JUC并发容器-ConcurrentHashMap
ConcurrentHashMap是在多线程情况下在线程安全的HashMap,它是一个高性能的线程安全的HashMap。在1.8版本以前，ConcurrentHashMap采用分段锁的概念，使锁更加细化，在jdk1.8以后，是利用CAS+Synchronized来保证并发更新的安全，底层采用数组+链表+红黑树的存储结构。本文基于1.8版本阅读ConcurrentHashMap源码。
内部类
ConcurrentHashMap中定义了一系列内部类以及成员变量及常量等。此处阅读Node对象：
static class Node implements Map.Entry {
final int hash;//Hash值
final K key;//key值
volatile V val;//value
volatile Node next; //链表下一个Node
//初始化
Node(int hash, K key, V val, Node 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 find(int h, Object k) {
Node 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;
}
} Node类的定义和HashMap中Node类定义基本一致，用来存储对象的key值和value值，以及下一个Node对象。
成员属性：
//节点数组
transient volatile Node[] table;
/**
* The next table to use; non-null only while resizing.
*/
//扩容时使用的扩容数组，为table的2倍
private transient volatile Node[] 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 keySet;
private transient ValuesView values;
private transient EntrySetView entrySet;
重要的成员属性：
- table : 用于存储Node节点数据，默认为Null,默认大小为16，每次扩容2的幂次方；
- nextTable ： 扩容时生成的新数据，数组为table的2倍。
构造函数
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(int initialCapacity, float loadFactor) {
this(initialCapacity, loadFactor, 1);
}
public ConcurrentHashMap(Map m) {
this.sizeCtl = DEFAULT_CAPACITY;
putAll(m);
}
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;
}initTable方法
//初始化table
private final Node[] initTable() {
Node[] tab; int sc;
while ((tab = table) == null || tab.length == 0) {
if ((sc = sizeCtl) < 0)
Thread.yield(); // lost initialization race; just spin
//设置SIZECTL 为 -1 表示当前线程正在初始化
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[] nt = (Node[])new Node[n];
table = tab = nt;
//扩容阈值 相当于 0.75*n
sc = n - (n >>> 2);
}
} finally {
sizeCtl = sc;
}
break;
}
}
return tab;
} 初始化的关键就是sizeCtl值，该值默认为0，设置为 -1 表示其他线程正在初始化。最后将sizeCtl值设置为0.75*2，表示扩容阈值。
put操作
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());//计算hash值
int binCount = 0;
for (Node[] tab = table;;) {
Node f; int n, i, fh;
if (tab == null || (n = tab.length) == 0)
tab = initTable();//tab为null，初始化table
else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) {
//该Node数组上没有对象，直接CAS添加对象，无需加锁。
if (casTabAt(tab, i, null,
new Node(hash, key, value, null)))
break; // no lock when adding to empty bin
}
//有线程正在进行扩容操作，帮助扩容
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
else {
V oldVal = null;
//对该节点加锁，进行插入操作，此操作对性能有点影响
synchronized (f) {
if (tabAt(tab, i) == f) {
if (fh >= 0) {
binCount = 1;
for (Node e = f;; ++binCount) {
K ek;
//hash和key一样，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;
}
Node pred = e;
//添加新节点对象在Node链表结尾
if ((e = e.next) == null) {
pred.next = new Node(hash, key,
value, null);
break;
}
}
}
//如果时红黑树结构，添加到红黑树结构中
else if (f instanceof TreeBin) {
Node p;
binCount = 2;
if ((p = ((TreeBin)f).putTreeVal(hash, key,
value)) != null) {
oldVal = p.val;
if (!onlyIfAbsent)
p.val = value;
}
}
}
}
//判断是否达到转换树结构的阈值
if (binCount != 0) {
if (binCount >= TREEIFY_THRESHOLD)
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
//size + 1
addCount(1L, binCount);
return null;
} put操作的流程如下：
- 判断tab是否为null，如果为null，则进行初始化操作
- 判断要添加的键的hash所在的Node链表是否为null，如果为null，表示该数组位置没有值，可以直接添加数据，不需要加锁。
- 判断是否有线程进行扩容操作，如果有，则帮助扩容
- 如果Node节点不为空，对该Node对象进行加锁，然后同步插入值，此时会导致插入该节点链表的其他对象阻塞。
- 添加过程首先查找应该插入的位置，然后插入，如果时红黑树结构，则添加到树结构中。
- 判断是否到达树结构阈值，到达则转换为树结构。
- size + 1.
