1 |
768 |
jeremybenn |
/*
|
2 |
|
|
* Written by Doug Lea, Bill Scherer, and Michael Scott with
|
3 |
|
|
* assistance from members of JCP JSR-166 Expert Group and released to
|
4 |
|
|
* the public domain, as explained at
|
5 |
|
|
* http://creativecommons.org/licenses/publicdomain
|
6 |
|
|
*/
|
7 |
|
|
|
8 |
|
|
package java.util.concurrent;
|
9 |
|
|
import java.util.concurrent.atomic.*;
|
10 |
|
|
import java.util.concurrent.locks.LockSupport;
|
11 |
|
|
|
12 |
|
|
/**
|
13 |
|
|
* A synchronization point at which threads can pair and swap elements
|
14 |
|
|
* within pairs. Each thread presents some object on entry to the
|
15 |
|
|
* {@link #exchange exchange} method, matches with a partner thread,
|
16 |
|
|
* and receives its partner's object on return. An Exchanger may be
|
17 |
|
|
* viewed as a bidirectional form of a {@link SynchronousQueue}.
|
18 |
|
|
* Exchangers may be useful in applications such as genetic algorithms
|
19 |
|
|
* and pipeline designs.
|
20 |
|
|
*
|
21 |
|
|
* <p><b>Sample Usage:</b>
|
22 |
|
|
* Here are the highlights of a class that uses an {@code Exchanger}
|
23 |
|
|
* to swap buffers between threads so that the thread filling the
|
24 |
|
|
* buffer gets a freshly emptied one when it needs it, handing off the
|
25 |
|
|
* filled one to the thread emptying the buffer.
|
26 |
|
|
* <pre>{@code
|
27 |
|
|
* class FillAndEmpty {
|
28 |
|
|
* Exchanger<DataBuffer> exchanger = new Exchanger<DataBuffer>();
|
29 |
|
|
* DataBuffer initialEmptyBuffer = ... a made-up type
|
30 |
|
|
* DataBuffer initialFullBuffer = ...
|
31 |
|
|
*
|
32 |
|
|
* class FillingLoop implements Runnable {
|
33 |
|
|
* public void run() {
|
34 |
|
|
* DataBuffer currentBuffer = initialEmptyBuffer;
|
35 |
|
|
* try {
|
36 |
|
|
* while (currentBuffer != null) {
|
37 |
|
|
* addToBuffer(currentBuffer);
|
38 |
|
|
* if (currentBuffer.isFull())
|
39 |
|
|
* currentBuffer = exchanger.exchange(currentBuffer);
|
40 |
|
|
* }
|
41 |
|
|
* } catch (InterruptedException ex) { ... handle ... }
|
42 |
|
|
* }
|
43 |
|
|
* }
|
44 |
|
|
*
|
45 |
|
|
* class EmptyingLoop implements Runnable {
|
46 |
|
|
* public void run() {
|
47 |
|
|
* DataBuffer currentBuffer = initialFullBuffer;
|
48 |
|
|
* try {
|
49 |
|
|
* while (currentBuffer != null) {
|
50 |
|
|
* takeFromBuffer(currentBuffer);
|
51 |
|
|
* if (currentBuffer.isEmpty())
|
52 |
|
|
* currentBuffer = exchanger.exchange(currentBuffer);
|
53 |
|
|
* }
|
54 |
|
|
* } catch (InterruptedException ex) { ... handle ...}
|
55 |
|
|
* }
|
56 |
|
|
* }
|
57 |
|
|
*
|
58 |
|
|
* void start() {
|
59 |
|
|
* new Thread(new FillingLoop()).start();
|
60 |
|
|
* new Thread(new EmptyingLoop()).start();
|
61 |
|
|
* }
|
62 |
|
|
* }
|
63 |
|
|
* }</pre>
|
64 |
|
|
*
|
65 |
|
|
* <p>Memory consistency effects: For each pair of threads that
|
66 |
|
|
* successfully exchange objects via an {@code Exchanger}, actions
|
67 |
|
|
* prior to the {@code exchange()} in each thread
|
68 |
|
|
* <a href="package-summary.html#MemoryVisibility"><i>happen-before</i></a>
|
69 |
|
|
* those subsequent to a return from the corresponding {@code exchange()}
|
70 |
|
|
* in the other thread.
