1 |
dl |
1.1 |
/* |
2 |
|
|
* Written by Doug Lea with assistance from members of JCP JSR-166 |
3 |
|
|
* Expert Group and released to the public domain, as explained at |
4 |
|
|
* http://creativecommons.org/licenses/publicdomain |
5 |
|
|
*/ |
6 |
|
|
|
7 |
|
|
package jsr166y; |
8 |
jsr166 |
1.18 |
|
9 |
dl |
1.1 |
import java.util.concurrent.*; |
10 |
jsr166 |
1.18 |
|
11 |
|
|
import java.util.Collection; |
12 |
dl |
1.1 |
|
13 |
|
|
/** |
14 |
dl |
1.2 |
* A thread managed by a {@link ForkJoinPool}. This class is |
15 |
|
|
* subclassable solely for the sake of adding functionality -- there |
16 |
|
|
* are no overridable methods dealing with scheduling or |
17 |
|
|
* execution. However, you can override initialization and termination |
18 |
dl |
1.7 |
* methods surrounding the main task processing loop. If you do |
19 |
|
|
* create such a subclass, you will also need to supply a custom |
20 |
dl |
1.2 |
* ForkJoinWorkerThreadFactory to use it in a ForkJoinPool. |
21 |
jsr166 |
1.6 |
* |
22 |
jsr166 |
1.13 |
* @since 1.7 |
23 |
|
|
* @author Doug Lea |
24 |
dl |
1.1 |
*/ |
25 |
|
|
public class ForkJoinWorkerThread extends Thread { |
26 |
|
|
/* |
27 |
|
|
* Algorithm overview: |
28 |
|
|
* |
29 |
|
|
* 1. Work-Stealing: Work-stealing queues are special forms of |
30 |
|
|
* Deques that support only three of the four possible |
31 |
|
|
* end-operations -- push, pop, and deq (aka steal), and only do |
32 |
|
|
* so under the constraints that push and pop are called only from |
33 |
|
|
* the owning thread, while deq may be called from other threads. |
34 |
|
|
* (If you are unfamiliar with them, you probably want to read |
35 |
|
|
* Herlihy and Shavit's book "The Art of Multiprocessor |
36 |
|
|
* programming", chapter 16 describing these in more detail before |
37 |
|
|
* proceeding.) The main work-stealing queue design is roughly |
38 |
|
|
* similar to "Dynamic Circular Work-Stealing Deque" by David |
39 |
|
|
* Chase and Yossi Lev, SPAA 2005 |
40 |
|
|
* (http://research.sun.com/scalable/pubs/index.html). The main |
41 |
|
|
* difference ultimately stems from gc requirements that we null |
42 |
|
|
* out taken slots as soon as we can, to maintain as small a |
43 |
|
|
* footprint as possible even in programs generating huge numbers |
44 |
|
|
* of tasks. To accomplish this, we shift the CAS arbitrating pop |
45 |
|
|
* vs deq (steal) from being on the indices ("base" and "sp") to |
46 |
|
|
* the slots themselves (mainly via method "casSlotNull()"). So, |
47 |
jsr166 |
1.10 |
* both a successful pop and deq mainly entail CAS'ing a non-null |
48 |
dl |
1.1 |
* slot to null. Because we rely on CASes of references, we do |
49 |
|
|
* not need tag bits on base or sp. They are simple ints as used |
50 |
|
|
* in any circular array-based queue (see for example ArrayDeque). |
51 |
|
|
* Updates to the indices must still be ordered in a way that |
52 |
|
|
* guarantees that (sp - base) > 0 means the queue is empty, but |
53 |
|
|
* otherwise may err on the side of possibly making the queue |
54 |
|
|
* appear nonempty when a push, pop, or deq have not fully |
55 |
|
|
* committed. Note that this means that the deq operation, |
56 |
|
|
* considered individually, is not wait-free. One thief cannot |
57 |
|
|
* successfully continue until another in-progress one (or, if |
58 |
|
|
* previously empty, a push) completes. However, in the |
59 |
jsr166 |
1.9 |
* aggregate, we ensure at least probabilistic non-blockingness. If |
60 |
dl |
1.1 |
* an attempted steal fails, a thief always chooses a different |
61 |
|
|
* random victim target to try next. So, in order for one thief to |
62 |
|
|
* progress, it suffices for any in-progress deq or new push on |
63 |
|
|
* any empty queue to complete. One reason this works well here is |
64 |
|
|
* that apparently-nonempty often means soon-to-be-stealable, |
65 |
|
|
* which gives threads a chance to activate if necessary before |
66 |
|
|
* stealing (see below). |
67 |
|
|
* |
68 |
dl |
1.23 |
* This approach also enables support for "async mode" where local |
69 |
|
|
* task processing is in FIFO, not LIFO order; simply by using a |
70 |
|
|
* version of deq rather than pop when locallyFifo is true (as set |
71 |
|
|
* by the ForkJoinPool). This allows use in message-passing |
72 |
|
|
* frameworks in which tasks are never joined. |
73 |
|
|
* |
74 |
dl |
1.1 |
