一、简介
前面介绍了jdk1.7的ConcurrentHashMap,这里介绍下jdk1.8版本的ConcurrentHashMap,相对于jdk1.7版本,
jdk1.8有比较大的改动。取消之前的分段锁,引入了CAS(compare and swap)机制,冲突时采用了synchronize关键字,
数据结构引入红黑树,加快了查找速度。
二、知识点
1、数据结构
数据结构采用:数组+链表+红黑树
基本数据存在Node[]数组中,当有冲突时引入链表,链表达到一定长度时,转为红黑树,
每个Node结点采用CAS机制(保证原子性)进行替换,只有当前值与指定值相等时,才替换。
对关键数据使用volatile关键字保证可见性。
在有冲突的Node节点,采用synchronize进行加锁。
数据结构示意图如下:
Node[0] (synchronize)-> Node -> Node Node[1] (synchronize)-> Node Node[2] Node[3] (synchronize)->TreeNode . . . .三、源码浅读
1、ConcurrentHashMap继承了AbstractMap类,实现了ConcurrentMap接口,
源码如下:
public class ConcurrentHashMap<K,V> extends AbstractMap<K,V> implements ConcurrentMap<K,V>, Serializable {2、基本内部类有Node、TreeNode
Node为基本存储单元,类定义如下:
/** * 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. */ static class Node<K,V> implements Map.Entry<K,V> { final int hash; final K key; volatile V val; volatile Node<K,V> next; 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) { Object k, v, u; Map.Entry<?,?> e; return ((o instanceof Map.Entry) && (k = (e = (Map.Entry<?,?>)o).getKey()) != null && (v = e.getValue()) != null && (k == key || k.equals(key)) && (v == (u = val) || v.equals(u))); } /** * 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)))) return e; } while ((e = e.next) != null); } return null; } }TreeNode为红黑树的数据存储单元,对应的红黑树为TreeBin,TreeNode类定义如下:
/** * Nodes for use in TreeBins */ static final class TreeNode<K,V> extends Node<K,V> { TreeNode<K,V> parent; // red-black tree links TreeNode<K,V> left; TreeNode<K,V> right; TreeNode<K,V> prev; // needed to unlink next upon deletion boolean red; TreeNode(int hash, K key, V val, Node<K,V> next, TreeNode<K,V> parent) { super(hash, key, val, next); this.parent = parent; } Node<K,V> find(int h, Object k) { return findTreeNode(h, k, null); } /** * Returns the TreeNode (or null if not found) for the given key * starting at given root. */ final TreeNode<K,V> findTreeNode(int h, Object k, Class<?> kc) { if (k != null) { TreeNode<K,V> p = this; do { int ph, dir; K pk; TreeNode<K,V> q; TreeNode<K,V> pl = p.left, pr = p.right; if ((ph = p.hash) > h) p = pl; else if (ph < h) p = pr; else if ((pk = p.key) == k || (pk != null && k.equals(pk))) return p; else if (pl == null) p = pr; else if (pr == null) p = pl; else if ((kc != null || (kc = comparableClassFor(k)) != null) && (dir = compareComparables(kc, k, pk)) != 0) p = (dir < 0) ? pl : pr; else if ((q = pr.findTreeNode(h, k, kc)) != null) return q; else p = pl; } while (p != null); } return null; } }3、ConcurrentHashMap采用cas和velocity机制保证在读取、设置、替换时原子性,其关键实现代码如下:
/* * Volatile access methods are used for table elements as well as * elements of in-progress next table while resizing. All uses of * the tab arguments must be null checked by callers. All callers * also paranoically precheck that tab's length is not zero (or an * equivalent check), thus ensuring that any index argument taking * the form of a hash value anded with (length - 1) is a valid * index. Note that, to be correct wrt arbitrary concurrency * errors by users, these checks must operate on local variables, * which accounts for some odd-looking inline assignments below. * Note that calls to setTabAt always occur within locked regions, * and so in principle require only release ordering, not * full volatile semantics, but are currently coded as volatile * writes to be conservative. */ @SuppressWarnings("unchecked") static final <K,V> Node<K,V> tabAt(Node<K,V>[] tab, int i) { return (Node<K,V>)U.getObjectVolatile(tab, ((long)i << ASHIFT) + ABASE); } static final <K,V> boolean casTabAt(Node<K,V>[] tab, int i, Node<K,V> c, Node<K,V> v) { return U.compareAndSwapObject(tab, ((long)i << ASHIFT) + ABASE, c, v); } static final <K,V> void setTabAt(Node<K,V>[] tab, int i, Node<K,V> v) { U.putObjectVolatile(tab, ((long)i << ASHIFT) + ABASE, v); }4、ConcurrentHashMap的字段及构造函数
ConcurrentHashMap的基本数组结构为数组,基本字段即为Node[]数组,
默认链表最大长度为8,否则转为红黑树,
红黑树默认最少元素个数为6,否则转为链表。
容量最大为2的30次方。
加载因子默认为0.75。
另外其它一些默认设置。
其源码如下:
