HashMap 如何解决冲突?扩容机制?

正文

我们来看看HashMap的put数据的时候,是怎么处理的:

/**
     * Implements Map.put and related methods
     *
     * @param hash hash for key
     * @param key the key
     * @param value the value to put
     * @param onlyIfAbsent if true, don't change existing value
     * @param evict if false, the table is in creation mode.
     * @return previous value, or null if none
     */
    final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
                   boolean evict) {
        Node<K,V>[] tab; Node<K,V> p; int n, i;
        if ((tab = table) == null || (n = tab.length) == 0)
            n = (tab = resize()).length;
        if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);
        else {
            Node<K,V> e; K k;
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                e = p;
            else if (p instanceof TreeNode)
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
                for (int binCount = 0; ; ++binCount) {
                    if ((e = p.next) == null) {
                        p.next = newNode(hash, key, value, null);
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        break;
                    p = e;
                }
            }
            if (e != null) { // existing mapping for key
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                afterNodeAccess(e);
                return oldValue;
            }
        }
        ++modCount;
        if (++size > threshold)
            resize();
        afterNodeInsertion(evict);
        return null;
    }

计算HashCode的操作:

/**
     * Computes key.hashCode() and spreads (XORs) higher bits of hash
     * to lower.  Because the table uses power-of-two masking, sets of
     * hashes that vary only in bits above the current mask will
     * always collide. (Among known examples are sets of Float keys
     * holding consecutive whole numbers in small tables.)  So we
     * apply a transform that spreads the impact of higher bits
     * downward. There is a tradeoff between speed, utility, and
     * quality of bit-spreading. Because many common sets of hashes
     * are already reasonably distributed (so don't benefit from
     * spreading), and because we use trees to handle large sets of
     * collisions in bins, we just XOR some shifted bits in the
     * cheapest possible way to reduce systematic lossage, as well as
     * to incorporate impact of the highest bits that would otherwise
     * never be used in index calculations because of table bounds.
     */
    static final int hash(Object key) {
        int h;
        return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
    }

解决冲突的核心逻辑代码:

Node<K,V> e; K k;
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                e = p;
            else if (p instanceof TreeNode)
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
                for (int binCount = 0; ; ++binCount) {
                    if ((e = p.next) == null) {
                        p.next = newNode(hash, key, value, null);
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        break;
                    p = e;
                }
            }
            if (e != null) { // existing mapping for key
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                afterNodeAccess(e);
                return oldValue;
            }

这里再贴一下创建Node的代码:
Node<K,V> newNode(int hash, K key, V value, Node<K,V> e) {
        LinkedHashMap.Entry<K,V> p =
            new LinkedHashMap.Entry<K,V>(hash, key, value, e);
        linkNodeLast(p);
        return p;
    }

HashMap的扩容

说道HashMap的扩容,我们先来看看HashMap的resize()方法。

/**
     * Initializes or doubles table size.  If null, allocates in
     * accord with initial capacity target held in field threshold.
     * Otherwise, because we are using power-of-two expansion, the
     * elements from each bin must either stay at same index, or move
     * with a power of two offset in the new table.
     *
     * @return the table
     */
    final Node<K,V>[] resize() {
        Node<K,V>[] oldTab = table;
        int oldCap = (oldTab == null) ? 0 : oldTab.length;
        int oldThr = threshold;
        int newCap, newThr = 0;
        if (oldCap > 0) {
            if (oldCap >= MAXIMUM_CAPACITY) {
                threshold = Integer.MAX_VALUE;
                return oldTab;
            }
            else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                     oldCap >= DEFAULT_INITIAL_CAPACITY)
                newThr = oldThr << 1; // double threshold
        }
        else if (oldThr > 0) // initial capacity was placed in threshold
            newCap = oldThr;
        else {               // zero initial threshold signifies using defaults
            newCap = DEFAULT_INITIAL_CAPACITY;
            newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
        }
        if (newThr == 0) {
            float ft = (float)newCap * loadFactor;
            newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                      (int)ft : Integer.MAX_VALUE);
        }
        threshold = newThr;
        @SuppressWarnings({"rawtypes","unchecked"})
            Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
        table = newTab;
        if (oldTab != null) {
            for (int j = 0; j < oldCap; ++j) {
                Node<K,V> e;
                if ((e = oldTab[j]) != null) {
                    oldTab[j] = null;
                    if (e.next == null)
                        newTab[e.hash & (newCap - 1)] = e;
                    else if (e instanceof TreeNode)
                        ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                    else { // preserve order
                        Node<K,V> loHead = null, loTail = null;
                        Node<K,V> hiHead = null, hiTail = null;
                        Node<K,V> next;
                        do {
                            next = e.next;
                            if ((e.hash & oldCap) == 0) {
                                if (loTail == null)
                                    loHead = e;
                                else
                                    loTail.next = e;
                                loTail = e;
                            }
                            else {
                                if (hiTail == null)
                                    hiHead = e;
                                else
                                    hiTail.next = e;
                                hiTail = e;
                            }
                        } while ((e = next) != null);
                        if (loTail != null) {
                            loTail.next = null;
                            newTab[j] = loHead;
                        }
                        if (hiTail != null) {
                            hiTail.next = null;
                            newTab[j + oldCap] = hiHead;
                        }
                    }
                }
            }
        }
        return newTab;
    }

