ViewVC Help

View File | Revision Log | Show Annotations | Download File | Root Listing

root/jsr166/jsr166/src/jsr166y/ForkJoinPool.java

Comparing jsr166/src/jsr166y/ForkJoinPool.java (file contents):
Revision 1.63 by dl, Fri Aug 13 16:21:23 2010 UTC vs.
Revision 1.93 by dl, Wed Feb 23 12:48:43 2011 UTC

#	Line 6 | Line 6
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;
12		import java.util.Collections;
13		import java.util.List;
14	+	import java.util.Random;
15	+	import java.util.concurrent.AbstractExecutorService;
16	+	import java.util.concurrent.Callable;
17	+	import java.util.concurrent.ExecutorService;
18	+	import java.util.concurrent.Future;
19	+	import java.util.concurrent.RejectedExecutionException;
20	+	import java.util.concurrent.RunnableFuture;
21	+	import java.util.concurrent.TimeUnit;
22	+	import java.util.concurrent.TimeoutException;
23	+	import java.util.concurrent.atomic.AtomicInteger;
24		import java.util.concurrent.locks.LockSupport;
25		import java.util.concurrent.locks.ReentrantLock;
26	<	import java.util.concurrent.atomic.AtomicInteger;
19	<	import java.util.concurrent.CountDownLatch;
26	>	import java.util.concurrent.locks.Condition;
27
28		/**
29		* An {@link ExecutorService} for running {@link ForkJoinTask}s.
#	Line 69 | Line 76 | import java.util.concurrent.CountDownLat
76		*    <td ALIGN=CENTER> <b>Call from within fork/join computations</b></td>
77		*  </tr>
78		*  <tr>
79	<	*    <td> <b>Arange async execution</td>
79	>	*    <td> <b>Arrange async execution</td>
80		*    <td> {@link #execute(ForkJoinTask)}</td>
81		*    <td> {@link ForkJoinTask#fork}</td>
82		*  </tr>
#	Line 124 | Line 131 | public class ForkJoinPool extends Abstra
131		* set of worker threads: Submissions from non-FJ threads enter
132		* into a submission queue. Workers take these tasks and typically
133		* split them into subtasks that may be stolen by other workers.
134	<	* The main work-stealing mechanics implemented in class
135	<	* ForkJoinWorkerThread give first priority to processing tasks
136	<	* from their own queues (LIFO or FIFO, depending on mode), then
137	<	* to randomized FIFO steals of tasks in other worker queues, and
138	<	* lastly to new submissions. These mechanics do not consider
139	<	* affinities, loads, cache localities, etc, so rarely provide the
140	<	* best possible performance on a given machine, but portably
141	<	* provide good throughput by averaging over these factors.
142	<	* (Further, even if we did try to use such information, we do not
143	<	* usually have a basis for exploiting it. For example, some sets
144	<	* of tasks profit from cache affinities, but others are harmed by
145	<	* cache pollution effects.)
146	<	*
147	<	* Beyond work-stealing support and essential bookkeeping, the
148	<	* main responsibility of this framework is to take actions when
149	<	* one worker is waiting to join a task stolen (or always held by)
150	<	* another.  Becauae we are multiplexing many tasks on to a pool
151	<	* of workers, we can't just let them block (as in Thread.join).
152	<	* We also cannot just reassign the joiner's run-time stack with
153	<	* another and replace it later, which would be a form of
154	<	* "continuation", that even if possible is not necessarily a good
155	<	* idea. Given that the creation costs of most threads on most
156	<	* systems mainly surrounds setting up runtime stacks, thread
157	<	* creation and switching is usually not much more expensive than
158	<	* stack creation and switching, and is more flexible). Instead we
134	>	* Preference rules give first priority to processing tasks from
135	>	* their own queues (LIFO or FIFO, depending on mode), then to
136	>	* randomized FIFO steals of tasks in other worker queues, and
137	>	* lastly to new submissions.
138	>	*
139	>	* The main throughput advantages of work-stealing stem from
140	>	* decentralized control -- workers mostly take tasks from
141	>	* themselves or each other. We cannot negate this in the
142	>	* implementation of other management responsibilities. The main
143	>	* tactic for avoiding bottlenecks is packing nearly all
144	>	* essentially atomic control state into a single 64bit volatile
145	>	* variable ("ctl"). This variable is read on the order of 10-100
146	>	* times as often as it is modified (always via CAS). (There is
147	>	* some additional control state, for example variable "shutdown"
148	>	* for which we can cope with uncoordinated updates.)  This
149	>	* streamlines synchronization and control at the expense of messy
150	>	* constructions needed to repack status bits upon updates.
151	>	* Updates tend not to contend with each other except during
152	>	* bursts while submitted tasks begin or end.  In some cases when
153	>	* they do contend, threads can instead do something else
154	>	* (usually, scan for tesks) until contention subsides.
155	>	*
156	>	* To enable packing, we restrict maximum parallelism to (1<<15)-1
157	>	* (which is far in excess of normal operating range) to allow
158	>	* ids, counts, and their negations (used for thresholding) to fit
159	>	* into 16bit fields.
160	>	*
161	>	* Recording Workers.  Workers are recorded in the "workers" array
162	>	* that is created upon pool construction and expanded if (rarely)
163	>	* necessary.  This is an array as opposed to some other data
164	>	* structure to support index-based random steals by workers.
165	>	* Updates to the array recording new workers and unrecording
166	>	* terminated ones are protected from each other by a seqLock
167	>	* (scanGuard) but the array is otherwise concurrently readable,
168	>	* and accessed directly by workers. To simplify index-based
169	>	* operations, the array size is always a power of two, and all
170	>	* readers must tolerate null slots. To avoid flailing during
171	>	* start-up, the array is presized to hold twice #parallelism
172	>	* workers (which is unlikely to need further resizing during
173	>	* execution). But to avoid dealing with so many null slots,
174	>	* variable scanGuard includes a mask for the nearest power of two
175	>	* that contains all current workers.  All worker thread creation
176	>	* is on-demand, triggered by task submissions, replacement of
177	>	* terminated workers, and/or compensation for blocked
178	>	* workers. However, all other support code is set up to work with
179	>	* other policies.  To ensure that we do not hold on to worker
180	>	* references that would prevent GC, ALL accesses to workers are
181	>	* via indices into the workers array (which is one source of some
182	>	* of the messy code constructions here). In essence, the workers
183	>	* array serves as a weak reference mechanism. Thus for example
184	>	* the wait queue field of ctl stores worker indices, not worker
185	>	* references.  Access to the workers in associated methods (for
186	>	* example signalWork) must both index-check and null-check the
187	>	* IDs. All such accesses ignore bad IDs by returning out early
188	>	* from what they are doing, since this can only be associated
189	>	* with termination, in which case it is OK to give up.
190	>	*
191	>	* All uses of the workers array, as well as queue arrays, check
192	>	* that the array is non-null (even if previously non-null). This
193	>	* allows nulling during termination, which is currently not
194	>	* necessary, but remains an option for resource-revocation-based
195	>	* shutdown schemes.
196	>	*
197	>	* Wait Queuing. Unlike HPC work-stealing frameworks, we cannot
198	>	* let workers spin indefinitely scanning for tasks when none are
199	>	* can be immediately found, and we cannot start/resume workers
200	>	* unless there appear to be tasks available.  On the other hand,
201	>	* we must quickly prod them into action when new tasks are
202	>	* submitted or generated.  We park/unpark workers after placing
203	>	* in an event wait queue when they cannot find work. This "queue"
204	>	* is actually a simple Treiber stack, headed by the "id" field of
205	>	* ctl, plus a 15bit counter value to both wake up waiters (by
206	>	* advancing their count) and avoid ABA effects. Successors are
207	>	* held in worker field "nextWait".  Queuing deals with several
208	>	* intrinsic races, mainly that a task-producing thread can miss
209	>	* seeing (and signalling) another thread that gave up looking for
210	>	* work but has not yet entered the wait queue. We solve this by
211	>	* requiring a full sweep of all workers both before (in scan())
212	>	* and after (in awaitWork()) a newly waiting worker is added to
213	>	* the wait queue. During a rescan, the worker might release some
214	>	* other queued worker rather than itself, which has the same net
215	>	* effect.
216	>	*
217	>	* Signalling.  We create or wake up workers only when there
218	>	* appears to be at least one task they might be able to find and
219	>	* execute.  When a submission is added or another worker adds a
220	>	* task to a queue that previously had two or fewer tasks, they
221	>	* signal waiting workers (or trigger creation of new ones if
222	>	* fewer than the given parallelism level -- see signalWork).
223	>	* These primary signals are buttressed by signals during rescans
224	>	* as well as those performed when a worker steals a task and
225	>	* notices that there are more tasks too; together these cover the
226	>	* signals needed in cases when more than two tasks are pushed
227	>	* but untaken.
228	>	*
229	>	* Trimming workers. To release resources after periods of lack of
230	>	* use, a worker starting to wait when the pool is quiescent will
231	>	* time out and terminate if the pool has remained quiescent for
232	>	* SHRINK_RATE nanosecs.
233	>	*
234	>	* Submissions. External submissions are maintained in an
235	>	* array-based queue that is structured identically to
236	>	* ForkJoinWorkerThread queues (which see) except for the use of
237	>	* submissionLock in method addSubmission. Unlike worker queues,
238	>	* multiple external threads can add new submissions.
239	>	*
240	>	* Compensation. Beyond work-stealing support and lifecycle
241	>	* control, the main responsibility of this framework is to take
242	>	* actions when one worker is waiting to join a task stolen (or
243	>	* always held by) another.  Because we are multiplexing many
244	>	* tasks on to a pool of workers, we can't just let them block (as
245	>	* in Thread.join).  We also cannot just reassign the joiner's
246	>	* run-time stack with another and replace it later, which would
247	>	* be a form of "continuation", that even if possible is not
248	>	* necessarily a good idea since we sometimes need both an
249	>	* unblocked task and its continuation to progress. Instead we
250		* combine two tactics:
251		*
252		*   Helping: Arranging for the joiner to execute some task that it
253		*      would be running if the steal had not occurred.  Method
254	<	*      ForkJoinWorkerThread.helpJoinTask tracks joining->stealing
254	>	*      ForkJoinWorkerThread.joinTask tracks joining->stealing
255		*      links to try to find such a task.
256		*
257		*   Compensating: Unless there are already enough live threads,
258	<	*      method helpMaintainParallelism() may create or or
259	<	*      re-activate a spare thread to compensate for blocked
260	<	*      joiners until they unblock.
163	<	*
164	<	* Because the determining existence of conservatively safe
165	<	* helping targets, the availability of already-created spares,
166	<	* and the apparent need to create new spares are all racy and
167	<	* require heuristic guidance, we rely on multiple retries of
168	<	* each. Further, because it is impossible to keep exactly the
169	<	* target (parallelism) number of threads running at any given
170	<	* time, we allow compensation during joins to fail, and enlist
171	<	* all other threads to help out whenever they are not otherwise
172	<	* occupied (i.e., mainly in method preStep).
258	>	*      method tryPreBlock() may create or re-activate a spare
259	>	*      thread to compensate for blocked joiners until they
260	>	*      unblock.
261		*
262		* The ManagedBlocker extension API can't use helping so relies
263		* only on compensation in method awaitBlocker.
264		*
265	<	* The main throughput advantages of work-stealing stem from
266	<	* decentralized control -- workers mostly steal tasks from each
267	<	* other. We do not want to negate this by creating bottlenecks
268	<	* implementing other management responsibilities. So we use a
269	<	* collection of techniques that avoid, reduce, or cope well with
270	<	* contention. These entail several instances of bit-packing into
271	<	* CASable fields to maintain only the minimally required
272	<	* atomicity. To enable such packing, we restrict maximum
273	<	* parallelism to (1<<15)-1 (enabling twice this (to accommodate
274	<	* unbalanced increments and decrements) to fit into a 16 bit
275	<	* field, which is far in excess of normal operating range.  Even
276	<	* though updates to some of these bookkeeping fields do sometimes
277	<	* contend with each other, they don't normally cache-contend with
278	<	* updates to others enough to warrant memory padding or
279	<	* isolation. So they are all held as fields of ForkJoinPool
280	<	* objects.  The main capabilities are as follows:
265	>	* It is impossible to keep exactly the target parallelism number
266	>	* of threads running at any given time.  Determining the
267	>	* existence of conservatively safe helping targets, the
268	>	* availability of already-created spares, and the apparent need
269	>	* to create new spares are all racy and require heuristic
270	>	* guidance, so we rely on multiple retries of each.  Currently,
271	>	* in keeping with on-demand signalling policy, we compensate only
272	>	* if blocking would leave less than one active (non-waiting,
273	>	* non-blocked) worker. Additionally, to avoid some false alarms
274	>	* due to GC, lagging counters, system activity, etc, compensated
275	>	* blocking for joins is only attempted after a number of rechecks
276	>	* proportional to the current apparent deficit (where retries are
277	>	* interspersed with Thread.yield, for good citizenship).  The
278	>	* variable blockedCount, incremented before blocking and
279	>	* decremented after, is sometimes needed to distinguish cases of
280	>	* waiting for work vs blocking on joins or other managed sync,
281	>	* but both the cases are equivalent for most pool control, so we
282	>	* can update non-atomically. (Additionally, contention on
283	>	* blockedCount alleviates some contention on ctl).
284	>	*
285	>	* Shutdown and Termination. A call to shutdownNow atomically sets
286	>	* the ctl stop bit and then (non-atomically) sets each workers
287	>	* "terminate" status, cancels all unprocessed tasks, and wakes up
288	>	* all waiting workers.  Detecting whether termination should
289	>	* commence after a non-abrupt shutdown() call requires more work
290	>	* and bookkeeping. We need consensus about quiesence (i.e., that
291	>	* there is no more work) which is reflected in active counts so
292	>	* long as there are no current blockers, as well as possible
293	>	* re-evaluations during independent changes in blocking or
294	>	* quiescing workers.
295		*
296	<	* 1. Creating and removing workers. Workers are recorded in the
195	<	* "workers" array. This is an array as opposed to some other data
196	<	* structure to support index-based random steals by workers.
197	<	* Updates to the array recording new workers and unrecording
198	<	* terminated ones are protected from each other by a lock
199	<	* (workerLock) but the array is otherwise concurrently readable,
200	<	* and accessed directly by workers. To simplify index-based
201	<	* operations, the array size is always a power of two, and all
202	<	* readers must tolerate null slots. Currently, all worker thread
203	<	* creation is on-demand, triggered by task submissions,
204	<	* replacement of terminated workers, and/or compensation for
205	<	* blocked workers. However, all other support code is set up to
206	<	* work with other policies.
