java8-using-cms-gc.txt

nitsan:object-pool-benchmarks% java -jar target/benchmarks.jar 'Simulation.(newObject|claimReleaseWithout)' -bm sample -i 10 -wi 10 -tu ns -t 1 -f 1 -r 10 -jvmArgsPrepend '-XX:+UseConcMarkSweepGC'
# JMH 1.5.1 (released 10 days ago)
# VM invoker: /usr/lib/jvm/java-8-jdk/jre/bin/java
# VM options: -XX:+UseConcMarkSweepGC
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Sampling time
# Benchmark: objectpoolbenchmark.specific.stormpot.Simulation.claimReleaseWithoutReturn

# Run progress: 0.00% complete, ETA 00:03:40
# Fork: 1 of 1
# Warmup Iteration   1: n = 36487, mean = 94 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 26, 42, 44, 45, 613, 9800, 25209, 966656 ns/op
# Warmup Iteration   2: n = 18463, mean = 43 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 31, 43, 45, 45, 49, 74, 140, 145 ns/op
# Warmup Iteration   3: n = 18651, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 48, 86, 96, 99 ns/op
# Warmup Iteration   4: n = 18628, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 52, 79, 122, 130 ns/op
# Warmup Iteration   5: n = 18675, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 47, 82, 99, 140 ns/op
# Warmup Iteration   6: n = 18710, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 54, 72, 72 ns/op
# Warmup Iteration   7: n = 18688, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 47, 62, 81, 84 ns/op
# Warmup Iteration   8: n = 18709, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 53, 73, 78 ns/op
# Warmup Iteration   9: n = 18703, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 53, 73, 74 ns/op
# Warmup Iteration  10: n = 18707, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 53, 66, 71 ns/op
Iteration   1: n = 187025, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 53, 69, 891 ns/op
Iteration   2: n = 187119, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 65, 913 ns/op
Iteration   3: n = 187116, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 57, 1240 ns/op
Iteration   4: n = 187122, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 65, 896 ns/op
Iteration   5: n = 187105, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 52, 64, 879 ns/op
Iteration   6: n = 187112, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 64, 1146 ns/op
Iteration   7: n = 187029, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 62, 1120 ns/op
Iteration   8: n = 187026, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 47, 62, 912 ns/op
Iteration   9: n = 187023, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 60, 1166 ns/op
Iteration  10: n = 187093, mean = 44 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 44, 45, 46, 46, 48, 58, 1152 ns/op


Result: 43.934 ±(99.9%) 0.008 ns/op [Average]
  Statistics: (min, avg, max) = (30.000, 43.934, 1240.000), stdev = 3.530
  Confidence interval (99.9%): [43.925, 43.942]
  Samples, N = 1870770
        mean =     43.934 ±(99.9%) 0.008 ns/op
         min =     30.000 ns/op
  p( 0.0000) =     30.000 ns/op
  p(50.0000) =     44.000 ns/op
  p(90.0000) =     45.000 ns/op
  p(95.0000) =     46.000 ns/op
  p(99.0000) =     46.000 ns/op
  p(99.9000) =     48.000 ns/op
  p(99.9900) =     64.000 ns/op
  p(99.9990) =    888.292 ns/op
  p(99.9999) =   1175.563 ns/op
         max =   1240.000 ns/op


# JMH 1.5.1 (released 10 days ago)
# VM invoker: /usr/lib/jvm/java-8-jdk/jre/bin/java
# VM options: -XX:+UseConcMarkSweepGC
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Sampling time
# Benchmark: objectpoolbenchmark.specific.stormpot.Simulation.newObject