HashMap默认的容量是DEFAULT_INITIAL_CAPACITY,16。

默认容量大小和阈值:

newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);

DEFAULT_LOAD_FACTOR负载因子: 0.75。至于为什么是0.75,这里查阅了一下资料:

JDK中的解释就是尽量减少rehash的次数,并且在时间和空间上做了一个很好的折中。同时,如果这个值设置的比较大的话,桶中的键值碰撞的几率就会大大上升。

扩容的核心代码:

for (int j = 0; j < oldCap; ++j) {
            Node<K,V> e;
            if ((e = oldTab[j]) != null) {
                oldTab[j] = null;
                if (e.next == null)
                    newTab[e.hash & (newCap - 1)] = e;
                else if (e instanceof HashMap.TreeNode)
                    ((HashMap.TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                else { // preserve order
                    Node<K,V> loHead = null, loTail = null;
                    Node<K,V> hiHead = null, hiTail = null;
                    Node<K,V> next;
                    do {
                        next = e.next;
                        if ((e.hash & oldCap) == 0) {
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        else {
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    if (loTail != null) {
                        loTail.next = null;
                        newTab[j] = loHead;
                    }
                    if (hiTail != null) {
                        hiTail.next = null;
                        newTab[j + oldCap] = hiHead;
                    }
                }
            }
        }

这个桶中的内容有可能是链表,也有可能是红黑树。

Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
    next = e.next;
    if ((e.hash & oldCap) == 0) {
        if (loTail == null)
            loHead = e;
        else
            loTail.next = e;
        loTail = e;
    }
    else {
        if (hiTail == null)
            hiHead = e;
        else
            hiTail.next = e;
        hiTail = e;
    }
} while ((e = next) != null);
if (loTail != null) {
    loTail.next = null;
    newTab[j] = loHead;
}
if (hiTail != null) {
    hiTail.next = null;
    newTab[j + oldCap] = hiHead;
}

以上是针对链表结构的一个扩容。

loHead这部分表示的是在扩容之后,在table中的位置没有变动的数据,然后将他们拼装到链表中,然后在后面拼接到newTab[j]中。

hiHead这部分表示的是在扩容之后,位置有发生变动,然后将他们拼装的链表拼接到newTab[j + oldCap]中。

注意: 在我们这个Jdk1.8中,不会发生扩容的死循环.

当我们的链表的大小超过7的时候,就会将链表转换成红黑树:

for (int binCount = 0; ; ++binCount) {
    if ((e = p.next) == null) {
        p.next = newNode(hash, key, value, null);
        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
            treeifyBin(tab, hash);
        break;
    }
    if (e.hash == hash &&
        ((k = e.key) == key || (key != null && key.equals(k))))
        break;
    p = e;
}

TREEIFY_THRESHOLD这里的数值是为8

树的分裂

关于红黑树的原理,建议参考这篇文章: 红黑树

((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
/**
 * Splits nodes in a tree bin into lower and upper tree bins,
 * or untreeifies if now too small. Called only from resize;
 * see above discussion about split bits and indices.
 *
 * @param map the map
 * @param tab the table for recording bin heads
 * @param index the index of the table being split
 * @param bit the bit of hash to split on
 */
final void split(HashMap<K,V> map, Node<K,V>[] tab, int index, int bit) {
    TreeNode<K,V> b = this;
    // Relink into lo and hi lists, preserving order
    TreeNode<K,V> loHead = null, loTail = null;
    TreeNode<K,V> hiHead = null, hiTail = null;
    int lc = 0, hc = 0;
    for (TreeNode<K,V> e = b, next; e != null; e = next) {
        next = (TreeNode<K,V>)e.next;
        e.next = null;
        if ((e.hash & bit) == 0) {
            if ((e.prev = loTail) == null)
                loHead = e;
            else
                loTail.next = e;
                loTail = e;
                ++lc;
        } else {
                if ((e.prev = hiTail) == null)
                    hiHead = e;
                else
                    hiTail.next = e;
                hiTail = e;
                ++hc;
            }
        }

    if (loHead != null) {
        if (lc <= UNTREEIFY_THRESHOLD)
            tab[index] = loHead.untreeify(map);
        else {
            tab[index] = loHead;
            if (hiHead != null) // (else is already treeified)
                loHead.treeify(tab);
        }
    }
    if (hiHead != null) {
        if (hc <= UNTREEIFY_THRESHOLD)
            tab[index + bit] = hiHead.untreeify(map);
        else {
            tab[index + bit] = hiHead;
            if (loHead != null)
                hiHead.treeify(tab);
        }
    }
}

/* ------------------------------------------------------------ */
// Red-black tree methods, all adapted from CLR

原文发布于微信公众号 - 云端漫记(BB_gzhsh)

原文发表时间:2019-10-15

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

扫码关注云+社区

领取腾讯云代金券