ConcurrentHashMap为什么高效?
与Hashtable不同的是,ConcurrentHashMap使用的是分段锁技术,将ConcurrentHashMap容器的数据分段存储,每一段数据分配一个Segment,当线程占用一个Segment时,其他线程可以访问其他段的数据.
概念
Segment : 可重入锁,继承ReentrantLock
HashEntry : 主要存储键值对,可以叫节点
HashEntry结构:
static final class HashEntry<K,V> {
final int hash;
// key值初始化后不能改变
final K key;
//volatile保证读到的数据为最新值
volatile V value;
//volatile保证读到的数据为最新的
volatile HashEntry<K,V> next;
总结:
ConcurrentHashMap包含一个Segment数组,每个Segment包含一个HashEntry数组,当修改HashEntry数组采用开链法处理冲突,所以它的每个HashEntry元素又是链表结构的元素。
基本操作源码分析
内部类
HashEntry
//HashEntry类,作为一个Segment中的节点类。HashEntry类基本不可变。
static final class HashEntry<K,V> {
final int hash; //hash和key都是final,保证了读操作时不用加锁
final K key;
volatile V value;//为了确保读操作能够看到最新的值,将value设置成volatile
volatile HashEntry<K,V> next;
//不再用final关键字,采用unsafe操作保证并发安全
HashEntry(int hash, K key, V value, HashEntry<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
//setNext方法可以设置该节点的next节点
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);
}
}
}
Setment
//Segment类
static final class Segment<K,V> extends ReentrantLock implements Serializable
//继承ReentrantLock,说明每一个Segment都是一个锁
Segment(float lf, int threshold, HashEntry<K,V>[] tab) {
this.loadFactor = lf;
this.threshold = threshold;
//HashEntry的数组
this.table = tab;
}
// 1.put方法,将一个HashEntry放入到该Segment中,使用自旋机制,减少了加锁的可能性
final V put(K key, int hash, V value, boolean onlyIfAbsent) {
HashEntry<K,V> node = tryLock() ? null :
scanAndLockForPut(key, hash, value); //如果加锁失败,则调用该方法
V oldValue;
try {
HashEntry<K,V>[] tab = table;
int index = (tab.length - 1) & hash; //同hashMap相同的哈希定位方式
HashEntry<K,V> first = entryAt(tab, index);
for (HashEntry<K,V> e = first;;) {
if (e != null) {
//若不为null,则持续查找,知道找到key和hash值相同的节点,将其value更新
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 { //若头结点为null
if (node != null) //在遍历key对应节点链时没有找到相应的节点
node.setNext(first);
//当前修改并不需要让其他线程知道,在锁退出时修改自然会
//更新到内存中,可提升性能
else
node = new HashEntry<K,V>(hash, key, value, first);
int c = count + 1;
if (c > threshold && tab.length < MAXIMUM_CAPACITY)
rehash(node); //如果超过阈值,则进行rehash操作
else
setEntryAt(tab, index, node);
++modCount;
count = c;
//没有值,返回null
oldValue = null;
break;
}
}
} finally {
unlock();
}
return oldValue;
}
// 2.scanAndLockForPut方法,该操作持续查找key对应的节点链中是否已存在该节点,如果没有找到已存在的节点,则预创建一个新节点,并且尝试n次,直到尝试次数超出限制,才真正进入等待状态,即所谓的自旋等待。
private HashEntry<K,V> scanAndLockForPut(K key, int hash, V value) {
//根据hash值找到segment中的HashEntry节点
HashEntry<K,V> first = entryForHash(this, hash); //首先获取头结点
HashEntry<K,V> e = first;
HashEntry<K,V> node = null;
int retries = -1; // negative while locating node
while (!tryLock()) { //持续遍历该哈希链
HashEntry<K,V> f; // to recheck first below
if (retries < 0) {
if (e == null) {
if (node == null) //若不存在要插入的节点,则创建一个新的节点
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) {
//尝试次数超出限制,则进行自旋等待
lock();
break;
}
/*当在自旋过程中发现节点链的链头发生了变化,则更新节点链的链头,
并重置retries值为-1,重新为尝试获取锁而自旋遍历*/
else if ((retries & 1) == 0 &&
(f = entryForHash(this, hash)) != first) {
e = first = f; // re-traverse if entry changed
retries = -1;
}
}
return node;
}
// rehash方法,用于当容量超出阈值后,进行扩容操作,类似于hashMap的扩容操作
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; //判断添加到哪个链表中去
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;
}
// remove方法,用于移除某个节点,返回移除的节点值
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;
//根据这种哈希定位方式来定位对应的HashEntry
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;
}
// clear方法,要首先对整个segment加锁,然后将每一个HashEntry都设置为null