207	<	*
208	<	* To ensure that we do not hold on to worker references that
209	<	* would prevent GC, ALL accesses to workers are via indices into
210	<	* the workers array (which is one source of some of the unusual
211	<	* code constructions here). In essence, the workers array serves
212	<	* as a WeakReference mechanism. Thus for example the event queue
213	<	* stores worker indices, not worker references. Access to the
214	<	* workers in associated methods (for example releaseEventWaiters)
215	<	* must both index-check and null-check the IDs. All such accesses
216	<	* ignore bad IDs by returning out early from what they are doing,
217	<	* since this can only be associated with shutdown, in which case
218	<	* it is OK to give up. On termination, we just clobber these
219	<	* data structures without trying to use them.
220	<	*
221	<	* 2. Bookkeeping for dynamically adding and removing workers. We
222	<	* aim to approximately maintain the given level of parallelism.
223	<	* When some workers are known to be blocked (on joins or via
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
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
232	<	* particular updates for unblocked threads may lag until they
233	<	* actually wake up.
234	<	*
235	<	* 3. Maintaining global run state. The run state of the pool
236	<	* consists of a runLevel (SHUTDOWN, TERMINATING, etc) similar to
237	<	* those in other Executor implementations, as well as a count of
238	<	* "active" workers -- those that are, or soon will be, or
239	<	* recently were executing tasks. The runLevel and active count
240	<	* are packed together in order to correctly trigger shutdown and
241	<	* termination. Without care, active counts can be subject to very
242	<	* high contention.  We substantially reduce this contention by
243	<	* relaxing update rules.  A worker must claim active status
244	<	* prospectively, by activating if it sees that a submitted or
245	<	* stealable task exists (it may find after activating that the
246	<	* task no longer exists). It stays active while processing this
247	<	* task (if it exists) and any other local subtasks it produces,
248	<	* until it cannot find any other tasks. It then tries
249	<	* inactivating (see method preStep), but upon update contention
250	<	* instead scans for more tasks, later retrying inactivation if it
251	<	* doesn't find any.
252	<	*
253	<	* 4. Managing idle workers waiting for tasks. We cannot let
254	<	* workers spin indefinitely scanning for tasks when none are
255	<	* available. On the other hand, we must quickly prod them into
256	<	* action when new tasks are submitted or generated.  We
257	<	* park/unpark these idle workers using an event-count scheme.
258	<	* Field eventCount is incremented upon events that may enable
259	<	* workers that previously could not find a task to now find one:
260	<	* Submission of a new task to the pool, or another worker pushing
261	<	* a task onto a previously empty queue.  (We also use this
262	<	* mechanism for termination actions that require wakeups of idle
263	<	* workers).  Each worker maintains its last known event count,
264	<	* and blocks when a scan for work did not find a task AND its
265	<	* lastEventCount matches the current eventCount. Waiting idle
266	<	* workers are recorded in a variant of Treiber stack headed by
267	<	* field eventWaiters which, when nonzero, encodes the thread
268	<	* index and count awaited for by the worker thread most recently
269	<	* calling eventSync. This thread in turn has a record (field
270	<	* nextEventWaiter) for the next waiting worker.  In addition to
271	<	* allowing simpler decisions about need for wakeup, the event
272	<	* count bits in eventWaiters serve the role of tags to avoid ABA
273	<	* errors in Treiber stacks.  To reduce delays in task diffusion,
274	<	* workers not otherwise occupied may invoke method
275	<	* releaseEventWaiters, that removes and signals (unparks) workers
276	<	* not waiting on current count. To reduce stalls, To minimize
277	<	* task production stalls associate with signalling, any worker
278	<	* pushing a task on an empty queue invokes the weaker method
279	<	* signalWork, that only releases idle workers until it detects
280	<	* interference by other threads trying to release, and lets them
281	<	* take over.  The net effect is a tree-like diffusion of signals,
282	<	* where released threads (and possibly others) help with unparks.
283	<	* To further reduce contention effects a bit, failed CASes to
284	<	* increment field eventCount are tolerated without retries.
285	<	* Conceptually they are merged into the same event, which is OK
286	<	* when their only purpose is to enable workers to scan for work.
287	<	*
288	<	* 5. Managing suspension of extra workers. When a worker is about
289	<	* to block waiting for a join (or via ManagedBlockers), we may
290	<	* create a new thread to maintain parallelism level, or at least
291	<	* avoid starvation. Usually, extra threads are needed for only
292	<	* very short periods, yet join dependencies are such that we
293	<	* sometimes need them in bursts. Rather than create new threads
294	<	* each time this happens, we suspend no-longer-needed extra ones
295	<	* as "spares". For most purposes, we don't distinguish "extra"
296	<	* spare threads from normal "core" threads: On each call to
297	<	* preStep (the only point at which we can do this) a worker
298	<	* checks to see if there are now too many running workers, and if
299	<	* so, suspends itself.  Method helpMaintainParallelism looks for
300	<	* suspended threads to resume before considering creating a new
301	<	* replacement. The spares themselves are encoded on another
302	<	* variant of a Treiber Stack, headed at field "spareWaiters".
303	<	* Note that the use of spares is intrinsically racy.  One thread
304	<	* may become a spare at about the same time as another is
305	<	* needlessly being created. We counteract this and related slop
306	<	* in part by requiring resumed spares to immediately recheck (in
307	<	* preStep) to see whether they they should re-suspend.  To avoid
308	<	* long-term build-up of spares, the oldest spare (see
309	<	* ForkJoinWorkerThread.suspendAsSpare) occasionally wakes up if
310	<	* not signalled and calls tryTrimSpare, which uses two different
311	<	* thresholds: Always killing if the number of spares is greater
312	<	* that 25% of total, and killing others only at a slower rate
313	<	* (UNUSED_SPARE_TRIM_RATE_NANOS).
314	<	*
315	<	* 6. Deciding when to create new workers. The main dynamic
316	<	* control in this class is deciding when to create extra threads
317	<	* in method helpMaintainParallelism. We would like to keep
318	<	* exactly #parallelism threads running, which is an impossble
319	<	* task. We always need to create one when the number of running
320	<	* threads would become zero and all workers are busy. Beyond
321	<	* this, we must rely on heuristics that work well in the the
322	<	* presence of transients phenomena such as GC stalls, dynamic
323	<	* compilation, and wake-up lags. These transients are extremely
324	<	* common -- we are normally trying to fully saturate the CPUs on
325	<	* a machine, so almost any activity other than running tasks
326	<	* impedes accuracy. Our main defense is to allow some slack in
327	<	* creation thresholds, using rules that reflect the fact that the
328	<	* more threads we have running, the more likely that we are
329	<	* underestimating the number running threads. The rules also
330	<	* better cope with the fact that some of the methods in this
331	<	* class tend to never become compiled (but are interpreted), so
332	<	* some components of the entire set of controls might execute 100
333	<	* times faster than others. And similarly for cases where the
334	<	* apparent lack of work is just due to GC stalls and other
335	<	* transient system activity.
336	<	*
337	<	* Beware that there is a lot of representation-level coupling
296	>	* Style notes: There is a lot of representation-level coupling
297		* among classes ForkJoinPool, ForkJoinWorkerThread, and
298	<	* ForkJoinTask.  For example, direct access to "workers" array by
298	>	* ForkJoinTask.  Most fields of ForkJoinWorkerThread maintain
299	>	* data structures managed by ForkJoinPool, so are directly
300	>	* accessed.  Conversely we allow access to "workers" array by
301		* workers, and direct access to ForkJoinTask.status by both
302		* ForkJoinPool and ForkJoinWorkerThread.  There is little point
303		* trying to reduce this, since any associated future changes in
304		* representations will need to be accompanied by algorithmic
305	<	* changes anyway.
306	<	*
307	<	* Style notes: There are lots of inline assignments (of form
308	<	* "while ((local = field) != 0)") which are usually the simplest
309	<	* way to ensure the required read orderings (which are sometimes
310	<	* critical). Also several occurrences of the unusual "do {}
311	<	* while(!cas...)" which is the simplest way to force an update of
312	<	* a CAS'ed variable. There are also other coding oddities that
313	<	* help some methods perform reasonably even when interpreted (not
314	<	* compiled), at the expense of some messy constructions that
315	<	* reduce byte code counts.
316	<	*
317	<	* The order of declarations in this file is: (1) statics (2)
318	<	* fields (along with constants used when unpacking some of them)
319	<	* (3) internal control methods (4) callbacks and other support
320	<	* for ForkJoinTask and ForkJoinWorkerThread classes, (5) exported
321	<	* methods (plus a few little helpers).
305	>	* changes anyway. All together, these low-level implementation
306	>	* choices produce as much as a factor of 4 performance
307	>	* improvement compared to naive implementations, and enable the
308	>	* processing of billions of tasks per second, at the expense of
309	>	* some ugliness.
310	>	*
311	>	* Methods signalWork() and scan() are the main bottlenecks so are
312	>	* especially heavily micro-optimized/mangled.  There are lots of
313	>	* inline assignments (of form "while ((local = field) != 0)")
314	>	* which are usually the simplest way to ensure the required read
315	>	* orderings (which are sometimes critical). This leads to a
316	>	* "C"-like style of listing declarations of these locals at the
317	>	* heads of methods or blocks.  There are several occurrences of
318	>	* the unusual "do {} while (!cas...)"  which is the simplest way
319	>	* to force an update of a CAS'ed variable. There are also other
320	>	* coding oddities that help some methods perform reasonably even
321	>	* when interpreted (not compiled).
322	>	*
323	>	* The order of declarations in this file is: (1) declarations of
324	>	* statics (2) fields (along with constants used when unpacking
325	>	* some of them), listed in an order that tends to reduce
326	>	* contention among them a bit under most JVMs.  (3) internal
327	>	* control methods (4) callbacks and other support for
328	>	* ForkJoinTask and ForkJoinWorkerThread classes, (5) exported
329	>	* methods (plus a few little helpers). (6) static block
330	>	* initializing all statics in a minimally dependent order.
331		*/
332
333		/**
#	Line 392 | Line 362 | public class ForkJoinPool extends Abstra
362		* overridden in ForkJoinPool constructors.
363		*/
364		public static final ForkJoinWorkerThreadFactory
365	<	defaultForkJoinWorkerThreadFactory =
396	<	new DefaultForkJoinWorkerThreadFactory();
365	>	defaultForkJoinWorkerThreadFactory;
366
367		/**
368		* Permission required for callers of methods that may start or
369		* kill threads.
370		*/
371	<	private static final RuntimePermission modifyThreadPermission =
403	<	new RuntimePermission("modifyThread");
371	>	private static final RuntimePermission modifyThreadPermission;
372
373		/**
374		* If there is a security manager, makes sure caller has
#	Line 415 | Line 383 | public class ForkJoinPool extends Abstra
383		/**
384		* Generator for assigning sequence numbers as pool names.
385		*/
386	<	private static final AtomicInteger poolNumberGenerator =
419	<	new AtomicInteger();
386	>	private static final AtomicInteger poolNumberGenerator;
387
388		/**
389	<	* Absolute bound for parallelism level. Twice this number plus
390	<	* one (i.e., 0xfff) must fit into a 16bit field to enable
391	<	* word-packing for some counts and indices.
389	>	* Generator for initial random seeds for worker victim
390	>	* selection. This is used only to create initial seeds. Random
391	>	* steals use a cheaper xorshift generator per steal attempt. We
392	>	* don't expect much contention on seedGenerator, so just use a
393	>	* plain Random.
394		*/
395	<	private static final int MAX_WORKERS   = 0x7fff;
395	>	static final Random workerSeedGenerator;
396
397		/**
398	<	* Array holding all worker threads in the pool.  Array size must
399	<	* be a power of two.  Updates and replacements are protected by
400	<	* workerLock, but the array is always kept in a consistent enough
401	<	* state to be randomly accessed without locking by workers
402	<	* performing work-stealing, as well as other traversal-based
403	<	* methods in this class. All readers must tolerate that some
404	<	* array slots may be null.
398	>	* Array holding all worker threads in the pool.  Initialized upon
399	>	* construction. Array size must be a power of two.  Updates and
400	>	* replacements are protected by scanGuard, but the array is
401	>	* always kept in a consistent enough state to be randomly
402	>	* accessed without locking by workers performing work-stealing,
403	>	* as well as other traversal-based methods in this class, so long
404	>	* as reads memory-acquire by first reading ctl. All readers must
405	>	* tolerate that some array slots may be null.
406		*/
407	<	volatile ForkJoinWorkerThread[] workers;
407	>	ForkJoinWorkerThread[] workers;
408
409		/**
410	<	* Queue for external submissions.
410	>	* Initial size for submission queue array. Must be a power of
411	>	* two.  In many applications, these always stay small so we use a
412	>	* small initial cap.
413		*/
414	<	private final LinkedTransferQueue<ForkJoinTask<?>> submissionQueue;
414	>	private static final int INITIAL_QUEUE_CAPACITY = 8;
415
416		/**
417	<	* Lock protecting updates to workers array.
417	>	* Maximum size for submission queue array. Must be a power of two
418	>	* less than or equal to 1 << (31 - width of array entry) to
419	>	* ensure lack of index wraparound, but is capped at a lower
420	>	* value to help users trap runaway computations.
421		*/
422	<	private final ReentrantLock workerLock;
422	>	private static final int MAXIMUM_QUEUE_CAPACITY = 1 << 24; // 16M
423
424		/**
425	<	* Latch released upon termination.
425	>	* Array serving as submission queue. Initialized upon construction.
426		*/
427	<	private final Phaser termination;
427	>	private ForkJoinTask<?>[] submissionQueue;
428
429		/**
430	<	* Creation factory for worker threads.
430	>	* Lock protecting submissions array for addSubmission
431		*/
432	<	private final ForkJoinWorkerThreadFactory factory;
432	>	private final ReentrantLock submissionLock;
433
434		/**
435	<	* Sum of per-thread steal counts, updated only when threads are
436	<	* idle or terminating.
435	>	* Condition for awaitTermination, using submissionLock for
436	>	* convenience.
437		*/
438	<	private volatile long stealCount;
438	>	private final Condition termination;
439
440		/**
441	<	* The last nanoTime that a spare thread was trimmed
441	>	* Creation factory for worker threads.
442		*/
443	<	private volatile long trimTime;
443	>	private final ForkJoinWorkerThreadFactory factory;
444
445		/**
446	<	* The rate at which to trim unused spares
446	>	* The uncaught exception handler used when any worker abruptly
447	>	* terminates.
448		*/
449	<	static final long UNUSED_SPARE_TRIM_RATE_NANOS =
474	<	1000L * 1000L * 1000L; // 1 sec
449	>	final Thread.UncaughtExceptionHandler ueh;
450
451		/**
452	<	* Encoded record of top of treiber stack of threads waiting for
478	<	* events. The top 32 bits contain the count being waited for. The
479	<	* bottom 16 bits contains one plus the pool index of waiting
480	<	* worker thread. (Bits 16-31 are unused.)