|
71 |
|
|
*
|
72 |
|
|
* @since 1.5
|
73 |
|
|
* @author Doug Lea and Bill Scherer and Michael Scott
|
74 |
|
|
* @param <V> The type of objects that may be exchanged
|
75 |
|
|
*/
|
76 |
|
|
public class Exchanger<V> {
|
77 |
|
|
/*
|
78 |
|
|
* Algorithm Description:
|
79 |
|
|
*
|
80 |
|
|
* The basic idea is to maintain a "slot", which is a reference to
|
81 |
|
|
* a Node containing both an Item to offer and a "hole" waiting to
|
82 |
|
|
* get filled in. If an incoming "occupying" thread sees that the
|
83 |
|
|
* slot is null, it CAS'es (compareAndSets) a Node there and waits
|
84 |
|
|
* for another to invoke exchange. That second "fulfilling" thread
|
85 |
|
|
* sees that the slot is non-null, and so CASes it back to null,
|
86 |
|
|
* also exchanging items by CASing the hole, plus waking up the
|
87 |
|
|
* occupying thread if it is blocked. In each case CAS'es may
|
88 |
|
|
* fail because a slot at first appears non-null but is null upon
|
89 |
|
|
* CAS, or vice-versa. So threads may need to retry these
|
90 |
|
|
* actions.
|
91 |
|
|
*
|
92 |
|
|
* This simple approach works great when there are only a few
|
93 |
|
|
* threads using an Exchanger, but performance rapidly
|
94 |
|
|
* deteriorates due to CAS contention on the single slot when
|
95 |
|
|
* there are lots of threads using an exchanger. So instead we use
|
96 |
|
|
* an "arena"; basically a kind of hash table with a dynamically
|
97 |
|
|
* varying number of slots, any one of which can be used by
|
98 |
|
|
* threads performing an exchange. Incoming threads pick slots
|
99 |
|
|
* based on a hash of their Thread ids. If an incoming thread
|
100 |
|
|
* fails to CAS in its chosen slot, it picks an alternative slot
|
101 |
|
|
* instead. And similarly from there. If a thread successfully
|
102 |
|
|
* CASes into a slot but no other thread arrives, it tries
|
103 |
|
|
* another, heading toward the zero slot, which always exists even
|
104 |
|
|
* if the table shrinks. The particular mechanics controlling this
|
105 |
|
|
* are as follows:
|
106 |
|
|
*
|
107 |
|
|
* Waiting: Slot zero is special in that it is the only slot that
|
108 |
|
|
* exists when there is no contention. A thread occupying slot
|
109 |
|
|
* zero will block if no thread fulfills it after a short spin.
|
110 |
|
|
* In other cases, occupying threads eventually give up and try
|
111 |
|
|
* another slot. Waiting threads spin for a while (a period that
|
112 |
|
|
* should be a little less than a typical context-switch time)
|
113 |
|
|
* before either blocking (if slot zero) or giving up (if other
|
114 |
|
|
* slots) and restarting. There is no reason for threads to block
|
115 |
|
|
* unless there are unlikely to be any other threads present.
|
116 |
|
|
* Occupants are mainly avoiding memory contention so sit there
|
117 |
|
|
* quietly polling for a shorter period than it would take to
|
118 |
|
|
* block and then unblock them. Non-slot-zero waits that elapse
|
119 |
|
|
* because of lack of other threads waste around one extra
|
120 |
|
|
* context-switch time per try, which is still on average much
|
121 |
|
|
* faster than alternative approaches.
|
122 |
|
|
*
|
123 |
|
|
* Sizing: Usually, using only a few slots suffices to reduce
|
124 |
|
|
* contention. Especially with small numbers of threads, using
|
125 |
|
|
* too many slots can lead to just as poor performance as using
|
126 |
|
|
* too few of them, and there's not much room for error. The
|
127 |
|
|
* variable "max" maintains the number of slots actually in
|
128 |
|
|
* use. It is increased when a thread sees too many CAS
|
129 |
|
|
* failures. (This is analogous to resizing a regular hash table
|
130 |
|
|
* based on a target load factor, except here, growth steps are
|
131 |
|
|
* just one-by-one rather than proportional.) Growth requires
|
132 |
|
|
* contention failures in each of three tried slots. Requiring
|
133 |
|
|
* multiple failures for expansion copes with the fact that some
|
134 |
|
|
* failed CASes are not due to contention but instead to simple
|
135 |
|
|
* races between two threads or thread pre-emptions occurring
|
136 |
|
|
* between reading and CASing. Also, very transient peak
|
137 |
|
|
* contention can be much higher than the average sustainable
|
138 |
|
|
* levels. The max limit is decreased on average 50% of the times
|
139 |
|
|
* that a non-slot-zero wait elapses without being fulfilled.
|
140 |
|
|
* Threads experiencing elapsed waits move closer to zero, so
|
141 |
|
|
* eventually find existing (or future) threads even if the table
|
142 |
|
|
* has been shrunk due to inactivity. The chosen mechanics and
|
143 |
|
|
* thresholds for growing and shrinking are intrinsically
|
144 |
|
|
* entangled with indexing and hashing inside the exchange code,
|
145 |
|
|
* and can't be nicely abstracted out.
