1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
|
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
* This file is available under and governed by the GNU General Public
* License version 2 only, as published by the Free Software Foundation.
* However, the following notice accompanied the original version of this
* file:
*
* Written by Doug Lea with assistance from members of JCP JSR-166
* Expert Group and released to the public domain, as explained at
* http://creativecommons.org/publicdomain/zero/1.0/
*/
package java.util.concurrent.atomic;
import java.util.function.LongBinaryOperator;
import java.util.function.DoubleBinaryOperator;
import java.util.concurrent.ThreadLocalRandom;
/**
* A package-local class holding common representation and mechanics
* for classes supporting dynamic striping on 64bit values. The class
* extends Number so that concrete subclasses must publicly do so.
*/
@SuppressWarnings("serial")
abstract class Striped64 extends Number {
/*
* This class maintains a lazily-initialized table of atomically
* updated variables, plus an extra "base" field. The table size
* is a power of two. Indexing uses masked per-thread hash codes.
* Nearly all declarations in this class are package-private,
* accessed directly by subclasses.
*
* Table entries are of class Cell; a variant of AtomicLong padded
* (via @sun.misc.Contended) to reduce cache contention. Padding
* is overkill for most Atomics because they are usually
* irregularly scattered in memory and thus don't interfere much
* with each other. But Atomic objects residing in arrays will
* tend to be placed adjacent to each other, and so will most
* often share cache lines (with a huge negative performance
* impact) without this precaution.
*
* In part because Cells are relatively large, we avoid creating
* them until they are needed. When there is no contention, all
* updates are made to the base field. Upon first contention (a
* failed CAS on base update), the table is initialized to size 2.
* The table size is doubled upon further contention until
* reaching the nearest power of two greater than or equal to the
* number of CPUS. Table slots remain empty (null) until they are
* needed.
*
* A single spinlock ("cellsBusy") is used for initializing and
* resizing the table, as well as populating slots with new Cells.
* There is no need for a blocking lock; when the lock is not
* available, threads try other slots (or the base). During these
* retries, there is increased contention and reduced locality,
* which is still better than alternatives.
*
* The Thread probe fields maintained via ThreadLocalRandom serve
* as per-thread hash codes. We let them remain uninitialized as
* zero (if they come in this way) until they contend at slot
* 0. They are then initialized to values that typically do not
* often conflict with others. Contention and/or table collisions
* are indicated by failed CASes when performing an update
* operation. Upon a collision, if the table size is less than
* the capacity, it is doubled in size unless some other thread
* holds the lock. If a hashed slot is empty, and lock is
* available, a new Cell is created. Otherwise, if the slot
* exists, a CAS is tried. Retries proceed by "double hashing",
* using a secondary hash (Marsaglia XorShift) to try to find a
* free slot.
*
* The table size is capped because, when there are more threads
* than CPUs, supposing that each thread were bound to a CPU,
* there would exist a perfect hash function mapping threads to
* slots that eliminates collisions. When we reach capacity, we
* search for this mapping by randomly varying the hash codes of
* colliding threads. Because search is random, and collisions
* only become known via CAS failures, convergence can be slow,
* and because threads are typically not bound to CPUS forever,
* may not occur at all. However, despite these limitations,
* observed contention rates are typically low in these cases.
*
* It is possible for a Cell to become unused when threads that
* once hashed to it terminate, as well as in the case where
* doubling the table causes no thread to hash to it under
* expanded mask. We do not try to detect or remove such cells,
* under the assumption that for long-running instances, observed
* contention levels will recur, so the cells will eventually be
* needed again; and for short-lived ones, it does not matter.
*/
/**
* Padded variant of AtomicLong supporting only raw accesses plus CAS.
*
* JVM intrinsics note: It would be possible to use a release-only
* form of CAS here, if it were provided.
*/
@sun.misc.Contended static final class Cell {
volatile long value;
Cell(long x) { value = x; }
@ikvm.internal.InterlockedCompareAndSet("value")
final native boolean cas(long cmp, long val);
}
/** Number of CPUS, to place bound on table size */
static final int NCPU = Runtime.getRuntime().availableProcessors();
/**
* Table of cells. When non-null, size is a power of 2.
*/
transient volatile Cell[] cells;
/**
* Base value, used mainly when there is no contention, but also as
* a fallback during table initialization races. Updated via CAS.
*/
transient volatile long base;
/**
* Spinlock (locked via CAS) used when resizing and/or creating Cells.
*/
transient volatile int cellsBusy;
/**
* Package-private default constructor
*/
Striped64() {
}
/**
* CASes the base field.
*/
@ikvm.internal.InterlockedCompareAndSet("base")
final native boolean casBase(long cmp, long val);
/**
* CASes the cellsBusy field from 0 to 1 to acquire lock.
*/
final boolean casCellsBusy() {
return casCellsBusy(0, 1);
}
@ikvm.internal.InterlockedCompareAndSet("cellsBusy")
private native boolean casCellsBusy(int cmp, int newVal);
/**
* Returns the probe value for the current thread.
* Duplicated from ThreadLocalRandom because of packaging restrictions.
*/
static final int getProbe() {
return Thread.currentThread().threadLocalRandomProbe;
}
/**
* Pseudo-randomly advances and records the given probe value for the
* given thread.
* Duplicated from ThreadLocalRandom because of packaging restrictions.
