hashmap
在JDK1.6中,HashMap采用Node数组+链表实现,即使用链表处理冲突,同一hash值的链表都存储在一个链表里。但是当位于一个桶中的元素较多,即hash值相等的元素较多时,通过key值依次查找的效率较低。而JDK1.8中,HashMap采用Node数组+链表+红黑树实现,当链表长度超过阈值(8)时,将链表转换为红黑树,这样大大减少了查找时间。
hashMap的实现
put方法的实现
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
hash函数
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
//其中的hashCode()是一个native方法
红黑树
static final class TreeNode<K,V> extends LinkedHashMap.Entry<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) {
super(hash, key, val, next);
}
/**
* Returns root of tree containing this node.
*/
final TreeNode<K,V> root() {
for (TreeNode<K,V> r = this, p;;) {
if ((p = r.parent) == null)
return r;
r = p;
}
}
Node存储对象,该类实现了Map.Entry接口
其实就是一个链表
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;
Node(int hash, K key, V value, Node<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
public final K getKey() { return key; }
public final V getValue() { return value; }
public final String toString() { return key + "=" + value; }
public final int hashCode() {
return Objects.hashCode(key) ^ Objects.hashCode(value);
}
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
public final boolean equals(Object o) {
if (o == this)
return true;
if (o instanceof Map.Entry) {
Map.Entry<?,?> e = (Map.Entry<?,?>)o;
if (Objects.equals(key, e.getKey()) &&
Objects.equals(value, e.getValue()))
return true;
}
return false;
}
}
存储过程
首先,当添加一个元素(key-value)时,就首先计算元素key的hash值,以此确定插入数组中的位置,但是可能存在同一hash值的元素已经被放在数组同一位置了,这时就添加到同一hash值的元素的后面,他们在数组的同一位置,但是形成了链表
而当链表长度太长时,链表就转换为红黑树,这样大大提高了查找的效率。
putVal的方法的实现
transient Node<K,V>[] table;//存储的数组
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//1. 判断键值对数组tab[]是否为空或为null,否则resize();
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//2. 根据键值key计算hash值得到插入的数组索引i,如果tab[i]==null,直接新建节点添加(n - 1) &
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//3. 判断当前数组中处理hash冲突的方式为链表还是红黑树(check第一个节点类型即可),分别处理
else {
Node<K,V> e; K k;
//第一节节点hash值同,且key值与插入key相同
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)//属于红黑树处理冲突
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//链表处理冲突
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
putVal的步骤:
- 判断键值对数组tab[]是否为空或为null,否则resize();
- 根据键值key计算hash值得到插入的数组索引i,如果tab[i]==null,直接新建节点添加
- 判断当前数组中处理hash冲突的方式为链表还是红黑树(check第一个节点类型即可),分别处理
获取过程
注意HashMap中key和value都容许为null
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
//hash & (length-1)得到对象的地址
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
//如果第一个节点是TreeNode,说明采用的是数组+红黑树结构处理冲突,遍历红黑树,得到节点值
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
//链表结构处理
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
concurrentHashMap
数据结构
核心存储结构是segment
static class Segment<K,V> extends ReentrantLock implements Serializable {
private static final long serialVersionUID = 2249069246763182397L;
final float loadFactor;
Segment(float lf) { this.loadFactor = lf; }
}
为什么在高并发的情况下高效?
一个ConcurrentHashMap由多个segment组成,每一个segment都包含了一个HashEntry数组的 hashtable, 每一个segment包含了对自己的hashtable的操作,比如get,put,replace等操作,这些操作发生的时候,对自己的 hashtable进行锁定。由于每一个segment写操作只锁定自己的hashtable,所以可能存在多个线程同时写的情况,性能无疑好于只有一个 hashtable锁定的情况。
在ConcurrentHashMap的remove,put操作还是比较简单的,都是将remove或者put操作交给key所对应的segment去做的,所以当几个操作不在同一个segment的时候就可以并发的进行。
remove
public V remove(Object key) {
return replaceNode(key, null, null);
}
//注意,这里不是加锁,是同步实现的
**synchronized (f)**
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;
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;
synchronized (f) {
if (tabAt(tab, i) == f) {
if (fh >= 0) {
validated = true;
for (Node<K,V> e = f, pred = null;;) {
K ek;
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
setTabAt(tab, i, e.next);
}
break;
}
pred = e;
if ((e = e.next) == null)
break;
}
}
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;
}
put
这里也是同步
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());
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
}
else if ((fh = f.hash) == MOVED)
tab = helpTransfer(tab, f);
else {
V oldVal = null;
synchronized (f) {
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;
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;
binCount = 2;
if ((p = ((TreeBin<K,V>)f).putTreeVal(hash, key,
value)) != null) {
oldVal = p.val;
if (!onlyIfAbsent)
p.val = value;
}
}
}
}
if (binCount != 0) {
if (binCount >= TREEIFY_THRESHOLD)
treeifyBin(tab, i);
if (oldVal != null)
return oldVal;
break;
}
}
}
addCount(1L, binCount);
return null;
}
get
不加锁,也没有同步
public V get(Object key) {
Node<K,V>[] tab; Node<K,V> e, p; int n, eh; K ek;
int h = spread(key.hashCode());
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;
while ((e = e.next) != null) {
if (e.hash == h &&
((ek = e.key) == key || (ek != null && key.equals(ek))))
return e.val;
}
}
return null;
}