|
146 |
|
|
*
|
147 |
|
|
* Hashing: Each thread picks its initial slot to use in accord
|
148 |
|
|
* with a simple hashcode. The sequence is the same on each
|
149 |
|
|
* encounter by any given thread, but effectively random across
|
150 |
|
|
* threads. Using arenas encounters the classic cost vs quality
|
151 |
|
|
* tradeoffs of all hash tables. Here, we use a one-step FNV-1a
|
152 |
|
|
* hash code based on the current thread's Thread.getId(), along
|
153 |
|
|
* with a cheap approximation to a mod operation to select an
|
154 |
|
|
* index. The downside of optimizing index selection in this way
|
155 |
|
|
* is that the code is hardwired to use a maximum table size of
|
156 |
|
|
* 32. But this value more than suffices for known platforms and
|
157 |
|
|
* applications.
|
158 |
|
|
*
|
159 |
|
|
* Probing: On sensed contention of a selected slot, we probe
|
160 |
|
|
* sequentially through the table, analogously to linear probing
|
161 |
|
|
* after collision in a hash table. (We move circularly, in
|
162 |
|
|
* reverse order, to mesh best with table growth and shrinkage
|
163 |
|
|
* rules.) Except that to minimize the effects of false-alarms
|
164 |
|
|
* and cache thrashing, we try the first selected slot twice
|
165 |
|
|
* before moving.
|
166 |
|
|
*
|
167 |
|
|
* Padding: Even with contention management, slots are heavily
|
168 |
|
|
* contended, so use cache-padding to avoid poor memory
|
169 |
|
|
* performance. Because of this, slots are lazily constructed
|
170 |
|
|
* only when used, to avoid wasting this space unnecessarily.
|
171 |
|
|
* While isolation of locations is not much of an issue at first
|
172 |
|
|
* in an application, as time goes on and garbage-collectors
|
173 |
|
|
* perform compaction, slots are very likely to be moved adjacent
|
174 |
|
|
* to each other, which can cause much thrashing of cache lines on
|
175 |
|
|
* MPs unless padding is employed.
|
176 |
|
|
*
|
177 |
|
|
* This is an improvement of the algorithm described in the paper
|
178 |
|
|
* "A Scalable Elimination-based Exchange Channel" by William
|
179 |
|
|
* Scherer, Doug Lea, and Michael Scott in Proceedings of SCOOL05
|
180 |
|
|
* workshop. Available at: http://hdl.handle.net/1802/2104
|
181 |
|
|
*/
|
182 |
|
|
|
183 |
|
|
/** The number of CPUs, for sizing and spin control */
|
184 |
|
|
private static final int NCPU = Runtime.getRuntime().availableProcessors();
|
185 |
|
|
|
186 |
|
|
/**
|
187 |
|
|
* The capacity of the arena. Set to a value that provides more
|
188 |
|
|
* than enough space to handle contention. On small machines
|
189 |
|
|
* most slots won't be used, but it is still not wasted because
|
190 |
|
|
* the extra space provides some machine-level address padding
|
191 |
|
|
* to minimize interference with heavily CAS'ed Slot locations.
|
192 |
|
|
* And on very large machines, performance eventually becomes
|
193 |
|
|
* bounded by memory bandwidth, not numbers of threads/CPUs.
|
194 |
|
|
* This constant cannot be changed without also modifying
|
195 |
|
|
* indexing and hashing algorithms.
|
196 |
|
|
*/
|
197 |
|
|
private static final int CAPACITY = 32;
|
198 |
|
|
|
199 |
|
|
/**
|
200 |
|
|
* The value of "max" that will hold all threads without
|
201 |
|
|
* contention. When this value is less than CAPACITY, some
|
202 |
|
|
* otherwise wasted expansion can be avoided.
|
203 |
|
|
*/
|
204 |
|
|
private static final int FULL =
|
205 |
|
|
Math.max(0, Math.min(CAPACITY, NCPU / 2) - 1);
|
206 |
|
|
|
207 |
|
|
/**
|
208 |
|
|
* The number of times to spin (doing nothing except polling a
|
209 |
|
|
* memory location) before blocking or giving up while waiting to
|
210 |
|
|
* be fulfilled. Should be zero on uniprocessors. On
|
211 |
|
|
* multiprocessors, this value should be large enough so that two
|
212 |
|
|
* threads exchanging items as fast as possible block only when
|
213 |
|
|
* one of them is stalled (due to GC or preemption), but not much
|
214 |
|
|
* longer, to avoid wasting CPU resources. Seen differently, this
|
215 |
|
|
* value is a little over half the number of cycles of an average
|
216 |
|
|
* context switch time on most systems. The value here is
|
217 |
|
|
* approximately the average of those across a range of tested
|
218 |
|
|
* systems.
|
219 |
|
|
*/
|
220 |
|
|
private static final int SPINS = (NCPU == 1) ? 0 : 2000;
|
221 |
|
|
|
222 |
|
|
/**
|
223 |
|
|
* The number of times to spin before blocking in timed waits.