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();
}
}
构造方法
public ConcurrentHashMap(int initialCapacity,
float loadFactor, int concurrencyLevel) {
//处理异常情况
if (!(loadFactor > 0) || initialCapacity < 0 || concurrencyLevel <= 0)
throw new IllegalArgumentException();
//判断并发级别是否大于最大并发级别(最大的并发等级不能超过MAX_SEGMENTS 1<<16(也就是1的二进制向左移16位,65536))
if (concurrencyLevel > MAX_SEGMENTS)
concurrencyLevel = MAX_SEGMENTS;
int sshift = 0;
int ssize = 1;
//取得大于数值最小的2的整数倍值
while (ssize < concurrencyLevel) {
++sshift;
ssize <<= 1;
}
//向左移动的位数
this.segmentShift = 32 - sshift; //3定位segment
//达到最后取余的情况下(其余为正好全为11),正好是&的结果
this.segmentMask = ssize - 1; //4定位segment
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
//c代表平均每个元素的多少(不足时,全+1)
int c = initialCapacity / ssize;
if (c * ssize < initialCapacity)
++c;
//最小HashEntry表的数量
int cap = MIN_SEGMENT_TABLE_CAPACITY;
while (cap < c)
cap <<= 1;
//segment初始化
Segment<K,V> s0 =
new Segment<K,V>(loadFactor, (int)(cap * loadFactor),(HashEntry<K,V>[])new HashEntry[cap]);//初始化每个segment的长度
Segment<K,V>[] ss = (Segment<K,V>[])new Segment[ssize]; //初始化segment数组
UNSAFE.putOrderedObject(ss, SBASE, s0);
this.segments = ss;
}
get操作
public V get(Object key) {
Segment<K,V> s;
HashEntry<K,V>[] tab;
//根据key的值计算hash值
int h = hash(key);
//获得segment的index
long u = (((h >>> segmentShift) & segmentMask) << SSHIFT) + SBASE;
if ((s = (Segment<K,V>)UNSAFE.getObjectVolatile(segments, u)) != null && //通过hash值定位segment中对应的HashEntry 遍历HashEntry,如果key存在,返回key对应的value 如果不存在则返回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;
}
put操作
public V put(K key, V value) {
Segment<K,V> s;
//键和值都不能为空
if (value == null)
throw new NullPointerException();
//计算key的hash值
int hash = hash(key);
//获得key所属的segemngt
int j = (hash >>> segmentShift) & segmentMask;
if ((s = (Segment<K,V>)UNSAFE.getObject
(segments, (j << SSHIFT) + SBASE)) == null)
//初试化segment(懒加载模式)
s = ensureSegment(j);
return s.put(key, hash, value, false);
}
segment的put方法:
final V put(K key, int hash, V value, boolean onlyIfAbsent) {
//获取锁,保证线程安全
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); //定位到具体的HashEntry
for (HashEntry<K,V> e = first;;) { //3
if (e != null) {
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) {
oldValue = e.value;
//覆盖旧值
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 {
//释放锁
unlock();
}
//返回旧值
return oldValue;
}
获取size
public int size() {
final Segment<K,V>[] segments = this.segments;
int size;
boolean overflow;
long sum;
long last = 0L;
int retries = -1;
try {
for (;;) {
//RETRIES_BEFORE_LOCK为不变常量2 尝试两次不锁住Segment的方式来统计每个Segment的大小,如果在统计的过程中Segment的count发生变化,这时候再加锁统计Segment的count
if (retries++ == RETRIES_BEFORE_LOCK) { //加锁
for (int j = 0; j < segments.length; ++j)
ensureSegment(j).lock();
}
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; //2
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;
}
弱一致性体现
get与containsKey两个方法几乎完全一致:他们都没有使用锁,而是通过Unsafe对象的getObjectVolatile()方法提供的原子读语义,来获得Segment以及对应的链表,然后对链表遍历判断是否存在key相同的节点以及获得该节点的value。但由于遍历过程中其他线程可能对链表结构做了调整,因此get和containsKey返回的可能是过时的数据,这一点是ConcurrentHashMap在弱一致性上的体现。如果要求强一致性,那么必须使用Collections.synchronizedMap()方法。
对比
- ConcurrentHashMap中的key和value值都不能为null,HashMap中key可以为null,HashTable中key不能为null。
- ConcurrentHashMap是线程安全的类并不能保证使用了ConcurrentHashMap的操作都是线程安全的!
- ConcurrentHashMap的get操作不需要加锁,put操作需要加锁 - put和get都只关心一个segment里面的hash操作质量也是很高的,如果hash后都存放在同一个segment中,那么使用这个类的意义就不会很大.