} for
     * the associated resizing threshold.
     */
    private static final float LOAD_FACTOR = 0.75f; //如果超过这个值就需要创建一个新的ConcurrentHashMap来存储数据，然后废弃原有的，这和HashMap的设定是一样的
    //如果每一个桶的平均负载超过这个值，表的大小就会被重新调整
    //然后是大部分我这个档次的程序员不理解的常量...
    /**
     * The bin count threshold for using a tree rather than list for a
     * bin.  Bins are converted to trees when adding an element to a
     * bin with at least this many nodes. The value must be greater
     * than 2, and should be at least 8 to mesh with assumptions in
     * tree removal about conversion back to plain bins upon
     * shrinkage.
     */
    static final int TREEIFY_THRESHOLD = 8;//大致是说插入数大于这个量就把容器转化成树而不用list？

    /**
     * The bin count threshold for untreeifying a (split) bin during a
     * resize operation. Should be less than TREEIFY_THRESHOLD, and at
     * most 6 to mesh with shrinkage detection under removal.
     */
    static final int UNTREEIFY_THRESHOLD = 6; //容器数小于这个值就将树型存储转化为List了

    /**
     * The smallest table capacity for which bins may be treeified.
     * (Otherwise the table is resized if too many nodes in a bin.)
     * The value should be at least 4 * TREEIFY_THRESHOLD to avoid
     * conflicts between resizing and treeification thresholds.
     */
    static final int MIN_TREEIFY_CAPACITY = 64; //

    /**
     * Minimum number of rebinnings per transfer step. Ranges are
     * subdivided to allow multiple resizer threads.  This value
     * serves as a lower bound to avoid resizers encountering
     * excessive memory contention.  The value should be at least
     * DEFAULT_CAPACITY.
     */
    private static final int MIN_TRANSFER_STRIDE = 16;

    /**
     * The number of bits used for generation stamp in sizeCtl.
     * Must be at least 6 for 32bit arrays.
     */
    private static int RESIZE_STAMP_BITS = 16;

    /**
     * The maximum number of threads that can help resize.
     * Must fit in 32 - RESIZE_STAMP_BITS bits.
     */
    private static final int MAX_RESIZERS = (1 << (32 - RESIZE_STAMP_BITS)) - 1;//看来大神都是用这个方法计算2^n的

    /**
     * The bit shift for recording size stamp in sizeCtl.
     */
    private static final int RESIZE_STAMP_SHIFT = 32 - RESIZE_STAMP_BITS;

    /*
     * Encodings for Node hash fields. See above for explanation.
     */
    static final int MOVED     = -1; // hash for forwarding nodes
    static final int TREEBIN   = -2; // hash for roots of trees
    static final int RESERVED  = -3; // hash for transient reservations
    static final int HASH_BITS = 0x7fffffff; // usable bits of normal node hash

    /** Number of CPUS, to place bounds on some sizings */
    static final int NCPU = Runtime.getRuntime().availableProcessors(); //CPU的数量！JAVA真是太coooooooooooool了

Serialization

  /** For serialization compatibility. */
    private static final ObjectStreamField[] serialPersistentFields = {
        new ObjectStreamField("segments", Segment[].class),  //事实上我还没懂这个serialization接口的作用
        new ObjectStreamField("segmentMask", Integer.TYPE),
        new ObjectStreamField("segmentShift", Integer.TYPE)
    };

Node

   /**
     * Key-value entry.  This class is never exported out as a
     * user-mutable Map.Entry (i.e., one supporting setValue; see
     * MapEntry below), but can be used for read-only traversals used
     * in bulk tasks.  Subclasses of Node with a negative hash field
     * are special, and contain null keys and values (but are never
     * exported).  Otherwise, keys and vals are never null.
     */
     //keys and vals are never null.这点很重要
    static class Node<K,V> implements Map.Entry<K,V> {
        final int hash;
        final K key;
        volatile V val;
        volatile Node<K,V> next; //这里用了这个关键字，同时是链表的形式进行存储