* Efficient implementation of this approach currently relies on |
75 |
|
|
* an uncomfortable amount of "Unsafe" mechanics. To maintain |
76 |
|
|
* correct orderings, reads and writes of variable base require |
77 |
|
|
* volatile ordering. Variable sp does not require volatile write |
78 |
|
|
* but needs cheaper store-ordering on writes. Because they are |
79 |
|
|
* protected by volatile base reads, reads of the queue array and |
80 |
|
|
* its slots do not need volatile load semantics, but writes (in |
81 |
|
|
* push) require store order and CASes (in pop and deq) require |
82 |
|
|
* (volatile) CAS semantics. Since these combinations aren't |
83 |
|
|
* supported using ordinary volatiles, the only way to accomplish |
84 |
jsr166 |
1.9 |
* these efficiently is to use direct Unsafe calls. (Using external |
85 |
dl |
1.1 |
* AtomicIntegers and AtomicReferenceArrays for the indices and |
86 |
|
|
* array is significantly slower because of memory locality and |
87 |
|
|
* indirection effects.) Further, performance on most platforms is |
88 |
|
|
* very sensitive to placement and sizing of the (resizable) queue |
89 |
|
|
* array. Even though these queues don't usually become all that |
90 |
|
|
* big, the initial size must be large enough to counteract cache |
91 |
|
|
* contention effects across multiple queues (especially in the |
92 |
|
|
* presence of GC cardmarking). Also, to improve thread-locality, |
93 |
|
|
* queues are currently initialized immediately after the thread |
94 |
|
|
* gets the initial signal to start processing tasks. However, |
95 |
|
|
* all queue-related methods except pushTask are written in a way |
96 |
|
|
* that allows them to instead be lazily allocated and/or disposed |
97 |
|
|
* of when empty. All together, these low-level implementation |
98 |
|
|
* choices produce as much as a factor of 4 performance |
99 |
|
|
* improvement compared to naive implementations, and enable the |
100 |
|
|
* processing of billions of tasks per second, sometimes at the |
101 |
|
|
* expense of ugliness. |
102 |
|
|
* |
103 |
|
|
* 2. Run control: The primary run control is based on a global |
104 |
|
|
* counter (activeCount) held by the pool. It uses an algorithm |
105 |
|
|
* similar to that in Herlihy and Shavit section 17.6 to cause |
106 |
|
|
* threads to eventually block when all threads declare they are |
107 |
|
|
* inactive. (See variable "scans".) For this to work, threads |
108 |
|
|
* must be declared active when executing tasks, and before |
109 |
|
|
* stealing a task. They must be inactive before blocking on the |
110 |
|
|
* Pool Barrier (awaiting a new submission or other Pool |
111 |
|
|
* event). In between, there is some free play which we take |
112 |
|
|
* advantage of to avoid contention and rapid flickering of the |
113 |
|
|
* global activeCount: If inactive, we activate only if a victim |
114 |
|
|
* queue appears to be nonempty (see above). Similarly, a thread |
115 |
|
|
* tries to inactivate only after a full scan of other threads. |
116 |
|
|
* The net effect is that contention on activeCount is rarely a |
117 |
|
|
* measurable performance issue. (There are also a few other cases |
118 |
|
|
* where we scan for work rather than retry/block upon |
119 |
|
|
* contention.) |
120 |
|
|
* |
121 |
|
|
* 3. Selection control. We maintain policy of always choosing to |
122 |
|
|
* run local tasks rather than stealing, and always trying to |
123 |
|
|
* steal tasks before trying to run a new submission. All steals |
124 |
|
|
* are currently performed in randomly-chosen deq-order. It may be |
125 |
|
|
* worthwhile to bias these with locality / anti-locality |
126 |
|
|
* information, but doing this well probably requires more |
127 |
|
|
* lower-level information from JVMs than currently provided. |
128 |
|
|
*/ |
129 |
|
|
|
130 |
|
|
/** |
131 |
|
|
* Capacity of work-stealing queue array upon initialization. |
132 |
|
|
* Must be a power of two. Initial size must be at least 2, but is |
133 |
|
|
* padded to minimize cache effects. |
134 |
|
|
*/ |
135 |
|
|
private static final int INITIAL_QUEUE_CAPACITY = 1 << 13; |
136 |
|
|
|
137 |
|
|
/** |
138 |
|
|
* Maximum work-stealing queue array size. Must be less than or |
139 |
dl |
1.5 |
* equal to 1 << 28 to ensure lack of index wraparound. (This |
140 |
|
|
* is less than usual bounds, because we need leftshift by 3 |
141 |
|
|
* to be in int range). |
142 |
dl |
1.1 |
*/ |
