一、CAS原理简介
Java8中,ConcurrentHashMap摒弃了Segment的概念,而是启用了一种全新的方式实现:利用CAS算法。它沿用了HashMap的思想,底层依然由“数组”+链表+红黑树的方式实现。
那什么CAS算法呢?以前采用锁的方式实现同步,对于简单问题来说显得粒度过大,影响效率。现在的处理器都支持多重处理,当然也包含多个处理器共享外围设备和内存,同时,加强了指令集以支持一些多处理的特殊需求。特别是几乎所有的处理器都可以将其他处理器阻塞以便更新共享变量。
当前的处理器基本都支持CAS(Compare and swap),只不过每个厂家所实现的算法并不一样罢了,每一个CAS操作过程都包含三个运算符:一个内存地址V,一个期望的值A和一个新值B,操作的时候如果这个地址上存放的值等于这个期望的值A,则将地址上的值赋为新值B,否则不做任何操作。CAS的基本思路就是,如果这个地址上的值和期望的值相等,则给其赋予新值,否则不做任何事儿,但是要返回原值是多少。
简单地说,CAS使得同步并不阻塞在编程语言层面上,而是阻塞在硬件层面上。
二、存储结构
ConcurrentHashMap中有以下几种常见的存储结构:
- Node:大部分key-value对都存储在此结构中,用于hash冲突中,用链表法存储
- TreeNode:继承Node,用于hash冲突中,用红黑树存储
- TreeBin:用来保存TreeNode的根,并维护红黑树的添加、删除等操作
- ForwardingNode:在容器扩容时适用。被放置在bin的头部
- ReservationNode:在调用computeIfAbsent之类的函数时适用
(1)Node结构
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; }
// 不准对Node赋值
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)));
}
// map.get的辅助方法
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;
}
}
(2)TreeNode
// TreeNode 只比普通的Node多了一些属性,红色树的相关操作由TreeBin负责
static final class TreeNode<K,V> extends Node<K,V> {
TreeNode<K,V> parent;
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev;
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);
}
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)TreeBin
TreeNode作为bin的头节点,TreeBin实际上只是一系列的TreeNode和它们的根,并不包含key-value对。同时TreeBin还维护着这一系列TreeNode的读写锁。
static final class TreeBin<K,V> extends Node<K,V> {
TreeNode<K,V> root;
volatile TreeNode<K,V> first;
volatile Thread waiter;
volatile int lockState;
// values for lockState
static final int WRITER = 1; // set while holding write lock
static final int WAITER = 2; // set when waiting for write lock
static final int READER = 4; // increment value for setting read lock
// 构造函数
TreeBin(TreeNode<K,V> b) {
super(TREEBIN, null, null, null);
this.first = b;
TreeNode<K,V> r = null;
for (TreeNode<K,V> x = b, next; x != null; x = next) {
next = (TreeNode<K,V>)x.next;
x.left = x.right = null;
if (r == null) {
x.parent = null;
x.red = false;
r = x;
}
else {
K k = x.key;
int h = x.hash;
Class<?> kc = null;
for (TreeNode<K,V> p = r;;) {
int dir, ph;
K pk = p.key;
if ((ph = p.hash) > h)
dir = -1;
else if (ph < h)
dir = 1;
else if ((kc == null &&
(kc = comparableClassFor(k)) == null) ||
(dir = compareComparables(kc, k, pk)) == 0)
dir = tieBreakOrder(k, pk);
TreeNode<K,V> xp = p;
if ((p = (dir <= 0) ? p.left : p.right) == null) {
x.parent = xp;
if (dir <= 0)
xp.left = x;
else
xp.right = x;
r = balanceInsertion(r, x);
break;
}
}
}
}
this.root = r;
assert checkInvariants(root);
}
// 后面还有许多红黑树等相关操作
}
三、属性域
/* 常量 */
// 32位中的高2位被用来作为控制bit
private static final int MAXIMUM_CAPACITY = 1 << 30;
private static final int DEFAULT_CAPACITY = 16;
static final int MAX_ARRAY_SIZE = Integer.MAX_VALUE - 8;
// 未被用到,用来兼容之前版本
private static final int DEFAULT_CONCURRENCY_LEVEL = 16;
// 跟hashmap一样
private static final float LOAD_FACTOR = 0.75f;
