Jdk1.8的优化(相比1.7)
-
数组+链表改成了数组 + 链表/红黑树
-
链表插入由头插法改为尾插法
-
扩容时1.7对原数组中的元素重新hash定位,1.8是位置不变或者是索引+旧容量大小
-
插入与扩容的顺序。1.8是先插入再扩容。
线程安全的做法
hashmap有数据覆盖的问题。不是线程安全。
例子:putval 比如线程A符合判断条件if ((p = tab[i = (n - 1) & hash]) == null)
,
获取table数组的索引下标 index 和链表的头结点,进入条件判断后正好挂起;而线程B也符合条件判断语句,并且获取的table数组的索引下标也是index和链表的头结点,B的数据会写入table[index]。
之后A线程恢复,持有过期的链表的头结点,A的数据会写入table[index]中,覆盖B的数据。
这是A恢复现场,赋值操作。还有重复扩容。
putval的步骤:
一、若数组为空,则通过resize()扩容 二、计算数组索引,若为空则直接插入 三、 否则说明索引对应的位置已有元素,分类讨论
- 若数组索引对应的键相同,则直接覆盖
- 若数组索引对应的节点是红黑树节点,则插入红黑树
- 否则是链表
- 从头结点遍历链表,若链表中有键值相同的节点,则覆盖
- 若到达链表末尾,则直接插入
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//第一步:判断table是否为空,则调用resize()函数创建一个
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//第二步:计算元素的储存位置index,如果为空则直接插入
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//若不为空,说明要添加的位置上已经有元素,需要分类讨论
else {
Node<K,V> e; K k;
//第一种情况:key值相同,直接覆盖
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
//第二种情况:判断是否是红黑树
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//第三种情况:链表
for (int binCount = 0; ; ++binCount) {
// 如果是链表末尾,新增节点
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
// 如果链表中存在key,则覆盖
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;
//若链表长度>=7,转红黑树
if (!onlyIfAbsent || oldValue == null)
e.value = value;//放入值
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
复制代码
HashTable
直接在操作方法上加上synchronized,锁住整个数组,粗粒度。
public class Hashtable<K,V>
extends Dictionary<K,V>
implements Map<K,V>, Cloneable, java.io.Serializable {
......................................
public Hashtable(Map<? extends K, ? extends V> t) {
this(Math.max(2*t.size(), 11), 0.75f);
putAll(t);
}
public synchronized int size() {
return count;
}
public synchronized boolean isEmpty() {
return count == 0;
}
public synchronized Enumeration<K> keys() {
return this.<K>getEnumeration(KEYS);
}
public synchronized Enumeration<V> elements() {
return this.<V>getEnumeration(VALUES);
}
public synchronized boolean contains(Object value) {
if (value == null) {
throw new NullPointerException();
}
Entry<?,?> tab[] = table;
for (int i = tab.length ; i-- > 0 ;) {
for (Entry<?,?> e = tab[i] ; e != null ; e = e.next) {
if (e.value.equals(value)) {
return true;
}
}
}
return false;
}
}
.......................................
}
复制代码
Collections.synchronizedMap
内部定义一个对象锁mutex
public static <K,V> Map<K,V> synchronizedMap(Map<K,V> m) {
return new SynchronizedMap<>(m);
}
/**
* @serial include
*/
private static class SynchronizedMap<K,V>
implements Map<K,V>, Serializable {
private static final long serialVersionUID = 1978198479659022715L;
private final Map<K,V> m; // Backing Map
final Object mutex; // Object on which to synchronize
SynchronizedMap(Map<K,V> m) {
this.m = Objects.requireNonNull(m);
mutex = this;
}
SynchronizedMap(Map<K,V> m, Object mutex) {
this.m = m;
this.mutex = mutex;
}
public int size() {
synchronized (mutex) {return m.size();}
}
public boolean isEmpty() {
synchronized (mutex) {return m.isEmpty();}
}
public boolean containsKey(Object key) {
synchronized (mutex) {return m.containsKey(key);}
}
public boolean containsValue(Object value) {
synchronized (mutex) {return m.containsValue(value);}
}
public V get(Object key) {
synchronized (mutex) {return m.get(key);}
}
public V put(K key, V value) {
synchronized (mutex) {return m.put(key, value);}
}
public V remove(Object key) {
synchronized (mutex) {return m.remove(key);}
}
public void putAll(Map<? extends K, ? extends V> map) {
synchronized (mutex) {m.putAll(map);}
}
public void clear() {
synchronized (mutex) {m.clear();}
}
private transient Set<K> keySet;
private transient Set<Map.Entry<K,V>> entrySet;
private transient Collection<V> values;
public Set<K> keySet() {
synchronized (mutex) {
if (keySet==null)
keySet = new SynchronizedSet<>(m.keySet(), mutex);
return keySet;
}
}
public Set<Map.Entry<K,V>> entrySet() {
synchronized (mutex) {
if (entrySet==null)
entrySet = new SynchronizedSet<>(m.entrySet(), mutex);
return entrySet;
}
}
public Collection<V> values() {
synchronized (mutex) {
if (values==null)
values = new SynchronizedCollection<>(m.values(), mutex);
return values;
}
}
public boolean equals(Object o) {
if (this == o)
return true;
synchronized (mutex) {return m.equals(o);}
}
public int hashCode() {
synchronized (mutex) {return m.hashCode();}
}
public String toString() {
synchronized (mutex) {return m.toString();}
}
// Override default methods in Map
@Override
public V getOrDefault(Object k, V defaultValue) {
synchronized (mutex) {return m.getOrDefault(k, defaultValue);}
}
@Override
public void forEach(BiConsumer<? super K, ? super V> action) {
synchronized (mutex) {m.forEach(action);}
}
@Override
public void replaceAll(BiFunction<? super K, ? super V, ? extends V> function) {
synchronized (mutex) {m.replaceAll(function);}
}
@Override
public V putIfAbsent(K key, V value) {
synchronized (mutex) {return m.putIfAbsent(key, value);}
}
@Override
public boolean remove(Object key, Object value) {
synchronized (mutex) {return m.remove(key, value);}
}
@Override
public boolean replace(K key, V oldValue, V newValue) {
synchronized (mutex) {return m.replace(key, oldValue, newValue);}
}
@Override
public V replace(K key, V value) {
synchronized (mutex) {return m.replace(key, value);}
}
...........................
