ThreadLocal内存溢出问题

转载自：http://liwx2000.iteye.com/blog/1774169

最近碰到一个使用ThreadLocal时因为未调用remove()而险些引起内存溢出的问题，所以看了下ThreadLocal的源码，结合线程池原理做一个简单的分析，确认是否最终会导致内存溢出。

既然是因为没调用remove()方法而险些导致内存溢出，那首先看下remove()方法中做了什么。

Java代码

public void remove() {
ThreadLocalMap m = getMap(Thread.currentThread());
if (m != null)
m.remove(this);
}

从remove()的实现来看就是一个map.remove()的调用。既然不调用map.remove()可能会引起内存溢出的话，就需要看看ThreadLocalMap的实现了。

Java代码

/**
* ThreadLocalMap is a customized hash map suitable only for
* maintaining thread local values. No operations are exported
* outside of the ThreadLocal class. The class is package private to
* allow declaration of fields in class Thread. To help deal with
* very large and long-lived usages, the hash table entries use
* WeakReferences for keys. However, since reference queues are not
* used, stale entries are guaranteed to be removed only when
* the table starts running out of space.
*/
static class ThreadLocalMap {
/**
* The entries in this hash map extend WeakReference, using
* its main ref field as the key (which is always a
* ThreadLocal object). Note that null keys (i.e. entry.get()
* == null) mean that the key is no longer referenced, so the
* entry can be expunged from table. Such entries are referred to
* as "stale entries" in the code that follows.
*/
static class Entry extends WeakReference<ThreadLocal> {
/** The value associated with this ThreadLocal. */
Object value;
Entry(ThreadLocal k, Object v) {
super(k);
value = v;
}
}
/**
* The initial capacity -- MUST be a power of two.
*/
private static final int INITIAL_CAPACITY = 16;
/**
* The table, resized as necessary.
* table.length MUST always be a power of two.
*/
private Entry[] table;
/**
* The number of entries in the table.
*/
private int size = 0;
/**
* The next size value at which to resize.
*/
private int threshold; // Default to 0
/**
* Set the resize threshold to maintain at worst a 2/3 load factor.
*/
private void setThreshold(int len) {
threshold = len * 2 / 3;
}
/**
* Increment i modulo len.
*/
private static int nextIndex(int i, int len) {
return ((i + 1 < len) ? i + 1 : 0);
}
/**
* Decrement i modulo len.
*/
private static int prevIndex(int i, int len) {
return ((i - 1 >= 0) ? i - 1 : len - 1);
}
/**
* Construct a new map initially containing (firstKey, firstValue).
* ThreadLocalMaps are constructed lazily, so we only create
* one when we have at least one entry to put in it.
*/
ThreadLocalMap(ThreadLocal firstKey, Object firstValue) {
table = new Entry[INITIAL_CAPACITY];
int i = firstKey.threadLocalHashCode & (INITIAL_CAPACITY - 1);
table[i] = new Entry(firstKey, firstValue);
size = 1;
setThreshold(INITIAL_CAPACITY);
}
/**
* Construct a new map including all Inheritable ThreadLocals
* from given parent map. Called only by createInheritedMap.
*
* @param parentMap the map associated with parent thread.
*/
private ThreadLocalMap(ThreadLocalMap parentMap) {
Entry[] parentTable = parentMap.table;
int len = parentTable.length;
setThreshold(len);
table = new Entry[len];
for (int j = 0; j < len; j++) {
Entry e = parentTable[j];
if (e != null) {
ThreadLocal key = e.get();
if (key != null) {
Object value = key.childValue(e.value);
Entry c = new Entry(key, value);
int h = key.threadLocalHashCode & (len - 1);
while (table[h] != null)
h = nextIndex(h, len);
table[h] = c;
size++;
}
}
}
}
/**
* Get the entry associated with key. This method
* itself handles only the fast path: a direct hit of existing
* key. It otherwise relays to getEntryAfterMiss. This is
* designed to maximize performance for direct hits, in part
* by making this method readily inlinable.
*
* @param key the thread local object
* @return the entry associated with key, or null if no such
*/
private Entry getEntry(ThreadLocal key) {
int i = key.threadLocalHashCode & (table.length - 1);
Entry e = table[i];
if (e != null && e.get() == key)
return e;
else
return getEntryAfterMiss(key, i, e);
}
/**
* Version of getEntry method for use when key is not found in
* its direct hash slot.
*
* @param key the thread local object
* @param i the table index for key's hash code
* @param e the entry at table[i]
* @return the entry associated with key, or null if no such
*/
private Entry getEntryAfterMiss(ThreadLocal key, int i, Entry e) {
Entry[] tab = table;
int len = tab.length;
while (e != null) {
ThreadLocal k = e.get();
if (k == key)
return e;
if (k == null)
expungeStaleEntry(i);
else
i = nextIndex(i, len);
e = tab[i];
}
return null;
}
/**
* Set the value associated with key.
*
* @param key the thread local object
* @param value the value to be set
*/
private void set(ThreadLocal key, Object value) {
// We don't use a fast path as with get() because it is at
// least as common to use set() to create new entries as
// it is to replace existing ones, in which case, a fast
// path would fail more often than not.
Entry[] tab = table;
int len = tab.length;
int i = key.threadLocalHashCode & (len-1);
for (Entry e = tab[i];
e != null;
e = tab[i = nextIndex(i, len)]) {
ThreadLocal k = e.get();
if (k == key) {
e.value = value;
return;
}
if (k == null) {
replaceStaleEntry(key, value, i);
return;
}
}
tab[i] = new Entry(key, value);
int sz = ++size;
if (!cleanSomeSlots(i, sz) && sz >= threshold)
rehash();
}
/**
* Remove the entry for key.
*/
private void remove(ThreadLocal key) {
Entry[] tab = table;
int len = tab.length;
int i = key.threadLocalHashCode & (len-1);
for (Entry e = tab[i];
e != null;
e = tab[i = nextIndex(i, len)]) {
if (e.get() == key) {
e.clear();
expungeStaleEntry(i);
return;
}
}
}
/**
* Replace a stale entry encountered during a set operation
* with an entry for the specified key. The value passed in
