前言
记录一下,方便复习。
map是一个node数组,每一个node可以是tree或者链表。我称node中的每一个元素为slot,其实叫啥都行,槽、桶也可以。
1 插入
插入和resize等行为是有冲突的,所以再resize时,会往slot头部插入为含有MOVED标记的node,这样,put前检查到含MOVED标记就不可以修改了,等待迁移完才可以继续修改,这样当前线程就没事干了,所以可以让当前线程辅助修改。如果正修改时,node被迁移走了,会导致问题,因为之前同slot的node,rehash后可能不在一个slot里面了。
1.1 put
put调用了putVal方法
1.1.1 putVal
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
}
// slot被迁移了,所以只能帮助迁移,提前结束迁移
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
else {
V oldVal = null;
// 加锁,避免resize带来问题
synchronized (f) {
if (tabAt(tab, i) == f) {
// slot中是tree的话,fh会是-2。-1表示MOVED
if (fh >= 0) {
// slot中node数量
binCount = 1;
for (Node<K,V> e = f;; ++binCount) {
K ek;
// key相同就覆盖原值
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;
// 遍历到最后了,就放到后面
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;
// 扩容条件是>0
binCount = 2;
if ((p = ((TreeBin<K,V>)f).putTreeVal(hash, key,
value)) != null) {
oldVal = p.val;
if (!onlyIfAbsent)
p.val = value;
}
}
}
}
if (binCount != 0) {
// slot中节点数超过阈值,就转为树
if (binCount >= TREEIFY_THRESHOLD)
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
// 增加map的size值,并在有需要时扩容。
addCount(1L, binCount);
return null;
}
1.1.2 initTable
1.1.3 addCount
private final void addCount(long x, int check) {
CounterCell[] as; long b, s;
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))) {
// uncontended false表明需要重置Probe
fullAddCount(x, uncontended);
// 我认为可能是fullAddCount比较占时间,所以本次不再考虑扩容
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) {
// 当resize结束时长度n会先更新,此时会导致sc>>>16 != rs
// 所以这里主要都是判断是否resize结束
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);
}
// rs << RESIZE_STAMP_SHIFT是一个低16位都是0负数,+2后,
// 低16位成了0000 0000 0000 0010,负数由于是补码表示,
// 加法和正数加法一样
else if (U.compareAndSwapInt(this, SIZECTL, sc,
(rs << RESIZE_STAMP_SHIFT) + 2))
transfer(tab, null);
s = sumCount();
}
}
}
1.1.4 fullAddCount
private final void fullAddCount(long x, boolean wasUncontended) {
int h;
if ((h = ThreadLocalRandom.getProbe()) == 0) {
ThreadLocalRandom.localInit(); // force initialization
h = ThreadLocalRandom.getProbe();
// 因为cas失败表示当前线程和其他线程slot是同一个,
// 需要刷新Probe,避免cas竞争。此处已刷新,所以设为true
wasUncontended = true;
}
boolean collide = false; // True if last slot nonempty
for (;;) {
CounterCell[] as; CounterCell a; int n; long v;
// counterCells已经初始化
if ((as = counterCells) != null && (n = as.length) > 0) {
// 当前线程对应slot未初始化
if ((a = as[(n - 1) & h]) == null) {
if (cellsBusy == 0) { // Try to attach new Cell
// x即是上次修改数量正数表示添加元素,负数表示删除元素
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) {
rs[j] = r;
created = true;
}
} finally {
cellsBusy = 0;
}
if (created)
// 初始化完成,并在初始化slot时初始化了其中的值,
// 所以直接break
break;
// 其他线程初始化了slot
continue; // Slot is now non-empty
}
}
collide = false;
}
else if (!wasUncontended) // CAS already known to fail
// 直接执行下面的advanceProbe,减少竞争,然后再cas
wasUncontended = true; // Continue after rehash
else if (U.compareAndSwapLong(a, CELLVALUE, v = a.value, v + x))
break;
else if (counterCells != as || n >= NCPU)