452	>	* Prefix for assigning names to worker threads
453		*/
454	<	private volatile long eventWaiters;
483	<
484	<	private static final int  EVENT_COUNT_SHIFT = 32;
485	<	private static final long WAITER_ID_MASK    = (1L << 16) - 1L;
454	>	private final String workerNamePrefix;
455
456		/**
457	<	* A counter for events that may wake up worker threads:
458	<	*   - Submission of a new task to the pool
490	<	*   - A worker pushing a task on an empty queue
491	<	*   - termination
457	>	* Sum of per-thread steal counts, updated only when threads are
458	>	* idle or terminating.
459		*/
460	<	private volatile int eventCount;
460	>	private volatile long stealCount;
461
462		/**
463	<	* Encoded record of top of treiber stack of spare threads waiting
464	<	* for resumption. The top 16 bits contain an arbitrary count to
465	<	* avoid ABA effects. The bottom 16bits contains one plus the pool
466	<	* index of waiting worker thread.
467	<	*/
468	<	private volatile int spareWaiters;
469	<
470	<	private static final int SPARE_COUNT_SHIFT = 16;
471	<	private static final int SPARE_ID_MASK     = (1 << 16) - 1;
463	>	* Main pool control -- a long packed with:
464	>	* AC: Number of active running workers minus target parallelism (16 bits)
465	>	* TC: Number of total workers minus target parallelism (16bits)
466	>	* ST: true if pool is terminating (1 bit)
467	>	* EC: the wait count of top waiting thread (15 bits)
468	>	* ID: ~poolIndex of top of Treiber stack of waiting threads (16 bits)
469	>	*
470	>	* When convenient, we can extract the upper 32 bits of counts and
471	>	* the lower 32 bits of queue state, u = (int)(ctl >>> 32) and e =
472	>	* (int)ctl.  The ec field is never accessed alone, but always
473	>	* together with id and st. The offsets of counts by the target
474	>	* parallelism and the positionings of fields makes it possible to
475	>	* perform the most common checks via sign tests of fields: When
476	>	* ac is negative, there are not enough active workers, when tc is
477	>	* negative, there are not enough total workers, when id is
478	>	* negative, there is at least one waiting worker, and when e is
479	>	* negative, the pool is terminating.  To deal with these possibly
480	>	* negative fields, we use casts in and out of "short" and/or
481	>	* signed shifts to maintain signedness.  Note: AC_SHIFT is
482	>	* redundantly declared in ForkJoinWorkerThread in order to
483	>	* integrate a surplus-threads check.
484	>	*/
485	>	volatile long ctl;
486	>
487	>	// bit positions/shifts for fields
488	>	private static final int  AC_SHIFT   = 48;
489	>	private static final int  TC_SHIFT   = 32;
490	>	private static final int  ST_SHIFT   = 31;
491	>	private static final int  EC_SHIFT   = 16;
492	>
493	>	// bounds
494	>	private static final int  MAX_ID     = 0x7fff;  // max poolIndex
495	>	private static final int  SMASK      = 0xffff;  // mask short bits
496	>	private static final int  SHORT_SIGN = 1 << 15;
497	>	private static final int  INT_SIGN   = 1 << 31;
498	>
499	>	// masks
500	>	private static final long STOP_BIT   = 0x0001L << ST_SHIFT;
501	>	private static final long AC_MASK    = ((long)SMASK) << AC_SHIFT;
502	>	private static final long TC_MASK    = ((long)SMASK) << TC_SHIFT;
503	>
504	>	// units for incrementing and decrementing
505	>	private static final long TC_UNIT    = 1L << TC_SHIFT;
506	>	private static final long AC_UNIT    = 1L << AC_SHIFT;
507	>
508	>	// masks and units for dealing with u = (int)(ctl >>> 32)
509	>	private static final int  UAC_SHIFT  = AC_SHIFT - 32;
510	>	private static final int  UTC_SHIFT  = TC_SHIFT - 32;
511	>	private static final int  UAC_MASK   = SMASK << UAC_SHIFT;
512	>	private static final int  UTC_MASK   = SMASK << UTC_SHIFT;
513	>	private static final int  UAC_UNIT   = 1 << UAC_SHIFT;
514	>	private static final int  UTC_UNIT   = 1 << UTC_SHIFT;
515	>
516	>	// masks and units for dealing with e = (int)ctl
517	>	private static final int  E_MASK     = 0x7fffffff; // no STOP_BIT
518	>	private static final int  EC_UNIT    = 1 << EC_SHIFT;
519
520		/**
521	<	* Lifecycle control. The low word contains the number of workers
508	<	* that are (probably) executing tasks. This value is atomically
509	<	* incremented before a worker gets a task to run, and decremented
510	<	* when worker has no tasks and cannot find any.  Bits 16-18
511	<	* contain runLevel value. When all are zero, the pool is
512	<	* running. Level transitions are monotonic (running -> shutdown
513	<	* -> terminating -> terminated) so each transition adds a bit.
514	<	* These are bundled together to ensure consistent read for
515	<	* termination checks (i.e., that runLevel is at least SHUTDOWN
516	<	* and active threads is zero).
521	>	* The target parallelism level.
522		*/
523	<	private volatile int runState;
519	<
520	<	// Note: The order among run level values matters.
521	<	private static final int RUNLEVEL_SHIFT     = 16;
522	<	private static final int SHUTDOWN           = 1 << RUNLEVEL_SHIFT;
523	<	private static final int TERMINATING        = 1 << (RUNLEVEL_SHIFT + 1);
524	<	private static final int TERMINATED         = 1 << (RUNLEVEL_SHIFT + 2);
525	<	private static final int ACTIVE_COUNT_MASK  = (1 << RUNLEVEL_SHIFT) - 1;
526	<	private static final int ONE_ACTIVE         = 1; // active update delta
523	>	final int parallelism;
524
525		/**
526	<	* Holds number of total (i.e., created and not yet terminated)
527	<	* and running (i.e., not blocked on joins or other managed sync)
531	<	* threads, packed together to ensure consistent snapshot when
532	<	* making decisions about creating and suspending spare
533	<	* threads. Updated only by CAS. Note that adding a new worker
534	<	* requires incrementing both counts, since workers start off in
535	<	* running state.
526	>	* Index (mod submission queue length) of next element to take
527	>	* from submission queue.
528		*/
529	<	private volatile int workerCounts;
529	>	volatile int queueBase;
530
531	<	private static final int TOTAL_COUNT_SHIFT  = 16;
532	<	private static final int RUNNING_COUNT_MASK = (1 << TOTAL_COUNT_SHIFT) - 1;
533	<	private static final int ONE_RUNNING        = 1;
534	<	private static final int ONE_TOTAL          = 1 << TOTAL_COUNT_SHIFT;
531	>	/**
532	>	* Index (mod submission queue length) of next element to add
533	>	* in submission queue.
534	>	*/
535	>	int queueTop;
536
537		/**
538	<	* The target parallelism level.
546	<	* Accessed directly by ForkJoinWorkerThreads.
538	>	* True when shutdown() has been called.
539		*/
540	<	final int parallelism;
540	>	volatile boolean shutdown;
541
542		/**
543		* True if use local fifo, not default lifo, for local polling
#	Line 554 | Line 546 | public class ForkJoinPool extends Abstra
546		final boolean locallyFifo;
547
548		/**
549	<	* The uncaught exception handler used when any worker abruptly
550	<	* terminates.
549	>	* The number of threads in ForkJoinWorkerThreads.helpQuiescePool.
550	>	* When non-zero, suppresses automatic shutdown when active
551	>	* counts become zero.
552		*/
553	<	private final Thread.UncaughtExceptionHandler ueh;
553	>	volatile int quiescerCount;
554
555		/**
556	<	* Pool number, just for assigning useful names to worker threads
556	>	* The number of threads blocked in join.
557		*/
558	<	private final int poolNumber;
558	>	volatile int blockedCount;
559
560	+	/**
561	+	* Counter for worker Thread names (unrelated to their poolIndex)
562	+	*/
563	+	private volatile int nextWorkerNumber;
564
565	<	// Utilities for CASing fields. Note that several of these
566	<	// are manually inlined by callers
565	>	/**
566	>	* The index for the next created worker. Accessed under scanGuard.
567	>	*/
568	>	private int nextWorkerIndex;
569
570		/**
571	<	* Increments running count part of workerCounts
571	>	* SeqLock and index masking for for updates to workers array.
572	>	* Locked when SG_UNIT is set. Unlocking clears bit by adding
573	>	* SG_UNIT. Staleness of read-only operations can be checked by
574	>	* comparing scanGuard to value before the reads. The low 16 bits
575	>	* (i.e, anding with SMASK) hold (the smallest power of two
576	>	* covering all worker indices, minus one, and is used to avoid
577	>	* dealing with large numbers of null slots when the workers array
578	>	* is overallocated.
579		*/
580	<	final void incrementRunningCount() {
581	<	int c;
582	<	do {} while (!UNSAFE.compareAndSwapInt(this, workerCountsOffset,
577	<	c = workerCounts,
578	<	c + ONE_RUNNING));
579	<	}
580	>	volatile int scanGuard;
581	>
582	>	private static final int SG_UNIT = 1 << 16;
583
584		/**
585	<	* Tries to decrement running count unless already zero
585	>	* The wakeup interval (in nanoseconds) for a worker waiting for a
586	>	* task when the pool is quiescent to instead try to shrink the
587	>	* number of workers.  The exact value does not matter too
588	>	* much. It must be short enough to release resources during
589	>	* sustained periods of idleness, but not so short that threads
590	>	* are continually re-created.
591		*/
592	<	final boolean tryDecrementRunningCount() {
593	<	int wc = workerCounts;
586	<	if ((wc & RUNNING_COUNT_MASK) == 0)
587	<	return false;
588	<	return UNSAFE.compareAndSwapInt(this, workerCountsOffset,
589	<	wc, wc - ONE_RUNNING);
590	<	}
592	>	private static final long SHRINK_RATE =
593	>	4L * 1000L * 1000L * 1000L; // 4 seconds
594
595		/**
596	<	* Forces decrement of encoded workerCounts, awaiting nonzero if
597	<	* (rarely) necessary when other count updates lag.
596	>	* Top-level loop for worker threads: On each step: if the
597	>	* previous step swept through all queues and found no tasks, or
598	>	* there are excess threads, then possibly blocks. Otherwise,
599	>	* scans for and, if found, executes a task. Returns when pool
600	>	* and/or worker terminate.
601		*
602	<	* @param dr -- either zero or ONE_RUNNING
597	<	* @param dt == either zero or ONE_TOTAL
602	>	* @param w the worker
603		*/
604	<	private void decrementWorkerCounts(int dr, int dt) {
605	<	for (;;) {
606	<	int wc = workerCounts;
607	<	if (wc == 0 && (runState & TERMINATED) != 0)
608	<	return; // lagging termination on a backout
609	<	if ((wc & RUNNING_COUNT_MASK)  - dr < 0 ||
610	<	(wc >>> TOTAL_COUNT_SHIFT) - dt < 0)
611	<	Thread.yield();
612	<	if (UNSAFE.compareAndSwapInt(this, workerCountsOffset,
608	<	wc, wc - (dr + dt)))
609	<	return;
604	>	final void work(ForkJoinWorkerThread w) {
605	>	boolean swept = false;                // true on empty scans
606	>	long c;
607	>	while (!w.terminate && (int)(c = ctl) >= 0) {
608	>	int a;                            // active count
609	>	if (!swept && (a = (int)(c >> AC_SHIFT)) <= 0)
610	>	swept = scan(w, a);
611	>	else if (tryAwaitWork(w, c))
612	>	swept = false;
613		}
614		}
615
616	+	// Signalling
617	+
618		/**
619	<	* Increments event count
619	>	* Wakes up or creates a worker.
620		*/
621	<	private void advanceEventCount() {
622	<	int c;
623	<	do {} while(!UNSAFE.compareAndSwapInt(this, eventCountOffset,
624	<	c = eventCount, c+1));
621	>	final void signalWork() {
622	>	/*
623	>	* The while condition is true if: (there is are too few total
624	>	* workers OR there is at least one waiter) AND (there are too
625	>	* few active workers OR the pool is terminating).  The value
626	>	* of e distinguishes the remaining cases: zero (no waiters)
627	>	* for create, negative if terminating (in which case do
628	>	* nothing), else release a waiter. The secondary checks for
629	>	* release (non-null array etc) can fail if the pool begins
630	>	* terminating after the test, and don't impose any added cost
631	>	* because JVMs must perform null and bounds checks anyway.
632	>	*/
633	>	long c; int e, u;
634	>	while ((((e = (int)(c = ctl)) | (u = (int)(c >>> 32))) &
635	>	(INT_SIGN|SHORT_SIGN)) == (INT_SIGN|SHORT_SIGN) && e >= 0) {
636	>	if (e > 0) {                         // release a waiting worker
637	>	int i; ForkJoinWorkerThread w; ForkJoinWorkerThread[] ws;
638	>	if ((ws = workers) == null ||
639	>	(i = ~e & SMASK) >= ws.length ||
640	>	(w = ws[i]) == null)
641	>	break;
642	>	long nc = (((long)(w.nextWait & E_MASK)) |
643	>	((long)(u + UAC_UNIT) << 32));
644	>	if (w.eventCount == e &&
645	>	UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc)) {
646	>	w.eventCount = (e + EC_UNIT) & E_MASK;
647	>	if (w.parked)
648	>	UNSAFE.unpark(w);
649	>	break;
650	>	}
651	>	}
652	>	else if (UNSAFE.compareAndSwapLong
653	>	(this, ctlOffset, c,
654	>	(long)(((u + UTC_UNIT) & UTC_MASK) |
655	>	((u + UAC_UNIT) & UAC_MASK)) << 32)) {
656	>	addWorker();
657	>	break;
658	>	}
659	>	}
660		}
661
662		/**
663	<	* Tries incrementing active count; fails on contention.
664	<	* Called by workers before executing tasks.
663	>	* Variant of signalWork to help release waiters on rescans.
664	>	* Tries once to release a waiter if active count < 0.
