目录
Day1、为什么JDK1.8中HashMap从头插入改成尾插入
Day1、为什么JDK1.8中HashMap从头插入改成尾插入
头插入和尾插入是什么意思，首先我们知道，HashMap的实现原理是数组+单链表的形式，当出现hash冲突的时候，元素会以链表的形式存储，JDK1.7中元素插入链表是从头部插入，JDK1.8中是从尾部插入。
看看JDK1.8中HashMap的源码，从头捋一遍。
存储方式
//以数组的形式存储Hash值，当存在hash冲突时使用单链表存储
transient Node<K,V>[] table;
/**
* Basic hash bin node, used for most entries. (See below for
* TreeNode subclass, and in LinkedHashMap for its Entry subclass.)
*/
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;
}
}HashMap默认采用数组+单链表方式存储元素，当元素出现哈希冲突时，会存储到该位置的单链表中。
静态常量
/**
* The default initial capacity - MUST be a power of two.
* 初始容量为16，要求必须为2的幂
*/
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.
* 最大容量为2的30次方
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* The load factor used when none specified in constructor.
* 扩展因子为0.75，当容量超过当前容量0.75时自动扩容
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* The bin count threshold for using a tree rather than list for a
* bin. Bins are converted to trees when adding an element to a
* bin with at least this many nodes. The value must be greater
* than 2 and should be at least 8 to mesh with assumptions in
* tree removal about conversion back to plain bins upon
* shrinkage.
* hash冲突使用单链表存储，当单链表结点数超过8之后，转为红黑树存储
*/
static final int TREEIFY_THRESHOLD = 8;
/**
* The bin count threshold for untreeifying a (split) bin during a
* resize operation. Should be less than TREEIFY_THRESHOLD, and at
* most 6 to mesh with shrinkage detection under removal.
* hash冲突红黑树中的结点数少于6时传华为单链表存储
*/
static final int UNTREEIFY_THRESHOLD = 6;
/**
* The smallest table capacity for which bins may be treeified.
* (Otherwise the table is resized if too many nodes in a bin.)
* Should be at least 4 * TREEIFY_THRESHOLD to avoid conflicts
* between resizing and treeification thresholds.
* hash冲突单链表转化为红黑树的条件除了结点数大于8之外，还要求数组容量大于64
*/
static final int MIN_TREEIFY_CAPACITY = 64;HashMap默认采用数组+单链表方式存储元素，当元素出现哈希冲突时，会存储到该位置的单链表中。与JDK1.7相比，单链表不会一直增加元素，当元素个数超过8个时，会尝试将单链表转化为红黑树存储。但是在转化前，会再判断一次当前数组的长度，只有数组长度大于64才处理。否则，进行扩容操作。
插入元素
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
/**
* 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) == 0)
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
//hash冲突时，采用尾插法
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//判断此时是红黑树还是链表
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
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;
}JDK1.8中首先判断此时是否为树结构，如果是，插入新元素为树中的一个结点，否则遍历链表道末尾，将新元素未插入到链表末尾，然后判断链表长度是否超过转化数的临界值。
与之对比，JDK1.7中的插入元素源码。
public V put(K key, V value) {
if (key == null)
return putForNullKey(value);
int hash = hash(key);
int i = indexFor(hash, table.length);
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
Object k;
//覆盖原有值
if (e.hash == hash && ((k = e.key) == key || key.equals(k))) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
modCount++;
//插入新结点
addEntry(hash, key, value, i);
return null;
}
void addEntry(int hash, K key, V value, int bucketIndex) {
//判断是否需要扩容
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
hash = (null != key) ? hash(key) : 0;
bucketIndex = indexFor(hash, table.length);
}
//插入新的结点
createEntry(hash, key, value, bucketIndex);
}
void createEntry(int hash, K key, V value, int bucketIndex) {
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<>(hash, key, value, e);
size++;
}
/**
* Creates new entry.