|
224 |
|
|
* Timed waits spin more slowly because checking the time takes
|
225 |
|
|
* time. The best value relies mainly on the relative rate of
|
226 |
|
|
* System.nanoTime vs memory accesses. The value is empirically
|
227 |
|
|
* derived to work well across a variety of systems.
|
228 |
|
|
*/
|
229 |
|
|
private static final int TIMED_SPINS = SPINS / 20;
|
230 |
|
|
|
231 |
|
|
/**
|
232 |
|
|
* Sentinel item representing cancellation of a wait due to
|
233 |
|
|
* interruption, timeout, or elapsed spin-waits. This value is
|
234 |
|
|
* placed in holes on cancellation, and used as a return value
|
235 |
|
|
* from waiting methods to indicate failure to set or get hole.
|
236 |
|
|
*/
|
237 |
|
|
private static final Object CANCEL = new Object();
|
238 |
|
|
|
239 |
|
|
/**
|
240 |
|
|
* Value representing null arguments/returns from public
|
241 |
|
|
* methods. This disambiguates from internal requirement that
|
242 |
|
|
* holes start out as null to mean they are not yet set.
|
243 |
|
|
*/
|
244 |
|
|
private static final Object NULL_ITEM = new Object();
|
245 |
|
|
|
246 |
|
|
/**
|
247 |
|
|
* Nodes hold partially exchanged data. This class
|
248 |
|
|
* opportunistically subclasses AtomicReference to represent the
|
249 |
|
|
* hole. So get() returns hole, and compareAndSet CAS'es value
|
250 |
|
|
* into hole. This class cannot be parameterized as "V" because
|
251 |
|
|
* of the use of non-V CANCEL sentinels.
|
252 |
|
|
*/
|
253 |
|
|
private static final class Node extends AtomicReference<Object> {
|
254 |
|
|
/** The element offered by the Thread creating this node. */
|
255 |
|
|
public final Object item;
|
256 |
|
|
|
257 |
|
|
/** The Thread waiting to be signalled; null until waiting. */
|
258 |
|
|
public volatile Thread waiter;
|
259 |
|
|
|
260 |
|
|
/**
|
261 |
|
|
* Creates node with given item and empty hole.
|
262 |
|
|
* @param item the item
|
263 |
|
|
*/
|
264 |
|
|
public Node(Object item) {
|
265 |
|
|
this.item = item;
|
266 |
|
|
}
|
267 |
|
|
}
|
268 |
|
|
|
269 |
|
|
/**
|
270 |
|
|
* A Slot is an AtomicReference with heuristic padding to lessen
|
271 |
|
|
* cache effects of this heavily CAS'ed location. While the
|
272 |
|
|
* padding adds noticeable space, all slots are created only on
|
273 |
|
|
* demand, and there will be more than one of them only when it
|
274 |
|
|
* would improve throughput more than enough to outweigh using
|
275 |
|
|
* extra space.
|
276 |
|
|
*/
|
277 |
|
|
private static final class Slot extends AtomicReference<Object> {
|
278 |
|
|
// Improve likelihood of isolation on <= 64 byte cache lines
|
279 |
|
|
long q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, qa, qb, qc, qd, qe;
|
280 |
|
|
}
|
281 |
|
|
|
282 |
|
|
/**
|
283 |
|
|
* Slot array. Elements are lazily initialized when needed.
|
284 |
|
|
* Declared volatile to enable double-checked lazy construction.
|
285 |
|
|
*/
|
286 |
|
|
private volatile Slot[] arena = new Slot[CAPACITY];
|
287 |
|
|
|
288 |
|
|
/**
|
289 |
|
|
* The maximum slot index being used. The value sometimes
|
290 |
|
|
* increases when a thread experiences too many CAS contentions,
|
291 |
|
|
* and sometimes decreases when a spin-wait elapses. Changes
|
292 |
|
|
* are performed only via compareAndSet, to avoid stale values
|
293 |
|
|
* when a thread happens to stall right before setting.
|
294 |
|
|
*/
|
295 |
|
|
private final AtomicInteger max = new AtomicInteger();
|
296 |
|
|
|
297 |
|
|
/**
|
298 |
|
|
* Main exchange function, handling the different policy variants.
|
299 |
|
|
* Uses Object, not "V" as argument and return value to simplify
|
300 |
|
|
* handling of sentinel values. Callers from public methods decode
|
301 |
|
|
* and cast accordingly.