665		*
666	<	* @return true on success
666	>	* @return false if failed due to contention, else true
667		*/
668	<	final boolean tryIncrementActiveCount() {
669	<	int c;
670	<	return UNSAFE.compareAndSwapInt(this, runStateOffset,
671	<	c = runState, c + ONE_ACTIVE);
668	>	private boolean tryReleaseWaiter() {
669	>	long c; int e, i; ForkJoinWorkerThread w; ForkJoinWorkerThread[] ws;
670	>	if ((e = (int)(c = ctl)) > 0 &&
671	>	(int)(c >> AC_SHIFT) < 0 &&
672	>	(ws = workers) != null &&
673	>	(i = ~e & SMASK) < ws.length &&
674	>	(w = ws[i]) != null) {
675	>	long nc = ((long)(w.nextWait & E_MASK) |
676	>	((c + AC_UNIT) & (AC_MASK|TC_MASK)));
677	>	if (w.eventCount != e ||
678	>	!UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc))
679	>	return false;
680	>	w.eventCount = (e + EC_UNIT) & E_MASK;
681	>	if (w.parked)
682	>	UNSAFE.unpark(w);
683	>	}
684	>	return true;
685		}
686
687	+	// Scanning for tasks
688	+
689		/**
690	<	* Tries decrementing active count; fails on contention.
691	<	* Called when workers cannot find tasks to run.
690	>	* Scans for and, if found, executes one task. Scans start at a
691	>	* random index of workers array, and randomly select the first
692	>	* (2*#workers)-1 probes, and then, if all empty, resort to 2
693	>	* circular sweeps, which is necessary to check quiescence. and
694	>	* taking a submission only if no stealable tasks were found.  The
695	>	* steal code inside the loop is a specialized form of
696	>	* ForkJoinWorkerThread.deqTask, followed bookkeeping to support
697	>	* helpJoinTask and signal propagation. The code for submission
698	>	* queues is almost identical. On each steal, the worker completes
699	>	* not only the task, but also all local tasks that this task may
700	>	* have generated. On detecting staleness or contention when
701	>	* trying to take a task, this method returns without finishing
702	>	* sweep, which allows global state rechecks before retry.
703	>	*
704	>	* @param w the worker
705	>	* @param a the number of active workers
706	>	* @return true if swept all queues without finding a task
707		*/
708	<	final boolean tryDecrementActiveCount() {
709	<	int c;
710	<	return UNSAFE.compareAndSwapInt(this, runStateOffset,
711	<	c = runState, c - ONE_ACTIVE);
708	>	private boolean scan(ForkJoinWorkerThread w, int a) {
709	>	int g = scanGuard; // mask 0 avoids useless scans if only one active
710	>	int m = parallelism == 1 - a? 0 : g & SMASK;
711	>	ForkJoinWorkerThread[] ws = workers;
712	>	if (ws == null || ws.length <= m)         // staleness check
713	>	return false;
714	>	for (int r = w.seed, k = r, j = -(m + m); j <= m + m; ++j) {
715	>	ForkJoinTask<?> t; ForkJoinTask<?>[] q; int b, i;
716	>	ForkJoinWorkerThread v = ws[k & m];
717	>	if (v != null && (b = v.queueBase) != v.queueTop &&
718	>	(q = v.queue) != null && (i = (q.length - 1) & b) >= 0) {
719	>	long u = (i << ASHIFT) + ABASE;
720	>	if ((t = q[i]) != null && v.queueBase == b &&
721	>	UNSAFE.compareAndSwapObject(q, u, t, null)) {
722	>	int d = (v.queueBase = b + 1) - v.queueTop;
723	>	v.stealHint = w.poolIndex;
724	>	if (d != 0)
725	>	signalWork();             // propagate if nonempty
726	>	w.execTask(t);
727	>	}
728	>	r ^= r << 13; r ^= r >>> 17; w.seed = r ^ (r << 5);
729	>	return false;                     // store next seed
730	>	}
731	>	else if (j < 0) {                     // xorshift
732	>	r ^= r << 13; r ^= r >>> 17; k = r ^= r << 5;
733	>	}
734	>	else
735	>	++k;
736	>	}
737	>	if (scanGuard != g)                       // staleness check
738	>	return false;
739	>	else {                                    // try to take submission
740	>	ForkJoinTask<?> t; ForkJoinTask<?>[] q; int b, i;
741	>	if ((b = queueBase) != queueTop &&
742	>	(q = submissionQueue) != null &&
743	>	(i = (q.length - 1) & b) >= 0) {
744	>	long u = (i << ASHIFT) + ABASE;
745	>	if ((t = q[i]) != null && queueBase == b &&
746	>	UNSAFE.compareAndSwapObject(q, u, t, null)) {
747	>	queueBase = b + 1;
748	>	w.execTask(t);
749	>	}
750	>	return false;
751	>	}
752	>	return true;                         // all queues empty
753	>	}
754		}
755
756		/**
757	<	* Advances to at least the given level. Returns true if not
758	<	* already in at least the given level.
759	<	*/
760	<	private boolean advanceRunLevel(int level) {
761	<	for (;;) {
762	<	int s = runState;
763	<	if ((s & level) != 0)
764	<	return false;
765	<	if (UNSAFE.compareAndSwapInt(this, runStateOffset, s, s | level))
757	>	* Tries to enqueue worker w in wait queue and await change in
758	>	* worker's eventCount.  If the pool is quiescent, possibly
759	>	* terminates worker upon exit.  Otherwise, before blocking,
760	>	* rescans queues to avoid missed signals.  Upon finding work,
761	>	* releases at least one worker (which may be the current
762	>	* worker). Rescans restart upon detected staleness or failure to
763	>	* release due to contention.
764	>	*
765	>	* @param w the calling worker
766	>	* @param c the ctl value on entry
767	>	* @return true if waited or another thread was released upon enq
768	>	*/
769	>	private boolean tryAwaitWork(ForkJoinWorkerThread w, long c) {
770	>	int v = w.eventCount;
771	>	w.nextWait = (int)c;                      // w's successor record
772	>	long nc = (long)(v & E_MASK) | ((c - AC_UNIT) & (AC_MASK|TC_MASK));
773	>	if (ctl != c || !UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc)) {
774	>	long d = ctl; // return true if lost to a deq, to force scan
775	>	return (int)d != (int)c && ((d - c) & AC_MASK) >= 0L;
776	>	}
777	>	for (int sc = w.stealCount; sc != 0;) {   // accumulate stealCount
778	>	long s = stealCount;
779	>	if (UNSAFE.compareAndSwapLong(this, stealCountOffset, s, s + sc))
780	>	sc = w.stealCount = 0;
781	>	else if (w.eventCount != v)
782	>	return true;                      // update next time
783	>	}
784	>	if (parallelism + (int)(nc >> AC_SHIFT) == 0 &&
785	>	blockedCount == 0 && quiescerCount == 0)
786	>	idleAwaitWork(w, nc, c, v);           // quiescent
787	>	for (boolean rescanned = false;;) {
788	>	if (w.eventCount != v)
789		return true;
790	+	if (!rescanned) {
791	+	int g = scanGuard, m = g & SMASK;
792	+	ForkJoinWorkerThread[] ws = workers;
793	+	if (ws != null && m < ws.length) {
794	+	rescanned = true;
795	+	for (int i = 0; i <= m; ++i) {
796	+	ForkJoinWorkerThread u = ws[i];
797	+	if (u != null) {
798	+	if (u.queueBase != u.queueTop &&
799	+	!tryReleaseWaiter())
800	+	rescanned = false; // contended
801	+	if (w.eventCount != v)
802	+	return true;
803	+	}
804	+	}
805	+	}
806	+	if (scanGuard != g ||              // stale
807	+	(queueBase != queueTop && !tryReleaseWaiter()))
808	+	rescanned = false;
809	+	if (!rescanned)
810	+	Thread.yield();                // reduce contention
811	+	else
812	+	Thread.interrupted();          // clear before park
813	+	}
814	+	else {
815	+	w.parked = true;                   // must recheck
816	+	if (w.eventCount != v) {
817	+	w.parked = false;
818	+	return true;
819	+	}
820	+	LockSupport.park(this);
821	+	rescanned = w.parked = false;
822	+	}
823		}
824		}
825
658	–	// workers array maintenance
659	–
826		/**
827	<	* Records and returns a workers array index for new worker.
828	<	*/
829	<	private int recordWorker(ForkJoinWorkerThread w) {
830	<	// Try using slot totalCount-1. If not available, scan and/or resize
831	<	int k = (workerCounts >>> TOTAL_COUNT_SHIFT) - 1;
832	<	final ReentrantLock lock = this.workerLock;
833	<	lock.lock();
834	<	try {
835	<	ForkJoinWorkerThread[] ws = workers;
836	<	int n = ws.length;
837	<	if (k < 0 || k >= n || ws[k] != null) {
838	<	for (k = 0; k < n && ws[k] != null; ++k)
839	<	;
840	<	if (k == n)
841	<	ws = Arrays.copyOf(ws, n << 1);
827	>	* If inactivating worker w has caused pool to become
828	>	* quiescent, check for pool termination, and wait for event
829	>	* for up to SHRINK_RATE nanosecs (rescans are unnecessary in
830	>	* this case because quiescence reflects consensus about lack
831	>	* of work). On timeout, if ctl has not changed, terminate the
832	>	* worker. Upon its termination (see deregisterWorker), it may
833	>	* wake up another worker to possibly repeat this process.
834	>	*
835	>	* @param w the calling worker
836	>	* @param currentCtl the ctl value after enqueuing w
837	>	* @param prevCtl the ctl value if w terminated
838	>	* @param v the eventCount w awaits change
839	>	*/
840	>	private void idleAwaitWork(ForkJoinWorkerThread w, long currentCtl,
841	>	long prevCtl, int v) {
842	>	if (w.eventCount == v) {
843	>	if (shutdown)
844	>	tryTerminate(false);
845	>	ForkJoinTask.helpExpungeStaleExceptions(); // help clean weak refs
846	>	while (ctl == currentCtl) {
847	>	long startTime = System.nanoTime();
848	>	w.parked = true;
849	>	if (w.eventCount == v)             // must recheck
850	>	LockSupport.parkNanos(this, SHRINK_RATE);
851	>	w.parked = false;
852	>	if (w.eventCount != v)
853	>	break;
854	>	else if (System.nanoTime() - startTime < SHRINK_RATE)
855	>	Thread.interrupted();          // spurious wakeup
856	>	else if (UNSAFE.compareAndSwapLong(this, ctlOffset,
857	>	currentCtl, prevCtl)) {
858	>	w.terminate = true;            // restore previous
859	>	w.eventCount = ((int)currentCtl + EC_UNIT) & E_MASK;
860	>	break;
861	>	}
862		}
677	–	ws[k] = w;
678	–	workers = ws; // volatile array write ensures slot visibility
679	–	} finally {
680	–	lock.unlock();
863		}
682	–	return k;
864		}
865
866	+	// Submissions
867	+
868		/**
869	<	* Nulls out record of worker in workers array
869	>	* Enqueues the given task in the submissionQueue.  Same idea as
870	>	* ForkJoinWorkerThread.pushTask except for use of submissionLock.
871	>	*
872	>	* @param t the task
873		*/
874	<	private void forgetWorker(ForkJoinWorkerThread w) {
875	<	int idx = w.poolIndex;
690	<	// Locking helps method recordWorker avoid unecessary expansion
691	<	final ReentrantLock lock = this.workerLock;
874	>	private void addSubmission(ForkJoinTask<?> t) {
875	>	final ReentrantLock lock = this.submissionLock;
876		lock.lock();
877		try {
878	<	ForkJoinWorkerThread[] ws = workers;
879	<	if (idx >= 0 && idx < ws.length && ws[idx] == w) // verify
880	<	ws[idx] = null;
878	>	ForkJoinTask<?>[] q; int s, m;
879	>	if ((q = submissionQueue) != null) {    // ignore if queue removed
880	>	long u = (((s = queueTop) & (m = q.length-1)) << ASHIFT)+ABASE;
881	>	UNSAFE.putOrderedObject(q, u, t);
882	>	queueTop = s + 1;
883	>	if (s - queueBase == m)
884	>	growSubmissionQueue();
885	>	}
886		} finally {
887		lock.unlock();
888		}
889	+	signalWork();
890		}
891
892	<	// adding and removing workers
892	>	//  (pollSubmission is defined below with exported methods)
893
894		/**
895	<	* Tries to create and add new worker. Assumes that worker counts
896	<	* are already updated to accommodate the worker, so adjusts on
707	<	* failure.
895	>	* Creates or doubles submissionQueue array.
896	>	* Basically identical to ForkJoinWorkerThread version
897		*/
898	<	private void addWorker() {
899	<	ForkJoinWorkerThread w = null;
900	<	try {
901	<	w = factory.newThread(this);
902	<	} finally { // Adjust on either null or exceptional factory return
903	<	if (w == null) {
904	<	decrementWorkerCounts(ONE_RUNNING, ONE_TOTAL);
905	<	tryTerminate(false); // in case of failure during shutdown
898	>	private void growSubmissionQueue() {
899	>	ForkJoinTask<?>[] oldQ = submissionQueue;
900	>	int size = oldQ != null ? oldQ.length << 1 : INITIAL_QUEUE_CAPACITY;
901	>	if (size > MAXIMUM_QUEUE_CAPACITY)
902	>	throw new RejectedExecutionException("Queue capacity exceeded");
903	>	if (size < INITIAL_QUEUE_CAPACITY)
904	>	size = INITIAL_QUEUE_CAPACITY;
905	>	ForkJoinTask<?>[] q = submissionQueue = new ForkJoinTask<?>[size];
906	>	int mask = size - 1;
907	>	int top = queueTop;
908	>	int oldMask;
909	>	if (oldQ != null && (oldMask = oldQ.length - 1) >= 0) {
910	>	for (int b = queueBase; b != top; ++b) {
911	>	long u = ((b & oldMask) << ASHIFT) + ABASE;
912	>	Object x = UNSAFE.getObjectVolatile(oldQ, u);
913	>	if (x != null && UNSAFE.compareAndSwapObject(oldQ, u, x, null))
914	>	UNSAFE.putObjectVolatile
915	>	(q, ((b & mask) << ASHIFT) + ABASE, x);
916		}
917		}
719	–	if (w != null)
720	–	w.start(recordWorker(w), ueh);
918		}
919
920	+	// Blocking support
921	+
922		/**
923	<	* Final callback from terminating worker.  Removes record of
924	<	* worker from array, and adjusts counts. If pool is shutting
925	<	* down, tries to complete terminatation.
926	<	*
927	<	* @param w the worker
928	<	*/
929	<	final void workerTerminated(ForkJoinWorkerThread w) {
930	<	forgetWorker(w);
931	<	decrementWorkerCounts(w.isTrimmed()? 0 : ONE_RUNNING, ONE_TOTAL);
932	<	while (w.stealCount != 0) // collect final count
933	<	tryAccumulateStealCount(w);
934	<	tryTerminate(false);
923	>	* Tries to increment blockedCount, decrement active count
924	>	* (sometimes implicitly) and possibly release or create a
925	>	* compensating worker in preparation for blocking. Fails
926	>	* on contention or termination.
