ConcurrentHashMap源码分析
1.什么是ConcurrentHashMap?
ConcurrentHashMap是一个线程安全的Map类。
1.2ConcurrentHashMap是如何实现线程安全的?
ConcurrentHashMap通过cas、volatile、以及分段synchronized等逻辑实现线程安全操作。
2.ConcurrentHashMap#put源码分析
//put方法调用的putVal方法
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) {
//判空,若key或value有一个为null则报空指针异常
if (key == null || value == null) throw new NullPointerException();
//根据key的方法获取hash值 spread方法见下分析
int hash = spread(key.hashCode());
int binCount = 0;
for (Node<K,V>[] tab = table;;) {
Node<K,V> f; int n, i, fh;
//如果第一次进入tab为null时,则初始化tab
if (tab == null || (n = tab.length) == 0)
//详细分析见下
tab = initTable();
//如果非第一次进入,此处通过tabAt方法获取hash值对应的下标(见tabAt详解)
else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) {
//若当前元素为null,则构造一个Node节点通过casTabAt进行设置操作
if (casTabAt(tab, i, null,
new Node<K,V>(hash, key, value, null)))
break; // no lock when adding to empty bin
}
//如果hash为MOVED标识表示当前的节点处于移动状态,则此时会帮助扩容操作
else if ((fh = f.hash) == MOVED)
//详细分析见下
tab = helpTransfer(tab, f);
else {
V oldVal = null;
//锁定当前Node数组元素
synchronized (f) {
if (tabAt(tab, i) == f) {
if (fh >= 0) {
binCount = 1;
for (Node<K,V> e = f;; ++binCount) {
K ek;
//当前节点若与设置的节点key相同
if (e.hash == hash &&
((ek = e.key) == key ||
(ek != null && key.equals(ek)))) {
//将当前节点的val值赋值给oldVal
oldVal = e.val;
if (!onlyIfAbsent)
//将新的值赋给e.val
e.val = value;
break;
}
Node<K,V> pred = e;
//如果需要put的值与当前元素hash值相等,但是key不相同时,找到当前元素最后一个节点,
//并将next节点指向需要put的节点
if ((e = e.next) == null) {
pred.next = new Node<K,V>(hash, key,
value, null);
break;
}
}
}
//如果当前节点为红黑树,则构造节点加入红黑树中
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) {
//如果节点大于TREEIFY_THRESHOLD(8) 则构造红黑树
if (binCount >= TREEIFY_THRESHOLD)
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
//计数 分析见下
addCount(1L, binCount);
return null;
}
put方法的大致流程如注释所示,上面的代码细节分析如下:
2.1 spread方法分析
static final int spread(int h) {
return (h ^ (h >>> 16)) & HASH_BITS;
}
假设此处的key为"test",即h为"test"的hascode=3556498。
二进制位:
0000 0000 0011 0110 0100 0100 1001 0010
h(3556498)>>>16(将高16位移动到低16位,并将高16位补零):
0000 0000 0000 0000 0000 0000 0011 0110
(h ^ (h >>> 16))(原hascode高16位值不变,低16位与高16位左异或运算(对后续hash槽分配更均匀)):
0000 0000 0011 0110 0100 0100 1001 0010
^ 0000 0000 0000 0000 0000 0000 0011 0110
______________________________________________
0000 0000 0011 0110 0100 0100 1010 0100
(h ^ (h >>> 16)) & HASH_BITS(0x7fffffff) = 3556516(保证为正数,负数为红黑树节点):
0000 0000 0011 0110 0100 0100 1010 0100
& 0111 1111 1111 1111 1111 1111 1111 1111
————————————————————————————————————————————————
0000 0000 0011 0110 0100 0100 1010 0100
2.2 initTable()方法分析
private final Node<K,V>[] initTable() {
Node<K,V>[] tab; int sc;
while ((tab = table) == null || tab.length == 0) {
//sizeCtl默认为0 当sizeCtl为1时表示有线程正在初始化操作(见下方代码),当有线程初始化时则主动让出cpu执行权
if ((sc = sizeCtl) < 0)
Thread.yield(); // lost initialization race; just spin
//cas操作改变sizeCtl为-1,表示占位,有线程正在执行init操作
else if (U.compareAndSwapInt(this, SIZECTL, sc, -1)) {
try {
if ((tab = table) == null || tab.length == 0) {
//DEFAULT_CAPACITY = 16
int n = (sc > 0) ? sc : DEFAULT_CAPACITY;
@SuppressWarnings("unchecked")
Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n];
table = tab = nt;
//16-16/4 = 12 == n*0.7 进行百分之75的计算为扩容阈值
sc = n - (n >>> 2);
}
} finally {
//执行完后将sizeCtl赋值为扩容阈值
sizeCtl = sc;
}
break;
}
}
return tab;
}
2.3 tabAt()方法
@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);
}
为什么需要用getObjectVolatile?