}
复制代码
ConcurrentHashMap
使用分段锁,降低锁的粒度。
ConcurrentHashMap成员变量使用volatile 修饰。
使用CAS操作和synchronized结合实现赋值操作,多线程操作只会锁住当前操作索引的节点。
public class ConcurrentHashMap<K,V> extends AbstractMap<K,V>
implements ConcurrentMap<K,V>, Serializable {
.............................................
transient volatile Node<K,V>[] table;
/**
* The next table to use; non-null only while resizing.
*/
private transient volatile Node<K,V>[] 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;
...................................................
}
复制代码
HashMap
初始化
JDK1.8版本的,内部使用数组 + 链表/红黑树。 如果自己传入初始大小k,初始化大小为大于k的2的整数次方,例如如果传10,大小为16。默认初始值是16,最大容量是2^31次方。
/**
* The default initial capacity - MUST be a power of two.
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* The maximum capacity, used if a higher value is implicitly specified
* by either of the constructors with arguments.
* MUST be a power of two <= 1<<30.
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
复制代码
哈希函数
先拿到key的hashcode,然后让hashcode的前16位与后16位进行异或
-
尽可能降低hash碰撞,越分散越好
-
尽可能高效,这是高频操作,所以采用位运算
不直接使用hashcode的原因是hashcode函数的返回类型是int型散列值。初始化数组只有16,容易出现哈希冲突
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
复制代码
Node
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
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) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
复制代码
get函数
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
/**
* Implements Map.get and related methods
*
* @param hash hash for key
* @param key the key
* @return the node, or null if none
*/
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
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) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
复制代码
数据插入原理
判断数组是否为空,为空进行初始化;
不为空,计算 k 的 hash 值,通过(n - 1) & hash计算应当存放在数组中的下标 index; 查看 table[index] 是否存在数据,没有数据就构造一个Node节点存放在 table[index] 中; 存在数据,说明发生了hash冲突(存在二个节点key的hash值一样), 继续判断key是否相等,相等,用新的value替换原数据(onlyIfAbsent为false);
如果不相等,判断当前节点类型是不是树型节点,如果是树型节点,创造树型节点插入红黑树中;
如果不是树型节点,创建普通Node加入链表中;判断链表长度是否大于 8, 大于的话链表转换为红黑树;
插入完成之后判断当前节点数是否大于阈值,如果大于开始扩容为原数组的二倍。
LinkedHashMap
LinkedHashMap内部维护了一个单链表,有头尾节点。
LinkedHashMap节点Entry内部除了继承HashMap的Node属性,before 和 after用于标识前置节点和后置节点。
实现按插入的顺序或访问顺序排序。
public class LinkedHashMap<K,V>
extends HashMap<K,V>
implements Map<K,V>
{
/**
* HashMap.Node subclass for normal LinkedHashMap entries.
*/
static class Entry<K,V> extends HashMap.Node<K,V> {
Entry<K,V> before, after;
Entry(int hash, K key, V value, Node<K,V> next) {
super(hash, key, value, next);
}
}
.....................................................
}
复制代码
TreeMap
默认是自然排序。 key所属的类实现Comparable接口进行比较。
public class TreeMap<K,V>
extends AbstractMap<K,V>
implements NavigableMap<K,V>, Cloneable, java.io.Serializable
{
/**
* The comparator used to maintain order in this tree map, or
* null if it uses the natural ordering of its keys.
*
* @serial
*/
private final Comparator<? super K> comparator;
...........................................
public TreeMap(Comparator<? super K> comparator) {
this.comparator = comparator;
}
}
复制代码
总结
HashMap是一个有趣的数据类型,设计的知识很多。本文只选取了几个重要的点进行分析,包括存储结构里的数据红黑树,哈希函数中的冲突避免和线程安全问题。另外HashMap在面试中出现的次数也非常多,几乎是后端开发岗的必问题目,值得结合源码深入研究。
作者:AlexanderChen
链接:https://juejin.im/post/5efac964e51d4534883803a2
来源:掘金
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。