927	>	*
928	>	* @return true if the caller can block, else should recheck and retry
929	>	*/
930	>	private boolean tryPreBlock() {
931	>	int b = blockedCount;
932	>	if (UNSAFE.compareAndSwapInt(this, blockedCountOffset, b, b + 1)) {
933	>	int pc = parallelism;
934	>	do {
935	>	ForkJoinWorkerThread[] ws; ForkJoinWorkerThread w;
936	>	int e, ac, tc, rc, i;
937	>	long c = ctl;
938	>	int u = (int)(c >>> 32);
939	>	if ((e = (int)c) < 0) {
940	>	// skip -- terminating
941	>	}
942	>	else if ((ac = (u >> UAC_SHIFT)) <= 0 && e != 0 &&
943	>	(ws = workers) != null &&
944	>	(i = ~e & SMASK) < ws.length &&
945	>	(w = ws[i]) != null) {
946	>	long nc = ((long)(w.nextWait & E_MASK) |
947	>	(c & (AC_MASK|TC_MASK)));
948	>	if (w.eventCount == e &&
949	>	UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc)) {
950	>	w.eventCount = (e + EC_UNIT) & E_MASK;
951	>	if (w.parked)
952	>	UNSAFE.unpark(w);
953	>	return true;             // release an idle worker
954	>	}
955	>	}
956	>	else if ((tc = (short)(u >>> UTC_SHIFT)) >= 0 && ac + pc > 1) {
957	>	long nc = ((c - AC_UNIT) & AC_MASK) | (c & ~AC_MASK);
958	>	if (UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc))
959	>	return true;             // no compensation needed
960	>	}
961	>	else if (tc + pc < MAX_ID) {
962	>	long nc = ((c + TC_UNIT) & TC_MASK) | (c & ~TC_MASK);
963	>	if (UNSAFE.compareAndSwapLong(this, ctlOffset, c, nc)) {
964	>	addWorker();
965	>	return true;            // create a replacement
966	>	}
967	>	}
968	>	// try to back out on any failure and let caller retry
969	>	} while (!UNSAFE.compareAndSwapInt(this, blockedCountOffset,
970	>	b = blockedCount, b - 1));
971	>	}
972	>	return false;
973		}
974
738	–	// Waiting for and signalling events
739	–
975		/**
976	<	* Releases workers blocked on a count not equal to current count.
742	<	* Normally called after precheck that eventWaiters isn't zero to
743	<	* avoid wasted array checks.
744	<	*
745	<	* @param signalling true if caller is a signalling worker so can
746	<	* exit upon (conservatively) detected contention by other threads
747	<	* who will continue to release
976	>	* Decrements blockedCount and increments active count
977		*/
978	<	private void releaseEventWaiters(boolean signalling) {
979	<	ForkJoinWorkerThread[] ws = workers;
980	<	int n = ws.length;
981	<	long h; // head of stack
982	<	ForkJoinWorkerThread w; int id, ec;
983	<	while ((id = ((int)((h = eventWaiters) & WAITER_ID_MASK)) - 1) >= 0 &&
984	<	(int)(h >>> EVENT_COUNT_SHIFT) != (ec = eventCount) &&
756	<	id < n && (w = ws[id]) != null) {
757	<	if (UNSAFE.compareAndSwapLong(this, eventWaitersOffset,
758	<	h, h = w.nextWaiter))
759	<	LockSupport.unpark(w);
760	<	if (signalling && (eventCount != ec || eventWaiters != h))
761	<	break;
762	<	}
978	>	private void postBlock() {
979	>	long c;
980	>	do {} while (!UNSAFE.compareAndSwapLong(this, ctlOffset,  // no mask
981	>	c = ctl, c + AC_UNIT));
982	>	int b;
983	>	do {} while(!UNSAFE.compareAndSwapInt(this, blockedCountOffset,
984	>	b = blockedCount, b - 1));
985		}
986
987		/**
988	<	* Tries to advance eventCount and releases waiters. Called only
989	<	* from workers.
988	>	* Possibly blocks waiting for the given task to complete, or
989	>	* cancels the task if terminating.  Fails to wait if contended.
990	>	*
991	>	* @param joinMe the task
992		*/
993	<	final void signalWork() {
994	<	int c; // try to increment event count -- CAS failure OK
995	<	UNSAFE.compareAndSwapInt(this, eventCountOffset, c = eventCount, c+1);
996	<	if (eventWaiters != 0L)
997	<	releaseEventWaiters(true);
993	>	final void tryAwaitJoin(ForkJoinTask<?> joinMe) {
994	>	int s;
995	>	Thread.interrupted(); // clear interrupts before checking termination
996	>	if (joinMe.status >= 0) {
997	>	if (tryPreBlock()) {
998	>	joinMe.tryAwaitDone(0L);
999	>	postBlock();
1000	>	}
1001	>	if ((ctl & STOP_BIT) != 0L)
1002	>	joinMe.cancelIgnoringExceptions();
1003	>	}
1004		}
1005
1006		/**
1007	<	* Blocks worker until terminating or event count
1008	<	* advances from last value held by worker
1009	<	*
1010	<	* @param w the calling worker thread
1011	<	*/
1012	<	private void eventSync(ForkJoinWorkerThread w) {
1013	<	int wec = w.lastEventCount;
1014	<	long nh = (((long)wec) << EVENT_COUNT_SHIFT) | ((long)(w.poolIndex+1));
1015	<	long h;
1016	<	while ((runState < SHUTDOWN || !tryTerminate(false)) &&
1017	<	((h = eventWaiters) == 0L ||
1018	<	(int)(h >>> EVENT_COUNT_SHIFT) == wec) &&
1019	<	eventCount == wec) {
1020	<	if (UNSAFE.compareAndSwapLong(this, eventWaitersOffset,
1021	<	w.nextWaiter = h, nh)) {
1022	<	while (runState < TERMINATING && eventCount == wec) {
1023	<	if (!tryAccumulateStealCount(w))  // transfer while idle
1024	<	continue;
1025	<	Thread.interrupted();             // clear/ignore interrupt
1026	<	if (eventCount != wec)
1007	>	* Possibly blocks the given worker waiting for joinMe to
1008	>	* complete or timeout
1009	>	*
1010	>	* @param joinMe the task
1011	>	* @param millis the wait time for underlying Object.wait
1012	>	*/
1013	>	final void timedAwaitJoin(ForkJoinTask<?> joinMe, long nanos) {
1014	>	while (joinMe.status >= 0) {
1015	>	Thread.interrupted();
1016	>	if ((ctl & STOP_BIT) != 0L) {
1017	>	joinMe.cancelIgnoringExceptions();
1018	>	break;
1019	>	}
1020	>	if (tryPreBlock()) {
1021	>	long last = System.nanoTime();
1022	>	while (joinMe.status >= 0) {
1023	>	long millis = TimeUnit.NANOSECONDS.toMillis(nanos);
1024	>	if (millis <= 0)
1025	>	break;
1026	>	joinMe.tryAwaitDone(millis);
1027	>	if (joinMe.status < 0)
1028		break;
1029	<	LockSupport.park(w);
1029	>	if ((ctl & STOP_BIT) != 0L) {
1030	>	joinMe.cancelIgnoringExceptions();
1031	>	break;
1032	>	}
1033	>	long now = System.nanoTime();
1034	>	nanos -= now - last;
1035	>	last = now;
1036		}
1037	+	postBlock();
1038		break;
1039		}
1040		}
803	–	w.lastEventCount = eventCount;
804	–	}
805	–
806	–	// Maintaining spares
807	–
808	–	/**
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);
813	–	do {} while (!UNSAFE.compareAndSwapInt(this, spareWaitersOffset,
814	–	w.nextSpare = spareWaiters,ns));
1041		}
1042
1043		/**
1044	<	* Tries (once) to resume a spare if running count is less than
819	<	* target parallelism. Fails on contention or stale workers.
1044	>	* If necessary, compensates for blocker, and blocks
1045		*/
1046	<	private void tryResumeSpare() {
1047	<	int sw, id;
1048	<	ForkJoinWorkerThread w;
1049	<	ForkJoinWorkerThread[] ws;
1050	<	if ((id = ((sw = spareWaiters) & SPARE_ID_MASK) - 1) >= 0 &&
1051	<	id < (ws = workers).length && (w = ws[id]) != null &&
1052	<	(workerCounts & RUNNING_COUNT_MASK) < parallelism &&
1053	<	eventWaiters == 0L &&
1054	<	spareWaiters == sw &&
1055	<	UNSAFE.compareAndSwapInt(this, spareWaitersOffset,
831	<	sw, w.nextSpare) &&
832	<	w.tryUnsuspend()) {
833	<	int c; // try increment; if contended, finish after unpark
834	<	boolean inc = UNSAFE.compareAndSwapInt(this, workerCountsOffset,
835	<	c = workerCounts,
836	<	c + ONE_RUNNING);
837	<	LockSupport.unpark(w);
838	<	if (!inc) {
839	<	do {} while(!UNSAFE.compareAndSwapInt(this, workerCountsOffset,
840	<	c = workerCounts,
841	<	c + ONE_RUNNING));
1046	>	private void awaitBlocker(ManagedBlocker blocker)
1047	>	throws InterruptedException {
1048	>	while (!blocker.isReleasable()) {
1049	>	if (tryPreBlock()) {
1050	>	try {
1051	>	do {} while (!blocker.isReleasable() && !blocker.block());
1052	>	} finally {
1053	>	postBlock();
1054	>	}
1055	>	break;
1056		}
1057		}
1058		}
1059
1060	<	/**
847	<	* Callback from oldest spare occasionally waking up.  Tries
848	<	* (once) to shutdown a spare if more than 25% spare overage, or
849	<	* if UNUSED_SPARE_TRIM_RATE_NANOS have elapsed and there are at
850	<	* least #parallelism running threads. Note that we don't need CAS
851	<	* or locks here because the method is called only from the oldest
852	<	* suspended spare occasionally waking (and even misfires are OK).
853	<	*
854	<	* @param now the wake up nanoTime of caller
855	<	*/
856	<	final void tryTrimSpare(long now) {
857	<	long lastTrim = trimTime;
858	<	trimTime = now;
859	<	helpMaintainParallelism(); // first, help wake up any needed spares
860	<	int sw, id;
861	<	ForkJoinWorkerThread w;
862	<	ForkJoinWorkerThread[] ws;
863	<	int pc = parallelism;
864	<	int wc = workerCounts;
865	<	if ((wc & RUNNING_COUNT_MASK) >= pc &&
866	<	(((wc >>> TOTAL_COUNT_SHIFT) - pc) > (pc >>> 2) + 1 ||// approx 25%
867	<	now - lastTrim >= UNUSED_SPARE_TRIM_RATE_NANOS) &&
868	<	(id = ((sw = spareWaiters) & SPARE_ID_MASK) - 1) >= 0 &&
869	<	id < (ws = workers).length && (w = ws[id]) != null &&
870	<	UNSAFE.compareAndSwapInt(this, spareWaitersOffset,
871	<	sw, w.nextSpare))
872	<	w.shutdown(false);
873	<	}
1060	>	// Creating, registering and deregistring workers
1061
1062		/**
1063	<	* Does at most one of:
1064	<	*
1065	<	* 1. Help wake up existing workers waiting for work via
1066	<	*    releaseEventWaiters. (If any exist, then it probably doesn't
1067	<	*    matter right now if under target parallelism level.)
1068	<	*
1069	<	* 2. If below parallelism level and a spare exists, try (once)
1070	<	*    to resume it via tryResumeSpare.
1071	<	*
1072	<	* 3. If neither of the above, tries (once) to add a new
1073	<	*    worker if either there are not enough total, or if all
1074	<	*    existing workers are busy, there are either no running
1075	<	*    workers or the deficit is at least twice the surplus.
1076	<	*/
1077	<	private void helpMaintainParallelism() {
1078	<	// uglified to work better when not compiled
1079	<	int pc, wc, rc, tc, rs; long h;
1080	<	if ((h = eventWaiters) != 0L) {
1081	<	if ((int)(h >>> EVENT_COUNT_SHIFT) != eventCount)
1082	<	releaseEventWaiters(false); // avoid useless call
1083	<	}
1084	<	else if ((pc = parallelism) >
898	<	(rc = ((wc = workerCounts) & RUNNING_COUNT_MASK))) {
899	<	if (spareWaiters != 0)
900	<	tryResumeSpare();
901	<	else if ((rs = runState) < TERMINATING &&
902	<	((tc = wc >>> TOTAL_COUNT_SHIFT) < pc ||
903	<	(tc == (rs & ACTIVE_COUNT_MASK) && // all busy
904	<	(rc == 0 ||                       // must add
905	<	rc < pc - ((tc - pc) << 1)) &&   // within slack
906	<	tc < MAX_WORKERS && runState == rs)) && // recheck busy
907	<	workerCounts == wc &&
908	<	UNSAFE.compareAndSwapInt(this, workerCountsOffset, wc,
909	<	wc + (ONE_RUNNING|ONE_TOTAL)))
910	<	addWorker();
1063	>	* Tries to create and start a worker; minimally rolls back counts
1064	>	* on failure.
1065	>	*/
1066	>	private void addWorker() {
1067	>	Throwable ex = null;
1068	>	ForkJoinWorkerThread t = null;
1069	>	try {
1070	>	t = factory.newThread(this);
1071	>	} catch (Throwable e) {
1072	>	ex = e;
1073	>	}
1074	>	if (t == null) {  // null or exceptional factory return
1075	>	long c;       // adjust counts
1076	>	do {} while (!UNSAFE.compareAndSwapLong
1077	>	(this, ctlOffset, c = ctl,
1078	>	(((c - AC_UNIT) & AC_MASK) |
1079	>	((c - TC_UNIT) & TC_MASK) |
1080	>	(c & ~(AC_MASK|TC_MASK)))));
1081	>	// Propagate exception if originating from an external caller
1082	>	if (!tryTerminate(false) && ex != null &&
1083	>	!(Thread.currentThread() instanceof ForkJoinWorkerThread))
1084	>	UNSAFE.throwException(ex);
1085		}
1086	+	else
1087	+	t.start();
1088		}
1089
1090		/**
1091	<	* Callback from workers invoked upon each top-level action (i.e.,
1092	<	* stealing a task or taking a submission and running
917	<	* it). Performs one or more of the following:
918	<	*
919	<	* 1. If the worker cannot find work (misses > 0), updates its
920	<	*    active status to inactive and updates activeCount unless
921	<	*    this is the first miss and there is contention, in which
922	<	*    case it may try again (either in this or a subsequent
923	<	*    call).
924	<	*
925	<	* 2. If there are at least 2 misses, awaits the next task event
926	<	*    via eventSync
927	<	*
928	<	* 3. If there are too many running threads, suspends this worker
929	<	*    (first forcing inactivation if necessary).  If it is not
930	<	*    needed, it may be killed while suspended via
931	<	*    tryTrimSpare. Otherwise, upon resume it rechecks to make
932	<	*    sure that it is still needed.