1.volatile无法保证数组元素的可见性
2.假设当有对元素进行写操作时(之前为null),若无getObjectVolatile则可能导致此时获取的元素数据为null。本身应该进行挂链表操作的,此时则会对数组元素进行赋值操作(不使用casTabAt的前提)
3.使用getObjectVolatile可确保写操作happens-before读操作,即可避免上面的问题
2.4 casTabAt()
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);
}
cas操作设置元素
2.5 addCount()
2.5.1 addCount方法思想
思考:
一、如何保证ConcurrentHashMap的size增加为线程安全的?
1.使用锁?
使用锁当然是ok的,但是因为在多线程的情况下,每put一个元素(key不重的情况下)都需要做一次size++操作,如果此时的并发请求量大,对于性能来说无非是噩梦般的存在。
2.使用cas?
同理,性能堪忧。当一个线程在cas操作时,其他的线程只能一直去循环。
二、那么jdk究竟是如何优化size的呢?
1. 当不存在并发增加size时,使用cas对baseCount进行++操作。
2. 若cas操作失败,则会创建或者扩容counterCells数组
3. 通过一个随机算法,分配一个counterCells元素,通过cas操作对元素的value值进行+1操作。
4.获取size = baseCount+各个counterCells元素的value值
* 这里引入的counterCells,有点像分片的概念,多个线程并发进行++操作时,则将多个请求分流到不同的元素中进行cas++操作。
2.5.2 addCount()源码分析
private final void addCount(long x, int check) {
CounterCell[] as; long b, s;
//如果counterCells不为null,或者尝试去对baseCount进行++操作失败
if ((as = counterCells) != null ||
!U.compareAndSwapLong(this, BASECOUNT, b = baseCount, s = b + x)) {
CounterCell a; long v; int m;
boolean uncontended = true;
//如果counterCells为null 或者as.length小于1或者counterCells[随机数取模]==null
//或者cas设置counterCells[随机数取模]失败进入下面的方法
if (as == null || (m = as.length - 1) < 0 ||
(a = as[ThreadLocalRandom.getProbe() & m]) == null ||
!(uncontended =
U.compareAndSwapLong(a, CELLVALUE, v = a.value, v + x))) {
//下面分析
fullAddCount(x, uncontended);
return;
}
if (check <= 1)
return;
s = sumCount();
}
if (check >= 0) {
Node<K,V>[] tab, nt; int n, sc;
while (s >= (long)(sc = sizeCtl) && (tab = table) != null &&
(n = tab.length) < MAXIMUM_CAPACITY) {
int rs = resizeStamp(n);
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);
}
else if (U.compareAndSwapInt(this, SIZECTL, sc,
(rs << RESIZE_STAMP_SHIFT) + 2))
transfer(tab, null);
s = sumCount();
}
}
}
2.5.3 fullAddCount()
//先看最下面的init方法
private final void fullAddCount(long x, boolean wasUncontended) {
int h;
//取模调优
if ((h = ThreadLocalRandom.getProbe()) == 0) {
ThreadLocalRandom.localInit(); // force initialization
h = ThreadLocalRandom.getProbe();
wasUncontended = true;
}
boolean collide = false; // True if last slot nonempty
for (;;) {
CounterCell[] as; CounterCell a; int n; long v;
if ((as = counterCells) != null && (n = as.length) > 0) {
//如果获取的随机元素为null时
if ((a = as[(n - 1) & h]) == null) {
//CounterCell没有被其他线程占用时
if (cellsBusy == 0) { // Try to attach new Cell
CounterCell r = new CounterCell(x); // Optimistic create
if (cellsBusy == 0 &&
U.compareAndSwapInt(this, CELLSBUSY, 0, 1)) {
boolean created = false;
try { // Recheck under lock
CounterCell[] rs; int m, j;
if ((rs = counterCells) != null &&
(m = rs.length) > 0 &&
rs[j = (m - 1) & h] == null) {
//将元素赋值给随机分配的元素
rs[j] = r;
created = true;
}
} finally {
cellsBusy = 0;
}
if (created)
break;
continue; // Slot is now non-empty
}
}
collide = false;
}
//当cas操作失败时,会有一次重试的机会
else if (!wasUncontended) // CAS already known to fail
wasUncontended = true; // Continue after rehash
//进行cas操作设置数组元素++
else if (U.compareAndSwapLong(a, CELLVALUE, v = a.value, v + x))
break;
//若其他线程对counterCells 进行了扩容操作,则退出当前的if else操作,重新开始判断
else if (counterCells != as || n >= NCPU)
collide = false; // At max size or stale
else if (!collide)
collide = true;
//若counterCells中的元素都以初始化,并且多次cas操作失败,则进行扩容操作
else if (cellsBusy == 0 &&
