6785442: ConcurrentLinkedQueue.remove() and poll() can both remove the same element
6493942: ConcurrentLinkedQueue.remove sometimes very slow
Summary: new algorithm for handling concurrent linked lists
Reviewed-by: martin
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Sun designates this
* particular file as subject to the "Classpath" exception as provided
* by Sun in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
* CA 95054 USA or visit www.sun.com if you need additional information or
* have any questions.
*/
/*
* This file is available under and governed by the GNU General Public
* License version 2 only, as published by the Free Software Foundation.
* However, the following notice accompanied the original version of this
* file:
*
* Written by Doug Lea with assistance from members of JCP JSR-166
* Expert Group and released to the public domain, as explained at
* http://creativecommons.org/licenses/publicdomain
*/
package java.util.concurrent;
import java.util.AbstractQueue;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Iterator;
import java.util.NoSuchElementException;
import java.util.Queue;
/**
* An unbounded thread-safe {@linkplain Queue queue} based on linked nodes.
* This queue orders elements FIFO (first-in-first-out).
* The <em>head</em> of the queue is that element that has been on the
* queue the longest time.
* The <em>tail</em> of the queue is that element that has been on the
* queue the shortest time. New elements
* are inserted at the tail of the queue, and the queue retrieval
* operations obtain elements at the head of the queue.
* A {@code ConcurrentLinkedQueue} is an appropriate choice when
* many threads will share access to a common collection.
* This queue does not permit {@code null} elements.
*
* <p>This implementation employs an efficient "wait-free"
* algorithm based on one described in <a
* href="http://www.cs.rochester.edu/u/michael/PODC96.html"> Simple,
* Fast, and Practical Non-Blocking and Blocking Concurrent Queue
* Algorithms</a> by Maged M. Michael and Michael L. Scott.
*
* <p>Beware that, unlike in most collections, the {@code size} method
* is <em>NOT</em> a constant-time operation. Because of the
* asynchronous nature of these queues, determining the current number
* of elements requires a traversal of the elements.
*
* <p>This class and its iterator implement all of the
* <em>optional</em> methods of the {@link Collection} and {@link
* Iterator} interfaces.
*
* <p>Memory consistency effects: As with other concurrent
* collections, actions in a thread prior to placing an object into a
* {@code ConcurrentLinkedQueue}
* <a href="package-summary.html#MemoryVisibility"><i>happen-before</i></a>
* actions subsequent to the access or removal of that element from
* the {@code ConcurrentLinkedQueue} in another thread.
*
* <p>This class is a member of the
* <a href="{@docRoot}/../technotes/guides/collections/index.html">
* Java Collections Framework</a>.
*
* @since 1.5
* @author Doug Lea
* @param <E> the type of elements held in this collection
*
*/
public class ConcurrentLinkedQueue<E> extends AbstractQueue<E>
implements Queue<E>, java.io.Serializable {
private static final long serialVersionUID = 196745693267521676L;
/*
* This is a modification of the Michael & Scott algorithm,
* adapted for a garbage-collected environment, with support for
* interior node deletion (to support remove(Object)). For
* explanation, read the paper.
*
* Note that like most non-blocking algorithms in this package,
* this implementation relies on the fact that in garbage
* collected systems, there is no possibility of ABA problems due
* to recycled nodes, so there is no need to use "counted
* pointers" or related techniques seen in versions used in
* non-GC'ed settings.
*
* The fundamental invariants are:
* - There is exactly one (last) Node with a null next reference,
* which is CASed when enqueueing. This last Node can be
* reached in O(1) time from tail, but tail is merely an
* optimization - it can always be reached in O(N) time from
* head as well.
* - The elements contained in the queue are the non-null items in
* Nodes that are reachable from head. CASing the item
* reference of a Node to null atomically removes it from the
* queue. Reachability of all elements from head must remain
* true even in the case of concurrent modifications that cause
* head to advance. A dequeued Node may remain in use
* indefinitely due to creation of an Iterator or simply a
* poll() that has lost its time slice.
