ConcurrentHashMap 结构分析
ConcurrentHashMap 类中包含两个静态内部类 HashEntry 和 Segment。HashEntry 用来封装映射表的键 / 值对;Segment 用来充当锁的角色,每个 Segment 对象守护整个散列映射表的若干个桶。每个桶是由若干个 HashEntry 对象链接起来的链表。一个ConcurrentHashMap 实例中包含由若干个 Segment 对象组成的数组。
ConcurrentHashMap 应用场景
HashMap是非线程安全的,在多线程环境下,使用HashMap进行put操作会引起死循环,导致CPU利用率接近100%,所以在并发情况下不能使用HashMap。
Hashtable是线程安全的,HashTable容器使用synchronized来保证线程安全,但在线程竞争激烈的情况下HashTable的效率非常低下。因为当一个线程访问HashTable的同步方法时,其他线程访问HashTable的同步方法时,可能会进入阻塞或轮询状态。
ConcurrentHashMap 是Java concurrent 包的重要成员。当有一个大数组时需要在多个线程共享时就可以考虑是否把它给分层多个节点了,避免大锁。是在高并发环境下的,性能大大优于HashTable。
ConcurrentHashMap 源码解读
/*
*构造函数
*/
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;
}
public ConcurrentHashMap(int initialCapacity, float loadFactor) {
this(initialCapacity, loadFactor, DEFAULT_CONCURRENCY_LEVEL);
}
public ConcurrentHashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR, DEFAULT_CONCURRENCY_LEVEL);
}
public ConcurrentHashMap() {
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR, DEFAULT_CONCURRENCY_LEVEL);
}
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);
}
/*
*功能函数
*/
//判断是否为空,空为真,非空为假。
public boolean isEmpty() {
long sum = 0L;
final Segment<K,V>[] segments = this.segments;
for (int j = 0; j < segments.length; ++j) {
Segment<K,V> seg = segmentAt(segments, j);
if (seg != null) {
if (seg.count != 0)
return false;
sum += seg.modCount;
}
}
if (sum != 0L) { // recheck unless no modifications
for (int j = 0; j < segments.length; ++j) {
Segment<K,V> seg = segmentAt(segments, j);
if (seg != null) {
if (seg.count != 0)
return false;
sum -= seg.modCount;
}
}
if (sum != 0L)
return false;
}
return true;
}
//获取map的大小
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 (;;) {
if (retries++ == RETRIES_BEFORE_LOCK) {
for (int j = 0; j < segments.length; ++j)
ensureSegment(j).lock(); // force creation
}
sum = 0L;
size = 0;
overflow = false;
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;
}
//获取某个具体的value值
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;
}
//判断map是否包含某个key
@SuppressWarnings("unchecked")
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;
}
//判断map是否包含某个value
public boolean containsValue(Object value) {
// Same idea as size()
if (value == null)
throw new NullPointerException();
final Segment<K,V>[] segments = this.segments;
boolean found = false;
long last = 0;
int retries = -1;
try {
outer: for (;;) {
if (retries++ == RETRIES_BEFORE_LOCK) {
for (int j = 0; j < segments.length; ++j)
ensureSegment(j).lock(); // force creation
}
long hashSum = 0L;
int sum = 0;
for (int j = 0; j < segments.length; ++j) {
HashEntry<K,V>[] tab;
Segment<K,V> seg = segmentAt(segments, j);
if (seg != null && (tab = seg.table) != null) {
for (int i = 0 ; i < tab.length; i++) {
HashEntry<K,V> e;
for (e = entryAt(tab, i); e != null; e = e.next) {
V v = e.value;
if (v != null && value.equals(v)) {
found = true;
break outer;
}
}
}
sum += seg.modCount;
}
}
if (retries > 0 && sum == last)
break;
last = sum;
}
} finally {
if (retries > RETRIES_BEFORE_LOCK) {
for (int j = 0; j < segments.length; ++j)