* the value parameter is stored in the entry, whether or not
* an entry already exists for the specified key.
*
* As a side effect, this method expunges all stale entries in the
* "run" containing the stale entry. (A run is a sequence of entries
* between two null slots.)
*
* @param key the key
* @param value the value to be associated with key
* @param staleSlot index of the first stale entry encountered while
* searching for key.
*/
private void replaceStaleEntry(ThreadLocal key, Object value,
int staleSlot) {
Entry[] tab = table;
int len = tab.length;
Entry e;
// Back up to check for prior stale entry in current run.
// We clean out whole runs at a time to avoid continual
// incremental rehashing due to garbage collector freeing
// up refs in bunches (i.e., whenever the collector runs).
int slotToExpunge = staleSlot;
for (int i = prevIndex(staleSlot, len);
(e = tab[i]) != null;
i = prevIndex(i, len))
if (e.get() == null)
slotToExpunge = i;
// Find either the key or trailing null slot of run, whichever
// occurs first
for (int i = nextIndex(staleSlot, len);
(e = tab[i]) != null;
i = nextIndex(i, len)) {
ThreadLocal k = e.get();
// If we find key, then we need to swap it
// with the stale entry to maintain hash table order.
// The newly stale slot, or any other stale slot
// encountered above it, can then be sent to expungeStaleEntry
// to remove or rehash all of the other entries in run.
if (k == key) {
e.value = value;
tab[i] = tab[staleSlot];
tab[staleSlot] = e;
// Start expunge at preceding stale entry if it exists
if (slotToExpunge == staleSlot)
slotToExpunge = i;
cleanSomeSlots(expungeStaleEntry(slotToExpunge), len);
return;
}
// If we didn't find stale entry on backward scan, the
// first stale entry seen while scanning for key is the
// first still present in the run.
if (k == null && slotToExpunge == staleSlot)
slotToExpunge = i;
}
// If key not found, put new entry in stale slot
tab[staleSlot].value = null;
tab[staleSlot] = new Entry(key, value);
// If there are any other stale entries in run, expunge them
if (slotToExpunge != staleSlot)
cleanSomeSlots(expungeStaleEntry(slotToExpunge), len);
}
/**
* Expunge a stale entry by rehashing any possibly colliding entries
* lying between staleSlot and the next null slot. This also expunges
* any other stale entries encountered before the trailing null. See
* Knuth, Section 6.4
*
* @param staleSlot index of slot known to have null key
* @return the index of the next null slot after staleSlot
* (all between staleSlot and this slot will have been checked
* for expunging).
*/
private int expungeStaleEntry(int staleSlot) {
Entry[] tab = table;
int len = tab.length;
// expunge entry at staleSlot
tab[staleSlot].value = null;
tab[staleSlot] = null;
size--;
// Rehash until we encounter null
Entry e;
int i;
for (i = nextIndex(staleSlot, len);
(e = tab[i]) != null;
i = nextIndex(i, len)) {
ThreadLocal k = e.get();
if (k == null) {
e.value = null;
tab[i] = null;
size--;
} else {
int h = k.threadLocalHashCode & (len - 1);
if (h != i) {
tab[i] = null;
// Unlike Knuth 6.4 Algorithm R, we must scan until
// null because multiple entries could have been stale.
while (tab[h] != null)
h = nextIndex(h, len);
tab[h] = e;
}
}
}
return i;
}
/**
* Heuristically scan some cells looking for stale entries.
* This is invoked when either a new element is added, or
* another stale one has been expunged. It performs a
* logarithmic number of scans, as a balance between no
* scanning (fast but retains garbage) and a number of scans
* proportional to number of elements, that would find all
* garbage but would cause some insertions to take O(n) time.
*
* @param i a position known NOT to hold a stale entry. The
* scan starts at the element after i.
*
* @param n scan control: <tt>log2(n)</tt> cells are scanned,
* unless a stale entry is found, in which case
* <tt>log2(table.length)-1</tt> additional cells are scanned.
* When called from insertions, this parameter is the number
* of elements, but when from replaceStaleEntry, it is the
* table length. (Note: all this could be changed to be either
* more or less aggressive by weighting n instead of just
* using straight log n. But this version is simple, fast, and
* seems to work well.)
*
* @return true if any stale entries have been removed.
*/
private boolean cleanSomeSlots(int i, int n) {
boolean removed = false;
Entry[] tab = table;
int len = tab.length;
do {
i = nextIndex(i, len);
Entry e = tab[i];
if (e != null && e.get() == null) {
n = len;
removed = true;
i = expungeStaleEntry(i);
}
} while ( (n >>>= 1) != 0);
return removed;
}
/**
* Re-pack and/or re-size the table. First scan the entire
* table removing stale entries. If this doesn't sufficiently
* shrink the size of the table, double the table size.
*/
private void rehash() {
expungeStaleEntries();
// Use lower threshold for doubling to avoid hysteresis
if (size >= threshold - threshold / 4)
resize();
}
/**
* Double the capacity of the table.
*/
private void resize() {
Entry[] oldTab = table;
int oldLen = oldTab.length;
int newLen = oldLen * 2;
Entry[] newTab = new Entry[newLen];
int count = 0;
for (int j = 0; j < oldLen; ++j) {
Entry e = oldTab[j];
if (e != null) {
ThreadLocal k = e.get();
if (k == null) {
e.value = null; // Help the GC
} else {
int h = k.threadLocalHashCode & (newLen - 1);
while (newTab[h] != null)
h = nextIndex(h, newLen);
newTab[h] = e;
count++;
}
}
}
setThreshold(newLen);
size = count;
table = newTab;
}
/**
* Expunge all stale entries in the table.
*/
private void expungeStaleEntries() {
Entry[] tab = table;
int len = tab.length;
for (int j = 0; j < len; j++) {
Entry e = tab[j];
if (e != null && e.get() == null)
expungeStaleEntry(j);
}
}
}