*
* The above might appear to imply that all Nodes are GC-reachable
* from a predecessor dequeued Node. That would cause two problems:
* - allow a rogue Iterator to cause unbounded memory retention
* - cause cross-generational linking of old Nodes to new Nodes if
* a Node was tenured while live, which generational GCs have a
* hard time dealing with, causing repeated major collections.
* However, only non-deleted Nodes need to be reachable from
* dequeued Nodes, and reachability does not necessarily have to
* be of the kind understood by the GC. We use the trick of
* linking a Node that has just been dequeued to itself. Such a
* self-link implicitly means to advance to head.
*
* Both head and tail are permitted to lag. In fact, failing to
* update them every time one could is a significant optimization
* (fewer CASes). This is controlled by local "hops" variables
* that only trigger helping-CASes after experiencing multiple
* lags.
*
* Since head and tail are updated concurrently and independently,
* it is possible for tail to lag behind head (why not)?
*
* CASing a Node's item reference to null atomically removes the
* element from the queue. Iterators skip over Nodes with null
* items. Prior implementations of this class had a race between
* poll() and remove(Object) where the same element would appear
* to be successfully removed by two concurrent operations. The
* method remove(Object) also lazily unlinks deleted Nodes, but
* this is merely an optimization.
*
* When constructing a Node (before enqueuing it) we avoid paying
* for a volatile write to item by using lazySet instead of a
* normal write. This allows the cost of enqueue to be
* "one-and-a-half" CASes.
*
* Both head and tail may or may not point to a Node with a
* non-null item. If the queue is empty, all items must of course
* be null. Upon creation, both head and tail refer to a dummy
* Node with null item. Both head and tail are only updated using
* CAS, so they never regress, although again this is merely an
* optimization.
*/
private static class Node<E> {
private volatile E item;
private volatile Node<E> next;
Node(E item) {
// Piggyback on imminent casNext()
lazySetItem(item);
}
E getItem() {
return item;
}
boolean casItem(E cmp, E val) {
return UNSAFE.compareAndSwapObject(this, itemOffset, cmp, val);
}
void setItem(E val) {
item = val;
}
void lazySetItem(E val) {
UNSAFE.putOrderedObject(this, itemOffset, val);
}
void lazySetNext(Node<E> val) {
UNSAFE.putOrderedObject(this, nextOffset, val);
}
Node<E> getNext() {
return next;
}
boolean casNext(Node<E> cmp, Node<E> val) {
return UNSAFE.compareAndSwapObject(this, nextOffset, cmp, val);
}
// Unsafe mechanics
private static final sun.misc.Unsafe UNSAFE =
sun.misc.Unsafe.getUnsafe();
private static final long nextOffset =
objectFieldOffset(UNSAFE, "next", Node.class);
private static final long itemOffset =
objectFieldOffset(UNSAFE, "item", Node.class);
}
/**
* A node from which the first live (non-deleted) node (if any)
* can be reached in O(1) time.
* Invariants:
* - all live nodes are reachable from head via succ()
* - head != null
* - (tmp = head).next != tmp || tmp != head
* Non-invariants:
* - head.item may or may not be null.
* - it is permitted for tail to lag behind head, that is, for tail
* to not be reachable from head!
*/
private transient volatile Node<E> head = new Node<E>(null);
/**
* A node from which the last node on list (that is, the unique
* node with node.next == null) can be reached in O(1) time.
* Invariants:
* - the last node is always reachable from tail via succ()
* - tail != null
* Non-invariants:
* - tail.item may or may not be null.
* - it is permitted for tail to lag behind head, that is, for tail
* to not be reachable from head!
* - tail.next may or may not be self-pointing to tail.
*/
private transient volatile Node<E> tail = head;
/**
* Creates a {@code ConcurrentLinkedQueue} that is initially empty.
*/
public ConcurrentLinkedQueue() {}
/**
* Creates a {@code ConcurrentLinkedQueue}
* initially containing the elements of the given collection,
* added in traversal order of the collection's iterator.
