对 1.8 的 ConcurrentHashMap 做一个小总结:
从数组开始
transient volatile Node<K,V>[] table;
扩容时用到
private transient volatile Node<K,V>[] nextTable;
哈希槽后面连接着链表,或者红黑树
节点哈希值的含义
static final int MOVED = -1; // hash for forwarding nodes static final int TREEBIN = -2; // hash for roots of trees
操作数组使用的是 Unsafe
private static final sun.misc.Unsafe U;
对槽中连的第一个元素的操作使用的是 CAS,而 CAS 是有可能失败的,因此,put 是在 for 循环中完成,有重试的动作。
put 方法
final V putVal(K key, V value, boolean onlyIfAbsent) { // key 和 value 不能为空 if (key == null || value == null) throw new NullPointerException(); // 计算 hash 值 int hash = spread(key.hashCode()); int binCount = 0; // 请一定注意,put 操作是在 for 循环里面完成的 for (Node<K,V>[] tab = table;;) { Node<K,V> f; int n, i, fh; if (tab == null || (n = tab.length) == 0) // table 还为空,初始化数组 tab = initTable(); // 对 hash 值取模 // 用 Unsafe#getObjectVolatile 获取数组元素 else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) { // 如果头节点为空,使用 Unsafe#compareAndSwapObject 设置头节点 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) tab = helpTransfer(tab, f); else { // 如果头节点存在,则对头节点加锁 V oldVal = null; synchronized (f) { if (tabAt(tab, i) == f) { // 当 Node.hash 等于 -2,表明 TreeBin,大于 0 ,则是正常的链表 if (fh >= 0) { binCount = 1; // 遍历链表 Node for (Node<K,V> e = f;; ++binCount) { K ek; // 遍历链表,如果发现相同的 key,onlyIfAbsent 默认 false,则替换 value if (e.hash == hash && ((ek = e.key) == key || (ek != null && key.equals(ek)))) { oldVal = e.val; if (!onlyIfAbsent) e.val = value; break; } // 没有相同的 key,插入链表尾部 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; // 节点插入红黑树中 if ((p = ((TreeBin<K,V>)f).putTreeVal(hash, key, value)) != null) { oldVal = p.val; if (!onlyIfAbsent) p.val = value; } } } } if (binCount != 0) { // 链表数量超过 8,且 table 数量大于 64, 则创建红黑树 if (binCount >= TREEIFY_THRESHOLD) treeifyBin(tab, i); if (oldVal != null) return oldVal; // 跳出外层 for 循环 break; } } } addCount(1L, binCount); return null; }
HashMap 的数组长度是 2 的幂,决定一个元素插在哪个槽,本质是对 len 取模,对应到代码是 &(len - 1)
例如,哈希表的数组长度是 8,两个键的 hash 值分别是 2 和 10
2 mod 8 = 2
10 mod 8 = 2
在扩容时,长度从 8 扩到 16
2 mod 16 = 2
10 mod 16 = 10
2 对应的槽位不变,10 对应的槽位变了
当 map 中节点数量超过容量时,或者链表长度大于8,但数组长度小于64时,会触发(纵向)扩容。扩容是多线程并发扩容,可以认为是每个线程处理 16 个槽。
原数组中,迁移的槽位号,从 n 到 0
private transient volatile int transferIndex;
private final void transfer(Node<K,V>[] tab, Node<K,V>[] nextTab) { int n = tab.length, stride; // stride 是每个线程需要处理的槽个数,暂认为是 16 if ((stride = (NCPU > 1) ? (n >>> 3) / NCPU : n) < MIN_TRANSFER_STRIDE) stride = MIN_TRANSFER_STRIDE; // subdivide range // 如果 nextTab 为空,则创建数组 if (nextTab == null) { // initiating try { @SuppressWarnings("unchecked") Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n << 1]; nextTab = nt; } catch (Throwable ex) { // try to cope with OOME sizeCtl = Integer.MAX_VALUE; return; } nextTable = nextTab; // 设置 transferIndex,线程从 transferIndex 开始,递减处理 16 个槽 transferIndex = n; } int nextn = nextTab.length; // 迁移完的标志节点 ForwardingNode<K,V> fwd = new ForwardingNode<K,V>(nextTab); boolean advance = true; boolean finishing = false; // to ensure sweep before committing nextTab for (int i = 0, bound = 0;;) { Node<K,V> f; int fh; // 这个 while 循环确定线程要处理的边界 // 这个 i 就是线程开始处理的原 table 的槽位置 while (advance) { int nextIndex, nextBound; if (--i >= bound || finishing) advance = false; else if ((nextIndex = transferIndex) <= 0) { i = -1; advance = false; } else if (U.compareAndSwapInt (this, TRANSFERINDEX, nextIndex, nextBound = (nextIndex > stride ? nextIndex - stride : 0))) { bound = nextBound; i = nextIndex - 1; advance = false; } } if (i < 0 || i >= n || i + n >= nextn) { int sc; if (finishing) { nextTable = null; table = nextTab; sizeCtl = (n << 1) - (n >>> 1); return; } if (U.compareAndSwapInt(this, SIZECTL, sc = sizeCtl, sc - 1)) { if ((sc - 2) != resizeStamp(n) << RESIZE_STAMP_SHIFT) return; finishing = advance = true; i = n; // recheck before commit } } // 原 table 槽 i 处的键为空 else if ((f = tabAt(tab, i)) == null) // 直接置为已迁移完标志 advance = casTabAt(tab, i, null, fwd); // 已迁移完 else if ((fh = f.hash) == MOVED) advance = true; // already processed else { synchronized (f) { if (tabAt(tab, i) == f) { // 低位节点,高位节点 // 低位节点插在新 table 的槽位不变,高位节点插在新 table 槽位 i+n 处 Node<K,V> ln, hn; if (fh >= 0) { // 键的哈希值与上原数组长度 int runBit = fh & n; // lastRun 表示最后的连续的高位为1或0的节点链表 Node<K,V> lastRun = f; for (Node<K,V> p = f.next; p != null; p = p.next) { int b = p.hash & n; if (b != runBit) { runBit = b; lastRun = p; } } if (runBit == 0) { ln = lastRun; hn = null; } else { hn = lastRun; ln = null; } for (Node<K,V> p = f; p != lastRun; p = p.next) { int ph = p.hash; K pk = p.key; V pv = p.val; // 哈希值与上原数组长度为 0,插入新数组槽 i if ((ph & n) == 0) ln = new Node<K,V>(ph, pk, pv, ln); // 哈希值与上原数组长度不为 0,插入新数组槽 i+n else hn = new Node<K,V>(ph, pk, pv, hn); } setTabAt(nextTab, i, ln); setTabAt(nextTab, i + n, hn); setTabAt(tab, i, fwd); advance = true; } else if (f instanceof TreeBin) { TreeBin<K,V> t = (TreeBin<K,V>)f; TreeNode<K,V> lo = null, loTail = null; TreeNode<K,V> hi = null, hiTail = null; int lc = 0, hc = 0; for (Node<K,V> e = t.first; e != null; e = e.next) { int h = e.hash; TreeNode<K,V> p = new TreeNode<K,V> (h, e.key, e.val, null, null); if ((h & n) == 0) { if ((p.prev = loTail) == null) lo = p; else loTail.next = p; loTail = p; ++lc; } else { if ((p.prev = hiTail) == null) hi = p; else hiTail.next = p; hiTail = p; ++hc; } } ln = (lc <= UNTREEIFY_THRESHOLD) ? untreeify(lo) : (hc != 0) ? new TreeBin<K,V>(lo) : t; hn = (hc <= UNTREEIFY_THRESHOLD) ? untreeify(hi) : (lc != 0) ? new TreeBin<K,V>(hi) : t; setTabAt(nextTab, i, ln); setTabAt(nextTab, i + n, hn); setTabAt(tab, i, fwd); advance = true; } } } } } }
-1 初始化
-(1+扩容线程数)
扩容阈值
当 map 中元素超过 sizeCtl 时,开始扩容
private transient volatile int sizeCtl;