933	<	*
934	<	* 4. Helps release and/or reactivate other workers via
935	<	*    helpMaintainParallelism
936	<	*
937	<	* @param w the worker
938	<	* @param misses the number of scans by caller failing to find work
939	<	* (saturating at 2 just to avoid wraparound)
1091	>	* Callback from ForkJoinWorkerThread constructor to assign a
1092	>	* public name
1093		*/
1094	<	final void preStep(ForkJoinWorkerThread w, int misses) {
1095	<	boolean active = w.active;
1096	<	int pc = parallelism;
1097	<	for (;;) {
1098	<	int wc = workerCounts;
946	<	int rc = wc & RUNNING_COUNT_MASK;
947	<	if (active && (misses > 0 || rc > pc)) {
948	<	int rs;                      // try inactivate
949	<	if (UNSAFE.compareAndSwapInt(this, runStateOffset,
950	<	rs = runState, rs - ONE_ACTIVE))
951	<	active = w.active = false;
952	<	else if (misses > 1 || rc > pc ||
953	<	(rs & ACTIVE_COUNT_MASK) >= pc)
954	<	continue;                // force inactivate
955	<	}
956	<	if (misses > 1) {
957	<	misses = 0;                  // don't re-sync
958	<	eventSync(w);                // continue loop to recheck rc
959	<	}
960	<	else if (rc > pc) {
961	<	if (workerCounts == wc &&   // try to suspend as spare
962	<	UNSAFE.compareAndSwapInt(this, workerCountsOffset,
963	<	wc, wc - ONE_RUNNING) &&
964	<	!w.suspendAsSpare())    // false if killed
965	<	break;
966	<	}
967	<	else {
968	<	if (rc < pc || eventWaiters != 0L)
969	<	helpMaintainParallelism();
970	<	break;
971	<	}
1094	>	final String nextWorkerName() {
1095	>	for (int n;;) {
1096	>	if (UNSAFE.compareAndSwapInt(this, nextWorkerNumberOffset,
1097	>	n = nextWorkerNumber, ++n))
1098	>	return workerNamePrefix + n;
1099		}
1100		}
1101
1102		/**
1103	<	* Helps and/or blocks awaiting join of the given task.
1104	<	* Alternates between helpJoinTask() and helpMaintainParallelism()
978	<	* as many times as there is a deficit in running count (or longer
979	<	* if running count would become zero), then blocks if task still
980	<	* not done.
1103	>	* Callback from ForkJoinWorkerThread constructor to
1104	>	* determine its poolIndex and record in workers array.
1105		*
1106	<	* @param joinMe the task to join
1106	>	* @param w the worker
1107	>	* @return the worker's pool index
1108		*/
1109	<	final void awaitJoin(ForkJoinTask<?> joinMe, ForkJoinWorkerThread worker) {
1110	<	int threshold = parallelism;         // descend blocking thresholds
1111	<	while (joinMe.status >= 0) {
1112	<	boolean block; int wc;
1113	<	worker.helpJoinTask(joinMe);
1114	<	if (joinMe.status < 0)
1115	<	break;
1116	<	if (((wc = workerCounts) & RUNNING_COUNT_MASK) <= threshold) {
1117	<	if (threshold > 0)
1118	<	--threshold;
1119	<	else
1120	<	advanceEventCount(); // force release
1121	<	block = false;
1109	>	final int registerWorker(ForkJoinWorkerThread w) {
1110	>	/*
1111	>	* In the typical case, a new worker acquires the lock, uses
1112	>	* next available index and returns quickly.  Since we should
1113	>	* not block callers (ultimately from signalWork or
1114	>	* tryPreBlock) waiting for the lock needed to do this, we
1115	>	* instead help release other workers while waiting for the
1116	>	* lock.
1117	>	*/
1118	>	for (int g;;) {
1119	>	ForkJoinWorkerThread[] ws;
1120	>	if (((g = scanGuard) & SG_UNIT) == 0 &&
1121	>	UNSAFE.compareAndSwapInt(this, scanGuardOffset,
1122	>	g, g | SG_UNIT)) {
1123	>	int k = nextWorkerIndex;
1124	>	try {
1125	>	if ((ws = workers) != null) { // ignore on shutdown
1126	>	int n = ws.length;
1127	>	if (k < 0 || k >= n || ws[k] != null) {
1128	>	for (k = 0; k < n && ws[k] != null; ++k)
1129	>	;
1130	>	if (k == n)
1131	>	ws = workers = Arrays.copyOf(ws, n << 1);
1132	>	}
1133	>	ws[k] = w;
1134	>	nextWorkerIndex = k + 1;
1135	>	int m = g & SMASK;
1136	>	g = k >= m? ((m << 1) + 1) & SMASK : g + (SG_UNIT<<1);
1137	>	}
1138	>	} finally {
1139	>	scanGuard = g;
1140	>	}
1141	>	return k;
1142		}
1143	<	else
1144	<	block = UNSAFE.compareAndSwapInt(this, workerCountsOffset,
1145	<	wc, wc - ONE_RUNNING);
1146	<	helpMaintainParallelism();
1147	<	if (block) {
1148	<	int c;
1149	<	joinMe.internalAwaitDone();
1005	<	do {} while (!UNSAFE.compareAndSwapInt
1006	<	(this, workerCountsOffset,
1007	<	c = workerCounts, c + ONE_RUNNING));
1008	<	break;
1143	>	else if ((ws = workers) != null) { // help release others
1144	>	for (ForkJoinWorkerThread u : ws) {
1145	>	if (u != null && u.queueBase != u.queueTop) {
1146	>	if (tryReleaseWaiter())
1147	>	break;
1148	>	}
1149	>	}
1150		}
1151		}
1152		}
1153
1154		/**
1155	<	* Same idea as awaitJoin, but no helping
1155	>	* Final callback from terminating worker.  Removes record of
1156	>	* worker from array, and adjusts counts. If pool is shutting
1157	>	* down, tries to complete termination.
1158	>	*
1159	>	* @param w the worker
1160		*/
1161	<	final void awaitBlocker(ManagedBlocker blocker)
1162	<	throws InterruptedException {
1163	<	int threshold = parallelism;
1164	<	while (!blocker.isReleasable()) {
1165	<	boolean block; int wc;
1166	<	if (((wc = workerCounts) & RUNNING_COUNT_MASK) <= threshold) {
1167	<	if (threshold > 0)
1168	<	--threshold;
1169	<	else
1170	<	advanceEventCount();
1171	<	block = false;
1161	>	final void deregisterWorker(ForkJoinWorkerThread w, Throwable ex) {
1162	>	int idx = w.poolIndex;
1163	>	int sc = w.stealCount;
1164	>	int steps = 0;
1165	>	// Remove from array, adjust worker counts and collect steal count.
1166	>	// We can intermix failed removes or adjusts with steal updates
1167	>	do {
1168	>	long s, c;
1169	>	int g;
1170	>	if (steps == 0 && ((g = scanGuard) & SG_UNIT) == 0 &&
1171	>	UNSAFE.compareAndSwapInt(this, scanGuardOffset,
1172	>	g, g |= SG_UNIT)) {
1173	>	ForkJoinWorkerThread[] ws = workers;
1174	>	if (ws != null && idx >= 0 &&
1175	>	idx < ws.length && ws[idx] == w)
1176	>	ws[idx] = null;    // verify
1177	>	nextWorkerIndex = idx;
1178	>	scanGuard = g + SG_UNIT;
1179	>	steps = 1;
1180		}
1181	+	if (steps == 1 &&
1182	+	UNSAFE.compareAndSwapLong(this, ctlOffset, c = ctl,
1183	+	(((c - AC_UNIT) & AC_MASK) |
1184	+	((c - TC_UNIT) & TC_MASK) |
1185	+	(c & ~(AC_MASK|TC_MASK)))))
1186	+	steps = 2;
1187	+	if (sc != 0 &&
1188	+	UNSAFE.compareAndSwapLong(this, stealCountOffset,
1189	+	s = stealCount, s + sc))
1190	+	sc = 0;
1191	+	} while (steps != 2 || sc != 0);
1192	+	if (!tryTerminate(false)) {
1193	+	if (ex != null)   // possibly replace if died abnormally
1194	+	signalWork();
1195		else
1196	<	block = UNSAFE.compareAndSwapInt(this, workerCountsOffset,
1030	<	wc, wc - ONE_RUNNING);
1031	<	helpMaintainParallelism();
1032	<	if (block) {
1033	<	try {
1034	<	do {} while (!blocker.isReleasable() && !blocker.block());
1035	<	} finally {
1036	<	int c;
1037	<	do {} while (!UNSAFE.compareAndSwapInt
1038	<	(this, workerCountsOffset,
1039	<	c = workerCounts, c + ONE_RUNNING));
1040	<	}
1041	<	break;
1042	<	}
1196	>	tryReleaseWaiter();
1197		}
1198		}
1199
1200	+	// Shutdown and termination
1201	+
1202		/**
1203		* Possibly initiates and/or completes termination.
1204		*
#	Line 1051 | Line 1207 | public class ForkJoinPool extends Abstra
1207		* @return true if now terminating or terminated
1208		*/
1209		private boolean tryTerminate(boolean now) {
1210	<	if (now)
1211	<	advanceRunLevel(SHUTDOWN); // ensure at least SHUTDOWN
1212	<	else if (runState < SHUTDOWN ||
1213	<	!submissionQueue.isEmpty() ||
1214	<	(runState & ACTIVE_COUNT_MASK) != 0)
1215	<	return false;
1216	<
1217	<	if (advanceRunLevel(TERMINATING))
1218	<	startTerminating();
1219	<
1220	<	// Finish now if all threads terminated; else in some subsequent call
1221	<	if ((workerCounts >>> TOTAL_COUNT_SHIFT) == 0) {
1222	<	advanceRunLevel(TERMINATED);
1223	<	termination.arrive();
1210	>	long c;
1211	>	while (((c = ctl) & STOP_BIT) == 0) {
1212	>	if (!now) {
1213	>	if ((int)(c >> AC_SHIFT) != -parallelism)
1214	>	return false;
1215	>	if (!shutdown || blockedCount != 0 || quiescerCount != 0 ||
1216	>	queueTop - queueBase > 0) {
1217	>	if (ctl == c) // staleness check
1218	>	return false;
1219	>	continue;
1220	>	}
1221	>	}
1222	>	if (UNSAFE.compareAndSwapLong(this, ctlOffset, c, c | STOP_BIT))
1223	>	startTerminating();
1224	>	}
1225	>	if ((short)(c >>> TC_SHIFT) == -parallelism) {
1226	>	submissionLock.lock();
1227	>	termination.signalAll();
1228	>	submissionLock.unlock();
1229		}
1230		return true;
1231		}
1232
1233		/**
1234	<	* Actions on transition to TERMINATING
1235	<	*
1236	<	* Runs up to four passes through workers: (0) shutting down each
1237	<	* quietly (without waking up if parked) to quickly spread
1238	<	* notifications without unnecessary bouncing around event queues
1239	<	* etc (1) wake up and help cancel tasks (2) interrupt (3) mop up
1079	<	* races with interrupted workers
1234	>	* Runs up to three passes through workers: (0) Setting
1235	>	* termination status for each worker, followed by wakeups up
1236	>	* queued workers (1) helping cancel tasks (2) interrupting
1237	>	* lagging threads (likely in external tasks, but possibly also
1238	>	* blocked in joins).  Each pass repeats previous steps because of
1239	>	* potential lagging thread creation.
1240		*/
1241		private void startTerminating() {
1242		cancelSubmissions();
1243	<	for (int passes = 0; passes < 4 && workerCounts != 0; ++passes) {
1084	<	advanceEventCount();
1085	<	eventWaiters = 0L; // clobber lists
1086	<	spareWaiters = 0;
1243	>	for (int pass = 0; pass < 3; ++pass) {
1244		ForkJoinWorkerThread[] ws = workers;
1245	<	int n = ws.length;
1246	<	for (int i = 0; i < n; ++i) {
1247	<	ForkJoinWorkerThread w = ws[i];
1248	<	if (w != null) {
1249	<	w.shutdown(true);
1250	<	if (passes > 0 && !w.isTerminated()) {
1251	<	w.cancelTasks();
1252	<	LockSupport.unpark(w);
1253	<	if (passes > 1) {
1254	<	try {
1255	<	w.interrupt();
1099	<	} catch (SecurityException ignore) {
1245	>	if (ws != null) {
1246	>	for (ForkJoinWorkerThread w : ws) {
1247	>	if (w != null) {
1248	>	w.terminate = true;
1249	>	if (pass > 0) {
1250	>	w.cancelTasks();
1251	>	if (pass > 1 && !w.isInterrupted()) {
1252	>	try {
1253	>	w.interrupt();
1254	>	} catch (SecurityException ignore) {
1255	>	}
1256		}
1257		}
1258		}
1259		}
1260	+	terminateWaiters();
1261		}
1262		}
1263		}
1264
1265		/**
1266	<	* Clear out and cancel submissions, ignoring exceptions
1266	>	* Polls and cancels all submissions. Called only during termination.
1267		*/
1268		private void cancelSubmissions() {
1269	<	ForkJoinTask<?> task;
1270	<	while ((task = submissionQueue.poll()) != null) {
1271	<	try {
1272	<	task.cancel(false);
1273	<	} catch (Throwable ignore) {
1269	>	while (queueBase != queueTop) {
1270	>	ForkJoinTask<?> task = pollSubmission();
1271	>	if (task != null) {
1272	>	try {
1273	>	task.cancel(false);
1274	>	} catch (Throwable ignore) {
1275	>	}
1276	>	}
1277	>	}
1278	>	}
1279	>
1280	>	/**
1281	>	* Tries to set the termination status of waiting workers, and
1282	>	* then wake them up (after which they will terminate).
1283	>	*/
1284	>	private void terminateWaiters() {
1285	>	ForkJoinWorkerThread[] ws = workers;
1286	>	if (ws != null) {
1287	>	ForkJoinWorkerThread w; long c; int i, e;
1288	>	int n = ws.length;
1289	>	while ((i = ~(e = (int)(c = ctl)) & SMASK) < n &&
1290	>	(w = ws[i]) != null && w.eventCount == (e & E_MASK)) {
1291	>	if (UNSAFE.compareAndSwapLong(this, ctlOffset, c,
1292	>	(long)(w.nextWait & E_MASK) |
1293	>	((c + AC_UNIT) & AC_MASK) |
1294	>	(c & (TC_MASK|STOP_BIT)))) {
1295	>	w.terminate = true;
1296	>	w.eventCount = e + EC_UNIT;
1297	>	if (w.parked)
1298	>	UNSAFE.unpark(w);
1299	>	}
1300		}
1301		}
1302		}
1303
1304	<	// misc support for ForkJoinWorkerThread
1304	>	// misc ForkJoinWorkerThread support
1305
1306		/**
1307	<	* Returns pool number
1307	>	* Increment or decrement quiescerCount. Needed only to prevent
1308	>	* triggering shutdown if a worker is transiently inactive while
1309	>	* checking quiescence.
