JDK8的源码是Node数组+Node链表+TreeNode组成
常量解释
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16 //Node数组默认长度 static final int MAXIMUM_CAPACITY = 1 << 30; //Node数组最大长度 static final float DEFAULT_LOAD_FACTOR = 0.75f; //扩容因子 static final int TREEIFY_THRESHOLD = 8; //有一个Node链表长度大于8 则有可能转化为TreeNode static final int UNTREEIFY_THRESHOLD = 6; //在Hash表扩容时候,如果发现当前链表长度小于6了则重新退化为Node链表 //在转为TreeNode之前还会有一次会比较Node数组的长度,如果<64则Hash表仅是扩容,这样做的目的是,如果多个K/V恰好在同一个Node链表上导致的不必要的转换
static final int MIN_TREEIFY_CAPACITY = 64;
transient int size;//Hash表中的K-V数量 transient int modCount;//记录Hash表修改的次数,增 删 改 都会+1 int threshold;//可以理解为下一次扩容的阀值
final float loadFactor; //Hash表的实际扩容因子,默认值(0.75)或者自己定义
初始化
HashMap有三个初始化方法
//默认长度16,扩容因子0.75 public HashMap() { this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted }
//手动设置容量,默认0.75的扩容因子 public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); }
public HashMap(int initialCapacity, float loadFactor) { //手动设置容量<0抛出异常 if (initialCapacity < 0) throw new IllegalArgumentException("Illegal initial capacity: " + initialCapacity); //手动设置容量超过最大容量,为最大容量 if (initialCapacity > MAXIMUM_CAPACITY) initialCapacity = MAXIMUM_CAPACITY; //扩展因子<=0 或者 不合法 抛出异常 if (loadFactor <= 0 || Float.isNaN(loadFactor)) throw new IllegalArgumentException("Illegal load factor: " + loadFactor); this.loadFactor = loadFactor; //计算Hash表的扩容阀值 this.threshold = tableSizeFor(initialCapacity); }
/** * Returns a power of two size for the given target capacity. * 翻译:返回大于输入参数且最近的2的整数次幂的数,例如9 返回16 ,17返回32 18返回32 */ 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; }
put数据
public V put(K key, V value) { return putVal(hash(key), key, value, false, true); }
final V putVal(int hash, K key, V value, boolean onlyIfAbsent, boolean evict) { //tab是Hash表的容量数组,p是当前key的计算后的索引值对应的Node节点,n是容器数组的长度,i是key值计算后的索引值
Node<K,V>[] tab; Node<K,V> p; int n, i; if ((tab = table) == null || (n = tab.length) == 0) //如果tab为空,或者n==0 则执行首次扩容
n = (tab = resize()).length; if ((p = tab[i = (n - 1) & hash]) == null) //当前key值计算后的索引值对应的Node为空,说明当前位置是首次添加
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)))) //如果当前key与查出来的Node的key hash值相同则直接覆盖老值
e = p; else if (p instanceof TreeNode) //当前节点是树类型,树形结构添加节点
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); else { //如果当前Node的next为空,则直接将put的值放在当前Node的next位置,并且要判断是否需要转为TreeNode
//如果当前Node的next不为空就需要循环next一直找到next为空的位置。说明了HashMap的put操作的时间复杂度最好为O(1),最坏O(n)
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; } } //修改次数+1
++modCount; //如果当前的K-V数量 > 阀值 执行扩容
if (++size > threshold) resize(); afterNodeInsertion(evict); return null; }
Node链表转为Tree
treeifyBin (Node转为TreeNode)
final void treeifyBin(Node<K,V>[] tab, int hash) { int n, index; Node<K,V> e;
//容量数组为空或者容量数组长度 < 64 继续扩容,避免不必要的转换 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 { 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); } }
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; }
//容量扩容一倍,扩容阀值也是一倍 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 //首次初始化,容量是默认值,扩容阀值是容量*扩容因子
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); } //设置扩容阀值
threshold = newThr;
//new一个长度为newCap的Node数组 @SuppressWarnings({"rawtypes","unchecked"}) Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap]; table = newTab; if (oldTab != null) { for (int j = 0; j < oldCap; ++j) { Node<K,V> e;
//将老的Node数组里的Node重新放到扩容之后的Node数组,分为3中情况,当前Node next为空,TreeNode节点,当前Node next不为空 if ((e = oldTab[j]) != null) { oldTab[j] = null; //释放老数组的引用 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
//loHead用户存储低位(位置不变)key的链头,loTail用于指向链位位置。
Node<K,V> loHead = null, loTail = null;
//hiHead用户存储即将存储在高位的key的链头,hiTail用于指向链尾位置。 Node<K,V> hiHead = null, hiTail = null; Node<K,V> next; do { next = e.next;
//与原数组长度相与后,得到的结果为0的,意味着在新数组中的位置是不变的,因此,将其组成一个链条
if ((e.hash & oldCap) == 0) { if (loTail == null) loHead = e; else loTail.next = e; loTail = e; } else {
//对于非0的key,其在新数组中的位置是需要更新的,需要存储在新增的数组中的一个新的位置,将其形成一个链条。 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; }
扩容避免1.7的出现的环形队列
JDK1.7高并发中出现环形队列的代码
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); } //以下代码容易出现环形队列 int i = indexFor(e.hash, newCapacity); e.next = newTable[i]; newTable[i] = e; e = next; } } }
1.8解决这个问题
1、首先改头插法为尾插法
2、使用高位和低位Node节点来放不同位置的Node
线程不安全
putVal()
if ((p = tab[i = (n - 1) & hash]) == null)
//高并发情况下,如果A线程执行完 if 语句,恰好CPU将资源给了B线程,这时候B也走到newNode这一行,那么就会覆盖线程A的值 tab[i] = newNode(hash, key, value, null);
resize()
if (e.next == null) //这里并没有判断当前索引位置是否存在节点,高并发情况下,假如put和resize同时进行,put的位置恰好是这个索引位置,那么oldNode就会覆盖这个新put的值 newTab[e.hash & (newCap - 1)] = e;