我想用java实现一个简单的速率限制器来学习如何使用jmh。一个简单的github项目在'https://github.com/william1104/rate-limiter'
有趣的是，当启用'-xx:+uselwpsynchronization'选项时，某些实现（使用stamplock）的吞吐量会受到影响。基准测试是在windows机器上执行的，我希望它对非solaris系统没有影响。然而，测试结果却有不同的表现。我能知道有谁能帮我弄清楚到底发生了什么吗？
以下是我机器上的测试结果作为参考：
带选项： -server, -XX:+UnlockDiagnosticVMOptions, -XX:+UseNUMA 基准（ratelimitertype）模式CntScoreErrorUnitsRaterLimiterBenchMark.thread\u 1stamplocklongarrayratelimiterthrpt9021487.385▒ 1082.163ops/msraterlimiterbenchmark.thread\u 1stamplockinstantarrayratelimiterthrpt9013162.330▒ 1585.555ops/msraterlimiterbenchmark.thread\u 1synchronizedlongarrayratelimitterthrpt9015362.934同步阵列卫星▒ 227.704ops/msraterlimiterbenchmark.thread\u 1同步标准阵列速率限制器hrpt9017281.675▒ 2148.057ops/msraterlimiterbenchmark.thread\u 10stamplocklongarrayratelimitterthrpt906868.653▒ 146.372ops/msraterlimiterbenchmark.thread\u 10stamplockinstantarrayratelimiterthrpt908189.747螺纹▒ 335.517ops/msraterlimiterbenchmark.thread\u 10同步长阵列卫星限制器thrpt906643.004▒ 103.568ops/msraterlimiterbenchmark.thread\u 10同步标准速率限制器hrpt905252.975▒ 190.363ops/msraterlimiterbenchmark.thread d 100stamplocklongarrayratelimitterthrpt907352.890▒ 2109.446 ops/msraterlimiterbenchmark.thread\u 100stamplockinstantarrayratelimiterthrpt908675.814线程▒ 922.653ops/msraterlimiterbenchmark.thread\u 100同步长阵列卫星限制器thrpt906509.368▒ 157.212ops/msraterlimiterbenchmark.thread\u 100同步标准速率限制器hrpt905042.867▒ 192.971ps/ms
带选项： -server, -XX:+UnlockDiagnosticVMOptions, -XX:+UseNUMA, -XX:+UseLWPSynchronization 基准（ratelimitertype）模式CntScoreErrorUnitsRaterLimiterBenchmark.thread\u 1stamplocklongarrayratelimiterthrpt9011383.198▒ 353.921ops/msraterlimiterbenchmark.thread\u 1stamplockinstantarrayratelimiterthrpt9011666.918螺纹▒ 842.426ops/msraterlimiterbenchmark.thread\u 1synchronizedlongarrayratelimitterthrpt9015696.852线程▒ 371.078ops/msraterlimiterbenchmark.thread\u 1同步标准阵列速率限制器hrpt9015357.617▒ 650.846ops/msraterlimiterbenchmark.thread\u 10stamplocklongarrayratelimitterthrpt906937.050▒ 130.727ops/msraterlimiterbenchmark.thread\u 10stamplockinstantarrayratelimiterthrpt908268.909线程▒ 291.471ops/msraterlimiterbenchmark.thread\u 10同步长阵列卫星限制器thrpt909134.319▒ 1208.998ops/msraterlimiterbenchmark.thread\u 10同步标准速率限制器hrpt905294.341▒ 225.995ops/msraterlimiterbenchmark.thread d 100stamplocklongarrayratelimitterthrpt908453.825▒ 1075.312ops/msraterlimiterbenchmark.thread\u 100stamplockinstantarrayratelimiterthrpt9016297.921螺纹▒ 611.255ops/msraterlimiterbenchmark.thread\u 100同步长阵列卫星限制器thrpt9012536.378▒ 974.951ops/msraterlimiterbenchmark.thread\u 100同步标准速率限制器hrpt909051.560▒ 1303.856操作/毫秒
有StampLockLongArrayLatelimeter和SynchronizedLongArrayLatelimeter的实现：

package one.williamwong.ratelimiter;

import java.time.Duration;
import java.util.Arrays;
import java.util.concurrent.locks.StampedLock;

public class StampLockLongArrayRateLimiter implements IRateLimiter {

    private final long duration;
    private final long[] records;
    private final StampedLock lock;
    private int pointer;

    public StampLockLongArrayRateLimiter(int maxInvokes, Duration duration) {
        this.duration = duration.toNanos();
        this.records = new long[maxInvokes];
        this.lock = new StampedLock();
        this.pointer = 0;
    }

    @Override public void acquire() {
        final long stamp = lock.writeLock();
        try {
            final long now = System.nanoTime();
            if (records[pointer] != 0) {
                final long awayFromHead = now - records[pointer];
                if (awayFromHead < duration) {
                    handleExcessLimit(records.length, Duration.ofNanos(awayFromHead));
                }
            }
            records[pointer] = now;
            pointer = (pointer + 1) % records.length;
        } finally {
            lock.unlockWrite(stamp);
        }
    }

    @Override public void reset() {
        final long stamp = lock.writeLock();
        try {
            Arrays.fill(records, 0);
            this.pointer = 0;
        } finally {
            lock.unlockWrite(stamp);
        }
    }

}

package one.williamwong.ratelimiter;

import java.time.Duration;
import java.util.Arrays;

public class SynchronizedLongArrayRateLimiter implements IRateLimiter {

    private final long duration;
    private final long[] records;
    private final Object lock;
    private int pointer;

    public SynchronizedLongArrayRateLimiter(int maxInvokes, Duration duration) {
        this.duration = duration.toNanos();
        this.records = new long[maxInvokes];
        this.lock = new Object();
        this.pointer = 0;
    }

    @Override
    public void acquire() {
        synchronized (lock) {
            final long now = System.nanoTime();
            if (records[pointer] != 0) {
                final long awayFromHead = now - records[pointer];
                if (awayFromHead < duration) {
                    handleExcessLimit(records.length, Duration.ofNanos(awayFromHead));
                }
            }
            records[pointer] = now;
            pointer = (pointer + 1) % records.length;
        }
    }

    @Override public void reset() {
        synchronized (lock) {
            Arrays.fill(records, 0);
            this.pointer = 0;
        }
    }

}