143 |
dl |
1.5 |
private static final int MAXIMUM_QUEUE_CAPACITY = 1 << 28; |
144 |
dl |
1.1 |
|
145 |
|
|
/** |
146 |
jsr166 |
1.16 |
* The pool this thread works in. Accessed directly by ForkJoinTask. |
147 |
dl |
1.1 |
*/ |
148 |
dl |
1.5 |
final ForkJoinPool pool; |
149 |
dl |
1.1 |
|
150 |
|
|
/** |
151 |
|
|
* The work-stealing queue array. Size must be a power of two. |
152 |
dl |
1.5 |
* Initialized when thread starts, to improve memory locality. |
153 |
dl |
1.1 |
*/ |
154 |
|
|
private ForkJoinTask<?>[] queue; |
155 |
|
|
|
156 |
|
|
/** |
157 |
|
|
* Index (mod queue.length) of next queue slot to push to or pop |
158 |
|
|
* from. It is written only by owner thread, via ordered store. |
159 |
|
|
* Both sp and base are allowed to wrap around on overflow, but |
160 |
|
|
* (sp - base) still estimates size. |
161 |
|
|
*/ |
162 |
|
|
private volatile int sp; |
163 |
|
|
|
164 |
|
|
/** |
165 |
|
|
* Index (mod queue.length) of least valid queue slot, which is |
166 |
|
|
* always the next position to steal from if nonempty. |
167 |
|
|
*/ |
168 |
|
|
private volatile int base; |
169 |
|
|
|
170 |
|
|
/** |
171 |
dl |
1.5 |
* Activity status. When true, this worker is considered active. |
172 |
|
|
* Must be false upon construction. It must be true when executing |
173 |
|
|
* tasks, and BEFORE stealing a task. It must be false before |
174 |
jsr166 |
1.16 |
* calling pool.sync. |
175 |
dl |
1.1 |
*/ |
176 |
dl |
1.5 |
private boolean active; |
177 |
dl |
1.1 |
|
178 |
|
|
/** |
179 |
|
|
* Run state of this worker. Supports simple versions of the usual |
180 |
|
|
* shutdown/shutdownNow control. |
181 |
|
|
*/ |
182 |
|
|
private volatile int runState; |
183 |
|
|
|
184 |
|
|
/** |
185 |
dl |
1.5 |
* Seed for random number generator for choosing steal victims. |
186 |
|
|
* Uses Marsaglia xorshift. Must be nonzero upon initialization. |
187 |
dl |
1.1 |
*/ |
188 |
dl |
1.5 |
private int seed; |
189 |
dl |
1.1 |
|
190 |
|
|
/** |
191 |
|
|
* Number of steals, transferred to pool when idle |
192 |
|
|
*/ |
193 |
|
|
private int stealCount; |
194 |
|
|
|
195 |
|
|
/** |
196 |
dl |
1.5 |
* Index of this worker in pool array. Set once by pool before |
197 |
jsr166 |
1.16 |
* running, and accessed directly by pool during cleanup etc. |
198 |
dl |
1.1 |
*/ |
199 |
dl |
1.5 |
int poolIndex; |
200 |
dl |
1.1 |
|
201 |
|
|
/** |
202 |
dl |
1.5 |
* The last barrier event waited for. Accessed in pool callback |
203 |
|
|
* methods, but only by current thread. |
204 |
dl |
1.1 |
*/ |
205 |
dl |
1.5 |
long lastEventCount; |
206 |
dl |
1.1 |
|
207 |
|
|
/** |
208 |
dl |
1.7 |
* True if use local fifo, not default lifo, for local polling |
209 |
|
|
*/ |
210 |
|
|
private boolean locallyFifo; |
211 |
|
|
|
212 |
|
|
/** |
213 |
dl |
1.1 |
* Creates a ForkJoinWorkerThread operating in the given pool. |
214 |
jsr166 |
1.11 |
* |
215 |
dl |
1.1 |
* @param pool the pool this thread works in |
216 |
|
|
* @throws NullPointerException if pool is null |
217 |
|
|
*/ |
218 |
|
|
protected ForkJoinWorkerThread(ForkJoinPool pool) { |
219 |
|
|
if (pool == null) throw new NullPointerException(); |
220 |
|
|
this.pool = pool; |
221 |
dl |
1.5 |
// Note: poolIndex is set by pool during construction |
222 |
|
|
// Remaining initialization is deferred to onStart |
223 |
dl |
1.1 |
} |
224 |
|
|
|
225 |
jsr166 |
1.6 |
// Public access methods |
226 |
dl |
1.2 |
|
227 |
|
|
/** |
228 |
jsr166 |
1.11 |
* Returns the pool hosting this thread. |
229 |
|
|
* |
230 |
dl |
1.2 |
* @return the pool |
231 |
|
|
*/ |
232 |
dl |
1.4 |
public ForkJoinPool getPool() { |
233 |
|
|
return pool; |
234 |
dl |
1.2 |
} |
235 |
|
|
|
236 |
|
|
/** |
237 |
dl |
1.4 |
* Returns the index number of this thread in its pool. The |
238 |
|
|
* returned value ranges from zero to the maximum number of |
239 |
|
|
* threads (minus one) that have ever been created in the pool. |
240 |
|
|
* This method may be useful for applications that track status or |
241 |
dl |
1.5 |
* collect results per-worker rather than per-task. |
242 |
jsr166 |
1.11 |
* |
243 |
|
|
* @return the index number |
244 |
dl |
1.2 |
*/ |
245 |
dl |
1.4 |
public int getPoolIndex() { |
246 |
|
|
return poolIndex; |
247 |
dl |
1.2 |
} |
248 |
|
|
|
249 |
dl |
1.7 |
/** |
250 |
|
|
* Establishes local first-in-first-out scheduling mode for forked |
251 |
jsr166 |
1.8 |
* tasks that are never joined. |
252 |
jsr166 |
1.11 |