1310	>	*
1311	>	* @param delta 1 for increment, -1 for decrement
1312		*/
1313	<	final int getPoolNumber() {
1314	<	return poolNumber;
1313	>	final void addQuiescerCount(int delta) {
1314	>	int c;
1315	>	do {} while(!UNSAFE.compareAndSwapInt(this, quiescerCountOffset,
1316	>	c = quiescerCount, c + delta));
1317		}
1318
1319		/**
1320	<	* Tries to accumulates steal count from a worker, clearing
1321	<	* the worker's value.
1320	>	* Directly increment or decrement active count without
1321	>	* queuing. This method is used to transiently assert inactivation
1322	>	* while checking quiescence.
1323		*
1324	<	* @return true if worker steal count now zero
1324	>	* @param delta 1 for increment, -1 for decrement
1325		*/
1326	<	final boolean tryAccumulateStealCount(ForkJoinWorkerThread w) {
1327	<	int sc = w.stealCount;
1328	<	long c = stealCount;
1329	<	// CAS even if zero, for fence effects
1330	<	if (UNSAFE.compareAndSwapLong(this, stealCountOffset, c, c + sc)) {
1331	<	if (sc != 0)
1142	<	w.stealCount = 0;
1143	<	return true;
1144	<	}
1145	<	return sc == 0;
1326	>	final void addActiveCount(int delta) {
1327	>	long d = delta < 0 ? -AC_UNIT : AC_UNIT;
1328	>	long c;
1329	>	do {} while (!UNSAFE.compareAndSwapLong(this, ctlOffset, c = ctl,
1330	>	((c + d) & AC_MASK) |
1331	>	(c & ~AC_MASK)));
1332		}
1333
1334		/**
#	Line 1150 | Line 1336 | public class ForkJoinPool extends Abstra
1336		* active thread.
1337		*/
1338		final int idlePerActive() {
1339	<	int pc = parallelism; // use parallelism, not rc
1340	<	int ac = runState;    // no mask -- artifically boosts during shutdown
1341	<	// Use exact results for small values, saturate past 4
1342	<	return pc <= ac? 0 : pc >>> 1 <= ac? 1 : pc >>> 2 <= ac? 3 : pc >>> 3;
1339	>	// Approximate at powers of two for small values, saturate past 4
1340	>	int p = parallelism;
1341	>	int a = p + (int)(ctl >> AC_SHIFT);
1342	>	return (a > (p >>>= 1) ? 0 :
1343	>	a > (p >>>= 1) ? 1 :
1344	>	a > (p >>>= 1) ? 2 :
1345	>	a > (p >>>= 1) ? 4 :
1346	>	8);
1347		}
1348
1349	<	// Public and protected methods
1349	>	// Exported methods
1350
1351		// Constructors
1352
#	Line 1203 | Line 1393 | public class ForkJoinPool extends Abstra
1393		* use {@link #defaultForkJoinWorkerThreadFactory}.
1394		* @param handler the handler for internal worker threads that
1395		* terminate due to unrecoverable errors encountered while executing
1396	<	* tasks. For default value, use <code>null</code>.
1396	>	* tasks. For default value, use {@code null}.
1397		* @param asyncMode if true,
1398		* establishes local first-in-first-out scheduling mode for forked
1399		* tasks that are never joined. This mode may be more appropriate
1400		* than default locally stack-based mode in applications in which
1401		* worker threads only process event-style asynchronous tasks.
1402	<	* For default value, use <code>false</code>.
1402	>	* For default value, use {@code false}.
1403		* @throws IllegalArgumentException if parallelism less than or
1404		*         equal to zero, or greater than implementation limit
1405		* @throws NullPointerException if the factory is null
#	Line 1225 | Line 1415 | public class ForkJoinPool extends Abstra
1415		checkPermission();
1416		if (factory == null)
1417		throw new NullPointerException();
1418	<	if (parallelism <= 0 || parallelism > MAX_WORKERS)
1418	>	if (parallelism <= 0 || parallelism > MAX_ID)
1419		throw new IllegalArgumentException();
1420		this.parallelism = parallelism;
1421		this.factory = factory;
1422		this.ueh = handler;
1423		this.locallyFifo = asyncMode;
1424	<	int arraySize = initialArraySizeFor(parallelism);
1425	<	this.workers = new ForkJoinWorkerThread[arraySize];
1426	<	this.submissionQueue = new LinkedTransferQueue<ForkJoinTask<?>>();
1427	<	this.workerLock = new ReentrantLock();
1428	<	this.termination = new Phaser(1);
1429	<	this.poolNumber = poolNumberGenerator.incrementAndGet();
1430	<	this.trimTime = System.nanoTime();
1431	<	}
1432	<
1433	<	/**
1434	<	* Returns initial power of two size for workers array.
1435	<	* @param pc the initial parallelism level
1436	<	*/
1437	<	private static int initialArraySizeFor(int pc) {
1438	<	// See Hackers Delight, sec 3.2. We know MAX_WORKERS < (1 >>> 16)
1439	<	int size = pc < MAX_WORKERS ? pc + 1 : MAX_WORKERS;
1440	<	size |= size >>> 1;
1251	<	size |= size >>> 2;
1252	<	size |= size >>> 4;
1253	<	size |= size >>> 8;
1254	<	return size + 1;
1424	>	long np = (long)(-parallelism); // offset ctl counts
1425	>	this.ctl = ((np << AC_SHIFT) & AC_MASK) | ((np << TC_SHIFT) & TC_MASK);
1426	>	this.submissionQueue = new ForkJoinTask<?>[INITIAL_QUEUE_CAPACITY];
1427	>	// initialize workers array with room for 2*parallelism if possible
1428	>	int n = parallelism << 1;
1429	>	if (n >= MAX_ID)
1430	>	n = MAX_ID;
1431	>	else { // See Hackers Delight, sec 3.2, where n < (1 << 16)
1432	>	n |= n >>> 1; n |= n >>> 2; n |= n >>> 4; n |= n >>> 8;
1433	>	}
1434	>	workers = new ForkJoinWorkerThread[n + 1];
1435	>	this.submissionLock = new ReentrantLock();
1436	>	this.termination = submissionLock.newCondition();
1437	>	StringBuilder sb = new StringBuilder("ForkJoinPool-");
1438	>	sb.append(poolNumberGenerator.incrementAndGet());
1439	>	sb.append("-worker-");
1440	>	this.workerNamePrefix = sb.toString();
1441		}
1442
1443		// Execution methods
1444
1445		/**
1260	–	* Common code for execute, invoke and submit
1261	–	*/
1262	–	private <T> void doSubmit(ForkJoinTask<T> task) {
1263	–	if (task == null)
1264	–	throw new NullPointerException();
1265	–	if (runState >= SHUTDOWN)
1266	–	throw new RejectedExecutionException();
1267	–	submissionQueue.offer(task);
1268	–	advanceEventCount();
1269	–	helpMaintainParallelism();         // start or wake up workers
1270	–	}
1271	–
1272	–	/**
1446		* Performs the given task, returning its result upon completion.
1447	+	* If the computation encounters an unchecked Exception or Error,
1448	+	* it is rethrown as the outcome of this invocation.  Rethrown
1449	+	* exceptions behave in the same way as regular exceptions, but,
1450	+	* when possible, contain stack traces (as displayed for example
1451	+	* using {@code ex.printStackTrace()}) of both the current thread
1452	+	* as well as the thread actually encountering the exception;
1453	+	* minimally only the latter.
1454		*
1455		* @param task the task
1456		* @return the task's result
#	Line 1279 | Line 1459 | public class ForkJoinPool extends Abstra
1459		*         scheduled for execution
1460		*/
1461		public <T> T invoke(ForkJoinTask<T> task) {
1462	<	doSubmit(task);
1463	<	return task.join();
1462	>	Thread t = Thread.currentThread();
1463	>	if (task == null)
1464	>	throw new NullPointerException();
1465	>	if (shutdown)
1466	>	throw new RejectedExecutionException();
1467	>	if ((t instanceof ForkJoinWorkerThread) &&
1468	>	((ForkJoinWorkerThread)t).pool == this)
1469	>	return task.invoke();  // bypass submit if in same pool
1470	>	else {
1471	>	addSubmission(task);
1472	>	return task.join();
1473	>	}
1474	>	}
1475	>
1476	>	/**
1477	>	* Unless terminating, forks task if within an ongoing FJ
1478	>	* computation in the current pool, else submits as external task.
1479	>	*/
1480	>	private <T> void forkOrSubmit(ForkJoinTask<T> task) {
1481	>	ForkJoinWorkerThread w;
1482	>	Thread t = Thread.currentThread();
1483	>	if (shutdown)
1484	>	throw new RejectedExecutionException();
1485	>	if ((t instanceof ForkJoinWorkerThread) &&
1486	>	(w = (ForkJoinWorkerThread)t).pool == this)
1487	>	w.pushTask(task);
1488	>	else
1489	>	addSubmission(task);
1490		}
1491
1492		/**
1493		* Arranges for (asynchronous) execution of the given task.
1288	–	* If the caller is already engaged in a fork/join computation in
1289	–	* the current pool, this method is equivalent in effect to
1290	–	* {@link ForkJoinTask#fork}.
1494		*
1495		* @param task the task
1496		* @throws NullPointerException if the task is null
#	Line 1295 | Line 1498 | public class ForkJoinPool extends Abstra
1498		*         scheduled for execution
1499		*/
1500		public void execute(ForkJoinTask<?> task) {
1501	<	doSubmit(task);
1501	>	if (task == null)
1502	>	throw new NullPointerException();
1503	>	forkOrSubmit(task);
1504		}
1505
1506		// AbstractExecutorService methods
#	Line 1306 | Line 1511 | public class ForkJoinPool extends Abstra
1511		*         scheduled for execution
1512		*/
1513		public void execute(Runnable task) {
1514	+	if (task == null)
1515	+	throw new NullPointerException();
1516		ForkJoinTask<?> job;
1517		if (task instanceof ForkJoinTask<?>) // avoid re-wrap
1518		job = (ForkJoinTask<?>) task;
1519		else
1520		job = ForkJoinTask.adapt(task, null);
1521	<	doSubmit(job);
1521	>	forkOrSubmit(job);
1522		}
1523
1524		/**
1525		* Submits a ForkJoinTask for execution.
1319	–	* If the caller is already engaged in a fork/join computation in
1320	–	* the current pool, this method is equivalent in effect to
1321	–	* {@link ForkJoinTask#fork}.
1526		*
1527		* @param task the task to submit
1528		* @return the task
#	Line 1327 | Line 1531 | public class ForkJoinPool extends Abstra
1531		*         scheduled for execution
1532		*/
1533		public <T> ForkJoinTask<T> submit(ForkJoinTask<T> task) {
1534	<	doSubmit(task);
1534	>	if (task == null)
1535	>	throw new NullPointerException();
1536	>	forkOrSubmit(task);
1537		return task;
1538		}
1539
#	Line 1337 | Line 1543 | public class ForkJoinPool extends Abstra
1543		*         scheduled for execution
1544		*/
1545		public <T> ForkJoinTask<T> submit(Callable<T> task) {
1546	+	if (task == null)
1547	+	throw new NullPointerException();
1548		ForkJoinTask<T> job = ForkJoinTask.adapt(task);
1549	<	doSubmit(job);
1549	>	forkOrSubmit(job);
1550		return job;
1551		}
1552
#	Line 1348 | Line 1556 | public class ForkJoinPool extends Abstra
1556		*         scheduled for execution
1557		*/
1558		public <T> ForkJoinTask<T> submit(Runnable task, T result) {
1559	+	if (task == null)
1560	+	throw new NullPointerException();
1561		ForkJoinTask<T> job = ForkJoinTask.adapt(task, result);
1562	<	doSubmit(job);
1562	>	forkOrSubmit(job);
1563		return job;
1564		}
1565
#	Line 1359 | Line 1569 | public class ForkJoinPool extends Abstra
1569		*         scheduled for execution
1570		*/
1571		public ForkJoinTask<?> submit(Runnable task) {
1572	+	if (task == null)
1573	+	throw new NullPointerException();
1574		ForkJoinTask<?> job;
1575		if (task instanceof ForkJoinTask<?>) // avoid re-wrap
1576		job = (ForkJoinTask<?>) task;
1577		else
1578		job = ForkJoinTask.adapt(task, null);
1579	<	doSubmit(job);
1579	>	forkOrSubmit(job);
1580		return job;
1581		}
1582
#	Line 1424 | Line 1636 | public class ForkJoinPool extends Abstra
1636
1637		/**
1638		* Returns the number of worker threads that have started but not
1639	<	* yet terminated.  This result returned by this method may differ
1639	>	* yet terminated.  The result returned by this method may differ
1640		* from {@link #getParallelism} when threads are created to
1641		* maintain parallelism when others are cooperatively blocked.
1642		*
1643		* @return the number of worker threads
1644		*/
1645		public int getPoolSize() {
1646	<	return workerCounts >>> TOTAL_COUNT_SHIFT;
1646	>	return parallelism + (short)(ctl >>> TC_SHIFT);
1647		}
1648
1649		/**
#	Line 1453 | Line 1665 | public class ForkJoinPool extends Abstra
1665		* @return the number of worker threads
1666		*/
1667		public int getRunningThreadCount() {
1668	<	return workerCounts & RUNNING_COUNT_MASK;
1668	>	int r = parallelism + (int)(ctl >> AC_SHIFT);
1669	>	return r <= 0? 0 : r; // suppress momentarily negative values
1670		}
1671
1672		/**
#	Line 1464 | Line 1677 | public class ForkJoinPool extends Abstra
1677		* @return the number of active threads
1678		*/
1679		public int getActiveThreadCount() {
1680	<	return runState & ACTIVE_COUNT_MASK;
1680	>	int r = parallelism + (int)(ctl >> AC_SHIFT) + blockedCount;
1681	>	return r <= 0? 0 : r; // suppress momentarily negative values
1682		}
1683
1684		/**
#	Line 1479 | Line 1693 | public class ForkJoinPool extends Abstra
1693		* @return {@code true} if all threads are currently idle
1694		*/
1695		public boolean isQuiescent() {
1696	<	return (runState & ACTIVE_COUNT_MASK) == 0;
1696	>	return parallelism + (int)(ctl >> AC_SHIFT) + blockedCount == 0;
1697		}
1698
1699		/**
#	Line 1509 | Line 1723 | public class ForkJoinPool extends Abstra
1723		*/
1724		public long getQueuedTaskCount() {
1725		long count = 0;
1726	<	ForkJoinWorkerThread[] ws = workers;
1727	<	int n = ws.length;
1728	<	for (int i = 0; i < n; ++i) {
1729	<	ForkJoinWorkerThread w = ws[i];
1730	<	if (w != null)
1731	<	count += w.getQueueSize();
1726	>	ForkJoinWorkerThread[] ws;
1727	>	if ((short)(ctl >>> TC_SHIFT) > -parallelism &&
1728	>	(ws = workers) != null) {
1729	>	for (ForkJoinWorkerThread w : ws)
1730	>	if (w != null)
1731	>	count -= w.queueBase - w.queueTop; // must read base first
1732		}
1733		return count;
1734		}
1735
1736		/**
1737		* Returns an estimate of the number of tasks submitted to this
1738	<	* pool that have not yet begun executing.  This method takes time
1739	<	* proportional to the number of submissions.
