HashMap源码解析
面试常见问题
1、你看过那些源码吗?
2、那你能讲讲HashMap的实现原理吗?
3、HashMap什么时候会进行rehash?
4、HashMap什么时候会进行扩容?
5、那HashMap的初始容量设置成多少比较合适呢?
6、结合源码说说HashMap在高并发场景中为什么会出现死循环?
7、JDK1.8中对HashMap做了哪些性能优化?
8、HashMap和HashTable有何不同?
9、HashMap 和 ConcurrentHashMap 的区别?
10、ConcurrentHashMap和LinkedHashMap有什么区别?
11、为什么ConcurrentHashMap中的链表转红黑树的阀值是8?
12、什么是ConcurrentSkipListMap?他和ConcurrentHashMap有什么区别?
13、还看过其他的源码吗?Spring的源码有了解吗?
14、SpringBoot的源码呢?知道starter是怎么实现的吗?
一、构造方法
1.1无参构造方法
默认初始化容量16,加载因子0.75
/**
* Constructs an empty <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
1.2 指定初始容量initialCapacity,默认加载因子0.75
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and the default load factor (0.75).
*
* @param initialCapacity the initial capacity.
* @throws IllegalArgumentException if the initial capacity is negative.
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
1.3 指定初始容量initialCapaticy和加载因子loadFactor
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and load factor.
*
* @param initialCapacity the initial capacity
* @param loadFactor the load factor
* @throws IllegalArgumentException if the initial capacity is negative
* or the load factor is nonpositive
*/
public HashMap(int initialCapacity, float loadFactor) {
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
// 阈值初始化为初始容量最小2的倍数
this.threshold = tableSizeFor(initialCapacity);
}
HashMap初始容量为指定容量的最小2的倍数。该方法将初始容量的二进制最高位右移再与原值进行或运算,将低位全部转换为1,最后加1,由此得到初始化容量的最小的2的倍数
/**
* Returns a power of two size for the given target capacity.
*/
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 < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
1.4 用其他Map初始化
/**
* Constructs a new <tt>HashMap</tt> with the same mappings as the
* specified <tt>Map</tt>. The <tt>HashMap</tt> is created with
* default load factor (0.75) and an initial capacity sufficient to
* hold the mappings in the specified <tt>Map</tt>.
*
* @param m the map whose mappings are to be placed in this map
* @throws NullPointerException if the specified map is null
*/
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
二、属性解析
2.1 基本属性
/**
* 默认初始化容量,必须是2的倍数,初始默认为16
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* 最大容量,小于2的30次方
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* 默认加载因子0.75
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* 列表转红黑树的阈值,列表大于等于8时将转为红黑树
*/
static final int TREEIFY_THRESHOLD = 8;
/**
* 红黑树转列表的阈值
*/
static final int UNTREEIFY_THRESHOLD = 6;
/**
* 列表转红黑树的最小容量,如果一个槽中的数据太多,HashMap应考虑扩容,该值用来解决扩容与列表转树的冲突
*/
static final int MIN_TREEIFY_CAPACITY = 64;
/**
* 在首次使用时初始化,根据需要扩容,大小始终为2的倍数
*/
transient Node<K,V>[] table;
/**
* Holds cached entrySet(). Note that AbstractMap fields are used
* for keySet() and values().
*/
transient Set<Map.Entry<K,V>> entrySet;
/**
* HashMap中键值对的数量
*/
transient int size;
/**
* HashMap结构修改次数
*/
transient int modCount;
/**
* 下次扩容时table的大小
* @serial
*/
int threshold;
/**
* hash table 加载因子
* @serial
*/
final float loadFactor;
2.2 内部类Node<K,V>
/**
* 基础hash节点,包含一个hash值,一个key-value键值对,和下个节点
*/
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;
}
}
2.3 内部类TreeNode<K,V>
/**
* 红黑树节点,包含父节点、左节点、右节点、前置节点以及节点颜色
*/
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;
}
}
......