* |
253 |
dl |
1.7 |
* @param async if true, use locally FIFO scheduling |
254 |
|
|
*/ |
255 |
|
|
void setAsyncMode(boolean async) { |
256 |
|
|
locallyFifo = async; |
257 |
|
|
} |
258 |
dl |
1.5 |
|
259 |
|
|
// Runstate management |
260 |
|
|
|
261 |
|
|
// Runstate values. Order matters |
262 |
|
|
private static final int RUNNING = 0; |
263 |
|
|
private static final int SHUTDOWN = 1; |
264 |
|
|
private static final int TERMINATING = 2; |
265 |
|
|
private static final int TERMINATED = 3; |
266 |
|
|
|
267 |
|
|
final boolean isShutdown() { return runState >= SHUTDOWN; } |
268 |
|
|
final boolean isTerminating() { return runState >= TERMINATING; } |
269 |
|
|
final boolean isTerminated() { return runState == TERMINATED; } |
270 |
|
|
final boolean shutdown() { return transitionRunStateTo(SHUTDOWN); } |
271 |
|
|
final boolean shutdownNow() { return transitionRunStateTo(TERMINATING); } |
272 |
|
|
|
273 |
|
|
/** |
274 |
jsr166 |
1.21 |
* Transitions to at least the given state. |
275 |
|
|
* |
276 |
|
|
* @return {@code true} if not already at least at given state |
277 |
dl |
1.5 |
*/ |
278 |
|
|
private boolean transitionRunStateTo(int state) { |
279 |
|
|
for (;;) { |
280 |
|
|
int s = runState; |
281 |
|
|
if (s >= state) |
282 |
|
|
return false; |
283 |
jsr166 |
1.12 |
if (UNSAFE.compareAndSwapInt(this, runStateOffset, s, state)) |
284 |
dl |
1.5 |
return true; |
285 |
|
|
} |
286 |
|
|
} |
287 |
|
|
|
288 |
|
|
/** |
289 |
jsr166 |
1.11 |
* Tries to set status to active; fails on contention. |
290 |
dl |
1.5 |
*/ |
291 |
|
|
private boolean tryActivate() { |
292 |
|
|
if (!active) { |
293 |
|
|
if (!pool.tryIncrementActiveCount()) |
294 |
|
|
return false; |
295 |
|
|
active = true; |
296 |
|
|
} |
297 |
|
|
return true; |
298 |
|
|
} |
299 |
|
|
|
300 |
|
|
/** |
301 |
jsr166 |
1.16 |
* Tries to set status to inactive; fails on contention. |
302 |
dl |
1.5 |
*/ |
303 |
|
|
private boolean tryInactivate() { |
304 |
|
|
if (active) { |
305 |
|
|
if (!pool.tryDecrementActiveCount()) |
306 |
|
|
return false; |
307 |
|
|
active = false; |
308 |
|
|
} |
309 |
|
|
return true; |
310 |
|
|
} |
311 |
|
|
|
312 |
|
|
/** |
313 |
jsr166 |
1.11 |
* Computes next value for random victim probe. Scans don't |
314 |
dl |
1.5 |
* require a very high quality generator, but also not a crummy |
315 |
jsr166 |
1.11 |
* one. Marsaglia xor-shift is cheap and works well. |
316 |
dl |
1.5 |
*/ |
317 |
|
|
private static int xorShift(int r) { |
318 |
dl |
1.23 |
r ^= (r << 13); |
319 |
|
|
r ^= (r >>> 17); |
320 |
jsr166 |
1.24 |
return r ^ (r << 5); |
321 |
dl |
1.5 |
} |
322 |
|
|
|
323 |
|
|
// Lifecycle methods |
324 |
dl |
1.1 |
|
325 |
|
|
/** |
326 |
dl |
1.5 |
* This method is required to be public, but should never be |
327 |
|
|
* called explicitly. It performs the main run loop to execute |
328 |
|
|
* ForkJoinTasks. |
329 |
dl |
1.1 |
*/ |
330 |
dl |
1.5 |
public void run() { |
331 |
|
|
Throwable exception = null; |
332 |
|
|
try { |
333 |
|
|
onStart(); |
334 |
|
|
pool.sync(this); // await first pool event |
335 |
|
|
mainLoop(); |
336 |
|
|
} catch (Throwable ex) { |
337 |
|
|
exception = ex; |
338 |
|
|
} finally { |
339 |
|
|
onTermination(exception); |
340 |
|
|
} |
341 |
dl |
1.1 |
} |
342 |
|
|
|
343 |
|
|
/** |
344 |
jsr166 |
1.11 |
* Executes tasks until shut down. |
345 |
dl |
1.1 |
*/ |
346 |
dl |
1.5 |
private void mainLoop() { |
347 |
|
|
while (!isShutdown()) { |
348 |
|
|
ForkJoinTask<?> t = pollTask(); |
349 |
jsr166 |
1.6 |
if (t != null || (t = pollSubmission()) != null) |
350 |
dl |
1.5 |
t.quietlyExec(); |
351 |
|
|
else if (tryInactivate()) |
352 |
|
|
pool.sync(this); |
353 |
|
|
} |
354 |
dl |
1.1 |
} |
355 |
|
|
|
356 |
dl |
1.5 |
/** |
357 |
|
|
* Initializes internal state after construction but before |
358 |
|
|
* processing any tasks. If you override this method, you must |
359 |
|
|
* invoke super.onStart() at the beginning of the method. |
360 |
|
|
* Initialization requires care: Most fields must have legal |
361 |
|
|
* default values, to ensure that attempted accesses from other |
362 |
|
|
* threads work correctly even before this thread starts |
363 |
|
|
* processing tasks. |
364 |
|
|
*/ |
365 |
|
|
protected void onStart() { |
366 |
|
|
// Allocate while starting to improve chances of thread-local |
367 |
|
|
// isolation |
368 |
|
|
queue = new ForkJoinTask<?>[INITIAL_QUEUE_CAPACITY]; |
369 |
