一、首先看下HashMap的put方法。java
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) // 1.1 初始化数组长度 n = (tab = resize()).length; // 1.2 查询数组对应下标是否有值,下标计算tab[i = (n - 1) & hash] // hash表示经过key.hashcode和key.hashcode的高16位进行异或操做,为何要这样作?,n-1表示15,二进制表示01111 /** * 解释:好比key.hashcode = 10010110101010,那么如何直接拿 key.hashcode & (n-1) 此处n-1 = 15 * 10010110101010 * 01111 *----------------------- * 01010 * 此时是否发现key.hashcode的高16位压根就没有进行计算,那么只用低位计算是否是冲突的几率较大? * 这就是为何将key.hashcode的高位和低位进行^操做后在与15进行&操做 */ if ((p = tab[i = (n - 1) & hash]) == null) // 1.3 将对应的值放入数组对应下标 tab[i] = newNode(hash, key, value, null); else { // hash 发生碰撞 Node<K,V> e; K k; // 而且发现key已存在,那么将新值和旧值互换 if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k)))) e = p; else if (p instanceof TreeNode) // 红黑二叉树 e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); else { // 链表 for (int binCount = 0; ; ++binCount) { // 判断链表的next是否有值 if ((e = p.next) == null) { p.next = newNode(hash, key, value, null); // 当链表的数量大于等于8时,链表会自动转换成红黑二叉树,由于链表过长会致使链表的查询效率太低 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; // 当map中的数据大于16*0.75=12 map的初始化大小位16,负载因子0.75 if (++size > threshold) resize(); afterNodeInsertion(evict); return null; }
二、 经过解读源码发现hashmap不时线程安全
那么此时hashtable登场 经过源码发现hashtable的put方法上加了synchronized关键字,HashTable容器使用synchronized来保证线程安全,但在线程竞争激烈的状况下HashTable的效率很是低下。由于当一个线程访问HashTable的同步方法时,其余线程访问HashTable的同步方法时,可能会进入阻塞或轮询状态。如线程1使用put进行添加元素,线程2不但不能使用put方法添加元素,而且也不能使用get方法来获取元素,因此竞争越激烈效率越低,此时会发现多线程操做时效率明显太低对吧!那么有办法解决吗?node
public synchronized V put(K key, V value) { // Make sure the value is not null if (value == null) { throw new NullPointerException(); } // Makes sure the key is not already in the hashtable. Entry<?,?> tab[] = table; int hash = key.hashCode(); int index = (hash & 0x7FFFFFFF) % tab.length; @SuppressWarnings("unchecked") Entry<K,V> entry = (Entry<K,V>)tab[index]; for(; entry != null ; entry = entry.next) { if ((entry.hash == hash) && entry.key.equals(key)) { V old = entry.value; entry.value = value; return old; } } addEntry(hash, key, value, index); return null; }
三、 当前有办法了,ConcurrentHashMap闪亮登场数组
/** Implementation for put and putIfAbsent */ final V putVal(K key, V value, boolean onlyIfAbsent) { if (key == null || value == null) throw new NullPointerException(); int hash = spread(key.hashCode()); int binCount = 0; for (Node<K,V>[] tab = table;;) { Node<K,V> f; int n, i, fh; if (tab == null || (n = tab.length) == 0) // 初始化数组,刚才咱们提到多线程,难道每一个线程都去初始化?下面单独拉出来看下 tab = initTable(); else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) { // 利用cas无锁机制,cas原子操做,在指定位置设定值 if (casTabAt(tab, i, null, new Node<K,V>(hash, key, value, null))) break; // no lock when adding to empty bin } else if ((fh = f.hash) == MOVED) // 此处map扩容后,数据转移 tab = helpTransfer(tab, f); else { // 锁住当前node节点,这样其余线程继续操做时,由于node对象不是同一个了, // 因此不会影响其余线程的操做,这样效率就提升了。 V oldVal = null; synchronized (f) { if (tabAt(tab, i) == f) { if (fh >= 0) { binCount = 1; for (Node<K,V> e = f;; ++binCount) { K ek; if (e.hash == hash && ((ek = e.key) == key || (ek != null && key.equals(ek)))) { oldVal = e.val; if (!onlyIfAbsent) e.val = value; break; } Node<K,V> pred = e; if ((e = e.next) == null) { pred.next = new Node<K,V>(hash, key, value, null); break; } } } else if (f instanceof TreeBin) { Node<K,V> p; binCount = 2; if ((p = ((TreeBin<K,V>)f).putTreeVal(hash, key, value)) != null) { oldVal = p.val; if (!onlyIfAbsent) p.val = value; } } } } if (binCount != 0) { if (binCount >= TREEIFY_THRESHOLD) treeifyBin(tab, i); if (oldVal != null) return oldVal; break; } } } addCount(1L, binCount); return null; }
四、回到刚才ConcurrentMap初始化 tab = initTable()安全
private transient volatile int sizeCtl; // 注意此处sizeCtl为volatile private final Node<K,V>[] initTable() { Node<K,V>[] tab; int sc; while ((tab = table) == null || tab.length == 0) { // 第一次进来sizeCtl值默认为0,那么其余线程过来时发现sizeCtl已经变成了-1, // 直接Thread.yield()让出cpu时间片。故此就实现了只有一个线程去初始化数组 if ((sc = sizeCtl) < 0) Thread.yield(); // lost initialization race; just spin else if (U.compareAndSwapInt(this, SIZECTL, sc, -1)) { // 将sc的值置为-1 try { if ((tab = table) == null || tab.length == 0) { int n = (sc > 0) ? sc : DEFAULT_CAPACITY; @SuppressWarnings("unchecked") Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n]; table = tab = nt; sc = n - (n >>> 2); } } finally { // 将sizeCtl置为 -1 sizeCtl = sc; } break; } } return tab; }
五、ConcurrentMap扩容注意点多线程
ConcurrentMap扩容时,其余线程不能再往map中添加/删除数据了,那么难道其余线程在那边等待,直到扩容完成?固然不是了,其余线程会去帮助扩容线程一块儿进行扩容,每一个线程都会去领取属于本身的任务app
final Node<K,V>[] helpTransfer(Node<K,V>[] tab, Node<K,V> f) { Node<K,V>[] nextTab; int sc; if (tab != null && (f instanceof ForwardingNode) && (nextTab = ((ForwardingNode<K,V>)f).nextTable) != null) { int rs = resizeStamp(tab.length); while (nextTab == nextTable && table == tab && (sc = sizeCtl) < 0) { if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 || sc == rs + MAX_RESIZERS || transferIndex <= 0) break; if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1)) { transfer(tab, nextTab); break; } } return nextTab; } return table; }