HashMap、ConcurrentHashMap 1.7和1.8对比
本篇内容是学习的记录，可能会有所不足。
一：JDK1.7中的HashMap
JDK1.7的hashMap是由数组 + 链表组成
/** 1 << 4，表示1，左移4位，变成10000，即16，以二进制形式运行，效率更高 * 默认的hashMap数组长度 * 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. * hashMap的最大容量 */ static final int MAXIMUM_CAPACITY = 1 << 30; //1 073 741 824 /** * The load factor used when none specified in constructor. * 负载因子 */ static final float DEFAULT_LOAD_FACTOR = 0.75f; /** * An empty table instance to share when the table is not inflated. */ static final Entry<?,?>[] EMPTY_TABLE = {}; /** * The table, resized as necessary. Length MUST Always be a power of two. * hashTable，根据需要调整大小。长度一定是2的幂。 */ transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE; /** * The number of key-value mappings contained in this map. * hashMap中元素的个数 */ transient int size; /** * The next size value at which to resize (capacity * load factor). * @serial */ // If table == EMPTY_TABLE then this is the initial capacity at which the // table will be created when inflated. int threshold; /** * The load factor for the hash table. * * @serial */ final float loadFactor; /** * The number of times this HashMap has been structurally modified * Structural modifications are those that change the number of mappings in * the HashMap or otherwise modify its internal structure (e.g., * rehash). This field is used to make iterators on Collection-views of * the HashMap fail-fast. (See ConcurrentModificationException). * 记录hashMap元素被修改的次数 */ transient int modCount;
1：DEFAULT_INITIAL_CAPACITY，是hashMap默认的初始容量，它的大小一定是2的幂。
2：MAXIMUM_CAPACITY，hashMap支持的最大容量。
3：DEFAULT_LOAD_FACTOR，hashMap默认的负载因子，值为0.75，它决定hashMap数据的密度。
4：Entry<K,V>[] table，hashMap数组，可以根据自己的需要调整大小，长度一定是2的幂。
5：size，主要是记录hashMap中元素的数量。
6：threshold，调整hashMap后的值，即容量*负载因子。
7：loadFactor，可以调整的负载因子。
8：modCount，用来记录hashMap结构被修改的次数。
hashMap源码中有四个构造函数，初始化的时候可以知道容量和负载因子的大小。
/** 做了两件事：1、为threshold、loadFactor赋值 2、调用init() * 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) //限制最大容量 initialCapacity = MAXIMUM_CAPACITY; if (loadFactor <= 0 || Float.isNaN(loadFactor)) //检查 loadFactor throw new IllegalArgumentException("Illegal load factor: " + loadFactor); //真正在做的，只是记录下loadFactor、initialCpacity的值 this.loadFactor = loadFactor; //记录下loadFactor threshold = initialCapacity; //初始的 阈值threshold=initialCapacity=16 init(); } /** * 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); } /** 默认的初始化容量、默认的加载因子 * Constructs an empty <tt>HashMap</tt> with the default initial capacity * (16) and the default load factor (0.75). */ public HashMap() { //16 0.75 this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR); } /** * 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(Math.max((int) (m.size() / DEFAULT_LOAD_FACTOR) + 1, DEFAULT_INITIAL_CAPACITY), DEFAULT_LOAD_FACTOR); inflateTable(threshold); putAllForCreate(m); }
接下来看下put方法：
public V put(K key, V value) { if (Entry<K,V>[] table == EMPTY_TABLE) { inflateTable(threshold); //初始化表 （初始化、扩容 合并为了一个方法） } if (key == null) //对key为null做特殊处理 return putForNullKey(value); int hash = hash(key); //计算hash值 int i = indexFor(hash, table.length); //根据hash值计算出index下标 for (Entry<K,V> e = table[i]; e != null; e = e.next) { //遍历下标为i处的链表 Object k; if (e.hash == hash && ((k = e.key) == key || key.equals(k))) { //如果key值相同，覆盖旧值，返回新值 V oldValue = e.value; e.value = value; //新值 覆盖 旧值 e.recordAccess(this); //do nothing return oldValue; //返回旧值 } } modCount++; //修改次数+1，类似于一个version number addEntry(hash, key, value, i); return null; }
