AtomicInteger 实现和代码复制

performance java jvm

2022-09-02 22:21:10

警告：问题有点长，但分隔线下方的部分仅用于好奇。

Oracle 的 AtomicInteger 的 JDK 7 实现包括以下方法：

public final int addAndGet(int delta) {
    for (;;) {
        int current = get();
        int next = current + delta;         // Only difference
        if (compareAndSet(current, next))
            return next;
    }
}

public final int incrementAndGet() {
    for (;;) {
        int current = get();
        int next = current + 1;             // Only difference
        if (compareAndSet(current, next))
            return next;
    }
}

很明显，第二种方法可以写成：

public final int incrementAndGet() {
    return addAndGet(1);
}

该类中还有其他几个类似代码重复的示例。我想不出任何理由来这样做，但性能考虑（*）。我很确定作者在确定该设计之前进行了一些深入的测试。

为什么（或在什么情况下）第一个代码的性能会比第二个代码更好？

(*)我无法抗拒，但写了一个快速的微观基准。它显示（JIT后）2-4%表现的系统性差距有利于vs（诚然，这很小，但它非常一致）。老实说，我也无法真正解释这个结果......addAndGet(1)incrementAndGet()

输出：

incrementAndGet（）： 905
addAndGet（1）： 868
incrementAndGet（）： 902
addAndGet（1）： 863
incrementAndGet（）： 891
addAndGet（1）： 867
...

法典：

public static void main(String[] args) throws Exception {
    final int size = 100_000_000;
    long start, end;
    AtomicInteger ai;

    System.out.println("JVM warmup");
    for (int j = 0; j < 10; j++) {
        start = System.nanoTime();
        ai = new AtomicInteger();
        for (int i = 0; i < size / 10; i++) {
            ai.addAndGet(1);
        }
        end = System.nanoTime();
        System.out.println("addAndGet(1): " + ((end - start) / 1_000_000));
        start = System.nanoTime();
        ai = new AtomicInteger();
        for (int i = 0; i < size / 10; i++) {
            ai.incrementAndGet();
        }
        end = System.nanoTime();
        System.out.println("incrementAndGet(): " + ((end - start) / 1_000_000));
    }


    System.out.println("\nStart measuring\n");

    for (int j = 0; j < 10; j++) {
        start = System.nanoTime();
        ai = new AtomicInteger();
        for (int i = 0; i < size; i++) {
            ai.incrementAndGet();
        }
        end = System.nanoTime();
        System.out.println("incrementAndGet(): " + ((end - start) / 1_000_000));
        start = System.nanoTime();
        ai = new AtomicInteger();
        for (int i = 0; i < size; i++) {
            ai.addAndGet(1);
        }
        end = System.nanoTime();
        System.out.println("addAndGet(1): " + ((end - start) / 1_000_000));
    }
}

答案 1

我会给出新的假设。如果我们研究字节码，我们会看到，它们之间的主要区别在于使用指令，并使用指令：AtomicIntegeraddAndGetiload_incrementAndGeticonst_

public final int addAndGet(int);
   ...
   4:   istore_2
   5:   iload_2
   6:   iload_1
   7:   iadd

public final int incrementAndGet();
   ...
   4:   istore_1
   5:   iload_1
   6:   iconst_1
   7:   iadd