# Run progress: 50.00% complete, ETA 00:01:50
# Fork: 1 of 1
# Warmup Iteration   1: n = 22140, mean = 41 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 15, 20, 23, 28, 134, 3995, 77115, 95232 ns/op
# Warmup Iteration   2: n = 11093, mean = 27 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 16, 22, 30, 33, 85, 264, 5472, 6096 ns/op
# Warmup Iteration   3: n = 9663, mean = 37 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 20, 33, 42, 69, 97, 203, 391, 391 ns/op
# Warmup Iteration   4: n = 9690, mean = 38 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 20, 38, 42, 69, 97, 272, 400, 400 ns/op
# Warmup Iteration   5: n = 9888, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 20, 37, 44, 60, 97, 255, 342, 342 ns/op
# Warmup Iteration   6: n = 9889, mean = 36 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 16, 32, 41, 64, 94, 189, 332, 332 ns/op
# Warmup Iteration   7: n = 9662, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 66, 98, 203, 352, 352 ns/op
# Warmup Iteration   8: n = 9862, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 38, 42, 67, 98, 209, 360, 360 ns/op
# Warmup Iteration   9: n = 10146, mean = 41 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 39, 42, 62, 97, 172, 347, 347 ns/op
# Warmup Iteration  10: n = 9925, mean = 40 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 69, 98, 256, 7432, 7432 ns/op
Iteration   1: n = 97660, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 67, 97, 236, 362, 6504 ns/op
Iteration   2: n = 96935, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 38, 43, 66, 97, 215, 364, 817152 ns/op
Iteration   3: n = 96442, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 38, 43, 68, 97, 215, 367, 737 ns/op
Iteration   4: n = 97477, mean = 112 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 44, 67, 98, 234, 393, 7061504 ns/op
Iteration   5: n = 98532, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 65, 97, 225, 356, 5368 ns/op
Iteration   6: n = 99637, mean = 39 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 60, 96, 205, 369, 3596 ns/op
Iteration   7: n = 100545, mean = 40 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 44, 56, 97, 243, 356, 411 ns/op
Iteration   8: n = 98855, mean = 40 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 43, 65, 97, 185, 341, 3632 ns/op
Iteration   9: n = 98193, mean = 47 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 38, 42, 66, 97, 212, 358, 724992 ns/op
Iteration  10: n = 98060, mean = 40 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 38, 42, 67, 98, 252, 359, 403 ns/op


Result: 48.234 ±(99.9%) 23.935 ns/op [Average]
  Statistics: (min, avg, max) = (17.000, 48.234, 7061504.000), stdev = 7209.438
  Confidence interval (99.9%): [24.299, 72.169]
  Samples, N = 982336
        mean =     48.234 ±(99.9%) 23.935 ns/op
         min =     17.000 ns/op
  p( 0.0000) =     17.000 ns/op
  p(50.0000) =     38.000 ns/op
  p(90.0000) =     43.000 ns/op
  p(95.0000) =     65.000 ns/op
  p(99.0000) =     97.000 ns/op
  p(99.9000) =    224.000 ns/op
  p(99.9900) =    357.000 ns/op
  p(99.9990) =   3602.359 ns/op
  p(99.9999) = 7061504.000 ns/op
         max = 7061504.000 ns/op


# Run complete. Total time: 00:03:40

Benchmark                               Mode      Cnt   Score    Error  Units
Simulation.claimReleaseWithoutReturn  sample  1870770  43.934 ±  0.008  ns/op
Simulation.newObject                  sample   982336  48.234 ± 23.935  ns/op
nitsan:object-pool-benchmarks% 

java8-using-default-gc.txt

nitsan:object-pool-benchmarks% java -jar target/benchmarks.jar 'Simulation.(newObject|claimReleaseWithout)' -bm sample -i 10 -wi 10 -tu ns -t 1 -f 1 -r 10
# JMH 1.5.1 (released 10 days ago)
# VM invoker: /usr/lib/jvm/java-8-jdk/jre/bin/java
# VM options: <none>
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Sampling time
# Benchmark: objectpoolbenchmark.specific.stormpot.Simulation.claimReleaseWithoutReturn

