浅谈ConcurrentHashMap（基于JDK1.8）
原理简介
在JDK1.8的的升级中，ConcurrentHashMap沿用了HashMap的结构，使用了数组+链表+红黑树的结构，并且在1.8之后取消了1.7时的Segment数组加锁的形式，而是使用了CAS+Node数组加synchronized 锁的形式，粒度相较于1.7时更细，支持的并发成都更高
在1.8之后key和value都不可以为null
- 结构示意图
ConcurrentHashMap在1.8的数据结构
2.源码解析
一些重要的属性
/* 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 bit shift for recording size stamp in sizeCtl.
*/
private static final int RESIZE_STAMP_SHIFT = 32 - RESIZE_STAMP_BITS;
// hash for forwarding nodes 代表这个节点是forward节点，也就是被扩容完成
//在另一个线程扫到这个标记之后，会继续下一个
static final int MOVED = -1;
// hash for roots of trees
//代表这个节点是一个TreeBin节点
static final int TREEBIN = -2;
sizeCtl
//hash在初始化时的控制标记位
//-1代表正在进行初始化
//-N表示N-1个线程正在进行扩容操作
//正数或0代表hash表还没有被初始化，这个数值表示初始化或下一次进行扩容的大小
private transient volatile int sizeCtl;
Node节点
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;//节点hash值
final K key;//节点的key
volatile V val;//节点的value，带有syn锁
volatile Node<K,V> next;//节点的指针，带有syn锁
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; }
//在这里确定了，不可以直接对value进行set操作
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)));
}
TreeNode
//不用的是这个节点对树的封装，是通过TreeBin的结构来进行封装的
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;
}
}
TreeBin
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
/**
* Tie-breaking utility for ordering insertions when equal
* hashCodes and non-comparable. We don't require a total
* order, just a consistent insertion rule to maintain
* equivalence across rebalancings. Tie-breaking further than
* necessary simplifies testing a bit.
*/
static int tieBreakOrder(Object a, Object b) {
int d;
if (a == null || b == null ||
(d = a.getClass().getName().
compareTo(b.getClass().getName())) == 0)
d = (System.identityHashCode(a) <= System.identityHashCode(b) ?
-1 : 1);
return d;
}
/**
* Creates bin with initial set of nodes headed by b.
*/
//这里可以认为是对之前构建的TreeNode节点进行遍历
//来重新组装成红黑树的结构
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);
}
ForwardingNode
/**
* A node inserted at head of bins during transfer operations.
*/
//这里详细介绍了Forward节点的结构，其实就是表明了这个点在被扩容
//写线程呢要参与并发扩容，读线程要去新表进行读取
static final class ForwardingNode<K,V> extends Node<K,V> {
final Node<K,V>[] nextTable;
ForwardingNode(Node<K,V>[] tab) {
super(MOVED, null, null, null);
this.nextTable = tab;
}
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;
}
}
}
}
Unsafe静态块
解释下Unsafe的意思，这个就是提供了手动管理内存的能力，这个类可以做到即使是私有属性也可以通过这个取出来
// Unsafe mechanics
private static final sun.misc.Unsafe U;
private static final long SIZECTL;
private static final long TRANSFERINDEX;
private static final long BASECOUNT;
private static final long CELLSBUSY;
private static final long CELLVALUE;
private static final long ABASE;
private static final int ASHIFT;
static {
try {
U = sun.misc.Unsafe.getUnsafe();
Class<?> k = ConcurrentHashMap.class;
SIZECTL = U.objectFieldOffset
(k.getDeclaredField("sizeCtl"));
TRANSFERINDEX = U.objectFieldOffset
(k.getDeclaredField("transferIndex"));
BASECOUNT = U.objectFieldOffset
(k.getDeclaredField("baseCount"));
CELLSBUSY = U.objectFieldOffset
(k.getDeclaredField("cellsBusy"));
Class<?> ck = CounterCell.class;
CELLVALUE = U.objectFieldOffset
(ck.getDeclaredField("value"));
Class<?> ak = Node[].class;
ABASE = U.arrayBaseOffset(ak);
int scale = U.arrayIndexScale(ak);
if ((scale & (scale - 1)) != 0)
throw new Error("data type scale not a power of two");
ASHIFT = 31 - Integer.numberOfLeadingZeros(scale);
} catch (Exception e) {
throw new Error(e);
}
}
CAS的三个核心方法
因为之前说的是在1.8之后从原来的ReentrantLock改成了CAS，这三个方法就有最直观的体现
