Java 线程 — ConcurrentHashMap

ConcurrentHashMap

ConcurrentHashMap 结构

采用了分段锁的方法提高COncurrentHashMap并发,一个map里面有一个Segment数组——即多个Segment,一个Segment有一个HashEntry数组——即多个HashEntry。每个Segment持有一个锁,在put的时候会给Segment上锁,但是get的时候没有锁

初始化

// initialCapacity:map初始化大小
// loadFactor:负载因子,当map中元素个数大于loadFactor*最大容量的时候进行refresh扩容
// concurrencyLevel:并发级别,因为这个类是采用分段锁的机制实现的,该值表示分段数,需要规整为2的n次方——为了按位与计算segment数组的索引
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;
    // 有可能传入的concurrencyLevel不是2的n次方,向上规整为2的n次方
    while (ssize < concurrencyLevel) {
    	// sshift记录左移的次数
        ++sshift;
        // 最终的segment个数——也就是并发级别
        ssize <<= 1;
    }
    // 参与定位segment散列
    this.segmentShift = 32 - sshift;
    // 参与定位segment散列
    this.segmentMask = ssize - 1;
    if (initialCapacity > MAXIMUM_CAPACITY)
        initialCapacity = MAXIMUM_CAPACITY;
    // c为每个segment的容量
    int c = initialCapacity / ssize;
    // 因为是整数除法,如果除不尽会去尾,加上1保证容量大于等于给定的值
    if (c * ssize < initialCapacity)
        ++c;
    int cap = MIN_SEGMENT_TABLE_CAPACITY;
    while (cap < c)
        cap <<= 1;
    // create segments and segments[0]
    // 新建一个segment作为segment数组的第一个元素
    // 这里没有初始化所有的segment,采用lazy-init的方式按需初始化
    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;
}

put操作

public V put(K key, V value) {
    Segment<K,V> s;
    if (value == null)
        throw new NullPointerException();
    int hash = hash(key);
    // 定位segment,因为segment是ssize个,所以定位segment就是用hash值对ssize取模,使用位运算就是
    // 将hash右移32-sshift位,因为hash是32位,ssize是sshift位
    // 将得到的值和segment与运算,segment是ssize位全1二进制大小
    int j = (hash >>> segmentShift) & segmentMask;
    if ((s = (Segment<K,V>)UNSAFE.getObject          // nonvolatile; recheck
         (segments, (j << SSHIFT) + SBASE)) == null) //  in ensureSegment
        // 因为是按需初始化,可能定位到的segment尚未初始化
        s = ensureSegment(j);
    return s.put(key, hash, value, false);
}

final V put(K key, int hash, V value, boolean onlyIfAbsent) {
	// 获取锁,如果失败,会进行指定次数的尝试,超过指定次数以后会调用AbstractQueuedSynchronizer的acquire方法再次尝试获取,如果获取不到则阻塞
    HashEntry<K,V> node = tryLock() ? null :
        scanAndLockForPut(key, hash, value);
    V oldValue;
    try {
        HashEntry<K,V>[] tab = table;
        // 与运算得到在hashEntry数组中中的位置
        int index = (tab.length - 1) & hash;
        HashEntry<K,V> first = entryAt(tab, index);
        for (HashEntry<K,V> e = first;;) {
            if (e != null) {
            	// 如果数组中该位置原来有值
                K k;
                // 如果存在相同的key则替换旧值
                if ((k = e.key) == key ||
                    (e.hash == hash && key.equals(k))) {
                    oldValue = e.value;
                    if (!onlyIfAbsent) {
                        e.value = value;
                        ++modCount;
                    }
                    break;
                }
                // 移到下一个元素
                e = e.next;
            }
            else {
            	// 链表查找到最后发现不包含这个key
                if (node != null)
                	// 如果scanAndLockForPut返回的node非空
                    node.setNext(first);
                else
                    node = new HashEntry<K,V>(hash, key, value, first);
                int c = count + 1;
                if (c > threshold && tab.length < MAXIMUM_CAPACITY)
                	// 如果当前元素数大于threshold阈值则扩容
                    rehash(node);
                else
                    setEntryAt(tab, index, node);
                ++modCount;
                count = c;
                oldValue = null;
                break;
            }
        }
    } finally {
        unlock();
    }
    return oldValue;
}

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()) {
    	// 自旋过程中遍历链表是为了缓存预热,减少hash表经常出现的cache miss
        // 原代码注释
        // we might as well help warm up the associated code and accesses as well
        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) {
        	// 超过次数之后阻塞
            lock();
            // 获得锁之后跳出循环
            break;
        }
        // 当retries个位是0并且tabel这个位置的头改变了(和之前的first不一致了,说明其他线程修改了)
        else if ((retries & 1) == 0 &&
                 (f = entryForHash(this, hash)) != first) {
            // 如果链表头改变则重新开始查找
            e = first = f; // re-traverse if entry changed
            retries = -1;
        }
    }
    return node;
}

hash算法

private int hash(Object k) {
	// 每次运行产生的随机种子
    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);
}

get方法

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) {
        // 因为Segment的table是votile,所以在读的时候不需要上锁
        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;
}

参考

http://nfhy.wang/Java-ConcurrenceHashMap-Segment/
Java并发编程的艺术

posted @ 2016-11-15 00:17  lacker  阅读(1335)  评论(0编辑  收藏  举报