在并发环境下使用Map有三种选择：
- Hashtable
- Collections.synchronizedMap(hashMap)
- ConcurrentHashMap
HashTable容器在竞争激烈的并发环境下表现出效率低下的原因是所有访问HashTable的线程都必须竞争同一把锁，那假如容器里有多把锁，每一把锁用于锁容器其中一部分数据，那么当多线程访问容器里不同数据段的数据时，线程间就不会存在锁竞争，从而可以有效的提高并发访问效率，这就是ConcurrentHashMap所使用的锁分段技术，首先将数据分成一段一段的存储，然后给每一段数据配一把锁，当一个线程占用锁访问其中一个段数据的时候，其他段的数据也能被其他线程访问。
ConcurrentHashMap的结构
我们通过ConcurrentHashMap的类图来分析ConcurrentHashMap的结构。
1.jpg
ConcurrentHashMap是由Segment数组结构和HashEntry数组结构组成。Segment是一种可重入锁ReentrantLock，在ConcurrentHashMap里扮演锁的角色，HashEntry则用于存储键值对数据。一个ConcurrentHashMap里包含一个Segment数组，Segment的结构和HashMap类似，是一种数组和链表结构， 一个Segment里包含一个HashEntry数组，每个HashEntry是一个链表结构的元素， 每个Segment守护者一个HashEntry数组里的元素,当对HashEntry数组的数据进行修改时，必须首先获得它对应的Segment锁。
ConcurrentHashMap 类源码
ConcurrentHashMap 的源码（基于JDK 1.7）如下：
public class ConcurrentHashMap<K, V> extends AbstractMap<K, V>
implements ConcurrentMap<K, V>, Serializable {
private static final long serialVersionUID = 7249069246763182397L;
/**
* 默认大小为16
*/
static final int DEFAULT_INITIAL_CAPACITY = 16;
/**
* 默认load factor 为0.75f
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* 默认并发度(concurrency level)为16
*/
static final int DEFAULT_CONCURRENCY_LEVEL = 16;
/**
* ConcurrentHashMap最大容量为2的30方
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* Segment的最小容量为2
*/
static final int MIN_SEGMENT_TABLE_CAPACITY = 2;
/**
* segments 最大容量为2的16方
*/
static final int MAX_SEGMENTS = 1 << 16; // slightly conservative
/**
*
*/
static final int RETRIES_BEFORE_LOCK = 2;
/**
* Mask value for indexing into segments. The upper bits of a
* key's hash code are used to choose the segment.
*/
final int segmentMask;
/**
* Shift value for indexing within segments.
*/
final int segmentShift;
/**
* The segments, each of which is a specialized hash table.
*/
final Segment<K,V>[] segments;
transient Set<K> keySet;
transient Set<Map.Entry<K,V>> entrySet;
transient Collection<V> values;
/**
* 构造方法
*/
@SuppressWarnings("unchecked")
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;
}
/**
* 构造方法
*/
public ConcurrentHashMap(int initialCapacity, float loadFactor) {
this(initialCapacity, loadFactor, DEFAULT_CONCURRENCY_LEVEL);
}
/**
* 构造方法
*/
public ConcurrentHashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR, DEFAULT_CONCURRENCY_LEVEL);
}
/**
* 默认构造方法
*/
public ConcurrentHashMap() {
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR, DEFAULT_CONCURRENCY_LEVEL);
}
/**
* 构造方法
*/
public ConcurrentHashMap(Map<? extends K, ? extends V> m) {
this(Math.max((int) (m.size() / DEFAULT_LOAD_FACTOR) + 1,
DEFAULT_INITIAL_CAPACITY),
DEFAULT_LOAD_FACTOR, DEFAULT_CONCURRENCY_LEVEL);
putAll(m);
}
}
ConcurrentHashMap的get操作
ConcurrentHashMap get方法 源码如下：
/**
* 根据key获取value
*/
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;
}
get操作的高效之处在于整个get过程不需要加锁，除非读到的值是空的才会加锁重读，我们知道HashTable容器的get方法是需要加锁的，那么ConcurrentHashMap的get操作是如何做到不加锁的呢？原因是它的get方法里将要使用的共享变量都定义成volatile，如用于统计当前Segement大小的count字段和用于存储值的HashEntry的value。
HashEntry 源码如下：
/**
* ConcurrentHashMap list entry. Note that this is never exported
* out as a user-visible Map.Entry.