|
|
// Initial value of seed need not be especially random but |
370 |
|
|
// should differ across workers and must be nonzero |
371 |
|
|
int p = poolIndex + 1; |
372 |
|
|
seed = p + (p << 8) + (p << 16) + (p << 24); // spread bits |
373 |
|
|
} |
374 |
dl |
1.1 |
|
375 |
|
|
/** |
376 |
jsr166 |
1.11 |
* Performs cleanup associated with termination of this worker |
377 |
dl |
1.5 |
* thread. If you override this method, you must invoke |
378 |
jsr166 |
1.16 |
* {@code super.onTermination} at the end of the overridden method. |
379 |
dl |
1.5 |
* |
380 |
|
|
* @param exception the exception causing this thread to abort due |
381 |
jsr166 |
1.21 |
* to an unrecoverable error, or {@code null} if completed normally |
382 |
dl |
1.1 |
*/ |
383 |
dl |
1.5 |
protected void onTermination(Throwable exception) { |
384 |
|
|
// Execute remaining local tasks unless aborting or terminating |
385 |
|
|
while (exception == null && !pool.isTerminating() && base != sp) { |
386 |
|
|
try { |
387 |
|
|
ForkJoinTask<?> t = popTask(); |
388 |
|
|
if (t != null) |
389 |
|
|
t.quietlyExec(); |
390 |
jsr166 |
1.16 |
} catch (Throwable ex) { |
391 |
dl |
1.5 |
exception = ex; |
392 |
|
|
} |
393 |
|
|
} |
394 |
|
|
// Cancel other tasks, transition status, notify pool, and |
395 |
|
|
// propagate exception to uncaught exception handler |
396 |
|
|
try { |
397 |
jsr166 |
1.16 |
do {} while (!tryInactivate()); // ensure inactive |
398 |
jsr166 |
1.6 |
cancelTasks(); |
399 |
dl |
1.5 |
runState = TERMINATED; |
400 |
|
|
pool.workerTerminated(this); |
401 |
|
|
} catch (Throwable ex) { // Shouldn't ever happen |
402 |
|
|
if (exception == null) // but if so, at least rethrown |
403 |
|
|
exception = ex; |
404 |
|
|
} finally { |
405 |
|
|
if (exception != null) |
406 |
|
|
ForkJoinTask.rethrowException(exception); |
407 |
|
|
} |
408 |
dl |
1.1 |
} |
409 |
|
|
|
410 |
jsr166 |
1.6 |
// Intrinsics-based support for queue operations. |
411 |
dl |
1.5 |
|
412 |
dl |
1.1 |
/** |
413 |
jsr166 |
1.10 |
* Adds in store-order the given task at given slot of q to null. |
414 |
|
|
* Caller must ensure q is non-null and index is in range. |
415 |
dl |
1.1 |
*/ |
416 |
|
|
private static void setSlot(ForkJoinTask<?>[] q, int i, |
417 |
jsr166 |
1.14 |
ForkJoinTask<?> t) { |
418 |
jsr166 |
1.12 |
UNSAFE.putOrderedObject(q, (i << qShift) + qBase, t); |
419 |
dl |
1.1 |
} |
420 |
|
|
|
421 |
|
|
/** |
422 |
jsr166 |
1.10 |
* CAS given slot of q to null. Caller must ensure q is non-null |
423 |
dl |
1.1 |
* and index is in range. |
424 |
|
|
*/ |
425 |
|
|
private static boolean casSlotNull(ForkJoinTask<?>[] q, int i, |
426 |
|
|
ForkJoinTask<?> t) { |
427 |
jsr166 |
1.12 |
return UNSAFE.compareAndSwapObject(q, (i << qShift) + qBase, t, null); |
428 |
dl |
1.1 |
} |
429 |
|
|
|
430 |
dl |
1.5 |
/** |
431 |
|
|
* Sets sp in store-order. |
432 |
|
|
*/ |
433 |
|
|
private void storeSp(int s) { |
434 |
jsr166 |
1.12 |
UNSAFE.putOrderedInt(this, spOffset, s); |
435 |
dl |
1.5 |
} |
436 |
|
|
|
437 |
dl |
1.1 |
// Main queue methods |
438 |
|
|
|
439 |
|
|
/** |
440 |
|
|
* Pushes a task. Called only by current thread. |
441 |
jsr166 |
1.11 |
* |
442 |
jsr166 |
1.10 |
* @param t the task. Caller must ensure non-null. |
443 |
dl |
1.1 |
*/ |
444 |
|
|
final void pushTask(ForkJoinTask<?> t) { |
445 |
|
|
ForkJoinTask<?>[] q = queue; |
446 |
|
|
int mask = q.length - 1; |
447 |
|
|
int s = sp; |
448 |
dl |
1.5 |
setSlot(q, s & mask, t); |
449 |
|
|
storeSp(++s); |
450 |
dl |
1.1 |
if ((s -= base) == 1) |
451 |
dl |
1.5 |
pool.signalWork(); |
452 |
dl |
1.1 |
else if (s >= mask) |
453 |
|
|
growQueue(); |
454 |
|
|
} |
455 |
|
|
|
456 |
|
|
/** |
457 |
|
|
* Tries to take a task from the base of the queue, failing if |
458 |
|
|
* either empty or contended. |
459 |
jsr166 |
1.11 |
* |
460 |
|
|
* @return a task, or null if none or contended |
461 |
dl |
1.1 |
*/ |
462 |
dl |
1.7 |
final ForkJoinTask<?> deqTask() { |
463 |
dl |
1.5 |
ForkJoinTask<?> t; |
464 |
dl |
1.1 |
ForkJoinTask<?>[] q; |
465 |
|
|
int i; |
466 |
|
|
int b; |
467 |
|
|
if (sp != (b = base) && |
468 |
|
|
(q = queue) != null && // must read q after b |
469 |
|
|
(t = q[i = (q.length - 1) & b]) != null && |
470 |
dl |
1.5 |
casSlotNull(q, i, t)) { |
471 |
dl |
1.1 |
base = b + 1; |
472 |
|
|
return t; |
473 |
|
|
} |
474 |
|
|
return null; |
475 |
|
|
} |
476 |
|
|
|
477 |
|
|
/** |
478 |
dl |
1.23 |