public ConcurrentHashMap(int initialCapacity) { if (initialCapacity < 0) throw new IllegalArgumentException(); int cap = ((initialCapacity >= (MAXIMUM_CAPACITY >>> 1)) ? MAXIMUM_CAPACITY : tableSizeFor(initialCapacity + (initialCapacity >>> 1) + 1)); // 初始值 cap,规格化 2 的幂 this.sizeCtl = cap; } private final Node<K,V>[] initTable() { Node<K,V>[] tab; int sc; while ((tab = table) == null || tab.length == 0) { if ((sc = sizeCtl) < 0) Thread.yield(); // lost initialization race; just spin // 设置 -1,开始初始化 else if (U.compareAndSwapInt(this, SIZECTL, sc, -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; // n - 0.25n = 0.75n sc = n - (n >>> 2); } } finally { sizeCtl = sc; } break; } } return tab; }
统计 map 中的数量
private transient volatile long baseCount;
使用 CAS 写 baseCount 变量,更新成功就成功,失败了需要再次更新。
链表转化为红黑树,当链表长度超过 8,且数组长度大于 64 时,树化(横向扩容)
private final void treeifyBin(Node<K,V>[] tab, int index) { Node<K,V> b; int n, sc; if (tab != null) { // 数组长度小于 64,数组扩容成 2n if ((n = tab.length) < MIN_TREEIFY_CAPACITY) tryPresize(n << 1); else if ((b = tabAt(tab, index)) != null && b.hash >= 0) { synchronized (b) { if (tabAt(tab, index) == b) { // 构建红黑树 TreeNode<K,V> hd = null, tl = null; for (Node<K,V> e = b; e != null; e = e.next) { TreeNode<K,V> p = new TreeNode<K,V>(e.hash, e.key, e.val, null, null); if ((p.prev = tl) == null) hd = p; else tl.next = p; tl = p; } setTabAt(tab, index, new TreeBin<K,V>(hd)); } } } } }
get 方法
public V get(Object key) { Node<K,V>[] tab; Node<K,V> e, p; int n, eh; K ek; int h = spread(key.hashCode()); if ((tab = table) != null && (n = tab.length) > 0 && (e = tabAt(tab, (n - 1) & h)) != null) { if ((eh = e.hash) == h) { if ((ek = e.key) == key || (ek != null && key.equals(ek))) return e.val; } // 节点的哈希值小于 0,可能是红黑树或者 ForwardingNode(扩容完成迁移) else if (eh < 0) return (p = e.find(h, key)) != null ? p.val : null; // 遍历链表查询 while ((e = e.next) != null) { if (e.hash == h && ((ek = e.key) == key || (ek != null && key.equals(ek)))) return e.val; } } return null; }
get 操作的槽位是 ForwardingNode 节点时,查询操作路由到新的数组中
// java.util.concurrent.ConcurrentHashMap.ForwardingNode#find Node<K,V> find(int h, Object k) { // loop to avoid arbitrarily deep recursion on forwarding nodes outer: for (Node<K,V>[] tab = nextTable;;) { Node<K,V> e; int n; if (k == null || tab == null || (n = tab.length) == 0 || (e = tabAt(tab, (n - 1) & h)) == null) return null; for (;;) { int eh; K ek; if ((eh = e.hash) == h && ((ek = e.key) == k || (ek != null && k.equals(ek)))) return e; if (eh < 0) { if (e instanceof ForwardingNode) { tab = ((ForwardingNode<K,V>)e).nextTable; continue outer; } else return e.find(h, k); } if ((e = e.next) == null) return null; } } }
场景1:在数组扩容时,插入键值对
当前线程 put 键值对时,如果插入的槽位正在迁移,因为这个槽被迁移线程加锁了,所以当前线程阻塞等待锁,槽位被其他线程迁移完后,置节点为 ForwardingNode,当前线程获得锁,因为槽位不是普通的链表和树,则开始 for 循环下一轮遍历,发现槽位是 ForwardingNode,则帮助迁移,当前线程完成自己的迁移任务后,返回新的 table,把键值对插入新的 table 中。
场景2:事实上,一个线程在扩容时只处理 16 个槽,所以有一段时间,数据会分布在新旧两个数组中。
浙公网安备 33010602011771号