put操作的第4个步骤，体现了ConcurrentHashMap的分段加锁机制，它针对Node数组的对象进行加锁，从而在并发情况下可以同时插入多个对象。
get方法
//获取值
public V get(Object key) {
Node[] tab; Node e, p; int n, eh; K ek;
int h = spread(key.hashCode());//hash值
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;
//遍历链表，获取Key对应的value
while ((e = e.next) != null) {
if (e.hash == h &&
((ek = e.key) == key || (ek != null && key.equals(ek))))
return e.val;
}
}
return null;
} get方法操作的逻辑相对简单
- 计算hash值
- 判断tabl是否为null，为空直接返回null
- 判断该hash所在数组Node对象的第一个节点是否是该对象，如果是返回，不是则遍历链表查找对象。
扩容操作
private final void addCount(long x, int check) {
CounterCell[] as; long b, s;
//更新baseCount
if ((as = counterCells) != null ||
!U.compareAndSwapLong(this, BASECOUNT, b = baseCount, s = b + x)) {
CounterCell a; long v; int m;
boolean uncontended = true;
if (as == null || (m = as.length - 1) < 0 ||
(a = as[ThreadLocalRandom.getProbe() & m]) == null ||
!(uncontended =
U.compareAndSwapLong(a, CELLVALUE, v = a.value, v + x))) {
fullAddCount(x, uncontended);
return;
}
if (check <= 1)
return;
s = sumCount();
}
//check >= 0 ,进行扩容操作
if (check >= 0) {
Node[] tab, nt; int n, sc;
while (s >= (long)(sc = sizeCtl) && (tab = table) != null &&
(n = tab.length) < MAXIMUM_CAPACITY) {
int rs = resizeStamp(n);//sizeCtl值 < 0 ,表示正在进行扩容，多线程情况下进行扩容
if (sc < 0) {
if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 ||
sc == rs + MAX_RESIZERS || (nt = nextTable) == null ||
transferIndex <= 0)
break;
if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1))
transfer(tab, nt);
}
//sizeCtl值 > 0 ，只有一个线程进行扩容操作，
else if (U.compareAndSwapInt(this, SIZECTL, sc,
(rs << RESIZE_STAMP_SHIFT) + 2))
transfer(tab, null);
s = sumCount();//计算总数
}
}
}
private final void transfer(Node[] tab, Node[] nextTab) {
int n = tab.length, stride;
//CUP个数， < MIN_TRANSFER_STRIDE则赋值MIN_TRANSFER_STRIDE （16）
if ((stride = (NCPU > 1) ? (n >>> 3) / NCPU : n) < MIN_TRANSFER_STRIDE)
stride = MIN_TRANSFER_STRIDE; // subdivide range
//扩容数组为null，进行扩容操作
if (nextTab == null) { // initiating
try {
@SuppressWarnings("unchecked")
Node[] nt = (Node[])new Node[n << 1];//扩容2倍
nextTab = nt;
} catch (Throwable ex) { // try to cope with OOME
sizeCtl = Integer.MAX_VALUE;
return;
}
nextTable = nextTab;
transferIndex = n;
}
int nextn = nextTab.length;
// 连接点指针，用于标志位（fwd的hash值为-1，fwd.nextTable=nextTab）
ForwardingNode fwd = new ForwardingNode(nextTab);
boolean advance = true;//advace为true时，该节点已处理
boolean finishing = false; // to ensure sweep before committing nextTab
for (int i = 0, bound = 0;;) {
Node f; int fh;
// 控制 --i ,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;
}
//CAS计算得到的transferIndex
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) {
//已完成，nextTable置null，table为nextTab
nextTable = null;
table = nextTab;
sizeCtl = (n << 1) - (n >>> 1);//扩容阈值增大为原来1.5倍
return;//跳出循环
}
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
}
}
// 遍历的节点为null，则放入到ForwardingNode 指针节点
else if ((f = tabAt(tab, i)) == null)
advance = casTabAt(tab, i, null, fwd);
else if ((fh = f.hash) == MOVED)//已经处理过的节点。
advance = true; // already processed
else {
//节点加锁
synchronized (f) {
if (tabAt(tab, i) == f) {
Node ln, hn;
if (fh >= 0) {
// 构造两个链表 一个是原链表 另一个是原链表的反序排列
int runBit = fh & n;
Node lastRun = f;
for (Node 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 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(ph, pk, pv, ln);
else
hn = new Node(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 t = (TreeBin)f;
TreeNode lo = null, loTail = null;
TreeNode hi = null, hiTail = null;
int lc = 0, hc = 0;
for (Node e = t.first; e != null; e = e.next) {
int h = e.hash;
TreeNode p = new TreeNode
(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(lo) : t;
hn = (hc <= UNTREEIFY_THRESHOLD) ? untreeify(hi) :
(lc != 0) ? new TreeBin(hi) : t;
setTabAt(nextTab, i, ln);
setTabAt(nextTab, i + n, hn);
setTabAt(tab, i, fwd);
advance = true;
}
}
}
}
}
} 扩容操作比较复杂，整体流程如下：
上面的源码有点儿长，稍微复杂了一些，在这里我们抛弃它多线程环境，我们从单线程角度来看：
- 为每个内核分任务，并保证其不小于16
- 检查nextTable是否为null，如果是，则初始化nextTable，使其容量为table的两倍
- 死循环遍历节点，知道finished：节点从table复制到nextTable中，支持并发，请思路如下：
- 如果节点 f 为null，则插入ForwardingNode（采用Unsafe.compareAndSwapObjectf方法实现），这个是触发并发扩容的关键
- 如果f为链表的头节点（fh >= 0）,则先构造一个反序链表，然后把他们分别放在nextTable的i和i + n位置，并将ForwardingNode 插入原节点位置，代表已经处理过了
- 如果f为TreeBin节点，同样也是构造一个反序 ，同时需要判断是否需要进行unTreeify()操作，并把处理的结果分别插入到nextTable的i 和i+nw位置，并插入ForwardingNode 节点
- 所有节点复制完成后，则将table指向nextTable，同时更新sizeCtl = nextTable的0.75倍，完成扩容过程
在多线程环境下，ConcurrentHashMap用两点来保证正确性：ForwardingNode和synchronized。当一个线程遍历到的节点如果是ForwardingNode，则继续往后遍历，如果不是，则将该节点加锁，防止其他线程进入，完成后设置ForwardingNode节点，以便要其他线程可以看到该节点已经处理过了，如此交叉进行，高效而又安全。
此段抄自【死磕 Java 并发】—– J.U.C 之 Java并发容器：ConcurrentHashMap
helpTransfer协助扩容方法
final Node[] helpTransfer(Node[] tab, Node f) {
Node[] nextTab; int sc;
if (tab != null && (f instanceof ForwardingNode) &&
(nextTab = ((ForwardingNode)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;
} helpTransfer()方法为协助扩容方法，当调用该方法的时候，nextTable一定已经创建了，所以该方法主要则是进行复制工作。