// 已经有线程在扩容counterCells了,或者counterCel容量超过cpu数,
// cpu数意味着线程并发数,所以无需扩容(确保同一时间
// 线程经过advanceProbe后,不再互相影响即可)
collide = false; // At max size or stale
else if (!collide)
// 这里和上面一样,也是为了直接执行下面的advanceProbe,
// 减少竞争,然后再cas
collide = true;
// 尝试获取counterCells的修改锁cellsBusy
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);
}
// 尝试获取counterCells修改锁cellsBusy
else if (cellsBusy == 0 && counterCells == as &&
U.compareAndSwapInt(this, CELLSBUSY, 0, 1)) {
boolean init = false;
try { // Initialize table
if (counterCells == as) {
CounterCell[] rs = new CounterCell[2];
// x即是上次修改数量正数表示添加元素,负数表示删除元素
rs[h & 1] = new CounterCell(x);
counterCells = rs;
init = true;
}
} finally {
cellsBusy = 0;
}
if (init)
break;
}
// counterCells初始化失败则尝试修改BASECOUNT
else if (U.compareAndSwapLong(this, BASECOUNT, v = baseCount, v + x))
break; // Fall back on using base
}
}
1.1.5 transfer
private final void transfer(Node<K,V>[] tab, Node<K,V>[] nextTab) {
// 每次迁移的slot数量
int n = tab.length, stride;
// cpu只有一个线程时,自然一次全迁完
if ((stride = (NCPU > 1) ? (n >>> 3) / NCPU : n) < MIN_TRANSFER_STRIDE)
stride = MIN_TRANSFER_STRIDE; // subdivide range
// 将table迁移到扩容的nextTable,迁移完,再让table = nextTable
if (nextTab == null) { // initiating
try {
@SuppressWarnings("unchecked")
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;
// slot被处理标记,slot迁移前,会将slot中数据置换为fwd,
// fwd由于有MOVED标记,在读取或修改时,提醒线程数据已被迁移
ForwardingNode<K,V> fwd = new ForwardingNode<K,V>(nextTab);
boolean advance = true;
boolean finishing = false; // to ensure sweep before committing nextTab
// i是当前需要处理的slot下标,bound是这一批要处理的slot,
// 每批处理不超过stride数量的slot
for (int i = 0, bound = 0;;) {
Node<K,V> f; int fh;
// 计算本次迁移slot范围
// advance true表示i下标slot迁移成功,false则重试
while (advance) {
int nextIndex, nextBound;
// --i得到这次迁移slot下标,>=bound表示本批次迁移没完成,直接跳出循环
// 继续迁移。如果结束,也跳出循环。
if (--i >= bound || finishing)
advance = false;
// 如果没有可迁移的了,跳出循环
else if ((nextIndex = transferIndex) <= 0) {
i = -1;
advance = false;
}
// 尝试cas更新nextIndex,获取新的迁移的批次,如果失败,则重新循环
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;
// transfer结束了
if (finishing) {
nextTable = null;
table = nextTab;
sizeCtl = (n << 1) - (n >>> 1);
return;
}
// 尝试将并发线程数-1
if (U.compareAndSwapInt(this, SIZECTL, sc = sizeCtl, sc - 1)) {
// 只有第一个transfer线程才相等,允许修改进行finish操作,
// 其他线程直接结束
if ((sc - 2) != resizeStamp(n) << RESIZE_STAMP_SHIFT)
return;
finishing = advance = true;
i = n; // recheck before commit
}
}
else if ((f = tabAt(tab, i)) == null)
advance = casTabAt(tab, i, null, fwd);
else if ((fh = f.hash) == MOVED)
advance = true; // already processed
else {
synchronized (f) {
if (tabAt(tab, i) == f) {
Node<K,V> ln, hn;
if (fh >= 0) {
int runBit = fh & n;
Node<K,V> lastRun = f;
// 由于table被扩大两倍,hash值有两种情况,新的最高位是1,
// 则需要移动,slot索引为i+n,或者是0,则slot的索引不变。
// 这里是将最后几个连续的高hash或低hash特意取出来,
// lastRun可以直接放在新slot的最后,提高效率
// 如 low->low->high->high,那么lastRun就是倒数第二个high
// hn被设为lastRun,然后高hash可以直接插入到hn前面,
// 不用一一移动lastRun后面节点
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;
}
}
}
}
}
}