}
三、主要方法解析
3.1 hash(Object key)
/**
* key首先经过原生的hash方法后返回int类型的hash值,将该值的高16位右移传递到低16位并与原来的值异或运算。
* 这样处理是为了将key的hash值的高位特征传递到低位,降低hash冲突的概率。
*/
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
3.2 put(K key, V value)
/**
* 在map中将指定的键和值进行关联映射,如果map中已经存在该键的映射关系,
* 那么map中该键关联的值将被替换。
*
* @param key key with which the specified value is to be associated
* @param value value to be associated with the specified key
* @return 返回key关联的旧值,如果原来key关联的为null,则返回null
*/
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;
// talbe在第一次使用时初始化
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// key的hash值未产生hash冲突,则将value作为第一个节点存储到map中
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e;
K k;
// 出现hash冲突,且key与第一个节点相同,用节点e标记该节点
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
// key所对应的槽中的第一个节点为TreeNode
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
// 出现hash冲突后,遍历列表
for (int binCount = 0; ; ++binCount) {
// 遍历列表,如无重复key值,将value值添加到列表末尾
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
// 如果列表长度大于等于阈值8,则将列表转换为红黑树
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
// 如果列表中存在重复的key,用节点e标记已存在的节点
if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
// 已存在key的映射
if (e != null) { // existing mapping for key
V oldValue = e.value;
// onlyIfAbsent为false或旧值为null,将新的value映射到map中
if (!onlyIfAbsent || oldValue == null)
e.value = value;
//
afterNodeAccess(e);
// 返回key关联的旧值
return oldValue;
}
}
++modCount;
// map中数据量大于容量阈值(容量*加载因子),map进行扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
3.3 resize()
/**
* 初始化或扩容(2倍), 如果为null,则按照初始容量分配,否则以2的倍数进行扩容。
* @return the table
*/
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) {
// 如果未超过容量最大值,则扩容2倍
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
// 初始化容量
newCap = oldThr;
else { // zero initial threshold signifies using defaults
// 初始容量值为0,初始化时容量为默认大小16
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) {
// 初始化阈值(初始容量 * 加载因子)
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
// 容量扩大为原来的两倍
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
// 进行rehash,把数据转移的扩容后的HashMap中
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
// hash槽中只有一个元素时,直接转移过去
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
// 节点类型为树节点,列表已转为红黑树了
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;
// HashMap槽中的数据为列表时,由于HashMap扩容后容量变为原来的两倍,通 // 过 `e.hash & oldCap` 运算,如果结果等于0, 则表示当前元素在新 // table中位置与原来相同,如果不等于0,则在新table中位置需要增加原来的 // 容量oldCap
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;
}
3.4 treeifyBin(Node<K,V>[] tab, int hash)
/**
* 将列表转红黑树
*/
final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index;
Node<K,V> e;
// 如果数组为null或数组容量小于列表转红黑树的阈值(64),则进行初始化或扩容
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
do {
// 将列表节点转换为红黑树节点
TreeNode<K,V> p = replacementTreeNode(e, null);
if (tl == null)
hd = p;
else {
p.prev = tl;
tl.next = p;
}
tl = p;
} while ((e = e.next) != null);
if ((tab[index] = hd) != null)
hd.treeify(tab);
}
}
四、多线程下HashMap死循环问题分析
HashMap多线程下死循环问题在JDK1.7存在,JDK1.8已经解决了死循环的问题,但仍然不是线程安全的。
JDK1.7多线程下死循环代码分析
/**
* Rehashes the contents of this map into a new array with a
* larger capacity. This method is called automatically when the
* number of keys in this map reaches its threshold.
*
* If current capacity is MAXIMUM_CAPACITY, this method does not
* resize the map, but sets threshold to Integer.MAX_VALUE.
* This has the effect of preventing future calls.
*
* @param newCapacity the new capacity, MUST be a power of two;
* must be greater than current capacity unless current
* capacity is MAXIMUM_CAPACITY (in which case value
* is irrelevant).
*/
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];
transfer(newTable, initHashSeedAsNeeded(newCapacity));
table = newTable;
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}
/**
* Transfers all entries from current table to newTable.
*/
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];
newTable[i] = e;
e = next;
}
}
}
上述代码在多线程下出现死循环的地方在transfer方法的内的do-while循环内,假设线程1在执行do-while循环的第2行代码时被挂起,此时线程1的记录了e节点信息和e.next节点信息,如果此时另外一个线程完成了整个扩容操作,此时线程1再次执行,由于线程2在执行扩容时,列表按照头插法的方式插入,线程1记录的仍是原列表的顺序,线程1继续操作,会导致列表首位相连,从而产生死循环。
此外,HashMap在多线程环境下还可能导致put操作导致元素丢失。
死循环产生的具体过程可参考:[深入理解JAVA集合系列三:HashMap的死循环解读]
五、总结
- HashMap底层基于数组和列表来实现的,将key经过hash散列再按数组长度取模运算,定位到一个hash槽,将key-value值作为一个节点存储到hash槽中,如果槽中出现hash冲突,则以列表的形式存储节点,当列表长度大于等于8时且map中总结点个数大于等于64时,则将列表转换为红黑树。
- 当HashMap中的节点个数超过容量阈值(容量*加载因子)时,HashMap会进行扩容,扩容是会进行rehash。
- 当HashMap中某个槽中的元素个数大于等于8且总元素个数小于64时,这时候HashMap会进行扩容而不是转为红黑树。
- HashMap的初始容量设置成initialCapacity = (需要存储的元素个数 / 负载因子) + 1,如果不确定,设置为16(默认值)。
- 在JDK1.8中,当HashMap某个槽中的元素个数大于等于8时,且总元素个数超过64,则将列表转化为红黑树提高查找速度。