segmentAt(segments, j).unlock();
}
}
return found;
}
//判断map是否包含某个key-value键值对
public boolean contains(Object value) {
return containsValue(value);
}
//向map中添加一个key-value键值对
@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);
}
//批量添加到map
public void putAll(Map<? extends K, ? extends V> m) {
for (Map.Entry<? extends K, ? extends V> e : m.entrySet())
put(e.getKey(), e.getValue());
}
//从map中移除某个key
public V remove(Object key) {
int hash = hash(key);
Segment<K,V> s = segmentForHash(hash);
return s == null ? null : s.remove(key, hash, null);
}
public boolean remove(Object key, Object value) {
int hash = hash(key);
Segment<K,V> s;
return value != null && (s = segmentForHash(hash)) != null &&
s.remove(key, hash, value) != null;
}
//替换map中的某个键值对
public boolean replace(K key, V oldValue, V newValue) {
int hash = hash(key);
if (oldValue == null || newValue == null)
throw new NullPointerException();
Segment<K,V> s = segmentForHash(hash);
return s != null && s.replace(key, hash, oldValue, newValue);
}
public V replace(K key, V value) {
int hash = hash(key);
if (value == null)
throw new NullPointerException();
Segment<K,V> s = segmentForHash(hash);
return s == null ? null : s.replace(key, hash, value);
}
//清除map中所有的键值对
public void clear() {
final Segment<K,V>[] segments = this.segments;
for (int j = 0; j < segments.length; ++j) {
Segment<K,V> s = segmentAt(segments, j);
if (s != null)
s.clear();
}
}
//返回一个set,set中的值是map中的key值
public Set<K> keySet() {
Set<K> ks = keySet;
return (ks != null) ? ks : (keySet = new KeySet());
}
//返回一个集合,集合中的值是map中的value值。
public Collection<V> values() {
Collection<V> vs = values;
return (vs != null) ? vs : (values = new Values());
}
public Set<Map.Entry<K,V>> entrySet() {
Set<Map.Entry<K,V>> es = entrySet;
return (es != null) ? es : (entrySet = new EntrySet());
}
//返回一个enumeration ,使用map中的key值
public Enumeration<K> keys() {
return new KeyIterator();
}
//返回一个enumeration ,使用map中的value值
public Enumeration<V> elements() {
return new ValueIterator();
}
ConcurrentHashMap 实现高并发的总结
在实际的应用中,散列表一般的应用场景是:除了少数插入操作和删除操作外,绝大多数都是读取操作,而且读操作在大多数时候都是成功的。正是基于这个前提,ConcurrentHashMap 针对读操作做了大量的优化。通过 HashEntry 对象的不变性和用 volatile 型变量协调线程间的内存可见性,使得 大多数时候,读操作不需要加锁就可以正确获得值。这个特性使得 ConcurrentHashMap 的并发性能在分离锁的基础上又有了近一步的提高。
ConcurrentHashMap 是一个并发散列映射表的实现,它允许完全并发的读取,并且支持给定数量的并发更新。相比于 HashTable 和用同步包装器包装的 HashMap(Collections.synchronizedMap(new HashMap())),ConcurrentHashMap 拥有更高的并发性。在 HashTable 和由同步包装器包装的 HashMap 中,使用一个全局的锁来同步不同线程间的并发访问。同一时间点,只能有一个线程持有锁,也就是说在同一时间点,只能有一个线程能访问容器。这虽然保证多线程间的安全并发访问,但同时也导致对容器的访问变成串行化的了。
在使用锁来协调多线程间并发访问的模式下,减小对锁的竞争可以有效提高并发性。有两种方式可以减小对锁的竞争:
- 减小请求 同一个锁的 频率。
- 减少持有锁的 时间。
ConcurrentHashMap 的高并发性主要来自于以下几个方面:
-
- 用分离锁实现多个线程间的更深层次的共享访问。用 HashEntery
对象的不变性来降低执行读操作的线程在遍历链表期间对加锁的需求。通过对同一个 Volatile 变量的写 / 读访问,协调不同线程间读 /
写操作的内存可见性。 - 使用分离锁,减小了请求 同一个锁的频率。 通过 HashEntery 对象的不变性及对同一个 Volatile 变量的读 /写来协调内存可见性,使得 读操作大多数时候不需要加锁就能成功获取到需要的值。由于散列映射表在实际应用中大多数操作都是成功的 读操作,所以既可以减少请求同一个锁的频率,也可以有效减少持有锁的时间。
- 通过减小请求同一个锁的频率和尽量减少持有锁的时间 ,使得 ConcurrentHashMap 的并发性相对于 HashTable和用同步包装器包装的 HashMap有了质的提高。