可以看到到table是空的时候，调用了一个方法：
private void inflateTable(int toSize) { // Find a power of 2 >= toSize int capacity = roundUpToPowerOf2(toSize); // threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1); table = new Entry[capacity]; //初始化表 initHashSeedAsNeeded(capacity); }
这个方法用来初始化table和table的扩容，roundUpToPowerOf2可以保证hashMap的容量一定是2的幂。
hashMap put元素时，会先根据hash运算计算出hash值，然后根据hash值和table的长度进行取模，计算出元素在table中的下标，如果key相同就覆盖原来的旧值，如果不相同就加入链表中。
/** * Returns index for hash code h. * 计算元素在table中的下标位置 */ static int indexFor(int h, int length) { // assert Integer.bitCount(length) == 1 : "length must be a non-zero power of 2"; return h & (length-1); } /** * Adds a new entry with the specified key, value and hash code to * the specified bucket. It is the responsibility of this * method to resize the table if appropriate. * * Subclass overrides this to alter the behavior of put method. */ void addEntry(int hash, K key, V value, int bucketIndex) { if ((size >= threshold) && (null != table[bucketIndex])) { //如果size大于threshold && table在下标为index的地方已经有entry了 resize(2 * table.length); //扩容，将数组长度变为原来两倍 hash = (null != key) ? hash(key) : 0; //重新计算 hash 值 bucketIndex = indexFor(hash, table.length); //重新计算下标 } createEntry(hash, key, value, bucketIndex); //创建entry } /** * Like addEntry except that this version is used when creating entries * as part of Map construction or "pseudo-construction" (cloning, * deserialization). This version needn't worry about resizing the table. * * Subclass overrides this to alter the behavior of HashMap(Map), * clone, and readObject. */ void createEntry(int hash, K key, V value, int bucketIndex) { Entry<K,V> e = table[bucketIndex]; //获取table中存的entry table[bucketIndex] = new Entry<>(hash, key, value, e); //将新的entry放到数组中，next指向旧的table[i] size++; //修改map中元素个数 }
当put的元素个数大于12时，即大于hashMap的容量*负载因子计算后的值，那么就会进行扩容，上述源代码可以看到扩容的条件， 除了大于12，还要看当前put进table所处的位置，是否为null，若是null，就不进行扩容，否则就扩容成原来容量的2倍，扩容后需要重新计算hash和计算下标，由于table的长度发生了变化，需要重新计算。
接下来看下get方法：
public V get(Object key) { if (key == null) return getForNullKey(); Entry<K,V> entry = getEntry(key); return null == entry ? null : entry.getValue(); } /** * Returns the entry associated with the specified key in the * HashMap. Returns null if the HashMap contains no mapping * for the key. */ final Entry<K,V> getEntry(Object key) { if (size == 0) { return null; } int hash = (key == null) ? 0 : hash(key); for (Entry<K,V> e = table[indexFor(hash, table.length)]; e != null; e = e.next) { Object k; if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) return e; } return null; }
get方法也是需要先计算hash然后计算下标，再去寻找元素。
二：JDK1.8中的HashMap
JDK1.8中的hashMap和1.7最大的区别就是引入了红黑树
/** * The table, initialized on first use, and resized as * necessary. When allocated, length is always a power of two. * (We also tolerate length zero in some operations to allow * bootstrapping mechanics that are currently not needed.) */ 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; /** * The number of key-value mappings contained in this map. */ transient int size; /** * The number of times this HashMap has been structurally modified * Structural modifications are those that change the number of mappings in * the HashMap or otherwise modify its internal structure (e.g., * rehash). This field is used to make iterators on Collection-views of * the HashMap fail-fast. (See ConcurrentModificationException). */ transient int modCount; /** * The next size value at which to resize (capacity * load factor). * * @serial */ // (The javadoc description is true upon serialization. // Additionally, if the table array has not been allocated, this // field holds the initial array capacity, or zero signifying // DEFAULT_INITIAL_CAPACITY.) int threshold; /** * The load factor for the hash table. * * @serial */ final float loadFactor; /** * 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; /** * The load factor used when none specified in constructor. */ 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. * */ 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. */ 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. */ static final int MIN_TREEIFY_CAPACITY = 64; /** * 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; } }
下面看下put方法：
public V put(K key, V value) { return putVal(hash(key), key, value, false, true); } /** * Implements Map.put and related methods. 添加元素 * * @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) //若table为null n = (tab = resize()).length; //resize if ((p = tab[i = (n - 1) & hash]) == null) //计算下标i，取出i处的元素为p，如果p为null tab[i] = newNode(hash, key, value, null); //创建新的node，放到数组中 else { //若 p!=null Node<K,V> e; K k; if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k)))) //若key相同 e = p; //直接覆盖 else if (p instanceof TreeNode) //如果为 树节点 e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); //放到树中 else { //如果key不相同，也不是treeNode for (int binCount = 0; ; ++binCount) { //遍历i处的链表 if ((e = p.next) == null) { //找到尾部 p.next = newNode(hash, key, value, null); //在末尾添加一个node if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st //如果链表长度 >= 8 treeifyBin(tab, hash); //将链表转成共黑树 break; } if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) //若果key相同，直接退出循环 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; }
可以看到，上述源代码中，put的时候加入了红黑树，当put元素时，若链表的长度大于8，即源代码中的TREEIFY_THRESHOLD的值，这个时候链表就会转化为红黑树结构；当进行扩容的时候，红黑树转移后，若元素个数小于6，那么就会重新转化为链表。
三：JDK1.7中的ConcurrentHashMap
JDK1.7中的ConcurrentHashMap和JDK1.7中的HashMap的区别就是数组所存的元素，我们知道ConcurrentHashMap 是线程安全的。
public V put(K key, V value) { Segment<K,V> s; if (value == null) throw new NullPointerException(); int hash = hash(key); // 计算Hash值 int j = (hash >>> segmentShift) & segmentMask; //计算下标j if ((s = (Segment<K,V>)UNSAFE.getObject // nonvolatile; recheck (segments, (j << SSHIFT) + SBASE)) == null) // in ensureSegment s = ensureSegment(j); //若j处有segment就返回，若没有就创建并返回 return s.put(key, hash, value, false); //将值put到segment中去 } final V put(K key, int hash, V value, boolean onlyIfAbsent) { HashEntry<K,V> node = tryLock() ? null : scanAndLockForPut(key, hash, value); //如果tryLock成功，就返回null，否则。。。 V oldValue; try { HashEntry<K,V>[] tab = table; int index = (tab.length - 1) & hash; //根据table数组的长度 和 hash值计算index小标 HashEntry<K,V> first = entryAt(tab, index); //找到table数组在 index处链表的头部 for (HashEntry<K,V> e = first;;) { //从first开始遍历链表 if (e != null) { //若e!=null K k; if ((k = e.key) == key || (e.hash == hash && key.equals(k))) { //如果key相同 oldValue = e.value; //获取旧值 if (!onlyIfAbsent) { //若absent=false e.value = value; //覆盖旧值 ++modCount; // } break; //若已经找到，就退出链表遍历 } e = e.next; //若key不相同，继续遍历 } else { //直到e为null if (node != null) //将元素放到链表头部 node.setNext(first); else node = new HashEntry<K,V>(hash, key, value, first); //创建新的Entry int c = count + 1; //count 用来记录元素个数 if (c > threshold && tab.length < MAXIMUM_CAPACITY) //如果hashmap元素个数超过threshold，并且table长度小于最大容量 rehash(node); //rehash跟resize的功能差不多,将table的长度变为原来的两倍，重新打包entries，并将给定的node添加到新的table