|
302 |
|
|
*
|
303 |
|
|
* @param item the (non-null) item to exchange
|
304 |
|
|
* @param timed true if the wait is timed
|
305 |
|
|
* @param nanos if timed, the maximum wait time
|
306 |
|
|
* @return the other thread's item, or CANCEL if interrupted or timed out
|
307 |
|
|
*/
|
308 |
|
|
private Object doExchange(Object item, boolean timed, long nanos) {
|
309 |
|
|
Node me = new Node(item); // Create in case occupying
|
310 |
|
|
int index = hashIndex(); // Index of current slot
|
311 |
|
|
int fails = 0; // Number of CAS failures
|
312 |
|
|
|
313 |
|
|
for (;;) {
|
314 |
|
|
Object y; // Contents of current slot
|
315 |
|
|
Slot slot = arena[index];
|
316 |
|
|
if (slot == null) // Lazily initialize slots
|
317 |
|
|
createSlot(index); // Continue loop to reread
|
318 |
|
|
else if ((y = slot.get()) != null && // Try to fulfill
|
319 |
|
|
slot.compareAndSet(y, null)) {
|
320 |
|
|
Node you = (Node)y; // Transfer item
|
321 |
|
|
if (you.compareAndSet(null, item)) {
|
322 |
|
|
LockSupport.unpark(you.waiter);
|
323 |
|
|
return you.item;
|
324 |
|
|
} // Else cancelled; continue
|
325 |
|
|
}
|
326 |
|
|
else if (y == null && // Try to occupy
|
327 |
|
|
slot.compareAndSet(null, me)) {
|
328 |
|
|
if (index == 0) // Blocking wait for slot 0
|
329 |
|
|
return timed? awaitNanos(me, slot, nanos): await(me, slot);
|
330 |
|
|
Object v = spinWait(me, slot); // Spin wait for non-0
|
331 |
|
|
if (v != CANCEL)
|
332 |
|
|
return v;
|
333 |
|
|
me = new Node(item); // Throw away cancelled node
|
334 |
|
|
int m = max.get();
|
335 |
|
|
if (m > (index >>>= 1)) // Decrease index
|
336 |
|
|
max.compareAndSet(m, m - 1); // Maybe shrink table
|
337 |
|
|
}
|
338 |
|
|
else if (++fails > 1) { // Allow 2 fails on 1st slot
|
339 |
|
|
int m = max.get();
|
340 |
|
|
if (fails > 3 && m < FULL && max.compareAndSet(m, m + 1))
|
341 |
|
|
index = m + 1; // Grow on 3rd failed slot
|
342 |
|
|
else if (--index < 0)
|
343 |
|
|
index = m; // Circularly traverse
|
344 |
|
|
}
|
345 |
|
|
}
|
346 |
|
|
}
|
347 |
|
|
|
348 |
|
|
/**
|
349 |
|
|
* Returns a hash index for the current thread. Uses a one-step
|
350 |
|
|
* FNV-1a hash code (http://www.isthe.com/chongo/tech/comp/fnv/)
|
351 |
|
|
* based on the current thread's Thread.getId(). These hash codes
|
352 |
|
|
* have more uniform distribution properties with respect to small
|
353 |
|
|
* moduli (here 1-31) than do other simple hashing functions.
|
354 |
|
|
*
|
355 |
|
|
* <p>To return an index between 0 and max, we use a cheap
|
356 |
|
|
* approximation to a mod operation, that also corrects for bias
|
357 |
|
|
* due to non-power-of-2 remaindering (see {@link
|
358 |
|
|
* java.util.Random#nextInt}). Bits of the hashcode are masked
|
359 |
|
|
* with "nbits", the ceiling power of two of table size (looked up
|
360 |
|
|
* in a table packed into three ints). If too large, this is
|
361 |
|
|
* retried after rotating the hash by nbits bits, while forcing new
|
362 |
|
|
* top bit to 0, which guarantees eventual termination (although
|
363 |
|
|
* with a non-random-bias). This requires an average of less than
|
364 |
|
|
* 2 tries for all table sizes, and has a maximum 2% difference
|
365 |
|
|
* from perfectly uniform slot probabilities when applied to all
|
366 |
|
|
* possible hash codes for sizes less than 32.
|
367 |
|
|
*
|
368 |
|
|
* @return a per-thread-random index, 0 <= index < max
|
369 |
|
|
*/
|
370 |
|
|
private final int hashIndex() {
|
371 |
|
|
long id = Thread.currentThread().getId();
|
372 |
|
|
int hash = (((int)(id ^ (id >>> 32))) ^ 0x811c9dc5) * 0x01000193;
|
373 |
|
|
|
374 |
|
|
int m = max.get();
|
375 |
|
|
int nbits = (((0xfffffc00 >> m) & 4) | // Compute ceil(log2(m+1))
|
376 |
|
|
((0x000001f8 >>> m) & 2) | // The constants hold
|
377 |
|
|
((0xffff00f2 >>> m) & 1)); // a lookup table
|
378 |
|
|
int index;
|
379 |
|
|
while ((index = hash & ((1 << nbits) - 1)) > m) // May retry on
|
380 |
|
|
hash = (hash >>> nbits) | (hash << (33 - nbits)); // non-power-2 m
|
381 |
|
|
return index;
|
382 |
|
|
}
|
383 |
|
|
|
384 |
|
|
/**
|
385 |
|
|
* Creates a new slot at given index. Called only when the slot
|
386 |
|
|
* appears to be null. Relies on double-check using builtin
|
387 |
|
|
* locks, since they rarely contend. This in turn relies on the
|
388 |
|
|
* arena array being declared volatile.
