最近看了一下ConcurrentHashMap的相关代码，感觉JDK1.7和JDK1.8差别挺大的，这次先看下JDK1.7是怎么实现的吧
哈希（hash）
先了解一下啥是哈希（网上有很多介绍），是一种散列函数，简单来说就是将输入值转换为固定值的一种压缩映射，在Java中最常见的就是Object.hashCode()，通过固定算法计算出来的一个值
数据结构
ConcurrentHashMap主要结构是有Segment<K,V>以及HashEntry<K,V>链表组成的
我们先看一下HashEntry<K,V>的主要结构，还是单向链表的数据结构：
static final class HashEntry<K,V> {
final int hash;//hash值
final K key;//存储key
volatile V value;//存储值
volatile HashEntry<K,V> next;//指向下一个，单向链表
HashEntry(int hash, K key, V value, HashEntry<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
//......
}再来看一下Segment<K,V>的数据结构，主要还是用到了HashEntry<K,V>数组：
static final class Segment<K,V> extends ReentrantLock implements Serializable {
//数据储存数组
transient volatile HashEntry<K,V>[] table;
/**
* The load factor for the hash table. Even though this value
* is same for all segments, it is replicated to avoid needing
* links to outer object.
* @serial
*/
//扩容因子，当Segment的数量大于initialCapacity* loadFactor就会扩容
final float loadFactor;
/**
* The table is rehashed when its size exceeds this threshold.
* (The value of this field is always <tt>(int)(capacity *
* loadFactor)</tt>.)
*/
//阈值，超出后就必须重新散列，就是扩容
transient int threshold;
Segment(float lf, int threshold, HashEntry<K,V>[] tab) {
this.loadFactor = lf;
this.threshold = threshold;
this.table = tab;
}
//.....
}接下来看一下ConcurrentHashMap的构造函数以及相关变量：
/**
* The default initial capacity for this table,
* used when not otherwise specified in a constructor.
*/
//容器的默认大小
static final int DEFAULT_INITIAL_CAPACITY = 16;
/**
* The default load factor for this table, used when not
* otherwise specified in a constructor.
*/
//用来调整大小的，就是扩容
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* The default concurrency level for this table, used when not
* otherwise specified in a constructor.
*/
//并发时访问的线程数量
static final int DEFAULT_CONCURRENCY_LEVEL = 16;
final Segment<K,V>[] segments;//数据存储的数组
//最大并发的线程数，不能超过65536
static final int MAX_SEGMENTS = 1 << 16; // slightly conservative
//最大容量数，不能超过2的30次方
static final int MAXIMUM_CAPACITY = 1 << 30;
public ConcurrentHashMap(int initialCapacity,
float loadFactor, int concurrencyLevel) {
if (!(loadFactor > 0) || initialCapacity < 0 || concurrencyLevel <= 0)
throw new IllegalArgumentException();
if (concurrencyLevel > MAX_SEGMENTS)
concurrencyLevel = MAX_SEGMENTS;
// Find power-of-two sizes best matching arguments
int sshift = 0;
int ssize = 1;
while (ssize < concurrencyLevel) {
++sshift;
ssize <<= 1;
}
this.segmentShift = 32 - sshift;
this.segmentMask = ssize - 1;
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
int c = initialCapacity / ssize;
if (c * ssize < initialCapacity)
++c;
int cap = MIN_SEGMENT_TABLE_CAPACITY;
while (cap < c)
cap <<= 1;
// create segments and segments[0]
Segment<K,V> s0 =
new Segment<K,V>(loadFactor, (int)(cap * loadFactor),
(HashEntry<K,V>[])new HashEntry[cap]);
Segment<K,V>[] ss = (Segment<K,V>[])new Segment[ssize];
UNSAFE.putOrderedObject(ss, SBASE, s0); // ordered write of segments[0]
this.segments = ss;
}在构造方法中可以看到，其实还是创建一个Segment的数组，默认的话长度为16，并且将s0变量赋值进去，s0中的HashEntry数组的大小默认为2。
接下来看一下我们经常用put()方法，源代码如下：
首先需要计算key值的hash值，计算方法是固定的算法，然后判断Segment数组中是否有这个hash值的数据，如果不存在的话，则进入扩容方法ensureSegment(j)；在这个方法中可以看到扩容新数组的长度为table.length * loadFactor，即每次扩容为initialCapacity* loadFactor，只会扩容HashEntry数组，并非Segment数组；如果存在的话，则调用Segment的put()方法，这个方法总共有四个参数，最后一个参数是用于区别putIfAbsent()以及put()，这两个方法区别简单来说就是，判断当前key存不存在，如果存在的话put()方法就是覆盖，而putIfAbsent()就是不覆盖，并且这两个方法都会返回旧值，在下面的有Segment的put方法解析。
@SuppressWarnings("unchecked")
public V put(K key, V value) {
Segment<K,V> s;
if (value == null)
throw new NullPointerException();
int hash = hash(key);
int j = (hash >>> segmentShift) & segmentMask;
if ((s = (Segment<K,V>)UNSAFE.getObject // nonvolatile; recheck
(segments, (j << SSHIFT) + SBASE)) == null) // in ensureSegment
s = ensureSegment(j);
return s.put(key, hash, value, false);
}
private int hash(Object k) {
int h = hashSeed;
if ((0 != h) && (k instanceof String)) {
return sun.misc.Hashing.stringHash32((String) k);
}
h ^= k.hashCode();
// Spread bits to regularize both segment and index locations,
// using variant of single-word Wang/Jenkins hash.