U.compareAndSwapInt(this, CELLSBUSY, 0, 1)) {
try {
if (counterCells == as) {// Expand table unless stale
CounterCell[] rs = new CounterCell[n << 1];
for (int i = 0; i < n; ++i)
rs[i] = as[i];
counterCells = rs;
}
} finally {
cellsBusy = 0;
}
collide = false;
continue; // Retry with expanded table
}
h = ThreadLocalRandom.advanceProbe(h);
}
//1、init方法,将cellbusy设置为1 1标识为占位
else if (cellsBusy == 0 && counterCells == as &&
U.compareAndSwapInt(this, CELLSBUSY, 0, 1)) {
boolean init = false;
try { // Initialize table
if (counterCells == as) {
//出事话一个长度为2的CounterCell数组
CounterCell[] rs = new CounterCell[2];
//随机一个数组元素,实例化并且将元素的value值设置为1
rs[h & 1] = new CounterCell(x);
//counterCell赋值
counterCells = rs;
init = true;
}
} finally {
cellsBusy = 0;
}
if (init)
break;
}
else if (U.compareAndSwapLong(this, BASECOUNT, v = baseCount, v + x))
break; // Fall back on using base
}
}
2.5.4 addCount下半段代码分析
if (check >= 0) {
Node<K,V>[] tab, nt; int n, sc;
while (s >= (long)(sc = sizeCtl) && (tab = table) != null &&
(n = tab.length) < MAXIMUM_CAPACITY) {
//获取一个resize时间戳,这里就不详细分析了
//高16位表示当前扩容的容度戳,后16位为线程数 为负数
int rs = resizeStamp(n);
//当sc<0时说明正在有线程进行扩容操作
if (sc < 0) {
if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 ||
sc == rs + MAX_RESIZERS || (nt = nextTable) == null ||
transferIndex <= 0)
break;
//进行cas操作 将后16位的线程数+1
if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1))
transfer(tab, nt);
}
//设置sizeCtl+2表示有一个线程正在参与扩容 -1为占位符,所以从-2开始
else if (U.compareAndSwapInt(this, SIZECTL, sc,
(rs << RESIZE_STAMP_SHIFT) + 2))
transfer(tab, null);
s = sumCount();
}
}
2.5.4 transfer()
private final void transfer(Node<K,V>[] tab, Node<K,V>[] nextTab) {
int n = tab.length, stride;
//计算每个cpu进行扩容的分配数,计算公式如下
if ((stride = (NCPU > 1) ? (n >>> 3) / NCPU : n) < MIN_TRANSFER_STRIDE)
stride = MIN_TRANSFER_STRIDE; // subdivide range
//当扩容tab为null时
if (nextTab == null) { // initiating
try {
@SuppressWarnings("unchecked")
//创建一个两倍的的数组
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;
transferIndex = n;
}
int nextn = nextTab.length;
//占位节点对应前面的helpTransfer
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;
//计算当前线程负责的下标区域
while (advance) {
int nextIndex, nextBound;
if (--i >= bound || finishing)
advance = false;
else if ((nextIndex = transferIndex) <= 0) {
i = -1;
advance = false;
}
//假设此时为32-》64 则第一个线程进入时分配的坐标没16-31 第二个进入时分配的下标为0-15
else if (U.compareAndSwapInt
(this, TRANSFERINDEX, nextIndex,
nextBound = (nextIndex > stride ?
nextIndex - stride : 0))) {
bound = nextBound;
i = nextIndex - 1;
advance = false;
}
}
//完成扩容操作
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
}
}
//如果当前hash桶为null则将cas占位节点
else if ((f = tabAt(tab, i)) == null)
advance = casTabAt(tab, i, null, fwd);
else if ((fh = f.hash) == MOVED)
advance = true; // already processed
else {
//将当前的hash桶锁住(所谓的分段锁)
synchronized (f) {
if (tabAt(tab, i) == f) {
Node<K,V> ln, hn;
if (fh >= 0) {
//runBit==0不能迁移 反之进行迁移操作,下面一系列操作如下所示
//简单的说0001 0000 (这是16) 如果hash值&16等于0表示不能迁移
//比如之前的后五位是00011(下标位3)&(10000)16 是不能迁移的(0&1==0) 为什么?
//00011&11111(31) 结果还是3
//10011&10000(16) 是可以迁移的(1&1==1)
//10011&11111(31) 结果是3(0011)+16(10000) = 19
int runBit = fh & n;
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);
}
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;
}
}
}
}
}
}