* Tries to take a task from the base of own queue, activating if |
479 |
|
|
* necessary, failing only if empty. Called only by current thread. |
480 |
|
|
* |
481 |
|
|
* @return a task, or null if none |
482 |
|
|
*/ |
483 |
|
|
final ForkJoinTask<?> locallyDeqTask() { |
484 |
|
|
int b; |
485 |
|
|
while (sp != (b = base)) { |
486 |
|
|
if (tryActivate()) { |
487 |
|
|
ForkJoinTask<?>[] q = queue; |
488 |
|
|
int i = (q.length - 1) & b; |
489 |
|
|
ForkJoinTask<?> t = q[i]; |
490 |
|
|
if (t != null && casSlotNull(q, i, t)) { |
491 |
|
|
base = b + 1; |
492 |
|
|
return t; |
493 |
|
|
} |
494 |
|
|
} |
495 |
|
|
} |
496 |
|
|
return null; |
497 |
|
|
} |
498 |
|
|
|
499 |
|
|
/** |
500 |
dl |
1.5 |
* Returns a popped task, or null if empty. Ensures active status |
501 |
jsr166 |
1.10 |
* if non-null. Called only by current thread. |
502 |
dl |
1.1 |
*/ |
503 |
|
|
final ForkJoinTask<?> popTask() { |
504 |
|
|
int s = sp; |
505 |
dl |
1.5 |
while (s != base) { |
506 |
|
|
if (tryActivate()) { |
507 |
|
|
ForkJoinTask<?>[] q = queue; |
508 |
|
|
int mask = q.length - 1; |
509 |
|
|
int i = (s - 1) & mask; |
510 |
|
|
ForkJoinTask<?> t = q[i]; |
511 |
|
|
if (t == null || !casSlotNull(q, i, t)) |
512 |
|
|
break; |
513 |
|
|
storeSp(s - 1); |
514 |
|
|
return t; |
515 |
|
|
} |
516 |
dl |
1.1 |
} |
517 |
|
|
return null; |
518 |
|
|
} |
519 |
|
|
|
520 |
|
|
/** |
521 |
|
|
* Specialized version of popTask to pop only if |
522 |
|
|
* topmost element is the given task. Called only |
523 |
dl |
1.5 |
* by current thread while active. |
524 |
jsr166 |
1.11 |
* |
525 |
|
|
* @param t the task. Caller must ensure non-null. |
526 |
dl |
1.1 |
*/ |
527 |
|
|
final boolean unpushTask(ForkJoinTask<?> t) { |
528 |
|
|
ForkJoinTask<?>[] q = queue; |
529 |
|
|
int mask = q.length - 1; |
530 |
|
|
int s = sp - 1; |
531 |
dl |
1.5 |
if (casSlotNull(q, s & mask, t)) { |
532 |
|
|
storeSp(s); |
533 |
dl |
1.1 |
return true; |
534 |
|
|
} |
535 |
|
|
return false; |
536 |
|
|
} |
537 |
|
|
|
538 |
|
|
/** |
539 |
dl |
1.23 |
* Returns next task or null if empty or contended |
540 |
dl |
1.1 |
*/ |
541 |
dl |
1.2 |
final ForkJoinTask<?> peekTask() { |
542 |
dl |
1.1 |
ForkJoinTask<?>[] q = queue; |
543 |
dl |
1.7 |
if (q == null) |
544 |
|
|
return null; |
545 |
|
|
int mask = q.length - 1; |
546 |
jsr166 |
1.15 |
int i = locallyFifo ? base : (sp - 1); |
547 |
dl |
1.7 |
return q[i & mask]; |
548 |
dl |
1.1 |
} |
549 |
|
|
|
550 |
|
|
/** |
551 |
|
|
* Doubles queue array size. Transfers elements by emulating |
552 |
|
|
* steals (deqs) from old array and placing, oldest first, into |
553 |
|
|
* new array. |
554 |
|
|
*/ |
555 |
|
|
private void growQueue() { |
556 |
|
|
ForkJoinTask<?>[] oldQ = queue; |
557 |
|
|
int oldSize = oldQ.length; |
558 |
|
|
int newSize = oldSize << 1; |
559 |
|
|
if (newSize > MAXIMUM_QUEUE_CAPACITY) |
560 |
|
|
throw new RejectedExecutionException("Queue capacity exceeded"); |
561 |
|
|
ForkJoinTask<?>[] newQ = queue = new ForkJoinTask<?>[newSize]; |
562 |
|
|
|
563 |
|
|
int b = base; |
564 |
|
|
int bf = b + oldSize; |
565 |
|
|
int oldMask = oldSize - 1; |
566 |
|
|
int newMask = newSize - 1; |
567 |
|
|
do { |
568 |
|
|
int oldIndex = b & oldMask; |
569 |
|
|
ForkJoinTask<?> t = oldQ[oldIndex]; |
570 |
|
|
if (t != null && !casSlotNull(oldQ, oldIndex, t)) |
571 |
|
|
t = null; |
572 |
|
|
setSlot(newQ, b & newMask, t); |
573 |
|
|
} while (++b != bf); |
574 |
dl |
1.5 |
pool.signalWork(); |
575 |
dl |
1.1 |
} |
576 |
|
|
|
577 |
|
|
/** |
578 |
dl |
1.5 |
* Tries to steal a task from another worker. Starts at a random |
579 |
|
|
* index of workers array, and probes workers until finding one |
580 |
|
|
* with non-empty queue or finding that all are empty. It |
581 |
|
|
* randomly selects the first n probes. If these are empty, it |
582 |
|
|
* resorts to a full circular traversal, which is necessary to |
583 |
|
|
* accurately set active status by caller. Also restarts if pool |
584 |
|
|
* events occurred since last scan, which forces refresh of |
585 |
|
|
* workers array, in case barrier was associated with resize. |
586 |
dl |
1.1 |
* |
587 |
|
|
* This method must be both fast and quiet -- usually avoiding |
588 |
|
|
* memory accesses that could disrupt cache sharing etc other than |
589 |
|
|
* those needed to check for and take tasks. This accounts for, |
590 |
|
|
* among other things, updating random seed in place without |