/* ---------------- Constants -------------- */ /** * 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; /** * 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; /** * 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; /** * 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; /** * 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; /** * 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; /** * 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(); /** For serialization compatibility. */ private static final ObjectStreamField[] serialPersistentFields = { new ObjectStreamField("segments", Segment[].class), new ObjectStreamField("segmentMask", Integer.TYPE), new ObjectStreamField("segmentShift", Integer.TYPE) };
/* ---------------- Fields -------------- */ /** * The array of bins. Lazily initialized upon first insertion. * Size is always a power of two. Accessed directly by iterators. */ transient volatile Node<K,V>[] table; /** * The next table to use; non-null only while resizing. */ private transient volatile Node<K,V>[] nextTable; /** * 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 initialization and resizing control. When negative, the * table is being initialized or resized: -1 for initialization, * else -(1 + the number of active resizing threads). Otherwise, * when table is null, holds the initial table size to use upon * creation, or 0 for default. After initialization, holds the * next element count value upon which to resize the table. */ private transient volatile int sizeCtl; /** * The next table index (plus one) to split while resizing. */ private transient volatile int transferIndex; /** * Spinlock (locked via CAS) used when resizing and/or creating CounterCells. */ private transient volatile int cellsBusy; /** * Table of counter cells. When non-null, size is a power of 2. */ private transient volatile CounterCell[] counterCells; // views private transient KeySetView<K,V> keySet; private transient ValuesView<K,V> values; private transient EntrySetView<K,V> entrySet; /* ---------------- Public operations -------------- */ /** * 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; }6、hash值的计算,根据key的hashCode进行计算的,
源码如下:
/** * Spreads (XORs) higher bits of hash to lower and also forces top * bit to 0. 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 spread(int h) { return (h ^ (h >>> 16)) & HASH_BITS; }7、get方法
首先根据key计算出在table(Node[]数组)中的位置,
若key相等,则返回结节,否则在链表或红黑树中查找,若还没找到,则返回null。
源码如下:
/** * Returns the value to which the specified key is mapped, * or {@code null} if this map contains no mapping for the key. * * <p>More formally, if this map contains a mapping from a key * {@code k} to a value {@code v} such that {@code key.equals(k)}, * then this method returns {@code v}; otherwise it returns * {@code null}. (There can be at most one such mapping.) * * @throws NullPointerException if the specified key is null */ 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; } else if (eh < 0) return (p = e.find(h, key)) != null ? p.val : null; while ((e = e.next) != null) { if (e.hash == h && ((ek = e.key) == key || (ek != null && key.equals(ek)))) return e.val; } } return null; }8、put方法
key和value都不能为null,否则会抛出异常。
若基本数组table未初始化,则先进行初始化。
若key指定的结点没有元素,则直接设置,
否则添加采用synchronized来保证线程安全。
也就是说,通常情况下,是不会加锁的,只有在冲突时,才会加锁,且锁是加在冲突的node上。有良好的并发性能。
源码如下:
/** * Maps the specified key to the specified value in this table. * Neither the key nor the value can be null. * * <p>The value can be retrieved by calling the {@code get} method * with a key that is equal to the original key. * * @param key key with which the specified value is to be associated * @param value value to be associated with the specified key * @return the previous value associated with {@code key}, or * {@code null} if there was no mapping for {@code key} * @throws NullPointerException if the specified key or value is null */ public V put(K key, V value) { return putVal(key, value, false); } /** 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) tab = initTable(); else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) { 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 { 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; }