        Node(int hash, K key, V val, Node<K,V> next) {
            this.hash = hash;
            this.key = key;
            this.val = val;
            this.next = next;
        }

        public final K getKey()       { return key; }
        public final V getValue()     { return val; }
        public final int hashCode()   { return key.hashCode() ^ val.hashCode(); }
        public final String toString(){ return key + "=" + val; }
        public final V setValue(V value) {
            throw new UnsupportedOperationException();
        }

        public final boolean equals(Object o) {//这里实现了equal方法，可以观摩一下大师的实现方法
            Object k, v, u; Map.Entry<?,?> e;
            return ((o instanceof Map.Entry) && //java 中的instanceof 运算符是用来在运行时指出对象是否是特定类的一个实例。这里就是检测输入的类是否是我们存储的类
                    (k = (e = (Map.Entry<?,?>)o).getKey()) != null && //(e = (Map.Entry<?,?>)o).getKey()是返回这个条目的键，这一则判断是确认o里面的key不为空，否则后面那就要报空指针了，大师的代码就是鲁棒性高
                    (v = e.getValue()) != null &&//同时value也不为空
                    (k == key || k.equals(key)) && //key就是this.key，如果在地址上或者值上有一个相等就为正确
                    (v == (u = val) || v.equals(u)));//不是很理解为什么要u=val再作对比
        }

        /**
         * Virtualized support for map.get(); overridden in subclasses.
         */
        Node<K,V> find(int h, Object k) {
            Node<K,V> e = this;
            if (k != null) {
                do {
                    K ek;
                    if (e.hash == h &&
                        ((ek = e.key) == k || (ek != null && k.equals(ek))))//这里也先赋值再对比
                        return e;
                } while ((e = e.next) != null);
            }
            return null;
        }
    }

初始化方法

    /**
     * Creates a new, empty map with the default initial table size (16).
     */
    public ConcurrentHashMap() {
    }

    /**
     * Creates a new, empty map with an initial table size
     * accommodating the specified number of elements without the need
     * to dynamically resize.
     *
     * @param initialCapacity The implementation performs internal
     * sizing to accommodate this many elements.
     * @throws IllegalArgumentException if the initial capacity of
     * elements is negative
     */
    public ConcurrentHashMap(int initialCapacity) {
        if (initialCapacity < 0)
            throw new IllegalArgumentException();
        int cap = ((initialCapacity >= (MAXIMUM_CAPACITY >>> 1)) ?
                   MAXIMUM_CAPACITY :
                   tableSizeFor(initialCapacity + (initialCapacity >>> 1) + 1));
        this.sizeCtl = cap;
    }

    /**
     * Creates a new map with the same mappings as the given map.
     *
     * @param m the map
     */
    public ConcurrentHashMap(Map<? extends K, ? extends V> m) {
        this.sizeCtl = DEFAULT_CAPACITY;
        putAll(m);
    }

    /**
     * Creates a new, empty map with an initial table size based on
     * the given number of elements ({@code initialCapacity}) and
     * initial table density ({@code loadFactor}).
     *
     * @param initialCapacity the initial capacity. The implementation
     * performs internal sizing to accommodate this many elements,
     * given the specified load factor.
     * @param loadFactor the load factor (table density) for
     * establishing the initial table size
     * @throws IllegalArgumentException if the initial capacity of
     * elements is negative or the load factor is nonpositive
     *
     * @since 1.6
     */
    public ConcurrentHashMap(int initialCapacity, float loadFactor) {
        this(initialCapacity, loadFactor, 1);
    }