@SuppressWarnings("unchecked")
//获得在i位置上的Node节点，因为使用了Volatile进行修饰，所以保持了可见性
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);
}
//在CAS算法中，对传入值与内存值进行比较，如果相等，才会接受修改
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);
}
//利用volatile方法设置节点位置的值
static final <K,V> void setTabAt(Node<K,V>[] tab, int i, Node<K,V> v) {
U.putObjectVolatile(tab, ((long)i << ASHIFT) + ABASE, v);
}
initTable
//初始化节点数组
private final Node<K,V>[] initTable() {
Node<K,V>[] tab; int sc;
while ((tab = table) == null || tab.length == 0) {
//判断sizeCtl状态小于零，代表正在进行初始化操作，线程让出时间片
if ((sc = sizeCtl) < 0)
Thread.yield(); // lost initialization race; just spin
//这里就会将当前的状态设置为-1，表示正在进行扩容
else if (U.compareAndSwapInt(this, SIZECTL, sc, -1)) {
try {
//首先判断数组是不是为null
if ((tab = table) == null || tab.length == 0) {
//sc此时被赋值成为状态码也就是-1，所以被赋值成默认的长度
int n = (sc > 0) ? sc : DEFAULT_CAPACITY;
@SuppressWarnings("unchecked")
//初始化一个node数组
Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n];
table = tab = nt;
sc = n - (n >>> 2);
}
} finally {
//也就是记录下一次扩容大小
sizeCtl = sc;
}
break;
}
}
return tab;
}
transfer
容量不足的时候，ConcurrentHashMap会对其进行扩容，但是由于他是支持并发扩容的，所以与HashMap的扩容还是有很大的区别的
另一个特点是他在扩容的时候是不需要加锁的，所以说明在效率上是较为优秀的
扩容操作
单线程的情况下进行扩容
大致可以认为是遍历和复制，首先获取需要遍历的次数，用tabAt获取位置在i的元素
如果这个位置为null，name就把他设置成一个forwardNode节点，这个就是并发扩容的关键所在，请大家先记住这个概念
这是我们判断这个节点，如果是一个node节点，如果他是一个链表，那么就把他做成一个反序链表，将其放在newtab的i和i+n的位置
如果是一个treebin节点，代表是一个红黑树结构，这时同样需要进行反序处理，已经判断是否需要消除树化，同样放在newtab的i和i+n的位置
全部遍历结束之后，将newtab作为tab，然后更新sizectl为新容量的0.75倍
多线程下进行扩容操作
同样是遍历节点，如果我们遍历到的节点是forward节点，就继续向后遍历
多线程的情况，处理一个就把这个节点设置为forward，那样另一个线程遍历到的时候，就会跳过他执行下一个，这样交叉进行提高效率
/**
* 一个过渡的table表，只有在扩容的时候才会使用
*/
private transient volatile Node<K,V>[] nextTable;
/**
* Moves and/or copies the nodes in each bin to new table. See
* above for explanation.
*/
private final void transfer(Node<K,V>[] tab, Node<K,V>[] nextTab) {
int n = tab.length, stride;
if ((stride = (NCPU > 1) ? (n >>> 3) / NCPU : n) < MIN_TRANSFER_STRIDE)
stride = MIN_TRANSFER_STRIDE; // subdivide range
if (nextTab == null) { // initiating
try {
@SuppressWarnings("unchecked")
Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n << 1];//构造一个nextTable对象 它的容量是原来的两倍
nextTab = nt;
} catch (Throwable ex) { // try to cope with OOME
sizeCtl = Integer.MAX_VALUE;
return;
}
nextTable = nextTab;
transferIndex = n;
}
int nextn = nextTab.length;
ForwardingNode<K,V> fwd = new ForwardingNode<K,V>(nextTab);//构造一个连节点指针 用于标志位
boolean advance = true;//并发扩容的关键属性 如果等于true 说明这个节点已经处理过
boolean finishing = false; // to ensure sweep before committing nextTab
for (int i = 0, bound = 0;;) {
Node<K,V> f; int fh;
//这个while循环体的作用就是在控制i-- 通过i--可以依次遍历原hash表中的节点
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) {
//如果所有的节点都已经完成复制工作 就把nextTable赋值给table 清空临时对象nextTable
nextTable = null;
table = nextTab;
sizeCtl = (n << 1) - (n >>> 1);//扩容阈值设置为原来容量的1.5倍 依然相当于现在容量的0.75倍
return;
}
//利用CAS方法更新这个扩容阈值，在这里面sizectl值减一，说明新加入一个线程参与到扩容操作
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
}
}
//如果遍历到的节点为空 则放入ForwardingNode指针
else if ((f = tabAt(tab, i)) == null)
advance = casTabAt(tab, i, null, fwd);
//如果遍历到ForwardingNode节点 说明这个点已经被处理过了 直接跳过 这里是控制并发扩容的核心
else if ((fh = f.hash) == MOVED)
advance = true; // already processed
else {
//节点上锁
synchronized (f) {
if (tabAt(tab, i) == f) {
Node<K,V> ln, hn;
//如果fh>=0 证明这是一个Node节点
if (fh >= 0) {
int runBit = fh & n;
//以下的部分在完成的工作是构造两个链表 一个是原链表 另一个是原链表的反序排列
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;
if ((ph & n) == 0)
ln = new Node<K,V>(ph, pk, pv, ln);