*/
static final class HashEntry<K,V> {
final int hash;
final K key;
volatile V value;
volatile HashEntry<K,V> next;
HashEntry(int hash, K key, V value, HashEntry<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
/**
* Sets next field with volatile write semantics. (See above
* about use of putOrderedObject.)
*/
final void setNext(HashEntry<K,V> n) {
UNSAFE.putOrderedObject(this, nextOffset, n);
}
// Unsafe mechanics
static final sun.misc.Unsafe UNSAFE;
static final long nextOffset;
static {
try {
UNSAFE = sun.misc.Unsafe.getUnsafe();
Class k = HashEntry.class;
nextOffset = UNSAFE.objectFieldOffset
(k.getDeclaredField("next"));
} catch (Exception e) {
throw new Error(e);
}
}
}
ConcurrentHashMap的put操作
接下来，看看ConcurrentHashMap put方法，源码如下：
/**
* 往map中添加 key-value
*/
@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);
}
/**
*
*/
@SuppressWarnings("unchecked")
public V putIfAbsent(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
(segments, (j << SSHIFT) + SBASE)) == null)
s = ensureSegment(j);
return s.put(key, hash, value, true);
}
/**
* 获取Segment, 如果不存在则创建并记录到segments数组中
*/
@SuppressWarnings("unchecked")
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;
}
/**
* hash函数
*/
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);
}
其中，Segment源码如下：
/**
* Segments 是一个改良版的 hash tables.
*/
static final class Segment<K,V> extends ReentrantLock implements Serializable {
private static final long serialVersionUID = 2249069246763182397L;
static final int MAX_SCAN_RETRIES =
Runtime.getRuntime().availableProcessors() > 1 ? 64 : 1;
/**
* Segment 内部 HashEntry table
*/
transient volatile HashEntry<K,V>[] table;
/**
* 数量
*/
transient int count;
/**
* 被修改次数
*/
transient int modCount;
/**
* 阈值
*/
transient int threshold;
/**
* 负载因子
*/
final float loadFactor;
Segment(float lf, int threshold, HashEntry<K,V>[] tab) {
this.loadFactor = lf;
this.threshold = threshold;
this.table = tab;
}
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;;) {
if (e != null) {
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
oldValue = e.value;
if (!onlyIfAbsent) {
e.value = value;
++modCount;
}
break;
}
e = e.next;
}
else {
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();
}
return oldValue;
}
/**
* 扩容大小为之前容量的2倍
*/
@SuppressWarnings("unchecked")
private void rehash(HashEntry<K,V> node) {
HashEntry<K,V>[] oldTable = table;
int oldCapacity = oldTable.length;
int newCapacity = oldCapacity << 1;
threshold = (int)(newCapacity * loadFactor);
HashEntry<K,V>[] newTable =
(HashEntry<K,V>[]) new HashEntry[newCapacity];
int sizeMask = newCapacity - 1;
for (int i = 0; i < oldCapacity ; i++) {
HashEntry<K,V> e = oldTable[i];
if (e != null) {
HashEntry<K,V> next = e.next;
int idx = e.hash & sizeMask;
if (next == null) // Single node on list
newTable[idx] = e;
else { // Reuse consecutive sequence at same slot
HashEntry<K,V> lastRun = e;
int lastIdx = idx;
for (HashEntry<K,V> last = next;
last != null;
last = last.next) {
int k = last.hash & sizeMask;
if (k != lastIdx) {
lastIdx = k;
lastRun = last;
}
}
newTable[lastIdx] = lastRun;
// Clone remaining nodes
for (HashEntry<K,V> p = e; p != lastRun; p = p.next) {
V v = p.value;
int h = p.hash;
int k = h & sizeMask;
HashEntry<K,V> n = newTable[k];
