ConcurrentHashMap分析:
闻其名,便知其义,并发的hashmap, 我们先来看看ConcurrentHashMap数据结构图:
ConcurrentHashMap由多个Segment组成,而Segment内部是由HashEntry(存放key-value对)数组组成(类似于HashMap的Entry数组)。
从代码来看ConcurrentHashMap的基本属性:
//segment掩码值: 用于计算key所在segments索引值
final int segmentMask;
//segment偏移值: 用于计算key所在segments索引值
final int segmentShift;
//segments数组,其内部也是由HashEntry数组实现,正因为有了多个segment,才提高了并发度
final Segment<K,V>[] segments;
看到重要的Segment数据结构:
/**
* 其实现了ReentrantLock, 自身可线程安全
* 其本身就像个HashMap
*/
static final class Segment<K,V> extends ReentrantLock implements Serializable {
//存放元素的table
transient volatile HashEntry<K,V>[] table;
//元素个数
transient int count;
//table resize阈值
transient int threshold;
//装载因子,默认0.75
final float loadFactor;
...
}
还是先从ConcurrentHashMap初始化工作开始说起:
public ConcurrentHashMap(int initialCapacity,
float loadFactor, int concurrencyLevel) {
if (!(loadFactor > 0) || initialCapacity < 0 || concurrencyLevel <= 0)
throw new IllegalArgumentException();
if (concurrencyLevel > MAX_SEGMENTS) //并发级别,默认16,最大值为65536
concurrencyLevel = MAX_SEGMENTS;
// Find power-of-two sizes best matching arguments
int sshift = 0;
int ssize = 1; //segment数组的大小,必须是大于concurrentLevel且最小的2的指数
while (ssize < concurrencyLevel) { //找到大于等于conrrencyLevel且为2的指数的最小ssize
++sshift;
ssize <<= 1;
}
this.segmentShift = 32 - sshift; //segmentShift段偏移, 32即hashCode是int型(4字节32位),用来计算key所在segment下标
this.segmentMask = ssize - 1; //segment段掩码:2^ssize - 1, 类似与子网掩码的道理,ssize默认16,掩码就是1111,用来计算key所在segment下标
if (initialCapacity > MAXIMUM_CAPACITY) //初始化容量(segments数组),默认16
initialCapacity = MAXIMUM_CAPACITY;
int c = initialCapacity / ssize;
if (c * ssize < initialCapacity)
++c;
int cap = MIN_SEGMENT_TABLE_CAPACITY; //segment中的table数组大小,最小为2, 值也必须是2的指数倍
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]); //创建segment[0],用于后面创建其他segment的模版
Segment<K,V>[] ss = (Segment<K,V>[])new Segment[ssize]; //创建segments
UNSAFE.putOrderedObject(ss, SBASE, s0); // ordered write of segments[0]
this.segments = ss;
}
一些基本的操作实现put(), get(), remove(),size():
- put操作实现:
public V put(K key, V value) {
Segment<K,V> s;
if (value == null)
throw new NullPointerException(); //键值都不可为null
int hash = hash(key); //计算key的hash值
int j = (hash >>> segmentShift) & segmentMask; //计算key所在segment索引值,保证j值会在segments索引范围内
if ((s = (Segment<K,V>)UNSAFE.getObject(segments, (j << SSHIFT) + SBASE)) == null)//若对应segment不存在
s = ensureSegment(j); //创建segment
return s.put(key, hash, value, false);
}
hash计算, 与HashMap有区别:
private int hash(Object k) {
int h = hashSeed;
if ((0 != h) && (k instanceof String)) {
return sun.misc.Hashing.stringHash32((String) k);
}
h ^= k.hashCode();
h += (h << 15) ^ 0xffffcd7d;
h ^= (h >>> 10);
h += (h << 3);
h ^= (h >>> 6);
h += (h << 2) + (h << 14);
return h ^ (h >>> 16);
}
ensureSegment方法:
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); //创建新的segment
while ((seg = (Segment<K,V>)UNSAFE.getObjectVolatile(ss, u))
== null) {
if (UNSAFE.compareAndSwapObject(ss, u, null, seg = s))
break;
}
}
}
return seg;
}
继续看Segment的put方法实现:
final V put(K key, int hash, V value, boolean onlyIfAbsent) {
HashEntry<K,V> node = tryLock() ? null : //获取到了segment锁,node为null
scanAndLockForPut(key, hash, value); //未获取到锁,则在等锁过程中先定位,构建新的node节点
V oldValue;
try {
HashEntry<K,V>[] tab = table;
int index = (tab.length - 1) & hash; //根据key的hash值计算key在table中的索引
HashEntry<K,V> first = entryAt(tab, index); //获取第一个对应bucket的第一个HashEntry
for (HashEntry<K,V> e = first;;) {
if (e != null) { //该HashEntry已经有元素
K k;
if ((k = e.key) == key ||
(e.hash == hash && key.equals(k))) { //若key相等
oldValue = e.value;
if (!onlyIfAbsent) { //需要覆盖旧值
e.value = value;
++modCount;
}
break;
}
e = e.next;
} else { //找完整个HashEntry bucket链表都没有相等的元素,则插入
if (node != null) //若前面等待锁时,已经初始化了node
node.setNext(first); //添加到bucket链表头部
else //新建node
node = new HashEntry<K,V>(hash, key, value, first);
int c = count + 1;
if (c > threshold && tab.length < MAXIMUM_CAPACITY)
rehash(node); //扩容
else
setEntryAt(tab, index, node); //插入新HashEntry到table的index下标位置
++modCount;
count = c;
oldValue = null;
break;
}
}
} finally {
unlock(); //解锁该segment
}
return oldValue;
}
也可看看等锁过程scanAndLockForPut()方法:
private HashEntry<K,V> scanAndLockForPut(K key, int hash, V value) {
HashEntry<K,V> first = entryForHash(this, hash); //该hash值对应的bucket链表的第一个节点
HashEntry<K,V> e = first;
HashEntry<K,V> node = null;
int retries = -1; // negative while locating node
while (!tryLock()) { //未获取到锁继续尝试构建new node
HashEntry<K,V> f; // to recheck first below
if (retries < 0) {
if (e == null) { //第一个节点为null, 表示该bucket index未被占用
if (node == null) // 创建新节点
node = new HashEntry<K,V>(hash, key, value, null);
retries = 0;
} else if (key.equals(e.key))//若找到相等的元素,就不用再尝试了
retries = 0;
else //继续看下一个节点
e = e.next;
} else if (++retries > MAX_SCAN_RETRIES) { //尝试次数太多,就直接锁上,该值在cpu核数>1时为64次,否则为1次
lock();
break;
} else if ((retries & 1) == 0 &&
(f = entryForHash(this, hash)) != first) { //若node新建了或找到相等,但是这时有可能在等锁过程,其他线程修改了头节点(那个节点hash后也在相同的bucket index)或删除该头节点
e = first = f; // re-traverse if entry changed
retries = -1;
}
}
return node;
}
上面这个过程类似put里的过程,只是希望线程在被锁住了可以尽量提前做一些事情。
最后再来看看,扩容rehash的过程:
private void rehash(HashEntry<K,V> node) {
HashEntry<K,V>[] oldTable = table;
int oldCapacity = oldTable.length;
int newCapacity = oldCapacity << 1; //扩容为原来的2倍
threshold = (int)(newCapacity * loadFactor); //新的阈值
HashEntry<K,V>[] newTable =
(HashEntry<K,V>[]) new HashEntry[newCapacity];
int sizeMask = newCapacity - 1; // table掩码
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) //在该bucket上只有一个节点,则直接添加到新table里
newTable[idx] = e;
else { // 该bucket链表上不止一个节点,则保持整个链表重用