else
hn = new Node<K,V>(ph, pk, pv, hn);
}
//在nextTable的i位置上插入一个链表
setTabAt(nextTab, i, ln);
//在nextTable的i+n的位置上插入另一个链表
setTabAt(nextTab, i + n, hn);
//在table的i位置上插入forwardNode节点 表示已经处理过该节点
setTabAt(tab, i, fwd);
//设置advance为true 返回到上面的while循环中 就可以执行i--操作
advance = true;
}
//对TreeBin对象进行处理 与上面的过程类似
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;
//构造正序和反序两个链表
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;
}
}
//如果扩容后已经不再需要tree的结构 反向转换为链表结构
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;
//在nextTable的i位置上插入一个链表
setTabAt(nextTab, i, ln);
//在nextTable的i+n的位置上插入另一个链表
setTabAt(nextTab, i + n, hn);
//在table的i位置上插入forwardNode节点 表示已经处理过该节点
setTabAt(tab, i, fwd);
//设置advance为true 返回到上面的while循环中 就可以执行i--操作
advance = true;
}
}
}
}
}
}
put
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) {
//校验key和value，都不可以为null
if (key == null || value == null) throw new NullPointerException();
//对key进行hash
int hash = spread(key.hashCode());
int binCount = 0;
//开始插入，但是这里是一个死循环，什么时候能够插入成功，成么时候才能跳出
for (Node<K,V>[] tab = table;;) {
Node<K,V> f; int n, i, fh;
//判断表是不是为null，是的话就进行初始化
if (tab == null || (n = tab.length) == 0)
tab = initTable();
//之后会将hash值和数组长度减一进行与运算，获取那个节点的数据
//如果为null，那么就讲这个数据放进去
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
}
//这里会判断这个节点是不是forward节点
//是的话就会帮助进行扩容
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
else {
V oldVal = null;
//所有情况判断结束之后，也就对当前节点进行加锁
//加锁之后会对其进行遍历
synchronized (f) {
//这里就遍历链表，有的话就进行覆盖操作
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;
//没有的话节点进行新增操作
if ((e = e.next) == null) {
pred.next = new Node<K,V>(hash, key,
value, null);
break;
}
}
}
//这里判断这个节点是不是一个树,是的话就进行遍历
//有相同的值就进行覆盖
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;
}
}
}
}
//这里就是判断链表是否已经达到或者大于阈值，就进行树化
//大量的CAS操作
if (binCount != 0) {
if (binCount >= TREEIFY_THRESHOLD)
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
//将当前ConcurrentHashMap的元素数量+1
addCount(1L, binCount);
return null;
}
helpTransfer方法
/**
* Helps transfer if a resize is in progress.
*/
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);//计算一个操作校验码
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;
}
treeifyBin方法
private final void treeifyBin(Node<K,V>[] tab, int index) {
Node<K,V> b; int n, sc;
if (tab != null) {
if ((n = tab.length) < MIN_TREEIFY_CAPACITY)//如果table.length<64 就扩大一倍 返回
tryPresize(n << 1);
else if ((b = tabAt(tab, index)) != null && b.hash >= 0) {
synchronized (b) {
if (tabAt(tab, index) == b) {
TreeNode<K,V> hd = null, tl = null;
//构造了一个TreeBin对象 把所有Node节点包装成TreeNode放进去
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);//这里只是利用了TreeNode封装 而没有利用TreeNode的next域和parent域
if ((p.prev = tl) == null)
hd = p;
else
tl.next = p;
tl = p;
}
//在原来index的位置 用TreeBin替换掉原来的Node对象
setTabAt(tab, index, new TreeBin<K,V>(hd));
}
}
}
}
}
get就没什么好说的了
public V get(Object key) {
Node<K,V>[] tab; Node<K,V> e, p; int n, eh; K ek;
//计算hash值
int h = spread(key.hashCode());
//根据hash值确定节点位置
if ((tab = table) != null && (n = tab.length) > 0 &&
(e = tabAt(tab, (n - 1) & h)) != null) {
//如果搜索到的节点key与传入的key相同且不为null,直接返回这个节点
if ((eh = e.hash) == h) {
if ((ek = e.key) == key || (ek != null && key.equals(ek)))
return e.val;
}
//如果eh<0 说明这个节点在树上 直接寻找
else if (eh < 0)
return (p = e.find(h, key)) != null ? p.val : null;
//否则遍历链表 找到对应的值并返回
while ((e = e.next) != null) {
if (e.hash == h &&
((ek = e.key) == key || (ek != null && key.equals(ek))))
return e.val;
}
}
return null;
}
1832
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