591 |
dl |
1.5 |
* storing it until exit. |
592 |
dl |
1.1 |
* |
593 |
|
|
* @return a task, or null if none found |
594 |
|
|
*/ |
595 |
dl |
1.5 |
private ForkJoinTask<?> scan() { |
596 |
|
|
ForkJoinTask<?> t = null; |
597 |
|
|
int r = seed; // extract once to keep scan quiet |
598 |
|
|
ForkJoinWorkerThread[] ws; // refreshed on outer loop |
599 |
|
|
int mask; // must be power 2 minus 1 and > 0 |
600 |
|
|
outer:do { |
601 |
|
|
if ((ws = pool.workers) != null && (mask = ws.length - 1) > 0) { |
602 |
dl |
1.1 |
int idx = r; |
603 |
dl |
1.5 |
int probes = ~mask; // use random index while negative |
604 |
dl |
1.1 |
for (;;) { |
605 |
dl |
1.5 |
r = xorShift(r); // update random seed |
606 |
|
|
ForkJoinWorkerThread v = ws[mask & idx]; |
607 |
|
|
if (v == null || v.sp == v.base) { |
608 |
|
|
if (probes <= mask) |
609 |
jsr166 |
1.15 |
idx = (probes++ < 0) ? r : (idx + 1); |
610 |
dl |
1.5 |
else |
611 |
|
|
break; |
612 |
dl |
1.1 |
} |
613 |
dl |
1.5 |
else if (!tryActivate() || (t = v.deqTask()) == null) |
614 |
|
|
continue outer; // restart on contention |
615 |
dl |
1.1 |
else |
616 |
dl |
1.5 |
break outer; |
617 |
dl |
1.1 |
} |
618 |
|
|
} |
619 |
dl |
1.5 |
} while (pool.hasNewSyncEvent(this)); // retry on pool events |
620 |
|
|
seed = r; |
621 |
|
|
return t; |
622 |
dl |
1.1 |
} |
623 |
|
|
|
624 |
|
|
/** |
625 |
jsr166 |
1.11 |
* Gets and removes a local or stolen task. |
626 |
|
|
* |
627 |
dl |
1.5 |
* @return a task, if available |
628 |
|
|
*/ |
629 |
|
|
final ForkJoinTask<?> pollTask() { |
630 |
dl |
1.23 |
ForkJoinTask<?> t = locallyFifo ? locallyDeqTask() : popTask(); |
631 |
dl |
1.5 |
if (t == null && (t = scan()) != null) |
632 |
|
|
++stealCount; |
633 |
|
|
return t; |
634 |
dl |
1.1 |
} |
635 |
|
|
|
636 |
|
|
/** |
637 |
jsr166 |
1.11 |
* Gets a local task. |
638 |
|
|
* |
639 |
dl |
1.7 |
* @return a task, if available |
640 |
|
|
*/ |
641 |
|
|
final ForkJoinTask<?> pollLocalTask() { |
642 |
dl |
1.23 |
return locallyFifo ? locallyDeqTask() : popTask(); |
643 |
dl |
1.7 |
} |
644 |
|
|
|
645 |
|
|
/** |
646 |
dl |
1.5 |
* Returns a pool submission, if one exists, activating first. |
647 |
jsr166 |
1.11 |
* |
648 |
dl |
1.5 |
* @return a submission, if available |
649 |
dl |
1.1 |
*/ |
650 |
dl |
1.5 |
private ForkJoinTask<?> pollSubmission() { |
651 |
|
|
ForkJoinPool p = pool; |
652 |
|
|
while (p.hasQueuedSubmissions()) { |
653 |
|
|
ForkJoinTask<?> t; |
654 |
|
|
if (tryActivate() && (t = p.pollSubmission()) != null) |
655 |
|
|
return t; |
656 |
dl |
1.1 |
} |
657 |
dl |
1.5 |
return null; |
658 |
dl |
1.1 |
} |
659 |
dl |
1.5 |
|
660 |
|
|
// Methods accessed only by Pool |
661 |
|
|
|
662 |
dl |
1.1 |
/** |
663 |
dl |
1.5 |
* Removes and cancels all tasks in queue. Can be called from any |
664 |
|
|
* thread. |
665 |
dl |
1.1 |
*/ |
666 |
dl |
1.5 |
final void cancelTasks() { |
667 |
dl |
1.3 |
ForkJoinTask<?> t; |
668 |
dl |
1.5 |
while (base != sp && (t = deqTask()) != null) |
669 |
|
|
t.cancelIgnoringExceptions(); |
670 |
dl |
1.1 |
} |
671 |
|
|
|
672 |
|
|
/** |
673 |
jsr166 |
1.11 |
* Drains tasks to given collection c. |
674 |
|
|
* |
675 |
dl |
1.7 |
* @return the number of tasks drained |
676 |
|
|
*/ |
677 |
dl |
1.22 |
final int drainTasksTo(Collection<? super ForkJoinTask<?>> c) { |
678 |
dl |
1.7 |
int n = 0; |
679 |
|
|
ForkJoinTask<?> t; |
680 |
|
|
while (base != sp && (t = deqTask()) != null) { |
681 |
|
|
c.add(t); |
682 |
|
|
++n; |
683 |
|
|
} |
684 |
|
|
return n; |
685 |
|
|
} |
686 |
|
|
|
687 |
|
|
/** |
688 |
jsr166 |
1.11 |
* Gets and clears steal count for accumulation by pool. Called |
689 |
dl |
1.5 |
* only when known to be idle (in pool.sync and termination). |
690 |
dl |
1.1 |
*/ |
691 |
dl |
1.5 |
final int getAndClearStealCount() { |
692 |
|
|
int sc = stealCount; |
693 |
|
|
stealCount = 0; |
694 |
|
|
return sc; |
695 |
|
|
} |
696 |
|
|
|
697 |
|
|
/** |
698 |
jsr166 |
1.21 |
* Returns {@code true} if at least one worker in the given array |
699 |
|
|
* appears to have at least one queued task. |
700 |
jsr166 |
1.16 |
* |
701 |
dl |
1.5 |
* @param ws array of workers |
702 |
|
|
*/ |
703 |
|
|
static boolean hasQueuedTasks(ForkJoinWorkerThread[] ws) { |
704 |
|
|
if (ws != null) { |
705 |
|
|
int len = ws.length; |
706 |
|
|
for (int j = 0; j < 2; ++j) { // need two passes for clean sweep |
707 |
|
|
for (int i = 0; i < len; ++i) { |
708 |
|
|