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
// 最小重排步
private static final int MIN_TRANSFER_STRIDE = 16;
// sizeCtl中记录size的bit数
private static int RESIZE_STAMP_BITS = 16;
// 参与扩容的最大线程数
private static final int MAX_RESIZERS = (1 << (32 - RESIZE_STAMP_BITS)) - 1;
// sizeCtl中记录size大小的偏移量
private static final int RESIZE_STAMP_SHIFT = 32 - RESIZE_STAMP_BITS;
// 一些特定的哈希值代表不同含义
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
// CPU数
static final int NCPU = Runtime.getRuntime().availableProcessors();
/* 属性域 */
// 桶表
transient volatile Node<K,V>[] table;
// 扩容时候使用
private transient volatile Node<K,V>[] nextTable;
// 没有竞争条件时,使用
private transient volatile long baseCount;
// 用来初始化和扩容控制
// == -1,代表初始化
// < -1,-sizeCtl - 1 代表扩容
// == 0,table为null
// > 0,sizeCtl代表下次扩容容量
private transient volatile int sizeCtl;
四、几个重要方法
// ConcurrentHashMap中的桶的访问和赋值
@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);
}
// valatile方法,需在临界区中执行
static final <K,V> void setTabAt(Node<K,V>[] tab, int i, Node<K,V> v) {
U.putObjectVolatile(tab, ((long)i << ASHIFT) + ABASE, v);
}
五、构造函数
public ConcurrentHashMap() {
}
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;
}
public ConcurrentHashMap(Map<? extends K, ? extends V> m) {
this.sizeCtl = DEFAULT_CAPACITY;
putAll(m);
}
public ConcurrentHashMap(int initialCapacity, float loadFactor) {
this(initialCapacity, loadFactor, 1);
}
// 第三个参数为更新容器的线程数
public ConcurrentHashMap(int initialCapacity,
float loadFactor, int concurrencyLevel) {
if (!(loadFactor > 0.0f) || initialCapacity < 0 || concurrencyLevel <= 0)
throw new IllegalArgumentException();
if (initialCapacity < concurrencyLevel)
initialCapacity = concurrencyLevel;
long size = (long)(1.0 + (long)initialCapacity / loadFactor);
int cap = (size >= (long)MAXIMUM_CAPACITY) ?
MAXIMUM_CAPACITY : tableSizeFor((int)size);
this.sizeCtl = cap;
}
六、查找操作
public V get(Object key) {
Node<K,V>[] tab; Node<K,V> e, p; int n, eh; K ek;
int h = spread(key.hashCode());
// 判断table是否null或者未空
if ((tab = table) != null && (n = tab.length) > 0 &&
// 注意:因为容器大小为2的次方,所以 h mod n = h & (n -1)
(e = tabAt(tab, (n - 1) & h)) != null) {
// 如果hash值相等
if ((eh = e.hash) == h) {
// 检查第一个Node
if ((ek = e.key) == key || (ek != null && key.equals(ek)))
return e.val;
}
// hash值小于0,代表此bin非一般的链表Node
else if (eh < 0)
return (p = e.find(h, key)) != null ? p.val : null;
// 遍历链表,对比key值
while ((e = e.next) != null) {
if (e.hash == h &&
((ek = e.key) == key || (ek != null && key.equals(ek))))
return e.val;
}
}
return null;
}
七、添加操作
// key值和value值均不能为null
public V put(K key, V value) {
return putVal(key, value, false);
}
final V putVal(K key, V value, boolean onlyIfAbsent) {
// key值和value值均不能为null
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;
// 如果table为空,执行初始化,也即是延迟初始化
if (tab == null || (n = tab.length) == 0)
tab = initTable();
// 如果bin为空,则采用cas算法赋值,无需加锁
else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) {