看起来，+翻译为指令，由于...作为指示。这一切都与关于vs等的众所周知的问题有关：iconst_iaddINCiload_iaddADDADD 1INC

x86 inc. 与添加指令的相对性能

ADD 1 真的比 INC 快吗？x86

这可能是答案，为什么比addAndGetincrementAndGet

答案 2

出于好奇，这里是 JIT 生成的汇编代码。综上所述，主要区别在于：

incrementAndGet

mov    r8d,eax
inc    r8d                ;*iadd

addAndGet

mov    r9d,r8d
add    r9d,eax            ;*iadd

代码的其余部分本质上是相同的。这证实了：

这些方法不是内部函数，不会在引擎盖下相互调用
唯一的区别是 vsINCADD 1

我不擅长阅读汇编，不知道为什么这会有所作为。这并没有真正回答我最初的问题。

完整列表（增量和获取）：

  # {method} 'incrementAndGet' '()I' in 'java/util/concurrent/atomic/AtomicInteger'
  #           [sp+0x20]  (sp of caller)
  0x00000000026804c0: mov    r10d,DWORD PTR [rdx+0x8]
  0x00000000026804c4: shl    r10,0x3
  0x00000000026804c8: cmp    rax,r10
  0x00000000026804cb: jne    0x0000000002657b60  ;   {runtime_call}
  0x00000000026804d1: data32 xchg ax,ax
  0x00000000026804d4: nop    DWORD PTR [rax+rax*1+0x0]
  0x00000000026804dc: data32 data32 xchg ax,ax
[Verified Entry Point]
  0x00000000026804e0: sub    rsp,0x18
  0x00000000026804e7: mov    QWORD PTR [rsp+0x10],rbp  ;*synchronization entry
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@-1 (line 204)
  0x00000000026804ec: mov    eax,DWORD PTR [rdx+0xc]  ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@12 (line 206)
  0x00000000026804ef: mov    r8d,eax
  0x00000000026804f2: inc    r8d                ;*iadd
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@7 (line 205)
  0x00000000026804f5: lock cmpxchg DWORD PTR [rdx+0xc],r8d
  0x00000000026804fb: sete   r11b
  0x00000000026804ff: movzx  r11d,r11b          ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@12 (line 206)
  0x0000000002680503: test   r11d,r11d
  0x0000000002680506: je     0x0000000002680520  ;*iload_2
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@18 (line 207)
  0x0000000002680508: mov    eax,r8d
  0x000000000268050b: add    rsp,0x10
  0x000000000268050f: pop    rbp
  0x0000000002680510: test   DWORD PTR [rip+0xfffffffffdbafaea],eax        # 0x0000000000230000
                                                ;   {poll_return}
  0x0000000002680516: ret    
  0x0000000002680517: nop    WORD PTR [rax+rax*1+0x0]  ; OopMap{rdx=Oop off=96}
                                                ;*goto
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@20 (line 208)
  0x0000000002680520: test   DWORD PTR [rip+0xfffffffffdbafada],eax        # 0x0000000000230000
                                                ;*goto
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@20 (line 208)
                                                ;   {poll}
  0x0000000002680526: mov    r11d,DWORD PTR [rdx+0xc]  ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@12 (line 206)
  0x000000000268052a: mov    r8d,r11d
  0x000000000268052d: inc    r8d                ;*iadd
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@7 (line 205)
  0x0000000002680530: mov    eax,r11d
  0x0000000002680533: lock cmpxchg DWORD PTR [rdx+0xc],r8d
  0x0000000002680539: sete   r11b
  0x000000000268053d: movzx  r11d,r11b          ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@12 (line 206)
  0x0000000002680541: test   r11d,r11d
  0x0000000002680544: je     0x0000000002680520  ;*ifeq
                                                ; - java.util.concurrent.atomic.AtomicInteger::incrementAndGet@15 (line 206)
  0x0000000002680546: jmp    0x0000000002680508

完整列表（addAndGet）：

  # {method} 'addAndGet' '(I)I' in 'java/util/concurrent/atomic/AtomicInteger'
  # this:     rdx:rdx   = 'java/util/concurrent/atomic/AtomicInteger'
  # parm0:    r8        = int
  #           [sp+0x20]  (sp of caller)
  0x0000000002680d00: mov    r10d,DWORD PTR [rdx+0x8]
  0x0000000002680d04: shl    r10,0x3
  0x0000000002680d08: cmp    rax,r10
  0x0000000002680d0b: jne    0x0000000002657b60  ;   {runtime_call}
  0x0000000002680d11: data32 xchg ax,ax
  0x0000000002680d14: nop    DWORD PTR [rax+rax*1+0x0]
  0x0000000002680d1c: data32 data32 xchg ax,ax
[Verified Entry Point]
  0x0000000002680d20: sub    rsp,0x18
  0x0000000002680d27: mov    QWORD PTR [rsp+0x10],rbp  ;*synchronization entry
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@-1 (line 233)
  0x0000000002680d2c: mov    eax,DWORD PTR [rdx+0xc]  ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@12 (line 235)
  0x0000000002680d2f: mov    r9d,r8d
  0x0000000002680d32: add    r9d,eax            ;*iadd
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@7 (line 234)
  0x0000000002680d35: lock cmpxchg DWORD PTR [rdx+0xc],r9d
  0x0000000002680d3b: sete   r11b
  0x0000000002680d3f: movzx  r11d,r11b          ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@12 (line 235)
  0x0000000002680d43: test   r11d,r11d
  0x0000000002680d46: je     0x0000000002680d60  ;*iload_3
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@18 (line 236)
  0x0000000002680d48: mov    eax,r9d
  0x0000000002680d4b: add    rsp,0x10
  0x0000000002680d4f: pop    rbp
  0x0000000002680d50: test   DWORD PTR [rip+0xfffffffffdbaf2aa],eax        # 0x0000000000230000
                                                ;   {poll_return}
  0x0000000002680d56: ret    
  0x0000000002680d57: nop    WORD PTR [rax+rax*1+0x0]  ; OopMap{rdx=Oop off=96}
                                                ;*goto
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@20 (line 237)
  0x0000000002680d60: test   DWORD PTR [rip+0xfffffffffdbaf29a],eax        # 0x0000000000230000
                                                ;*goto
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@20 (line 237)
                                                ;   {poll}
  0x0000000002680d66: mov    r11d,DWORD PTR [rdx+0xc]  ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@12 (line 235)
  0x0000000002680d6a: mov    r9d,r11d
  0x0000000002680d6d: add    r9d,r8d            ;*iadd
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@7 (line 234)
  0x0000000002680d70: mov    eax,r11d
  0x0000000002680d73: lock cmpxchg DWORD PTR [rdx+0xc],r9d
  0x0000000002680d79: sete   r11b
  0x0000000002680d7d: movzx  r11d,r11b          ;*invokevirtual compareAndSwapInt
                                                ; - java.util.concurrent.atomic.AtomicInteger::compareAndSet@9 (line 135)
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@12 (line 235)
  0x0000000002680d81: test   r11d,r11d
  0x0000000002680d84: je     0x0000000002680d60  ;*ifeq
                                                ; - java.util.concurrent.atomic.AtomicInteger::addAndGet@15 (line 235)
  0x0000000002680d86: jmp    0x0000000002680d48