*/
Entry(int h, K k, V v, Entry<K,V> n) {
value = v;
//将原链表连接到新元素的后边，即从头部插入
next = n;
key = k;
hash = h;
}扩容
JDK1.8扩容：
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
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 > 0) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
//重点在这，旧表到新表要重新hash
if (oldTab != null) {
for (int j = 0; 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) == 0) {
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;
}JDK1.7扩容：
void resize(int newCapacity) {
Entry[] oldTable = table;
int oldCapacity = oldTable.length;
if (oldCapacity == MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return;
}
Entry[] newTable = new Entry[newCapacity];
boolean oldAltHashing = useAltHashing;
useAltHashing |= sun.misc.VM.isBooted() &&
(newCapacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);
boolean rehash = oldAltHashing ^ useAltHashing;
transfer(newTable, rehash);
table = newTable;
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}
void transfer(Entry[] newTable, boolean rehash) {
int newCapacity = newTable.length;
for (Entry<K,V> e : table) {
while(null != e) {
Entry<K,V> next = e.next;
if (rehash) {
e.hash = null == e.key ? 0 : hash(e.key);
}
int i = indexFor(e.hash, newCapacity);
e.next = newTable[i];//每次rehash的元素都从头部插入
newTable[i] = e;
e = next;//遍历原链表
}
}
}JDK1.7中扩容时，每个元素的rehash之后，都会插入到新数组对应索引的链表头，所以这就导致原链表顺序为A->B->C，扩容之后，rehash之后的链表可能为C->B->A，元素的顺序发生了变化。在并发场景下，扩容时可能会出现循环链表的情况。而JDK1.8从头插入改成尾插入元素的顺序不变，避免出现循环链表的情况。
拓展问题
1.为什么JDK1.8采用红黑树存储Hash冲突的元素？
红黑树本质上是一棵二叉查找树，但它在二叉查找树的基础上增加了着色和相关的性质使得红黑树相对平衡，从而保证了红黑树的查找、插入、删除的时间复杂度最坏为O(log n)。能够加快检索速率。
2.为什么在长度小于8时使用链表，不一直使用红黑树？
桶中元素的插入只会在hash冲突时发生，而hash冲突发生的概率较小，一直维护一个红黑树比链表耗费资源更多，在桶中元素量较小时没有这个必要。
3.为什么要使用红黑树而不使用AVL树？
红黑树与AVLl树，在检索的时候效率差不多，都是通过平衡来二分查找。但红黑树不像avl树一样追求绝对的平衡，红黑树允许局部很少的不完全平衡，这样对于效率影响不大，但省去了很多没有必要的调平衡操作，avl树调平衡有时候代价较大，所以效率不如红黑树。
4.为什么数组容量必须是2次幂？
索引计算公式为i = (n - 1) & hash，如果n为2次幂，那么n-1的低位就全是1，哈希值进行与操作时可以保证低位的值不变，从而保证分布均匀，效果等同于hash%n，但是位运算比取余运算要高效的多。
5.为什么单链表转为红黑树要求桶内的元素个数大于8？
当hashCode离散性很好的时候，树型bin用到的概率非常小，因为数据均匀分布在每个bin中，几乎不会有bin中链表长度会达到阈值。但是在随机hashCode下，离散性可能会变差，然而JDK又不能阻止用户实现这种不好的hash算法，因此就可能导致不均匀的数据分布。不过理想情况下随机hashCode算法下所有bin中节点的分布频率会遵循泊松分布，而一个bin中链表长度达到8个元素的概率为0.00000006，几乎是不可能事件。
同理，少于6就从红黑树转回单链表是为了节省维护一个树的资源消耗，而选择6作为临界值，是因理想情况下一个bin中元素个数达到6的概率是0.00001316，达到7的概率为0.00000094，二者跨度较大，可以减小树和链表之间频繁转化的可能性。