【81期】面试官：说说HashMap 中的容量与扩容实现
来自：cnblogs.com/youzhibing/p/11833040.html
高手过招，招招致命
/**
* 数组
*/
transient Node<K,V>[] table;
/**
* 链表结构
*/
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;
}
}
/**
* 红黑树结构
*/
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;
...
斗智斗勇，见招拆招
问题 1：table 的初始化
/**
* 构造方法 1
*
* 通过 指定的 initialCapacity 和 loadFactor 实例化一个空的 HashMap 对象
*/
public HashMap(int initialCapacity, float loadFactor) {
if (initialCapacity < )
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
if (loadFactor <= || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
this.threshold = tableSizeFor(initialCapacity);
}
/**
* 构造方法 2
*
* 通过指定的 initialCapacity 和 默认的 loadFactor(0.75) 实例化一个空的 HashMap 对象
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
/**
* 构造方法 3
*
* 通过默认的 initialCapacity 和 默认的 loadFactor(0.75) 实例化一个空的 HashMap 对象
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
/**
*
* 构造方法 4
* 通过指定的 Map 对象实例化一个 HashMap 对象
*/
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
Map<String,Object> map = new HashMap();
map.put("name", "张三");
map.put("age", 21);
// 后续操作
...
/**
* Initializes or doubles table size. If null, allocates in
* accord with initial capacity target held in field threshold.
* Otherwise, because we are using power-of-two expansion, the
* elements from each bin must either stay at same index, or move
* with a power of two offset in the new table.
*
* @return the table
*/
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table; // 次 put 的时候，table = null
int oldCap = (oldTab == null) ? : oldTab.length; // oldCap = 0
int oldThr = threshold; // threshold=0, oldThr = 0
int newCap, newThr = ;
if (oldCap > ) { // 条件不满足，往下走
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
else if (oldThr > ) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults 走到这里，进行默认初始化
newCap = DEFAULT_INITIAL_CAPACITY; // DEFAULT_INITIAL_CAPACITY = 1 << 4 = 16, newCap = 16;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY); // newThr = 0.75 * 16 = 12;
}
if (newThr == ) { // 条件不满足
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr; // threshold = 12; 重置阀值为12
@SuppressWarnings({"raw*","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap]; // 初始化 newTab, length = 16;
table = newTab; // table 初始化完成, length = 16;
if (oldTab != null) { // 此时条件不满足，后续扩容的时候，走此if分支 将数组元素复制到新数组
for (int j = ; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
next = e.next;
if ((e.hash & oldCap) == ) {
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else {
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab; // 新数组
}
默认情况下，table.length = 16; 指定了 initialCapacity 的情况放到问题 5 中分析
默认情况下，threshold = 12; 指定了 initialCapacity 的情况放到问题 5 中分析
默认情况下，能存放 12 个元素，当存放第 13 个元素后进行扩容
问题 2 ：table 的扩容
/**
* Implements Map.put and related methods
*
* @param hash hash for key
* @param key the key
* @param value the value to put
* @param onlyIfAbsent if true, don't change existing value
* @param evict if false, the table is in creation mode.
* @return previous value, or null if none
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
if ((tab = table) == null || (n = tab.length) == )
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
for (int binCount = ; ; ++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) // 当size（已存放元素个数） > thrshold（阀值），进行扩容
resize();
afterNodeInsertion(evict);
return null;
}
/**
* Initializes or doubles table size. If null, allocates in
* accord with initial capacity target held in field threshold.
* Otherwise, because we are using power-of-two expansion, the
* elements from each bin must either stay at same index, or move
* with a power of two offset in the new table.
*
* @return the table
*/
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table; // 此时的 table != null，oldTab 指向旧的 table
int oldCap = (oldTab == null) ? : oldTab.length; // oldCap = table.length; 次扩容时是 16
int oldThr = threshold; // threshold=12, oldThr = 12;
int newCap, newThr = ;
if (oldCap > ) { // 条件满足，走此分支
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && // oldCap左移一位; newCap = 16 << 1 = 32;
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold // newThr = 12 << 1 = 24;
}
else if (oldThr > ) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY; // DEFAULT_INITIAL_CAPACITY = 1 << 4 = 16, newCap = 16;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == ) { // 条件不满足
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr; // threshold = newThr = 24; 重置阀值为 24
@SuppressWarnings({"raw*","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap]; // 初始化 newTab, length = 32;
table = newTab; // table 指向 newTab, length = 32;
if (oldTab != null) { // 扩容后，将 oldTab(旧table) 中的元素移到 newTab（新table）中
for (int j = ; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e; //
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
next = e.next;
if ((e.hash & oldCap) == ) {
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else {
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
当 size > threshold 的时候进行扩容
扩容之后的 table.length = 旧 table.length * 2,
扩容之后的 threshold = 旧 threshold * 2
问题 3、4 ：2 的 n 次幂
static final int hash(Object key) {
int h;
return (key == null) ? : (h = key.hashCode()) ^ (h >>> 16); // 这里的处理，有兴趣的可以琢磨下；能够减少碰撞
}
// put
table[h % table.length] = value;
// get
e = table[h % table.length];
1&1=1;
0&1=0;
1&0=0;
0&0=0;
1010&1111=1010; => 10&15=10;
1011&1111=1011; => 11&15=11;
01010&10000=00000; => 10&16=;
01011&10000=00000; => 11&16=;
h%length 效率不如位运算快
h&length 会提高碰撞几率，导致 table 的空间得不到更充分的利用、降低 table 的操作效率
问题 5：指定 initialCapacity
/**
* Returns a power of two size for the given target capacity.
* 返回 >= cap 小的 2^n
* cap = 10, 则返回 2^4 = 16;
* cap = 5, 则返回 2^3 = 8;
*/
static final int tableSizeFor(int cap) {
int n = cap - 1;
n |= n >>> 1;
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
return (n < ) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
问题6：加载因子
如果loadFactor太小，那么map中的table需要不断的扩容，扩容是个耗时的过程
如果loadFactor太大，那么map中table放满了也不不会扩容，导致冲突越来越多，解决冲突而起的链表越来越长，效率越来越低
而 0.75 这是一个折中的值，是一个比较理想的值
总结
相关文章