| 6 |
|
|
| 7 |
|
package jsr166y; |
| 8 |
|
|
| 9 |
– |
import java.util.concurrent.*; |
| 10 |
– |
|
| 9 |
|
import java.util.ArrayList; |
| 10 |
|
import java.util.Arrays; |
| 11 |
|
import java.util.Collection; |
| 67 |
|
* <td ALIGN=CENTER> <b>Call from within fork/join computations</b></td> |
| 68 |
|
* </tr> |
| 69 |
|
* <tr> |
| 70 |
< |
* <td> <b>Arange async execution</td> |
| 70 |
> |
* <td> <b>Arrange async execution</td> |
| 71 |
|
* <td> {@link #execute(ForkJoinTask)}</td> |
| 72 |
|
* <td> {@link ForkJoinTask#fork}</td> |
| 73 |
|
* </tr> |
| 138 |
|
* Beyond work-stealing support and essential bookkeeping, the |
| 139 |
|
* main responsibility of this framework is to take actions when |
| 140 |
|
* one worker is waiting to join a task stolen (or always held by) |
| 141 |
< |
* another. Becauae we are multiplexing many tasks on to a pool |
| 141 |
> |
* another. Because we are multiplexing many tasks on to a pool |
| 142 |
|
* of workers, we can't just let them block (as in Thread.join). |
| 143 |
|
* We also cannot just reassign the joiner's run-time stack with |
| 144 |
|
* another and replace it later, which would be a form of |
| 155 |
|
* links to try to find such a task. |
| 156 |
|
* |
| 157 |
|
* Compensating: Unless there are already enough live threads, |
| 158 |
< |
* method helpMaintainParallelism() may create or or |
| 158 |
> |
* method helpMaintainParallelism() may create or |
| 159 |
|
* re-activate a spare thread to compensate for blocked |
| 160 |
|
* joiners until they unblock. |
| 161 |
|
* |
| 224 |
|
* ManagedBlocker), we may create or resume others to take their |
| 225 |
|
* place until they unblock (see below). Implementing this |
| 226 |
|
* requires counts of the number of "running" threads (i.e., those |
| 227 |
< |
* that are neither blocked nor artifically suspended) as well as |
| 227 |
> |
* that are neither blocked nor artificially suspended) as well as |
| 228 |
|
* the total number. These two values are packed into one field, |
| 229 |
|
* "workerCounts" because we need accurate snapshots when deciding |
| 230 |
|
* to create, resume or suspend. Note however that the |
| 231 |
< |
* correspondance of these counts to reality is not guaranteed. In |
| 231 |
> |
* correspondence of these counts to reality is not guaranteed. In |
| 232 |
|
* particular updates for unblocked threads may lag until they |
| 233 |
|
* actually wake up. |
| 234 |
|
* |
| 299 |
|
* about the same time as another is needlessly being created. We |
| 300 |
|
* counteract this and related slop in part by requiring resumed |
| 301 |
|
* spares to immediately recheck (in preStep) to see whether they |
| 302 |
< |
* they should re-suspend. |
| 302 |
> |
* should re-suspend. |
| 303 |
|
* |
| 304 |
|
* 6. Killing off unneeded workers. A timeout mechanism is used to |
| 305 |
|
* shed unused workers: The oldest (first) event queue waiter uses |
| 313 |
|
* 7. Deciding when to create new workers. The main dynamic |
| 314 |
|
* control in this class is deciding when to create extra threads |
| 315 |
|
* in method helpMaintainParallelism. We would like to keep |
| 316 |
< |
* exactly #parallelism threads running, which is an impossble |
| 316 |
> |
* exactly #parallelism threads running, which is an impossible |
| 317 |
|
* task. We always need to create one when the number of running |
| 318 |
|
* threads would become zero and all workers are busy. Beyond |
| 319 |
< |
* this, we must rely on heuristics that work well in the the |
| 320 |
< |
* presence of transients phenomena such as GC stalls, dynamic |
| 319 |
> |
* this, we must rely on heuristics that work well in the |
| 320 |
> |
* presence of transient phenomena such as GC stalls, dynamic |
| 321 |
|
* compilation, and wake-up lags. These transients are extremely |
| 322 |
|