else //如果还有容量 setEntryAt(tab, index, node); //就在index处添加链表节点 ++modCount; //修改操作数 count = c; //将count+1 oldValue = null; // break; } } } finally { unlock(); //执行完操作后，释放锁 } return oldValue; //返回oldValue } private Segment<K,V> ensureSegment(int k) { final Segment<K,V>[] ss = this.segments; long u = (k << SSHIFT) + SBASE; // raw offset 获取下标k处的offset， Segment<K,V> seg; if ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u)) == null) { //如果下标k处没有元素 Segment<K,V> proto = ss[0]; // use segment 0 as prototype int cap = proto.table.length; //根据proto 获得 cap参数 float lf = proto.loadFactor; //。。。 int threshold = (int)(cap * lf); //计算threshold HashEntry<K,V>[] tab = (HashEntry<K,V>[])new HashEntry[cap]; if ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u)) == null) { // recheck //如果下标k处仍然没有元素 Segment<K,V> s = new Segment<K,V>(lf, threshold, tab); //创建segment while ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u)) == null) { //若下标k处仍然没有元素，自旋 if (UNSAFE.compareAndSwapObject(ss, u, null, seg = s)) //若通过CAS更新成功，则退出 break; } } } return seg; }
/** segments中每个元素都是一个专用的hashtable * The segments, each of which is a specialized hash table. */ final Segment<K,V>[] segments;
可以看到1.7中的ConcurrentHashMap数组中所存的是segments，每个segments下都是一个hashTable。当put元素时，会加锁，然后计算hash和下标，计算下标会计算两次，一次是在数组中的segments的位置，一次是在hashTable的位置。
四：JDK1.8中的ConcurrentHashMap
JDK1.8中的ConcurrentHashMap和JDK1.8中的HashMap结构一样，只是在处理上有区别
public V put(K key, V value) { return putVal(key, value, false); } /** Implementation for put and putIfAbsent */ final V putVal(K key, V value, boolean onlyIfAbsent) { if (key == null || value == null) throw new NullPointerException(); int hash = spread(key.hashCode()); //计算hash值 int binCount = 0; for (Node<K,V>[] tab = table;;) { //自旋 Node<K,V> f; int n, i, fh; if (tab == null || (n = tab.length) == 0) //table==null || table.length==0 tab = initTable(); //就initTable else if ((f = tabAt(tab, i = (n - 1) & hash)) == null) { //若下标 i 处的元素为null if (casTabAt(tab, i, null, //直接用CAS操作，i处的元素 new Node<K,V>(hash, key, value, null))) break; // no lock when adding to empty bin 想emptybin中假如元素的时候，不需要加锁 } else if ((fh = f.hash) == MOVED) //若下标 i 处的元素不为null，且f.hash==MOVED MOVED为常量值-1 tab = helpTransfer(tab, f); // else { //如果是一般的节点 V oldVal = null; synchronized (f) { //当头部元素不为null，且不需要转换成树时，需要进行同步操作 if (tabAt(tab, i) == f) { if (fh >= 0) { //若 链表头部hash值 >=0 binCount = 1; for (Node<K,V> e = f;; ++binCount) { K ek; if (e.hash == hash && ((ek = e.key) == key || (ek != null && key.equals(ek)))) { //如果key相同 oldVal = e.val; if (!onlyIfAbsent) //且不为absent e.val = value; //旧值覆盖新值 break; } Node<K,V> pred = e; if ((e = e.next) == null), { //如果链表遍历完成，还没退出，说明没有相同的key存在，在尾部添加节点 pred.next = new Node<K,V>(hash, key, value, null); break; } } } else if (f instanceof TreeBin) { //如果f是Tree的节点 Node<K,V> p; binCount = 2; if ((p = ((TreeBin<K,V>)f).putTreeVal(hash, key, value)) != null) { oldVal = p.val; if (!onlyIfAbsent) p.val = value; } } } } if (binCount != 0) { if (binCount >= TREEIFY_THRESHOLD) treeifyBin(tab, i); if (oldVal != null) return oldVal; break; } } } addCount(1L, binCount); return null; }
当put元素时，会使用CAS操作，去判断数组中所要put到的位置元素是否为空，为空就修改为当前的put的元素，若CAS操作失败，那么会自旋，这个时候发现数组里已经有元素了，那么就会锁住链表或者红黑树头部，把元素放入链表或者红黑树下面 。
五：hash冲突
当put的时候需要计算hash和下标，这个时候计算出来的值可能存在一样的，那么存到数组中的相同位置，就会发生hash冲突，
计算出的hash值一样一定会发生hash冲突，但是hash值一样的概率很小，计算出的下标值是一样的概率很大，所以hash冲突主要是由下标位置一样引起的，hashMap的解决方式是使用链地址法，即使用链表的方式解决，key一样的时候才会覆盖，否则就把元素放到链表的下一个位置。