|
389 |
|
|
*
|
390 |
|
|
* @param index the index to add slot at
|
391 |
|
|
*/
|
392 |
|
|
private void createSlot(int index) {
|
393 |
|
|
// Create slot outside of lock to narrow sync region
|
394 |
|
|
Slot newSlot = new Slot();
|
395 |
|
|
Slot[] a = arena;
|
396 |
|
|
synchronized (a) {
|
397 |
|
|
if (a[index] == null)
|
398 |
|
|
a[index] = newSlot;
|
399 |
|
|
}
|
400 |
|
|
}
|
401 |
|
|
|
402 |
|
|
/**
|
403 |
|
|
* Tries to cancel a wait for the given node waiting in the given
|
404 |
|
|
* slot, if so, helping clear the node from its slot to avoid
|
405 |
|
|
* garbage retention.
|
406 |
|
|
*
|
407 |
|
|
* @param node the waiting node
|
408 |
|
|
* @param the slot it is waiting in
|
409 |
|
|
* @return true if successfully cancelled
|
410 |
|
|
*/
|
411 |
|
|
private static boolean tryCancel(Node node, Slot slot) {
|
412 |
|
|
if (!node.compareAndSet(null, CANCEL))
|
413 |
|
|
return false;
|
414 |
|
|
if (slot.get() == node) // pre-check to minimize contention
|
415 |
|
|
slot.compareAndSet(node, null);
|
416 |
|
|
return true;
|
417 |
|
|
}
|
418 |
|
|
|
419 |
|
|
// Three forms of waiting. Each just different enough not to merge
|
420 |
|
|
// code with others.
|
421 |
|
|
|
422 |
|
|
/**
|
423 |
|
|
* Spin-waits for hole for a non-0 slot. Fails if spin elapses
|
424 |
|
|
* before hole filled. Does not check interrupt, relying on check
|
425 |
|
|
* in public exchange method to abort if interrupted on entry.
|
426 |
|
|
*
|
427 |
|
|
* @param node the waiting node
|
428 |
|
|
* @return on success, the hole; on failure, CANCEL
|
429 |
|
|
*/
|
430 |
|
|
private static Object spinWait(Node node, Slot slot) {
|
431 |
|
|
int spins = SPINS;
|
432 |
|
|
for (;;) {
|
433 |
|
|
Object v = node.get();
|
434 |
|
|
if (v != null)
|
435 |
|
|
return v;
|
436 |
|
|
else if (spins > 0)
|
437 |
|
|
--spins;
|
438 |
|
|
else
|
439 |
|
|
tryCancel(node, slot);
|
440 |
|
|
}
|
441 |
|
|
}
|
442 |
|
|
|
443 |
|
|
/**
|
444 |
|
|
* Waits for (by spinning and/or blocking) and gets the hole
|
445 |
|
|
* filled in by another thread. Fails if interrupted before
|
446 |
|
|
* hole filled.
|
447 |
|
|
*
|
448 |
|
|
* When a node/thread is about to block, it sets its waiter field
|
449 |
|
|
* and then rechecks state at least one more time before actually
|
450 |
|
|
* parking, thus covering race vs fulfiller noticing that waiter
|
451 |
|
|
* is non-null so should be woken.
|
452 |
|
|
*
|
453 |
|
|
* Thread interruption status is checked only surrounding calls to
|
454 |
|
|
* park. The caller is assumed to have checked interrupt status
|
455 |
|
|
* on entry.
|
456 |
|
|
*
|
457 |
|
|
* @param node the waiting node
|
458 |
|
|
* @return on success, the hole; on failure, CANCEL
|
459 |
|
|
*/
|
460 |
|
|
private static Object await(Node node, Slot slot) {
|
461 |
|
|
Thread w = Thread.currentThread();
|
462 |
|
|
int spins = SPINS;
|
463 |
|
|
for (;;) {
|
464 |
|
|
Object v = node.get();
|
465 |
|
|
if (v != null)
|
466 |
|
|
return v;
|
467 |
|
|
else if (spins > 0) // Spin-wait phase
|
468 |
|
|
--spins;
|
469 |
|
|
else if (node.waiter == null) // Set up to block next
|
470 |
|
|
node.waiter = w;
|
471 |
|
|
else if (w.isInterrupted()) // Abort on interrupt
|
472 |
|
|
tryCancel(node, slot);
|
473 |
|
|
else // Block
|
474 |
|
|
LockSupport.park(node);
|
475 |
|
|
}
|
476 |
|
|
}
|
477 |
|
|
|
478 |
|
|
/**
|
479 |
|
|
* Waits for (at index 0) and gets the hole filled in by another
|
480 |
|
|
* thread. Fails if timed out or interrupted before hole filled.