* common -- we are normally trying to fully saturate the CPUs on |
| 323 |
|
* a machine, so almost any activity other than running tasks |
| 344 |
|
* "while ((local = field) != 0)") which are usually the simplest |
| 345 |
|
* way to ensure the required read orderings (which are sometimes |
| 346 |
|
* critical). Also several occurrences of the unusual "do {} |
| 347 |
< |
* while(!cas...)" which is the simplest way to force an update of |
| 347 |
> |
* while (!cas...)" which is the simplest way to force an update of |
| 348 |
|
* a CAS'ed variable. There are also other coding oddities that |
| 349 |
|
* help some methods perform reasonably even when interpreted (not |
| 350 |
|
* compiled), at the expense of some messy constructions that |
| 418 |
|
/** |
| 419 |
|
* The time to block in a join (see awaitJoin) before checking if |
| 420 |
|
* a new worker should be (re)started to maintain parallelism |
| 421 |
< |
* level. The value should be short enough to maintain gloabal |
| 421 |
> |
* level. The value should be short enough to maintain global |
| 422 |
|
* responsiveness and progress but long enough to avoid |
| 423 |
|
* counterproductive firings during GC stalls or unrelated system |
| 424 |
|
* activity, and to not bog down systems with continual re-firings |
| 428 |
|
|
| 429 |
|
/** |
| 430 |
|
* The wakeup interval (in nanoseconds) for the oldest worker |
| 431 |
< |
* worker waiting for an event invokes tryShutdownUnusedWorker to shrink |
| 432 |
< |
* the number of workers. The exact value does not matter too |
| 433 |
< |
* much, but should be long enough to slowly release resources |
| 434 |
< |
* during long periods without use without disrupting normal use. |
| 431 |
> |
* waiting for an event to invoke tryShutdownUnusedWorker to |
| 432 |
> |
* shrink the number of workers. The exact value does not matter |
| 433 |
> |
* too much. It must be short enough to release resources during |
| 434 |
> |
* sustained periods of idleness, but not so short that threads |
| 435 |
> |
* are continually re-created. |
| 436 |
|
*/ |
| 437 |
|
private static final long SHRINK_RATE_NANOS = |
| 438 |
|
30L * 1000L * 1000L * 1000L; // 2 per minute |
| 482 |
|
private volatile long stealCount; |
| 483 |
|
|
| 484 |
|
/** |
| 485 |
< |
* Encoded record of top of treiber stack of threads waiting for |
| 485 |
> |
* Encoded record of top of Treiber stack of threads waiting for |
| 486 |
|
* events. The top 32 bits contain the count being waited for. The |
| 487 |
|
* bottom 16 bits contains one plus the pool index of waiting |
| 488 |
|
* worker thread. (Bits 16-31 are unused.) |
| 501 |
|
private volatile int eventCount; |
| 502 |
|
|
| 503 |
|
/** |
| 504 |
< |
* Encoded record of top of treiber stack of spare threads waiting |
| 504 |
> |
* Encoded record of top of Treiber stack of spare threads waiting |
| 505 |
|
* for resumption. The top 16 bits contain an arbitrary count to |
| 506 |
|
* avoid ABA effects. The bottom 16bits contains one plus the pool |
| 507 |
|
* index of waiting worker thread. |
| 604 |
|
* (rarely) necessary when other count updates lag. |
| 605 |
|
* |
| 606 |
|
* @param dr -- either zero or ONE_RUNNING |
| 607 |
< |
* @param dt == either zero or ONE_TOTAL |
| 607 |
> |
* @param dt -- either zero or ONE_TOTAL |
| 608 |
|
*/ |
| 609 |
|
private void decrementWorkerCounts(int dr, int dt) { |
| 610 |
|
for (;;) { |
| 673 |
|
} |
| 674 |
|
|
| 675 |
|
/** |
| 676 |
< |
* Nulls out record of worker in workers array |
| 676 |
> |
* Nulls out record of worker in workers array. |
| 677 |
|
*/ |
| 678 |
|
private void forgetWorker(ForkJoinWorkerThread w) { |
| 679 |
|
int idx = w.poolIndex; |
| 680 |
< |
// Locking helps method recordWorker avoid unecessary expansion |
| 680 |
> |
// Locking helps method recordWorker avoid unnecessary expansion |
| 681 |
|