* @param c the collection of elements to initially contain
* @throws NullPointerException if the specified collection or any
* of its elements are null
*/
public ConcurrentLinkedQueue(Collection<? extends E> c) {
for (Iterator<? extends E> it = c.iterator(); it.hasNext();)
add(it.next());
}
// Have to override just to update the javadoc
/**
* Inserts the specified element at the tail of this queue.
*
* @return {@code true} (as specified by {@link Collection#add})
* @throws NullPointerException if the specified element is null
*/
public boolean add(E e) {
return offer(e);
}
/**
* We don't bother to update head or tail pointers if fewer than
* HOPS links from "true" location. We assume that volatile
* writes are significantly more expensive than volatile reads.
*/
private static final int HOPS = 1;
/**
* Try to CAS head to p. If successful, repoint old head to itself
* as sentinel for succ(), below.
*/
final void updateHead(Node<E> h, Node<E> p) {
if (h != p && casHead(h, p))
h.lazySetNext(h);
}
/**
* Returns the successor of p, or the head node if p.next has been
* linked to self, which will only be true if traversing with a
* stale pointer that is now off the list.
*/
final Node<E> succ(Node<E> p) {
Node<E> next = p.getNext();
return (p == next) ? head : next;
}
/**
* Inserts the specified element at the tail of this queue.
*
* @return {@code true} (as specified by {@link Queue#offer})
* @throws NullPointerException if the specified element is null
*/
public boolean offer(E e) {
if (e == null) throw new NullPointerException();
Node<E> n = new Node<E>(e);
retry:
for (;;) {
Node<E> t = tail;
Node<E> p = t;
for (int hops = 0; ; hops++) {
Node<E> next = succ(p);
if (next != null) {
if (hops > HOPS && t != tail)
continue retry;
p = next;
} else if (p.casNext(null, n)) {
if (hops >= HOPS)
casTail(t, n); // Failure is OK.
return true;
} else {
p = succ(p);
}
}
}
}
public E poll() {
Node<E> h = head;
Node<E> p = h;
for (int hops = 0; ; hops++) {
E item = p.getItem();
if (item != null && p.casItem(item, null)) {
if (hops >= HOPS) {
Node<E> q = p.getNext();
updateHead(h, (q != null) ? q : p);
}
return item;
}
Node<E> next = succ(p);
if (next == null) {
updateHead(h, p);
break;
}
p = next;
}
return null;
}
public E peek() {
Node<E> h = head;
Node<E> p = h;
E item;
for (;;) {
item = p.getItem();
if (item != null)
break;
Node<E> next = succ(p);
if (next == null) {
break;
}
p = next;
}
updateHead(h, p);
return item;
}
/**
* Returns the first live (non-deleted) node on list, or null if none.
* This is yet another variant of poll/peek; here returning the
* first node, not element. We could make peek() a wrapper around
* first(), but that would cost an extra volatile read of item,
* and the need to add a retry loop to deal with the possibility
* of losing a race to a concurrent poll().
*/
Node<E> first() {
Node<E> h = head;
Node<E> p = h;
Node<E> result;
for (;;) {
E item = p.getItem();
if (item != null) {
result = p;
break;
}
Node<E> next = succ(p);
if (next == null) {
result = null;
break;
}
p = next;
}
updateHead(h, p);
return result;
}
/**
* Returns {@code true} if this queue contains no elements.
*
* @return {@code true} if this queue contains no elements
*/
public boolean isEmpty() {
return first() == null;
}
/**
* Returns the number of elements in this queue. If this queue
* contains more than {@code Integer.MAX_VALUE} elements, returns
* {@code Integer.MAX_VALUE}.
*
* <p>Beware that, unlike in most collections, this method is
* <em>NOT</em> a constant-time operation. Because of the
* asynchronous nature of these queues, determining the current
* number of elements requires an O(n) traversal.
*
* @return the number of elements in this queue
*/
public int size() {
int count = 0;
for (Node<E> p = first(); p != null; p = succ(p)) {
if (p.getItem() != null) {
// Collections.size() spec says to max out
if (++count == Integer.MAX_VALUE)
break;
}
}
return count;
}
/**
* Returns {@code true} if this queue contains the specified element.