首先从声明上来看，ThreadLocalMap并不是一个java.util.Map接口的实现，但是从Entry的实现和整个ThreadLocalMap的实现来看却实现了一个Map的功能，并且从具体的方法的实现上来看，整个ThreadLocalMap实现了一个HashMap的功能，对比HashMap的实现就能看出。

但是，值得注意的是ThreadLocalMap并没有put(K key, V value)方法，而是set(ThreadLocal key, Object value)，从这里可以看出，ThreadLocalMap并不是想象那样以Thread为key，而是以ThreadLocal为key。

了解了ThreadLocalMap的实现，也知道ThreadLocal.remove()其实就是ThreadLocalMap.remove()，那么再看看ThreadLocal的set(T value)方法，看看value是如何存储的。

Java代码

public void set(T value) {
Thread t = Thread.currentThread();
ThreadLocalMap map = getMap(t);
if (map != null)
map.set(this, value);
else
createMap(t, value);
}
ThreadLocalMap getMap(Thread t) {
return t.threadLocals;
}
void createMap(Thread t, T firstValue) {
t.threadLocals = new ThreadLocalMap(this, firstValue);
}

可以看到，set(T value)方法为每个Thread对象都创建了一个ThreadLocalMap，并且将value放入ThreadLocalMap中，ThreadLocalMap作为Thread对象的成员变量保存。那么可以用下图来表示ThreadLocal在存储value时的关系。

所以当ThreadLocal作为单例时，每个Thread对应的ThreadLocalMap中只会有一个键值对。那么如果不调用remove()会怎么样呢？

假设一种场景，使用线程池，线程池中有200个线程，并且这些线程都不会释放，ThreadLocal做单例使用。那么最多也就会产生200个ThreadLocalMap，而每个ThreadLocalMap中只有一个键值对，那最多也就是200个键值对存在。

但是线程池并不是固定一个线程数不改变，下面贴一段tomcat的线程池配置

Java代码

<Connector executor="tomcatThreadPool"
port="8080" protocol="HTTP/1.1"
connectionTimeout="60000"
keepAliveTimeout="30000"
minProcessors="5"
maxProcessors="75"
maxKeepAliveRequests="150"
redirectPort="8443" URIEncoding="UTF-8" acceptCount="1000" disableUploadTimeout="true"/>

可以看到线程池其实有线程最小值和最大值的，并且有超时时间，所以当线程空闲时间超时后，线程会被销毁。那么当线程销毁时，线程所持有的ThreadLocalMap也会失去引用，并且由于ThreadLocalMap中的Entry是WeakReference，所以当YGC时，被销毁的Thread所对应的value也会被回收掉，所以即使不调用remove()方法，也不会引起内存溢出。

ThreadLocal内存溢出问题

猜你喜欢