newTable[k] = new HashEntry<K,V>(h, p.key, v, n);
}
}
}
}
int nodeIndex = node.hash & sizeMask; // add the new node
node.setNext(newTable[nodeIndex]);
newTable[nodeIndex] = node;
table = newTable;
}
/**
* 根据key定位HashEntry
*/
private HashEntry<K,V> scanAndLockForPut(K key, int hash, V value) {
HashEntry<K,V> first = entryForHash(this, hash);
HashEntry<K,V> e = first;
HashEntry<K,V> node = null;
int retries = -1; // negative while locating node
while (!tryLock()) {
HashEntry<K,V> f; // to recheck first below
if (retries < 0) {
if (e == null) {
if (node == null) // speculatively create node
node = new HashEntry<K,V>(hash, key, value, null);
retries = 0;
}
else if (key.equals(e.key))
retries = 0;
else
e = e.next;
}
else if (++retries > MAX_SCAN_RETRIES) {
lock();
break;
}
else if ((retries & 1) == 0 &&
(f = entryForHash(this, hash)) != first) {
e = first = f; // re-traverse if entry changed
retries = -1;
}
}
return node;
}
/**
*
*/
private void scanAndLock(Object key, int hash) {
// similar to but simpler than scanAndLockForPut
HashEntry<K,V> first = entryForHash(this, hash);
HashEntry<K,V> e = first;
int retries = -1;
while (!tryLock()) {
HashEntry<K,V> f;
if (retries < 0) {
if (e == null || key.equals(e.key))
retries = 0;
else
e = e.next;
}
else if (++retries > MAX_SCAN_RETRIES) {
lock();
break;
}
else if ((retries & 1) == 0 &&
(f = entryForHash(this, hash)) != first) {
e = first = f;
retries = -1;
}
}
}
/**
* Remove; match on key only if value null, else match both.
*/
final V remove(Object key, int hash, Object value) {
if (!tryLock())
scanAndLock(key, hash);
V oldValue = null;
try {
HashEntry<K,V>[] tab = table;
int index = (tab.length - 1) & hash;
HashEntry<K,V> e = entryAt(tab, index);
HashEntry<K,V> pred = null;
while (e != null) {
K k;
HashEntry<K,V> next = e.next;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
V v = e.value;
if (value == null || value == v || value.equals(v)) {
if (pred == null)
setEntryAt(tab, index, next);
else
pred.setNext(next);
++modCount;
--count;
oldValue = v;
}
break;
}
pred = e;
e = next;
}
} finally {
unlock();
}
return oldValue;
}
final boolean replace(K key, int hash, V oldValue, V newValue) {
if (!tryLock())
scanAndLock(key, hash);
boolean replaced = false;
try {
HashEntry<K,V> e;
for (e = entryForHash(this, hash); e != null; e = e.next) {
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
if (oldValue.equals(e.value)) {
e.value = newValue;
++modCount;
replaced = true;
}
break;
}
}
} finally {
unlock();
}
return replaced;
}
final V replace(K key, int hash, V value) {
if (!tryLock())
scanAndLock(key, hash);
V oldValue = null;
try {
HashEntry<K,V> e;
for (e = entryForHash(this, hash); e != null; e = e.next) {
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
oldValue = e.value;
e.value = value;
++modCount;
break;
}
}
} finally {
unlock();
}
return oldValue;
}
final void clear() {
lock();
try {
HashEntry<K,V>[] tab = table;
for (int i = 0; i < tab.length ; i++)
setEntryAt(tab, i, null);
++modCount;
count = 0;
} finally {
unlock();
}
}
}
由于put方法里需要对共享变量进行写入操作，所以为了线程安全，在操作共享变量时必须得加锁。put方法首先定位到Segment，然后在Segment里进行插入操作。插入操作需要经历两个步骤，第一步判断是否需要对Segment里的HashEntry数组进行扩容，第二步定位添加元素的位置然后放在HashEntry数组里。