    /**
     * Creates a new, empty map with an initial table size based on
     * the given number of elements ({@code initialCapacity}), table
     * density ({@code loadFactor}), and number of concurrently
     * updating threads ({@code concurrencyLevel}).
     *
     * @param initialCapacity the initial capacity. The implementation
     * performs internal sizing to accommodate this many elements,
     * given the specified load factor.
     * @param loadFactor the load factor (table density) for
     * establishing the initial table size
     * @param concurrencyLevel the estimated number of concurrently
     * updating threads. The implementation may use this value as
     * a sizing hint.
     * @throws IllegalArgumentException if the initial capacity is
     * negative or the load factor or concurrencyLevel are
     * nonpositive
     */
    public ConcurrentHashMap(int initialCapacity,
                             float loadFactor, int concurrencyLevel) {
        if (!(loadFactor > 0.0f) || initialCapacity < 0 || concurrencyLevel <= 0)
            throw new IllegalArgumentException();
        if (initialCapacity < concurrencyLevel)   // Use at least as many bins
            initialCapacity = concurrencyLevel;   // as estimated threads
        long size = (long)(1.0 + (long)initialCapacity / loadFactor);
        int cap = (size >= (long)MAXIMUM_CAPACITY) ?
            MAXIMUM_CAPACITY : tableSizeFor((int)size);
        this.sizeCtl = cap;
    }

一些方法的实现

   /**
     * {@inheritDoc}
     */
    public int size() {
        long n = sumCount();
        return ((n < 0L) ? 0 :
                (n > (long)Integer.MAX_VALUE) ? Integer.MAX_VALUE :
                (int)n);
    }

而这里的sumCount是这个方法

    /**
     * Base counter value, used mainly when there is no contention,
     * but also as a fallback during table initialization
     * races. Updated via CAS.
     */
    private transient volatile long baseCount;
      /**
     * Table of counter cells. When non-null, size is a power of 2.
     */
    private transient volatile CounterCell[] counterCells;

 @sun.misc.Contended static final class CounterCell {
        volatile long value;
        CounterCell(long x) { value = x; }
    }

    final long sumCount() {//就是每个桶里面有几个元素就加上去
        CounterCell[] as = counterCells; CounterCell a;
        long sum = baseCount;
        if (as != null) {
            for (int i = 0; i < as.length; ++i) {
                if ((a = as[i]) != null)
                    sum += a.value;
            }
        }
        return sum;
    }

主要的clear()方法

    /**
     * Removes all of the mappings from this map.
     */
    public void clear() {
        long delta = 0L; // negative number of deletions
        int i = 0;
        Node<K,V>[] tab = table;
        while (tab != null && i < tab.length) {
            int fh;
            Node<K,V> f = tabAt(tab, i);
            if (f == null)
                ++i;
            else if ((fh = f.hash) == MOVED) {
                tab = helpTransfer(tab, f);
                i = 0; // restart
            }
            else {
                synchronized (f) {//支持了线程安全，这点很关键
                    if (tabAt(tab, i) == f) {
                        Node<K,V> p = (fh >= 0 ? f :
                                       (f instanceof TreeBin) ?
                                       ((TreeBin<K,V>)f).first : null);
                        while (p != null) {
                            --delta;
                            p = p.next;
                        }
                        setTabAt(tab, i++, null);
                    }
                }
            }
        }
        if (delta != 0L)
            addCount(delta, -1);
    }

contains()方法

    public boolean contains(Object value) {
        return containsValue(value);
    }


   /**
     * Returns {@code true} if this map maps one or more keys to the
     * specified value. Note: This method may require a full traversal
     * of the map, and is much slower than method {@code containsKey}.
     *
     * @param value value whose presence in this map is to be tested
     * @return {@code true} if this map maps one or more keys to the
     *         specified value
     * @throws NullPointerException if the specified value is null
     */
    public boolean containsValue(Object value) {
        if (value == null) //注意了，contains一个null也会报空指针的
            throw new NullPointerException();
        Node<K,V>[] t;
        if ((t = table) != null) {
            Traverser<K,V> it = new Traverser<K,V>(t, t.length, 0, t.length); 
            for (Node<K,V> p; (p = it.advance()) != null; ) {//advance是返回下一个存在的值或者返回空
                V v;
                if ((v = p.val) == value || (v != null && value.equals(v)))
                    return true;
            }
        }
        return false;
    }

---

to be continued