* More formally, returns {@code true} if and only if this queue contains
* at least one element {@code e} such that {@code o.equals(e)}.
*
* @param o object to be checked for containment in this queue
* @return {@code true} if this queue contains the specified element
*/
public boolean contains(Object o) {
if (o == null) return false;
for (Node<E> p = first(); p != null; p = succ(p)) {
E item = p.getItem();
if (item != null &&
o.equals(item))
return true;
}
return false;
}
/**
* Removes a single instance of the specified element from this queue,
* if it is present. More formally, removes an element {@code e} such
* that {@code o.equals(e)}, if this queue contains one or more such
* elements.
* Returns {@code true} if this queue contained the specified element
* (or equivalently, if this queue changed as a result of the call).
*
* @param o element to be removed from this queue, if present
* @return {@code true} if this queue changed as a result of the call
*/
public boolean remove(Object o) {
if (o == null) return false;
Node<E> pred = null;
for (Node<E> p = first(); p != null; p = succ(p)) {
E item = p.getItem();
if (item != null &&
o.equals(item) &&
p.casItem(item, null)) {
Node<E> next = succ(p);
if (pred != null && next != null)
pred.casNext(p, next);
return true;
}
pred = p;
}
return false;
}
/**
* Returns an array containing all of the elements in this queue, in
* proper sequence.
*
* <p>The returned array will be "safe" in that no references to it are
* maintained by this queue. (In other words, this method must allocate
* a new array). The caller is thus free to modify the returned array.
*
* <p>This method acts as bridge between array-based and collection-based
* APIs.
*
* @return an array containing all of the elements in this queue
*/
public Object[] toArray() {
// Use ArrayList to deal with resizing.
ArrayList<E> al = new ArrayList<E>();
for (Node<E> p = first(); p != null; p = succ(p)) {
E item = p.getItem();
if (item != null)
al.add(item);
}
return al.toArray();
}
/**
* Returns an array containing all of the elements in this queue, in
* proper sequence; the runtime type of the returned array is that of
* the specified array. If the queue fits in the specified array, it
* is returned therein. Otherwise, a new array is allocated with the
* runtime type of the specified array and the size of this queue.
*
* <p>If this queue fits in the specified array with room to spare
* (i.e., the array has more elements than this queue), the element in
* the array immediately following the end of the queue is set to
* {@code null}.
*
* <p>Like the {@link #toArray()} method, this method acts as bridge between
* array-based and collection-based APIs. Further, this method allows
* precise control over the runtime type of the output array, and may,
* under certain circumstances, be used to save allocation costs.
*
* <p>Suppose {@code x} is a queue known to contain only strings.
* The following code can be used to dump the queue into a newly
* allocated array of {@code String}:
*
* <pre>
* String[] y = x.toArray(new String[0]);</pre>
*
* Note that {@code toArray(new Object[0])} is identical in function to
* {@code toArray()}.
*
* @param a the array into which the elements of the queue are to
* be stored, if it is big enough; otherwise, a new array of the
* same runtime type is allocated for this purpose
* @return an array containing all of the elements in this queue
* @throws ArrayStoreException if the runtime type of the specified array
* is not a supertype of the runtime type of every element in
* this queue
* @throws NullPointerException if the specified array is null
*/
@SuppressWarnings("unchecked")
public <T> T[] toArray(T[] a) {
// try to use sent-in array
int k = 0;
Node<E> p;
for (p = first(); p != null && k < a.length; p = succ(p)) {
E item = p.getItem();
if (item != null)
a[k++] = (T)item;
}
if (p == null) {
if (k < a.length)
a[k] = null;
return a;
}
// If won't fit, use ArrayList version
ArrayList<E> al = new ArrayList<E>();
for (Node<E> q = first(); q != null; q = succ(q)) {
E item = q.getItem();
if (item != null)
al.add(item);
}
return al.toArray(a);
}
/**
* Returns an iterator over the elements in this queue in proper sequence.