HashEntry<K,V> lastRun = e;
int lastIdx = idx;
for (HashEntry<K,V> last = next; //找到该bucket链上最后一个节点
last != null;
last = last.next) {
int k = last.hash & sizeMask;
if (k != lastIdx) {
lastIdx = k;
lastRun = last;
}
}
newTable[lastIdx] = lastRun; //赋值该bucketin最后一个节点
//依次克隆该bucket链表上的所有节点
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; //添加新的节点
node.setNext(newTable[nodeIndex]);
newTable[nodeIndex] = node;
table = newTable;
}
这个put操作就简略说了,继续看看get方法吧。
- get操作实现, 比较好明白:
public V get(Object key) {
Segment<K,V> s; // manually integrate access methods to reduce overhead
HashEntry<K,V>[] tab;
int h = hash(key.hashCode());//根据key的hashCode计算hash值
long u = (((h >>> segmentShift) & segmentMask) << SSHIFT) + SBASE; //得到其key所在segment下标
if ((s = (Segment<K,V>)UNSAFE.getObjectVolatile(segments, u)) != null &&
(tab = s.table) != null) {
for (HashEntry<K,V> e = (HashEntry<K,V>) UNSAFE.getObjectVolatile //获取该key对应segment.table中的第一个节点
(tab, ((long)(((tab.length - 1) & h)) << TSHIFT) + TBASE);
e != null; e = e.next) { //遍历bucket链表,比较,返回
K k;
if ((k = e.key) == key || (e.hash == h && key.equals(k)))
return e.value;
}
}
return null;
}
- remove操作实现:
public V remove(Object key) {
int hash = hash(key.hashCode()); //计算hash值
Segment<K,V> s = segmentForHash(hash); //定位segment
return s == null ? null : s.remove(key, hash, null);
}
private Segment<K,V> segmentForHash(int h) {
long u = (((h >>> segmentShift) & segmentMask) << SSHIFT) + SBASE;
return (Segment<K,V>) UNSAFE.getObjectVolatile(segments, u);
}
Segment中的remove方法,基本就是链表的删除操作:
final V remove(Object key, int hash, Object value) {
if (!tryLock()) //请求锁
scanAndLock(key, hash); //尝试获取锁
V oldValue = null;
try {
HashEntry<K,V>[] tab = table;
int index = (tab.length - 1) & hash; //根据hash计算元素所在table的索引
HashEntry<K,V> e = entryAt(tab, index); //获取该元素
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) //删除元素头节点
setEntryAt(tab, index, next);
else //将删除节点的前一个节点--->删除节点的下一个节点
pred.setNext(next);
++modCount;
--count;
oldValue = v;
}
break;
}
pred = e;
e = next;
}
} finally {
unlock();//解锁
}
return oldValue;
}
- 最后看看size操作实现,这个是有点麻烦的,因为很有可能很多线程都在添加或删除操作segments, 看看怎么统计size:
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) { //在对每个segment加锁前先尝试不加锁(假设没有线程写操作),默认尝试2次
for (int j = 0; j < segments.length; ++j)
ensureSegment(j).lock(); //加锁
}
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) { //说明尝试失败,要解锁
for (int j = 0; j < segments.length; ++j)
segmentAt(segments, j).unlock();
}
}
return overflow ? Integer.MAX_VALUE : size;
}
上面就分析了ConcurrentHashMap的一些基本操作,还是比较有意思的,可能你会看到这里面有很多UNSAFE相关的操作,这是非jdk核心库的一个类,闻其名,就不安全,但jdk里很多都会用,因为其操作的性能要比普通的操作高,可以了解相关文章,那么ConcurrentHashMap并发性能到底怎么样呢?做了一些简单的性能测试, ConcurrentHashMap和HashTable:
5个线程,插入100w对象,ConcurrentHashMap性能高于HashTable, 而且会随着线程数和数据量增加,性能差会更大。
不吝指正。