*/
static final int advanceProbe(int probe) {
probe ^= probe << 13; // xorshift
probe ^= probe >>> 17;
probe ^= probe << 5;
Thread.currentThread().threadLocalRandomProbe = probe;
return probe;
}
/**
* Handles cases of updates involving initialization, resizing,
* creating new Cells, and/or contention. See above for
* explanation. This method suffers the usual non-modularity
* problems of optimistic retry code, relying on rechecked sets of
* reads.
*
* @param x the value
* @param fn the update function, or null for add (this convention
* avoids the need for an extra field or function in LongAdder).
* @param wasUncontended false if CAS failed before call
*/
final void longAccumulate(long x, LongBinaryOperator fn,
boolean wasUncontended) {
int h;
if ((h = getProbe()) == 0) {
ThreadLocalRandom.current(); // force initialization
h = getProbe();
wasUncontended = true;
}
boolean collide = false; // True if last slot nonempty
for (;;) {
Cell[] as; Cell a; int n; long v;
if ((as = cells) != null && (n = as.length) > 0) {
if ((a = as[(n - 1) & h]) == null) {
if (cellsBusy == 0) { // Try to attach new Cell
Cell r = new Cell(x); // Optimistically create
if (cellsBusy == 0 && casCellsBusy()) {
boolean created = false;
try { // Recheck under lock
Cell[] rs; int m, j;
if ((rs = cells) != null &&
(m = rs.length) > 0 &&
rs[j = (m - 1) & h] == null) {
rs[j] = r;
created = true;
}
} finally {
cellsBusy = 0;
}
if (created)
break;
continue; // Slot is now non-empty
}
}
collide = false;
}
else if (!wasUncontended) // CAS already known to fail
wasUncontended = true; // Continue after rehash
else if (a.cas(v = a.value, ((fn == null) ? v + x :
fn.applyAsLong(v, x))))
break;
else if (n >= NCPU || cells != as)
collide = false; // At max size or stale
else if (!collide)
collide = true;
else if (cellsBusy == 0 && casCellsBusy()) {
try {
if (cells == as) { // Expand table unless stale
Cell[] rs = new Cell[n << 1];
for (int i = 0; i < n; ++i)
rs[i] = as[i];
cells = rs;
}
} finally {
cellsBusy = 0;
}
collide = false;
continue; // Retry with expanded table
}
h = advanceProbe(h);
}
else if (cellsBusy == 0 && cells == as && casCellsBusy()) {
boolean init = false;
try { // Initialize table
if (cells == as) {
Cell[] rs = new Cell[2];
rs[h & 1] = new Cell(x);
cells = rs;
init = true;
}
} finally {
cellsBusy = 0;
}
if (init)
break;
}
else if (casBase(v = base, ((fn == null) ? v + x :
fn.applyAsLong(v, x))))
break; // Fall back on using base
}
}
/**
* Same as longAccumulate, but injecting long/double conversions
* in too many places to sensibly merge with long version, given
* the low-overhead requirements of this class. So must instead be
* maintained by copy/paste/adapt.
*/
final void doubleAccumulate(double x, DoubleBinaryOperator fn,
boolean wasUncontended) {
int h;
if ((h = getProbe()) == 0) {
ThreadLocalRandom.current(); // force initialization
h = getProbe();
wasUncontended = true;
}
boolean collide = false; // True if last slot nonempty
for (;;) {
Cell[] as; Cell a; int n; long v;
if ((as = cells) != null && (n = as.length) > 0) {
if ((a = as[(n - 1) & h]) == null) {
if (cellsBusy == 0) { // Try to attach new Cell
Cell r = new Cell(Double.doubleToRawLongBits(x));
if (cellsBusy == 0 && casCellsBusy()) {
boolean created = false;
try { // Recheck under lock
Cell[] rs; int m, j;
if ((rs = cells) != null &&
(m = rs.length) > 0 &&
rs[j = (m - 1) & h] == null) {
rs[j] = r;
created = true;
}
} finally {
cellsBusy = 0;
}
if (created)
break;
continue; // Slot is now non-empty
}
}
collide = false;
}
else if (!wasUncontended) // CAS already known to fail
wasUncontended = true; // Continue after rehash
else if (a.cas(v = a.value,
((fn == null) ?
Double.doubleToRawLongBits
(Double.longBitsToDouble(v) + x) :
Double.doubleToRawLongBits
(fn.applyAsDouble
(Double.longBitsToDouble(v), x)))))
break;
else if (n >= NCPU || cells != as)
collide = false; // At max size or stale
else if (!collide)
collide = true;
else if (cellsBusy == 0 && casCellsBusy()) {
try {
if (cells == as) { // Expand table unless stale
Cell[] rs = new Cell[n << 1];
for (int i = 0; i < n; ++i)
rs[i] = as[i];
cells = rs;
}
} finally {
cellsBusy = 0;
}
collide = false;
continue; // Retry with expanded table
}
h = advanceProbe(h);
}
else if (cellsBusy == 0 && cells == as && casCellsBusy()) {
boolean init = false;
try { // Initialize table
if (cells == as) {
Cell[] rs = new Cell[2];
rs[h & 1] = new Cell(Double.doubleToRawLongBits(x));
cells = rs;
init = true;
}
} finally {
cellsBusy = 0;
}
if (init)
break;
}
else if (casBase(v = base,
((fn == null) ?
Double.doubleToRawLongBits
(Double.longBitsToDouble(v) + x) :
Double.doubleToRawLongBits
(fn.applyAsDouble
(Double.longBitsToDouble(v), x)))))
break; // Fall back on using base
}
}
}
|