ConcurrentHashMap分析
2018-05-30 本文已影响0人
tengwind
ConcurrentHashMap的原理分析。在分析ConcurrentHashMap之前，应该先熟悉一下HashMap的原理。
HashMap原理
HashMap是一个数组+链表模式。内部维护一个Entry数组table，Entry是map的数据存储结构，包含了key，value，和next指向下一个Entry的指针。当插入元素时通过hash算找到对应的table的下标，如果数组下标存在元素，则将元素以链表方式，链接起来，插入到链表的头位置。
ConcurrentHashMap原理
ConcurrentHashMap使用了分段锁技术，将数据存储到不同的段(segment)中，每个段是一个ReentrantLock锁，当一个线程占用锁访问一个段时，其他的段可以继续访问。
ConcurrentHashMap维护了Segment的数组，每一个Segment中又维护了HashEntry数组，Segment类似于HashMap，HashEntry类似于Entry。这样将数据进行分段的存储，提高了并发访问map的效率，ConcurrentHashMap结构图如下：
简易图
下面看一下ConcurrentHashMap的源码，下面的源码都是jdk1.7版本,1.8版本和下面代码有很大区别。
类定义
public class ConcurrentHashMap<K, V> extends AbstractMap<K, V>
implements ConcurrentMap<K, V>, Serializable {
上面代码是ConcurrentHashMap的定义，可以看到
1.继承了AbstractMap类，说明他就是一个Map集合
2.实现了ConcurrentMap接口，改接口中增加了一些原子的操作方法
HashEntry内部静态类
static final class HashEntry<K,V> {
final int hash;//hash值
final K key; //map的key值
volatile V value;//value值
volatile HashEntry<K,V> next;//指向下一个hashEntry对象的引用
//唯一构造函数
HashEntry(int hash, K key, V value, HashEntry<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
}
从上面的代码可以看到HashEntry其实就是和HashMap中的Entry数据结构一样，用来存储正在设置的值。
Segment
static final class Segment<K,V> extends ReentrantLock implements Serializable {
static final int MAX_SCAN_RETRIES =
Runtime.getRuntime().availableProcessors() > 1 ? 64 : 1;
/**
* 存储HashEntry的数组
*/
transient volatile HashEntry<K,V>[] table;
/**
* 当前.HashEntry数组中元素的个数
*/
transient int count;
/**
* 当期segment段操作修改的次数统计
*/
transient int modCount;
/**
阀值，当size操过了阀值之后，将会进行rehash操作，值等于
* (int)(capacity * loadFactor)
*/
transient int threshold;
/**
* 加载因子
*/
final float loadFactor;
//构造函数
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;
}
/**
* Doubles size of table and repacks entries, also adding the
* given node to new table
*/
@SuppressWarnings("unchecked")
private void rehash(HashEntry<K,V> node) {
/*
* Reclassify nodes in each list to new table. Because we
* are using power-of-two expansion, the elements from
* each bin must either stay at same index, or move with a
* power of two offset. We eliminate unnecessary node
* creation by catching cases where old nodes can be
* reused because their next fields won't change.
* Statistically, at the default threshold, only about
* one-sixth of them need cloning when a table
* doubles. The nodes they replace will be garbage
* collectable as soon as they are no longer referenced by
* any reader thread that may be in the midst of
* concurrently traversing table. Entry accesses use plain
* array indexing because they are followed by volatile
* table write.
*/
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;
}
/**
* Scans for a node containing given key while trying to
* acquire lock, creating and returning one if not found. Upon
* return, guarantees that lock is held. UNlike in most
* methods, calls to method equals are not screened: Since
* traversal speed doesn't matter, we might as well help warm
* up the associated code and accesses as well.
*
* @return a new node if key not found, else null
*/
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;
}
/**
* Scans for a node containing the given key while trying to
* acquire lock for a remove or replace operation. Upon
* return, guarantees that lock is held. Note that we must
* lock even if the key is not found, to ensure sequential
* consistency of updates.
*/
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();
}
}
}