final ReentrantLock lock = this.workerLock; |
| 682 |
|
lock.lock(); |
| 683 |
|
try { |
| 692 |
|
/** |
| 693 |
|
* Final callback from terminating worker. Removes record of |
| 694 |
|
* worker from array, and adjusts counts. If pool is shutting |
| 695 |
< |
* down, tries to complete terminatation. |
| 695 |
> |
* down, tries to complete termination. |
| 696 |
|
* |
| 697 |
|
* @param w the worker |
| 698 |
|
*/ |
| 806 |
|
// Maintaining parallelism |
| 807 |
|
|
| 808 |
|
/** |
| 809 |
< |
* Pushes worker onto the spare stack |
| 809 |
> |
* Pushes worker onto the spare stack. |
| 810 |
|
*/ |
| 811 |
|
final void pushSpare(ForkJoinWorkerThread w) { |
| 812 |
|
int ns = (++w.spareCount << SPARE_COUNT_SHIFT) | (w.poolIndex + 1); |
| 831 |
|
UNSAFE.compareAndSwapInt(this, spareWaitersOffset, |
| 832 |
|
sw, w.nextSpare)) { |
| 833 |
|
int c; // increment running count before resume |
| 834 |
< |
do {} while(!UNSAFE.compareAndSwapInt |
| 835 |
< |
(this, workerCountsOffset, |
| 836 |
< |
c = workerCounts, c + ONE_RUNNING)); |
| 834 |
> |
do {} while (!UNSAFE.compareAndSwapInt |
| 835 |
> |
(this, workerCountsOffset, |
| 836 |
> |
c = workerCounts, c + ONE_RUNNING)); |
| 837 |
|
if (w.tryUnsuspend()) |
| 838 |
|
LockSupport.unpark(w); |
| 839 |
|
else // back out if w was shutdown |
| 845 |
|
* Tries to increase the number of running workers if below target |
| 846 |
|
* parallelism: If a spare exists tries to resume it via |
| 847 |
|
* tryResumeSpare. Otherwise, if not enough total workers or all |
| 848 |
< |
* existing workers are busy, adds a new worker. In all casses also |
| 848 |
> |
* existing workers are busy, adds a new worker. In all cases also |
| 849 |
|
* helps wake up releasable workers waiting for work. |
| 850 |
|
*/ |
| 851 |
|
private void helpMaintainParallelism() { |
| 984 |
|
w.lastEventCount = ec; // no need to wait |
| 985 |
|
break; |
| 986 |
|
} |
| 987 |
< |
else if (!(inactivate |= active)) |
| 987 |
> |
else if (!(inactivate |= active)) |
| 988 |
|
eventSync(w, wec); // must inactivate before sync |
| 989 |
|
} |
| 990 |
|
else |
| 1106 |
|
c = eventCount, c+1); |
| 1107 |
|
eventWaiters = 0L; // clobber lists |
| 1108 |
|
spareWaiters = 0; |
| 1109 |
< |
ForkJoinWorkerThread[] ws = workers; |
| 1111 |
< |
int n = ws.length; |
| 1112 |
< |
for (int i = 0; i < n; ++i) { |
| 1113 |
< |
ForkJoinWorkerThread w = ws[i]; |
| 1109 |
> |
for (ForkJoinWorkerThread w : workers) { |
| 1110 |
|
if (w != null) { |
| 1111 |
|
w.shutdown(); |
| 1112 |
|
if (passes > 0 && !w.isTerminated()) { |
| 1125 |
|
} |
| 1126 |
|
|
| 1127 |
|
/** |
| 1128 |
< |
* Clear out and cancel submissions, ignoring exceptions |
| 1128 |
> |
* Clears out and cancels submissions, ignoring exceptions. |
| 1129 |
|
*/ |
| 1130 |
|
private void cancelSubmissions() { |
| 1131 |
|
ForkJoinTask<?> task; |
| 1140 |
|
// misc support for ForkJoinWorkerThread |
| 1141 |
|
|
| 1142 |
|
/** |
| 1143 |
< |
* Returns pool number |
| 1143 |
> |
* Returns pool number. |
| 1144 |
|
*/ |
| 1145 |
|
final int getPoolNumber() { |
| 1146 |
|
return poolNumber; |
| 1147 |
|
} |
| 1148 |
|
|
| 1149 |
|
/** |
| 1150 |
< |
* Tries to accumulates steal count from a worker, clearing |
| 1151 |
< |
* the worker's value. |
| 1150 |
> |
* Tries to accumulate steal count from a worker, clearing |
| 1151 |
> |
* the worker's value if successful. |
| 1152 |
|
* |
| 1153 |
|
* @return true if worker steal count now zero |
| 1154 |
|
*/ |
| 1170 |
|
*/ |
| 1171 |
|
final int idlePerActive() { |
| 1172 |
|
int pc = parallelism; // use parallelism, not rc |
| 1173 |
< |
int ac = runState; // no mask -- artifically boosts during shutdown |
| 1173 |
> |
int ac = runState; // no mask -- artificially boosts during shutdown |
| 1174 |
|
// Use exact results for small values, saturate past 4 |
| 1175 |
< |