if (casTabAt(tab, i, null,
new Node<K,V>(hash, key, value, null)))
break;
}
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
// bin非空,且bin为一般的Node链表时
else {
V oldVal = null;
// 获取第一个Node的锁
synchronized (f) {
// 再判断以此f是否仍是第一个Node,如果不是,退出临界区,重复添加操作
if (tabAt(tab, i) == f) {
// 根据hash值判断,为一般的Node链表
if (fh >= 0) {
binCount = 1;
for (Node<K,V> e = f;; ++binCount) {
K ek;
// 如果key已经存在,替换,break退出
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;
// 如果遍历bin未找到key值相等等的,在bin末尾添加此Node
if ((e = e.next) == null) {
pred.next = new Node<K,V>(hash, key,
value, null);
break;
}
}
}
// 如果此bin是TreeBin
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;
}
}
}
}
// 如果bin的容量大于临界值,转为红黑树
if (binCount != 0) {
if (binCount >= TREEIFY_THRESHOLD)
// 此函数内部会判断是树化,还是扩容:tryPresize
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
// 此函数也有可能导致扩容
addCount(1L, binCount);
return null;
}
八、删除操作
public V remove(Object key) {
return replaceNode(key, null, null);
}
final V replaceNode(Object key, V value, Object cv) {
int hash = spread(key.hashCode());
for (Node<K,V>[] tab = table;;) {
Node<K,V> f; int n, i, fh;
// 不存在key值
if (tab == null || (n = tab.length) == 0 ||
(f = tabAt(tab, i = (n - 1) & hash)) == null)
break;
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
else {
V oldVal = null;
boolean validated = false;
// 替换操作,锁定第一个Node
synchronized (f) {
if (tabAt(tab, i) == f) {
// bin由Node链表组成
if (fh >= 0) {
validated = true;
for (Node<K,V> e = f, pred = null;;) {
K ek;
// 如果找到了
if (e.hash == hash &&
((ek = e.key) == key ||
(ek != null && key.equals(ek)))) {
V ev = e.val;
if (cv == null || cv == ev ||
(ev != null && cv.equals(ev))) {
oldVal = ev;
if (value != null)
e.val = value;
else if (pred != null)
pred.next = e.next;
else
// 注意:调用此方法必须在临界区中
setTabAt(tab, i, e.next);
}
break;
}
pred = e;
if ((e = e.next) == null)
break;
}
}
// 如果是TreeBin的红黑树结构
else if (f instanceof TreeBin) {
validated = true;
TreeBin<K,V> t = (TreeBin<K,V>)f;
TreeNode<K,V> r, p;
if ((r = t.root) != null &&
(p = r.findTreeNode(hash, key, null)) != null) {
V pv = p.val;
if (cv == null || cv == pv ||
(pv != null && cv.equals(pv))) {
oldVal = pv;
if (value != null)
p.val = value;
else if (t.removeTreeNode(p))
setTabAt(tab, i, untreeify(t.first));
}
}
}
}
}
if (validated) {
if (oldVal != null) {
if (value == null)
addCount(-1L, -1);
return oldVal;
}
break;
}
}
}
return null;
}
九、其他
- ConcurrentHashMap是延迟初始化的,只有在插入数据时,整个HashMap才被初始化为2的次方大小个桶(bin),每个bin包含哈希值相同的一系列Node(一般含有0或1个Node)。每个bin的第一个Node作为这个bin的锁,Hash值为零或者负的将被忽略
- 每个bin的第一个Node插入用到CAS原理,这是在ConcurrentHashMap中最常发生的操作,其余的插入、删除、替换操作对bin中的第一个Node加锁,进行操作
- ConcurrentHashMap的size()函数一般比较少用,同时为了提高增删查改的效率,容器并未在内部保存一个size值,而且采用每次调用size()函数时累加各个bin中Node的个数计算得到,而且这一过程不加锁,即得到的size值不一定是最新的
未完待续
参考
http://blog.csdn.net/u010723709/article/details/48007881
http://blog.csdn.net/u010887744/article/details/50637030