|
481 |
|
|
* Same basic logic as untimed version, but a bit messier.
|
482 |
|
|
*
|
483 |
|
|
* @param node the waiting node
|
484 |
|
|
* @param nanos the wait time
|
485 |
|
|
* @return on success, the hole; on failure, CANCEL
|
486 |
|
|
*/
|
487 |
|
|
private Object awaitNanos(Node node, Slot slot, long nanos) {
|
488 |
|
|
int spins = TIMED_SPINS;
|
489 |
|
|
long lastTime = 0;
|
490 |
|
|
Thread w = null;
|
491 |
|
|
for (;;) {
|
492 |
|
|
Object v = node.get();
|
493 |
|
|
if (v != null)
|
494 |
|
|
return v;
|
495 |
|
|
long now = System.nanoTime();
|
496 |
|
|
if (w == null)
|
497 |
|
|
w = Thread.currentThread();
|
498 |
|
|
else
|
499 |
|
|
nanos -= now - lastTime;
|
500 |
|
|
lastTime = now;
|
501 |
|
|
if (nanos > 0) {
|
502 |
|
|
if (spins > 0)
|
503 |
|
|
--spins;
|
504 |
|
|
else if (node.waiter == null)
|
505 |
|
|
node.waiter = w;
|
506 |
|
|
else if (w.isInterrupted())
|
507 |
|
|
tryCancel(node, slot);
|
508 |
|
|
else
|
509 |
|
|
LockSupport.parkNanos(node, nanos);
|
510 |
|
|
}
|
511 |
|
|
else if (tryCancel(node, slot) && !w.isInterrupted())
|
512 |
|
|
return scanOnTimeout(node);
|
513 |
|
|
}
|
514 |
|
|
}
|
515 |
|
|
|
516 |
|
|
/**
|
517 |
|
|
* Sweeps through arena checking for any waiting threads. Called
|
518 |
|
|
* only upon return from timeout while waiting in slot 0. When a
|
519 |
|
|
* thread gives up on a timed wait, it is possible that a
|
520 |
|
|
* previously-entered thread is still waiting in some other
|
521 |
|
|
* slot. So we scan to check for any. This is almost always
|
522 |
|
|
* overkill, but decreases the likelihood of timeouts when there
|
523 |
|
|
* are other threads present to far less than that in lock-based
|
524 |
|
|
* exchangers in which earlier-arriving threads may still be
|
525 |
|
|
* waiting on entry locks.
|
526 |
|
|
*
|
527 |
|
|
* @param node the waiting node
|
528 |
|
|
* @return another thread's item, or CANCEL
|
529 |
|
|
*/
|
530 |
|
|
private Object scanOnTimeout(Node node) {
|
531 |
|
|
Object y;
|
532 |
|
|
for (int j = arena.length - 1; j >= 0; --j) {
|
533 |
|
|
Slot slot = arena[j];
|
534 |
|
|
if (slot != null) {
|
535 |
|
|
while ((y = slot.get()) != null) {
|
536 |
|
|
if (slot.compareAndSet(y, null)) {
|
537 |
|
|
Node you = (Node)y;
|
538 |
|
|
if (you.compareAndSet(null, node.item)) {
|
539 |
|
|
LockSupport.unpark(you.waiter);
|
540 |
|
|
return you.item;
|
541 |
|
|
}
|
542 |
|
|
}
|
543 |
|
|
}
|
544 |
|
|
}
|
545 |
|
|
}
|
546 |
|
|
return CANCEL;
|
547 |
|
|
}
|
548 |
|
|
|
549 |
|
|
/**
|
550 |
|
|
* Creates a new Exchanger.
|
551 |
|
|
*/
|
552 |
|
|
public Exchanger() {
|
553 |
|
|
}
|
554 |
|
|
|
555 |
|
|
/**
|
556 |
|
|
* Waits for another thread to arrive at this exchange point (unless
|
557 |
|
|
* the current thread is {@linkplain Thread#interrupt interrupted}),
|
558 |
|
|
* and then transfers the given object to it, receiving its object
|
559 |
|
|
* in return.
|
560 |
|
|
*
|
561 |
|
|
* <p>If another thread is already waiting at the exchange point then
|
562 |
|
|
* it is resumed for thread scheduling purposes and receives the object
|
563 |
|
|
* passed in by the current thread. The current thread returns immediately,
|
564 |
|
|
* receiving the object passed to the exchange by that other thread.
|
565 |
|
|
*
|
566 |
|
|
* <p>If no other thread is already waiting at the exchange then the
|
567 |
|
|
* current thread is disabled for thread scheduling purposes and lies
|
568 |
|
|
* dormant until one of two things happens:
|
569 |
|
|
* <ul>
|
570 |
|
|
* <li>Some other thread enters the exchange; or
|
571 |
|
|
* <li>Some other thread {@linkplain Thread#interrupt interrupts} the current
|
572 |
|
|
* thread.