h += (h << 15) ^ 0xffffcd7d;
h ^= (h >>> 10);
h += (h << 3);
h ^= (h >>> 6);
h += (h << 2) + (h << 14);
return h ^ (h >>> 16);
}
//扩容Segment的数组，
private Segment<K,V> ensureSegment(int k) {
final Segment<K,V>[] ss = this.segments;
long u = (k << SSHIFT) + SBASE; // raw offset
Segment<K,V> seg;
if ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u)) == null) {
Segment<K,V> proto = ss[0]; // use segment 0 as prototype
int cap = proto.table.length;
float lf = proto.loadFactor;
int threshold = (int)(cap * lf);
HashEntry<K,V>[] tab = (HashEntry<K,V>[])new HashEntry[cap];
if ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u))
== null) { // recheck
Segment<K,V> s = new Segment<K,V>(lf, threshold, tab);
while ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u))
== null) {
if (UNSAFE.compareAndSwapObject(ss, u, null, seg = s))
break;
}
}
}
return seg;
}
//Segement中的put方法：可以看到，首先会先去获取锁
final V put(K key, int hash, V value, boolean onlyIfAbsent) {
HashEntry<K,V> node = tryLock() ? null :
scanAndLockForPut(key, hash, value);
V oldValue;
try {
HashEntry<K,V>[] tab = table;
int index = (tab.length - 1) & hash;
HashEntry<K,V> first = entryAt(tab, index);
for (HashEntry<K,V> e = first;;) {//循环判断
if (e != null) {
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
oldValue = e.value;//返回旧值
if (!onlyIfAbsent) {
e.value = value;//如果是putIfAbsent()则不执行这段覆盖代码
++modCount;
}
break;
}
e = e.next;
}
else {
//如果在对应的table数组中不存在则创建一个HashEntry节点，或者创建一个
if (node != null)
node.setNext(first);
else
node = new HashEntry<K,V>(hash, key, value, first);
int c = count + 1;
if (c > threshold && tab.length < MAXIMUM_CAPACITY)
rehash(node);
else
setEntryAt(tab, index, node);
++modCount;
count = c;
oldValue = null;
break;
}
}
} finally {
unlock();//释放锁
}
return oldValue;接下来看看get()方法，其实get()方法的现对来说较为简单，在定位segment和定位table后，依次扫描这个table元素下的的链表，要么找到元素，要么返回null。这里可能会有个并发问题如何获取是最新的，因为在HashEntry设计当中value属性的使用了 volatile保证了数据的可见性，但是key并非使用了volatile修饰，所以在使用get()以及containsKey()方法会存在一致性问题，由于HashEntry是链表结构，所以在并发情况下如果其他线程进行修改HashEntry链表值的话，返回值并非是实时数据。
public V get(Object key) {
Segment<K,V> s; // manually integrate access methods to reduce overhead
HashEntry<K,V>[] tab;
int h = hash(key);
long u = (((h >>> segmentShift) & segmentMask) << SSHIFT) + SBASE;
if ((s = (Segment<K,V>)UNSAFE.getObjectVolatile(segments, u)) != null &&
(tab = s.table) != null) {
for (HashEntry<K,V> e = (HashEntry<K,V>) UNSAFE.getObjectVolatile
(tab, ((long)(((tab.length - 1) & h)) << TSHIFT) + TBASE);
e != null; e = e.next) {
K k;
if ((k = e.key) == key || (e.hash == h && key.equals(k)))
return e.value;
}
}
return null;
}
//获取containsKey的值
public boolean containsKey(Object key) {
Segment<K,V> s; // same as get() except no need for volatile value read
HashEntry<K,V>[] tab;
int h = hash(key);
long u = (((h >>> segmentShift) & segmentMask) << SSHIFT) + SBASE;
if ((s = (Segment<K,V>)UNSAFE.getObjectVolatile(segments, u)) != null &&
(tab = s.table) != null) {
for (HashEntry<K,V> e = (HashEntry<K,V>) UNSAFE.getObjectVolatile
(tab, ((long)(((tab.length - 1) & h)) << TSHIFT) + TBASE);
e != null; e = e.next) {
K k;
if ((k = e.key) == key || (e.hash == h && key.equals(k)))
return true;
}
}
return false;
}在使用size()时候，会进去两次统计，并且不是加锁统计，两次一致直接返回结果，不一致，重新加锁再次统计
public int size() {
// Try a few times to get accurate count. On failure due to
// continuous async changes in table, resort to locking.
final Segment<K,V>[] segments = this.segments;
int size;
boolean overflow; // true if size overflows 32 bits
long sum; // sum of modCounts
long last = 0L; // previous sum
int retries = -1; // first iteration isn't retry
try {
for (;;) {
//第一次统计
if (retries++ == RETRIES_BEFORE_LOCK) {
for (int j = 0; j < segments.length; ++j)
ensureSegment(j).lock(); // force creation
}
sum = 0L;
size = 0;
overflow = false;
//第二次统计
for (int j = 0; j < segments.length; ++j) {
Segment<K,V> seg = segmentAt(segments, j);
if (seg != null) {
sum += seg.modCount;
int c = seg.count;
if (c < 0 || (size += c) < 0)
overflow = true;
}
}
if (sum == last)
break;
last = sum;
}
} finally {
if (retries > RETRIES_BEFORE_LOCK) {
for (int j = 0; j < segments.length; ++j)
segmentAt(segments, j).unlock();
}
}
return overflow ? Integer.MAX_VALUE : size;
}其他方法我就不介绍啦，下次再看一点JDK1.8的ConcurrentHashMap源代码，写的不是很好，不要见怪咯