return pc <= ac? 0 : pc >>> 1 <= ac? 1 : pc >>> 2 <= ac? 3 : pc >>> 3; |
| 1175 |
> |
return ((pc <= ac) ? 0 : |
| 1176 |
> |
(pc >>> 1 <= ac) ? 1 : |
| 1177 |
> |
(pc >>> 2 <= ac) ? 3 : |
| 1178 |
> |
pc >>> 3); |
| 1179 |
|
} |
| 1180 |
|
|
| 1181 |
|
// Public and protected methods |
| 1225 |
|
* use {@link #defaultForkJoinWorkerThreadFactory}. |
| 1226 |
|
* @param handler the handler for internal worker threads that |
| 1227 |
|
* terminate due to unrecoverable errors encountered while executing |
| 1228 |
< |
* tasks. For default value, use <code>null</code>. |
| 1228 |
> |
* tasks. For default value, use {@code null}. |
| 1229 |
|
* @param asyncMode if true, |
| 1230 |
|
* establishes local first-in-first-out scheduling mode for forked |
| 1231 |
|
* tasks that are never joined. This mode may be more appropriate |
| 1232 |
|
* than default locally stack-based mode in applications in which |
| 1233 |
|
* worker threads only process event-style asynchronous tasks. |
| 1234 |
< |
* For default value, use <code>false</code>. |
| 1234 |
> |
* For default value, use {@code false}. |
| 1235 |
|
* @throws IllegalArgumentException if parallelism less than or |
| 1236 |
|
* equal to zero, or greater than implementation limit |
| 1237 |
|
* @throws NullPointerException if the factory is null |
| 1441 |
|
|
| 1442 |
|
/** |
| 1443 |
|
* Returns the number of worker threads that have started but not |
| 1444 |
< |
* yet terminated. This result returned by this method may differ |
| 1444 |
> |
* yet terminated. The result returned by this method may differ |
| 1445 |
|
* from {@link #getParallelism} when threads are created to |
| 1446 |
|
* maintain parallelism when others are cooperatively blocked. |
| 1447 |
|
* |
| 1526 |
|
*/ |
| 1527 |
|
public long getQueuedTaskCount() { |
| 1528 |
|
long count = 0; |
| 1529 |
< |
ForkJoinWorkerThread[] ws = workers; |
| 1531 |
< |
int n = ws.length; |
| 1532 |
< |
for (int i = 0; i < n; ++i) { |
| 1533 |
< |
ForkJoinWorkerThread w = ws[i]; |
| 1529 |
> |
for (ForkJoinWorkerThread w : workers) |
| 1530 |
|
if (w != null) |
| 1531 |
|
count += w.getQueueSize(); |
| 1536 |
– |
} |
| 1532 |
|
return count; |
| 1533 |
|
} |
| 1534 |
|
|
| 1583 |
|
*/ |
| 1584 |
|
protected int drainTasksTo(Collection<? super ForkJoinTask<?>> c) { |
| 1585 |
|
int count = submissionQueue.drainTo(c); |
| 1586 |
< |
ForkJoinWorkerThread[] ws = workers; |
| 1592 |
< |
int n = ws.length; |
| 1593 |
< |
for (int i = 0; i < n; ++i) { |
| 1594 |
< |
ForkJoinWorkerThread w = ws[i]; |
| 1586 |
> |
for (ForkJoinWorkerThread w : workers) |
| 1587 |
|
if (w != null) |
| 1588 |
|
count += w.drainTasksTo(c); |
| 1597 |
– |
} |
| 1589 |
|
return count; |
| 1590 |
|
} |
| 1591 |
|
|
| 1712 |
|
throws InterruptedException { |
| 1713 |
|
try { |
| 1714 |
|
return termination.awaitAdvanceInterruptibly(0, timeout, unit) > 0; |
| 1715 |
< |
} catch(TimeoutException ex) { |
| 1715 |
> |
} catch (TimeoutException ex) { |
| 1716 |
|
return false; |
| 1717 |
|
} |
| 1718 |
|
} |
| 1842 |
|
private static final long eventCountOffset = |
| 1843 |
|
objectFieldOffset("eventCount", ForkJoinPool.class); |
| 1844 |
|
private static final long eventWaitersOffset = |
| 1845 |
< |
objectFieldOffset("eventWaiters",ForkJoinPool.class); |
| 1845 |
> |
objectFieldOffset("eventWaiters", ForkJoinPool.class); |
| 1846 |
|
private static final long stealCountOffset = |
| 1847 |
< |
objectFieldOffset("stealCount",ForkJoinPool.class); |
| 1847 |
> |
objectFieldOffset("stealCount", ForkJoinPool.class); |
| 1848 |
|
private static final long spareWaitersOffset = |
| 1849 |
< |
objectFieldOffset("spareWaiters",ForkJoinPool.class); |
| 1849 |
> |
objectFieldOffset("spareWaiters", ForkJoinPool.class); |
| 1850 |
|
|
| 1851 |
|
private static long objectFieldOffset(String field, Class<?> klazz) { |
| 1852 |
|
try { |