|
573 |
|
|
* </ul>
|
574 |
|
|
* <p>If the current thread:
|
575 |
|
|
* <ul>
|
576 |
|
|
* <li>has its interrupted status set on entry to this method; or
|
577 |
|
|
* <li>is {@linkplain Thread#interrupt interrupted} while waiting
|
578 |
|
|
* for the exchange,
|
579 |
|
|
* </ul>
|
580 |
|
|
* then {@link InterruptedException} is thrown and the current thread's
|
581 |
|
|
* interrupted status is cleared.
|
582 |
|
|
*
|
583 |
|
|
* @param x the object to exchange
|
584 |
|
|
* @return the object provided by the other thread
|
585 |
|
|
* @throws InterruptedException if the current thread was
|
586 |
|
|
* interrupted while waiting
|
587 |
|
|
*/
|
588 |
|
|
public V exchange(V x) throws InterruptedException {
|
589 |
|
|
if (!Thread.interrupted()) {
|
590 |
|
|
Object v = doExchange(x == null? NULL_ITEM : x, false, 0);
|
591 |
|
|
if (v == NULL_ITEM)
|
592 |
|
|
return null;
|
593 |
|
|
if (v != CANCEL)
|
594 |
|
|
return (V)v;
|
595 |
|
|
Thread.interrupted(); // Clear interrupt status on IE throw
|
596 |
|
|
}
|
597 |
|
|
throw new InterruptedException();
|
598 |
|
|
}
|
599 |
|
|
|
600 |
|
|
/**
|
601 |
|
|
* Waits for another thread to arrive at this exchange point (unless
|
602 |
|
|
* the current thread is {@linkplain Thread#interrupt interrupted} or
|
603 |
|
|
* the specified waiting time elapses), and then transfers the given
|
604 |
|
|
* object to it, receiving its object in return.
|
605 |
|
|
*
|
606 |
|
|
* <p>If another thread is already waiting at the exchange point then
|
607 |
|
|
* it is resumed for thread scheduling purposes and receives the object
|
608 |
|
|
* passed in by the current thread. The current thread returns immediately,
|
609 |
|
|
* receiving the object passed to the exchange by that other thread.
|
610 |
|
|
*
|
611 |
|
|
* <p>If no other thread is already waiting at the exchange then the
|
612 |
|
|
* current thread is disabled for thread scheduling purposes and lies
|
613 |
|
|
* dormant until one of three things happens:
|
614 |
|
|
* <ul>
|
615 |
|
|
* <li>Some other thread enters the exchange; or
|
616 |
|
|
* <li>Some other thread {@linkplain Thread#interrupt interrupts}
|
617 |
|
|
* the current thread; or
|
618 |
|
|
* <li>The specified waiting time elapses.
|
619 |
|
|
* </ul>
|
620 |
|
|
* <p>If the current thread:
|
621 |
|
|
* <ul>
|
622 |
|
|
* <li>has its interrupted status set on entry to this method; or
|
623 |
|
|
* <li>is {@linkplain Thread#interrupt interrupted} while waiting
|
624 |
|
|
* for the exchange,
|
625 |
|
|
* </ul>
|
626 |
|
|
* then {@link InterruptedException} is thrown and the current thread's
|
627 |
|
|
* interrupted status is cleared.
|
628 |
|
|
*
|
629 |
|
|
* <p>If the specified waiting time elapses then {@link
|
630 |
|
|
* TimeoutException} is thrown. If the time is less than or equal
|
631 |
|
|
* to zero, the method will not wait at all.
|
632 |
|
|
*
|
633 |
|
|
* @param x the object to exchange
|
634 |
|
|
* @param timeout the maximum time to wait
|
635 |
|
|
* @param unit the time unit of the <tt>timeout</tt> argument
|
636 |
|
|
* @return the object provided by the other thread
|
637 |
|
|
* @throws InterruptedException if the current thread was
|
638 |
|
|
* interrupted while waiting
|
639 |
|
|
* @throws TimeoutException if the specified waiting time elapses
|
640 |
|
|
* before another thread enters the exchange
|
641 |
|
|
*/
|
642 |
|
|
public V exchange(V x, long timeout, TimeUnit unit)
|
643 |
|
|
throws InterruptedException, TimeoutException {
|
644 |
|
|
if (!Thread.interrupted()) {
|
645 |
|
|
Object v = doExchange(x == null? NULL_ITEM : x,
|
646 |
|
|
true, unit.toNanos(timeout));
|
647 |
|
|
if (v == NULL_ITEM)
|
648 |
|
|
return null;
|
649 |
|
|
if (v != CANCEL)
|
650 |
|
|
return (V)v;
|
651 |
|
|
if (!Thread.interrupted())
|
652 |
|
|
throw new TimeoutException();
|
653 |
|
|
}
|
654 |
|
|
throw new InterruptedException();
|
655 |
|
|
}
|
656 |
|
|
}
|