ForkJoinWorkerThread w = ws[i]; |
709 |
|
|
if (w != null && w.sp != w.base) |
710 |
|
|
return true; |
711 |
dl |
1.1 |
} |
712 |
|
|
} |
713 |
|
|
} |
714 |
dl |
1.5 |
return false; |
715 |
dl |
1.1 |
} |
716 |
|
|
|
717 |
dl |
1.5 |
// Support methods for ForkJoinTask |
718 |
|
|
|
719 |
dl |
1.1 |
/** |
720 |
dl |
1.2 |
* Returns an estimate of the number of tasks in the queue. |
721 |
|
|
*/ |
722 |
|
|
final int getQueueSize() { |
723 |
jsr166 |
1.15 |
// suppress momentarily negative values |
724 |
|
|
return Math.max(0, sp - base); |
725 |
dl |
1.2 |
} |
726 |
|
|
|
727 |
|
|
/** |
728 |
dl |
1.1 |
* Returns an estimate of the number of tasks, offset by a |
729 |
|
|
* function of number of idle workers. |
730 |
|
|
*/ |
731 |
|
|
final int getEstimatedSurplusTaskCount() { |
732 |
dl |
1.3 |
// The halving approximates weighting idle vs non-idle workers |
733 |
dl |
1.1 |
return (sp - base) - (pool.getIdleThreadCount() >>> 1); |
734 |
|
|
} |
735 |
|
|
|
736 |
|
|
/** |
737 |
jsr166 |
1.16 |
* Scans, returning early if joinMe done. |
738 |
dl |
1.1 |
*/ |
739 |
dl |
1.5 |
final ForkJoinTask<?> scanWhileJoining(ForkJoinTask<?> joinMe) { |
740 |
|
|
ForkJoinTask<?> t = pollTask(); |
741 |
|
|
if (t != null && joinMe.status < 0 && sp == base) { |
742 |
|
|
pushTask(t); // unsteal if done and this task would be stealable |
743 |
|
|
t = null; |
744 |
|
|
} |
745 |
|
|
return t; |
746 |
dl |
1.1 |
} |
747 |
jsr166 |
1.6 |
|
748 |
dl |
1.1 |
/** |
749 |
jsr166 |
1.16 |
* Runs tasks until {@code pool.isQuiescent()}. |
750 |
dl |
1.1 |
*/ |
751 |
dl |
1.5 |
final void helpQuiescePool() { |
752 |
|
|
for (;;) { |
753 |
|
|
ForkJoinTask<?> t = pollTask(); |
754 |
jsr166 |
1.6 |
if (t != null) |
755 |
dl |
1.5 |
t.quietlyExec(); |
756 |
|
|
else if (tryInactivate() && pool.isQuiescent()) |
757 |
|
|
break; |
758 |
|
|
} |
759 |
jsr166 |
1.16 |
do {} while (!tryActivate()); // re-activate on exit |
760 |
dl |
1.1 |
} |
761 |
|
|
|
762 |
jsr166 |
1.20 |
// Unsafe mechanics |
763 |
|
|
|
764 |
|
|
private static final sun.misc.Unsafe UNSAFE = getUnsafe(); |
765 |
|
|
private static final long spOffset = |
766 |
|
|
objectFieldOffset("sp", ForkJoinWorkerThread.class); |
767 |
|
|
private static final long runStateOffset = |
768 |
|
|
objectFieldOffset("runState", ForkJoinWorkerThread.class); |
769 |
|
|
private static final long qBase; |
770 |
|
|
private static final int qShift; |
771 |
|
|
|
772 |
|
|
static { |
773 |
|
|
qBase = UNSAFE.arrayBaseOffset(ForkJoinTask[].class); |
774 |
|
|
int s = UNSAFE.arrayIndexScale(ForkJoinTask[].class); |
775 |
|
|
if ((s & (s-1)) != 0) |
776 |
|
|
throw new Error("data type scale not a power of two"); |
777 |
|
|
qShift = 31 - Integer.numberOfLeadingZeros(s); |
778 |
|
|
} |
779 |
|
|
|
780 |
|
|
private static long objectFieldOffset(String field, Class<?> klazz) { |
781 |
|
|
try { |
782 |
|
|
return UNSAFE.objectFieldOffset(klazz.getDeclaredField(field)); |
783 |
|
|
} catch (NoSuchFieldException e) { |
784 |
|
|
// Convert Exception to corresponding Error |
785 |
|
|
NoSuchFieldError error = new NoSuchFieldError(field); |
786 |
|
|
error.initCause(e); |
787 |
|
|
throw error; |
788 |
|
|
} |
789 |
|
|
} |
790 |
|
|
|
791 |
|
|
/** |
792 |
|
|
* Returns a sun.misc.Unsafe. Suitable for use in a 3rd party package. |
793 |
|
|
* Replace with a simple call to Unsafe.getUnsafe when integrating |
794 |
|
|
* into a jdk. |
795 |
|
|
* |
796 |
|
|
* @return a sun.misc.Unsafe |
797 |
|
|
*/ |
798 |
jsr166 |
1.17 |
private static sun.misc.Unsafe getUnsafe() { |
799 |
jsr166 |
1.6 |
try { |
800 |
jsr166 |
1.17 |
return sun.misc.Unsafe.getUnsafe(); |
801 |
jsr166 |
1.6 |
} catch (SecurityException se) { |
802 |
|
|
try { |
803 |
|
|
return java.security.AccessController.doPrivileged |
804 |
jsr166 |
1.20 |
(new java.security |
805 |
|
|
.PrivilegedExceptionAction<sun.misc.Unsafe>() { |
806 |
jsr166 |
1.17 |
public sun.misc.Unsafe run() throws Exception { |
807 |
jsr166 |
1.20 |
java.lang.reflect.Field f = sun.misc |
808 |
|
|
.Unsafe.class.getDeclaredField("theUnsafe"); |
809 |
|
|
f.setAccessible(true); |
810 |
|
|
return (sun.misc.Unsafe) f.get(null); |
811 |
jsr166 |
1.6 |
}}); |
812 |
|
|
} catch (java.security.PrivilegedActionException e) { |
813 |
jsr166 |
1.17 |
throw new RuntimeException("Could not initialize intrinsics", |
814 |
|
|
e.getCause()); |
815 |
jsr166 |
1.6 |
} |
816 |
|
|
} |
817 |
|
|
} |
818 |
dl |
1.1 |
} |