1738	>	* pool that have not yet begun executing.  This meThod may take
1739	>	* time proportional to the number of submissions.
1740		*
1741		* @return the number of queued submissions
1742		*/
1743		public int getQueuedSubmissionCount() {
1744	<	return submissionQueue.size();
1744	>	return -queueBase + queueTop;
1745		}
1746
1747		/**
#	Line 1537 | Line 1751 | public class ForkJoinPool extends Abstra
1751		* @return {@code true} if there are any queued submissions
1752		*/
1753		public boolean hasQueuedSubmissions() {
1754	<	return !submissionQueue.isEmpty();
1754	>	return queueBase != queueTop;
1755		}
1756
1757		/**
#	Line 1548 | Line 1762 | public class ForkJoinPool extends Abstra
1762		* @return the next submission, or {@code null} if none
1763		*/
1764		protected ForkJoinTask<?> pollSubmission() {
1765	<	return submissionQueue.poll();
1765	>	ForkJoinTask<?> t; ForkJoinTask<?>[] q; int b, i;
1766	>	while ((b = queueBase) != queueTop &&
1767	>	(q = submissionQueue) != null &&
1768	>	(i = (q.length - 1) & b) >= 0) {
1769	>	long u = (i << ASHIFT) + ABASE;
1770	>	if ((t = q[i]) != null &&
1771	>	queueBase == b &&
1772	>	UNSAFE.compareAndSwapObject(q, u, t, null)) {
1773	>	queueBase = b + 1;
1774	>	return t;
1775	>	}
1776	>	}
1777	>	return null;
1778		}
1779
1780		/**
#	Line 1569 | Line 1795 | public class ForkJoinPool extends Abstra
1795		* @return the number of elements transferred
1796		*/
1797		protected int drainTasksTo(Collection<? super ForkJoinTask<?>> c) {
1798	<	int count = submissionQueue.drainTo(c);
1799	<	ForkJoinWorkerThread[] ws = workers;
1800	<	int n = ws.length;
1801	<	for (int i = 0; i < n; ++i) {
1802	<	ForkJoinWorkerThread w = ws[i];
1803	<	if (w != null)
1804	<	count += w.drainTasksTo(c);
1798	>	int count = 0;
1799	>	while (queueBase != queueTop) {
1800	>	ForkJoinTask<?> t = pollSubmission();
1801	>	if (t != null) {
1802	>	c.add(t);
1803	>	++count;
1804	>	}
1805	>	}
1806	>	ForkJoinWorkerThread[] ws;
1807	>	if ((short)(ctl >>> TC_SHIFT) > -parallelism &&
1808	>	(ws = workers) != null) {
1809	>	for (ForkJoinWorkerThread w : ws)
1810	>	if (w != null)
1811	>	count += w.drainTasksTo(c);
1812		}
1813		return count;
1814		}
#	Line 1591 | Line 1824 | public class ForkJoinPool extends Abstra
1824		long st = getStealCount();
1825		long qt = getQueuedTaskCount();
1826		long qs = getQueuedSubmissionCount();
1594	–	int wc = workerCounts;
1595	–	int tc = wc >>> TOTAL_COUNT_SHIFT;
1596	–	int rc = wc & RUNNING_COUNT_MASK;
1827		int pc = parallelism;
1828	<	int rs = runState;
1829	<	int ac = rs & ACTIVE_COUNT_MASK;
1828	>	long c = ctl;
1829	>	int tc = pc + (short)(c >>> TC_SHIFT);
1830	>	int rc = pc + (int)(c >> AC_SHIFT);
1831	>	if (rc < 0) // ignore transient negative
1832	>	rc = 0;
1833	>	int ac = rc + blockedCount;
1834	>	String level;
1835	>	if ((c & STOP_BIT) != 0)
1836	>	level = (tc == 0)? "Terminated" : "Terminating";
1837	>	else
1838	>	level = shutdown? "Shutting down" : "Running";
1839		return super.toString() +
1840	<	"[" + runLevelToString(rs) +
1840	>	"[" + level +
1841		", parallelism = " + pc +
1842		", size = " + tc +
1843		", active = " + ac +
#	Line 1609 | Line 1848 | public class ForkJoinPool extends Abstra
1848		"]";
1849		}
1850
1612	–	private static String runLevelToString(int s) {
1613	–	return ((s & TERMINATED) != 0 ? "Terminated" :
1614	–	((s & TERMINATING) != 0 ? "Terminating" :
1615	–	((s & SHUTDOWN) != 0 ? "Shutting down" :
1616	–	"Running")));
1617	–	}
1618	–
1851		/**
1852		* Initiates an orderly shutdown in which previously submitted
1853		* tasks are executed, but no new tasks will be accepted.
#	Line 1630 | Line 1862 | public class ForkJoinPool extends Abstra
1862		*/
1863		public void shutdown() {
1864		checkPermission();
1865	<	advanceRunLevel(SHUTDOWN);
1865	>	shutdown = true;
1866		tryTerminate(false);
1867		}
1868
#	Line 1652 | Line 1884 | public class ForkJoinPool extends Abstra
1884		*/
1885		public List<Runnable> shutdownNow() {
1886		checkPermission();
1887	+	shutdown = true;
1888		tryTerminate(true);
1889		return Collections.emptyList();
1890		}
#	Line 1662 | Line 1895 | public class ForkJoinPool extends Abstra
1895		* @return {@code true} if all tasks have completed following shut down
1896		*/
1897		public boolean isTerminated() {
1898	<	return runState >= TERMINATED;
1898	>	long c = ctl;
1899	>	return ((c & STOP_BIT) != 0L &&
1900	>	(short)(c >>> TC_SHIFT) == -parallelism);
1901		}
1902
1903		/**
#	Line 1670 | Line 1905 | public class ForkJoinPool extends Abstra
1905		* commenced but not yet completed.  This method may be useful for
1906		* debugging. A return of {@code true} reported a sufficient
1907		* period after shutdown may indicate that submitted tasks have
1908	<	* ignored or suppressed interruption, causing this executor not
1909	<	* to properly terminate.
1908	>	* ignored or suppressed interruption, or are waiting for IO,
1909	>	* causing this executor not to properly terminate. (See the
1910	>	* advisory notes for class {@link ForkJoinTask} stating that
1911	>	* tasks should not normally entail blocking operations.  But if
1912	>	* they do, they must abort them on interrupt.)
1913		*
1914		* @return {@code true} if terminating but not yet terminated
1915		*/
1916		public boolean isTerminating() {
1917	<	return (runState & (TERMINATING|TERMINATED)) == TERMINATING;
1917	>	long c = ctl;
1918	>	return ((c & STOP_BIT) != 0L &&
1919	>	(short)(c >>> TC_SHIFT) != -parallelism);
1920	>	}
1921	>
1922	>	/**
1923	>	* Returns true if terminating or terminated. Used by ForkJoinWorkerThread.
1924	>	*/
1925	>	final boolean isAtLeastTerminating() {
1926	>	return (ctl & STOP_BIT) != 0L;
1927		}
1928
1929		/**
#	Line 1685 | Line 1932 | public class ForkJoinPool extends Abstra
1932		* @return {@code true} if this pool has been shut down
1933		*/
1934		public boolean isShutdown() {
1935	<	return runState >= SHUTDOWN;
1935	>	return shutdown;
1936		}
1937
1938		/**
#	Line 1701 | Line 1948 | public class ForkJoinPool extends Abstra
1948		*/
1949		public boolean awaitTermination(long timeout, TimeUnit unit)
1950		throws InterruptedException {
1951	+	long nanos = unit.toNanos(timeout);
1952	+	final ReentrantLock lock = this.submissionLock;
1953	+	lock.lock();
1954		try {
1955	<	return termination.awaitAdvanceInterruptibly(0, timeout, unit) > 0;
1956	<	} catch(TimeoutException ex) {
1957	<	return false;
1955	>	for (;;) {
1956	>	if (isTerminated())
1957	>	return true;
1958	>	if (nanos <= 0)
1959	>	return false;
1960	>	nanos = termination.awaitNanos(nanos);
1961	>	}
1962	>	} finally {
1963	>	lock.unlock();
1964		}
1965		}
1966
#	Line 1716 | Line 1972 | public class ForkJoinPool extends Abstra
1972		* {@code isReleasable} must return {@code true} if blocking is
1973		* not necessary. Method {@code block} blocks the current thread
1974		* if necessary (perhaps internally invoking {@code isReleasable}
1975	<	* before actually blocking). The unusual methods in this API
1976	<	* accommodate synchronizers that may, but don't usually, block
1977	<	* for long periods. Similarly, they allow more efficient internal
1978	<	* handling of cases in which additional workers may be, but
1979	<	* usually are not, needed to ensure sufficient parallelism.
1980	<	* Toward this end, implementations of method {@code isReleasable}
1981	<	* must be amenable to repeated invocation.
1975	>	* before actually blocking). These actions are performed by any
1976	>	* thread invoking {@link ForkJoinPool#managedBlock}.  The
1977	>	* unusual methods in this API accommodate synchronizers that may,
1978	>	* but don't usually, block for long periods. Similarly, they
1979	>	* allow more efficient internal handling of cases in which
1980	>	* additional workers may be, but usually are not, needed to
1981	>	* ensure sufficient parallelism.  Toward this end,
1982	>	* implementations of method {@code isReleasable} must be amenable
1983	>	* to repeated invocation.
1984		*
1985		* <p>For example, here is a ManagedBlocker based on a
1986		* ReentrantLock:
#	Line 1750 | Line 2008 | public class ForkJoinPool extends Abstra
2008		*   QueueTaker(BlockingQueue<E> q) { this.queue = q; }
2009		*   public boolean block() throws InterruptedException {
2010		*     if (item == null)
2011	<	*       item = queue.take
2011	>	*       item = queue.take();
2012		*     return true;
2013		*   }
2014		*   public boolean isReleasable() {
2015	<	*     return item != null || (item = queue.poll) != null;
2015	>	*     return item != null || (item = queue.poll()) != null;
2016		*   }
2017		*   public E getItem() { // call after pool.managedBlock completes
2018		*     return item;
#	Line 1824 | Line 2082 | public class ForkJoinPool extends Abstra
2082		}
2083
2084		// Unsafe mechanics
2085	<
2086	<	private static final sun.misc.Unsafe UNSAFE = getUnsafe();
2087	<	private static final long workerCountsOffset =
2088	<	objectFieldOffset("workerCounts", ForkJoinPool.class);
2089	<	private static final long runStateOffset =
2090	<	objectFieldOffset("runState", ForkJoinPool.class);
2091	<	private static final long eventCountOffset =
2092	<	objectFieldOffset("eventCount", ForkJoinPool.class);
2093	<	private static final long eventWaitersOffset =
2094	<	objectFieldOffset("eventWaiters",ForkJoinPool.class);
2095	<	private static final long stealCountOffset =
2096	<	objectFieldOffset("stealCount",ForkJoinPool.class);
2097	<	private static final long spareWaitersOffset =
2098	<	objectFieldOffset("spareWaiters",ForkJoinPool.class);
2099	<
2100	<	private static long objectFieldOffset(String field, Class<?> klazz) {
2085	>	private static final sun.misc.Unsafe UNSAFE;
2086	>	private static final long ctlOffset;
2087	>	private static final long stealCountOffset;
2088	>	private static final long blockedCountOffset;
2089	>	private static final long quiescerCountOffset;
2090	>	private static final long scanGuardOffset;
2091	>	private static final long nextWorkerNumberOffset;
2092	>	private static final long ABASE;
2093	>	private static final int ASHIFT;
2094	>
2095	>	static {
2096	>	poolNumberGenerator = new AtomicInteger();
2097	>	workerSeedGenerator = new Random();
2098	>	modifyThreadPermission = new RuntimePermission("modifyThread");
2099	>	defaultForkJoinWorkerThreadFactory =
2100	>	new DefaultForkJoinWorkerThreadFactory();
2101	>	int s;
2102		try {
2103	<	return UNSAFE.objectFieldOffset(klazz.getDeclaredField(field));
2104	<	} catch (NoSuchFieldException e) {
2105	<	// Convert Exception to corresponding Error
2106	<	NoSuchFieldError error = new NoSuchFieldError(field);
2107	<	error.initCause(e);
2108	<	throw error;
2109	<	}
2103	>	UNSAFE = getUnsafe();
2104	>	Class k = ForkJoinPool.class;
2105	>	ctlOffset = UNSAFE.objectFieldOffset
2106	>	(k.getDeclaredField("ctl"));
2107	>	stealCountOffset = UNSAFE.objectFieldOffset
2108	>	(k.getDeclaredField("stealCount"));
2109	>	blockedCountOffset = UNSAFE.objectFieldOffset
2110	>	(k.getDeclaredField("blockedCount"));
2111	>	quiescerCountOffset = UNSAFE.objectFieldOffset
2112	>	(k.getDeclaredField("quiescerCount"));
2113	>	scanGuardOffset = UNSAFE.objectFieldOffset
2114	>	(k.getDeclaredField("scanGuard"));
2115	>	nextWorkerNumberOffset = UNSAFE.objectFieldOffset
2116	>	(k.getDeclaredField("nextWorkerNumber"));
2117	>	Class a = ForkJoinTask[].class;
2118	>	ABASE = UNSAFE.arrayBaseOffset(a);
2119	>	s = UNSAFE.arrayIndexScale(a);
2120	>	} catch (Exception e) {
2121	>	throw new Error(e);
2122	>	}
2123	>	if ((s & (s-1)) != 0)
2124	>	throw new Error("data type scale not a power of two");
2125	>	ASHIFT = 31 - Integer.numberOfLeadingZeros(s);
2126		}
2127
2128		/**

Diff Legend

–	Removed lines
+	Added lines
<	Changed lines
>	Changed lines