* The returned iterator is a "weakly consistent" iterator that
* will never throw {@link ConcurrentModificationException},
* and guarantees to traverse elements as they existed upon
* construction of the iterator, and may (but is not guaranteed to)
* reflect any modifications subsequent to construction.
*
* @return an iterator over the elements in this queue in proper sequence
*/
public Iterator<E> iterator() {
return new Itr();
}
private class Itr implements Iterator<E> {
/**
* Next node to return item for.
*/
private Node<E> nextNode;
/**
* nextItem holds on to item fields because once we claim
* that an element exists in hasNext(), we must return it in
* the following next() call even if it was in the process of
* being removed when hasNext() was called.
*/
private E nextItem;
/**
* Node of the last returned item, to support remove.
*/
private Node<E> lastRet;
Itr() {
advance();
}
/**
* Moves to next valid node and returns item to return for
* next(), or null if no such.
*/
private E advance() {
lastRet = nextNode;
E x = nextItem;
Node<E> pred, p;
if (nextNode == null) {
p = first();
pred = null;
} else {
pred = nextNode;
p = succ(nextNode);
}
for (;;) {
if (p == null) {
nextNode = null;
nextItem = null;
return x;
}
E item = p.getItem();
if (item != null) {
nextNode = p;
nextItem = item;
return x;
} else {
// skip over nulls
Node<E> next = succ(p);
if (pred != null && next != null)
pred.casNext(p, next);
p = next;
}
}
}
public boolean hasNext() {
return nextNode != null;
}
public E next() {
if (nextNode == null) throw new NoSuchElementException();
return advance();
}
public void remove() {
Node<E> l = lastRet;
if (l == null) throw new IllegalStateException();
// rely on a future traversal to relink.
l.setItem(null);
lastRet = null;
}
}
/**
* Save the state to a stream (that is, serialize it).
*
* @serialData All of the elements (each an {@code E}) in
* the proper order, followed by a null
* @param s the stream
*/
private void writeObject(java.io.ObjectOutputStream s)
throws java.io.IOException {
// Write out any hidden stuff
s.defaultWriteObject();
// Write out all elements in the proper order.
for (Node<E> p = first(); p != null; p = succ(p)) {
Object item = p.getItem();
if (item != null)
s.writeObject(item);
}
// Use trailing null as sentinel
s.writeObject(null);
}
/**
* Reconstitute the Queue instance from a stream (that is,
* deserialize it).
* @param s the stream
*/
private void readObject(java.io.ObjectInputStream s)
throws java.io.IOException, ClassNotFoundException {
// Read in capacity, and any hidden stuff
s.defaultReadObject();
head = new Node<E>(null);
tail = head;
// Read in all elements and place in queue
for (;;) {
@SuppressWarnings("unchecked")
E item = (E)s.readObject();
if (item == null)
break;
else
offer(item);
}
}
// Unsafe mechanics
private static final sun.misc.Unsafe UNSAFE = sun.misc.Unsafe.getUnsafe();
private static final long headOffset =
objectFieldOffset(UNSAFE, "head", ConcurrentLinkedQueue.class);
private static final long tailOffset =
objectFieldOffset(UNSAFE, "tail", ConcurrentLinkedQueue.class);
private boolean casTail(Node<E> cmp, Node<E> val) {
return UNSAFE.compareAndSwapObject(this, tailOffset, cmp, val);
}
private boolean casHead(Node<E> cmp, Node<E> val) {
return UNSAFE.compareAndSwapObject(this, headOffset, cmp, val);
}
private void lazySetHead(Node<E> val) {
UNSAFE.putOrderedObject(this, headOffset, val);
}
static long objectFieldOffset(sun.misc.Unsafe UNSAFE,
String field, Class<?> klazz) {
try {
return UNSAFE.objectFieldOffset(klazz.getDeclaredField(field));
} catch (NoSuchFieldException e) {
// Convert Exception to corresponding Error
NoSuchFieldError error = new NoSuchFieldError(field);
error.initCause(e);
throw error;
}
}
}