# Run progress: 0.00% complete, ETA 00:03:40
# Fork: 1 of 1
# Warmup Iteration   1: n = 37011, mean = 101 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 27, 35, 42, 44, 818, 6845, 21390, 1366016 ns/op
# Warmup Iteration   2: n = 18713, mean = 36 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 28, 36, 38, 39, 43, 46, 547, 3352 ns/op
# Warmup Iteration   3: n = 18680, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 52, 66, 101, 104 ns/op
# Warmup Iteration   4: n = 18645, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 53, 83, 93, 96 ns/op
# Warmup Iteration   5: n = 18695, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 58, 82, 86 ns/op
# Warmup Iteration   6: n = 18701, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 54, 57, 57 ns/op
# Warmup Iteration   7: n = 18680, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 31, 48, 49, 50, 51, 79, 100, 106 ns/op
# Warmup Iteration   8: n = 18703, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 50, 51, 54, 218, 1224 ns/op
# Warmup Iteration   9: n = 18707, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 31, 48, 49, 49, 51, 54, 58, 60 ns/op
# Warmup Iteration  10: n = 18703, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 54, 63, 64 ns/op
Iteration   1: n = 187066, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 50, 50, 53, 57, 11232 ns/op
Iteration   2: n = 187006, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 26, 48, 49, 49, 51, 55, 83, 891 ns/op
Iteration   3: n = 187073, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 50, 51, 54, 56, 1180 ns/op
Iteration   4: n = 187070, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 50, 50, 53, 55, 1318 ns/op
Iteration   5: n = 187029, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 54, 78, 1168 ns/op
Iteration   6: n = 187066, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 29, 48, 49, 50, 51, 54, 59, 967 ns/op
Iteration   7: n = 187031, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 54, 70, 909 ns/op
Iteration   8: n = 187021, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 50, 53, 66, 1208 ns/op
Iteration   9: n = 187022, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 50, 54, 65, 1150 ns/op
Iteration  10: n = 187021, mean = 48 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 30, 48, 49, 49, 51, 54, 69, 1170 ns/op


Result: 47.734 ±(99.9%) 0.022 ns/op [Average]
  Statistics: (min, avg, max) = (26.000, 47.734, 11232.000), stdev = 9.249
  Confidence interval (99.9%): [47.711, 47.756]
  Samples, N = 1870405
        mean =     47.734 ±(99.9%) 0.022 ns/op
         min =     26.000 ns/op
  p( 0.0000) =     26.000 ns/op
  p(50.0000) =     48.000 ns/op
  p(90.0000) =     49.000 ns/op
  p(95.0000) =     49.000 ns/op
  p(99.0000) =     51.000 ns/op
  p(99.9000) =     54.000 ns/op
  p(99.9900) =     69.000 ns/op
  p(99.9990) =    917.255 ns/op
  p(99.9999) =   2602.795 ns/op
         max =  11232.000 ns/op


# JMH 1.5.1 (released 10 days ago)
# VM invoker: /usr/lib/jvm/java-8-jdk/jre/bin/java
# VM options: <none>
# Warmup: 10 iterations, 1 s each
# Measurement: 10 iterations, 10 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Sampling time
# Benchmark: objectpoolbenchmark.specific.stormpot.Simulation.newObject

# Run progress: 50.00% complete, ETA 00:01:50
# Fork: 1 of 1
# Warmup Iteration   1: n = 22382, mean = 41 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 15, 26, 29, 30, 133, 8926, 12564, 13328 ns/op
# Warmup Iteration   2: n = 11628, mean = 30 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 16, 28, 30, 36, 86, 254, 377, 380 ns/op
# Warmup Iteration   3: n = 10447, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 20, 27, 32, 61, 90, 314, 366, 366 ns/op
# Warmup Iteration   4: n = 10460, mean = 30 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 27, 33, 63, 89, 205, 329, 330 ns/op
# Warmup Iteration   5: n = 10433, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 31, 62, 85, 241, 350, 352 ns/op
# Warmup Iteration   6: n = 10469, mean = 26 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 21, 30, 57, 80, 214, 313, 313 ns/op
# Warmup Iteration   7: n = 10438, mean = 27 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 23, 29, 61, 83, 223, 8520, 8896 ns/op
# Warmup Iteration   8: n = 10458, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 33, 61, 87, 173, 399, 401 ns/op
# Warmup Iteration   9: n = 10415, mean = 28 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 25, 35, 61, 84, 234, 369, 370 ns/op
# Warmup Iteration  10: n = 10410, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 19, 26, 31, 62, 88, 149, 364, 365 ns/op
Iteration   1: n = 104685, mean = 28 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 31, 60, 84, 234, 353, 10112 ns/op
Iteration   2: n = 104609, mean = 28 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 35, 60, 85, 215, 349, 403 ns/op
Iteration   3: n = 104514, mean = 28 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 30, 61, 84, 226, 322, 374 ns/op
Iteration   4: n = 104587, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 35, 60, 87, 253, 372, 8912 ns/op
Iteration   5: n = 104556, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 31, 61, 86, 244, 340, 386 ns/op
Iteration   6: n = 104560, mean = 30 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 27, 34, 61, 90, 233, 347, 8816 ns/op
Iteration   7: n = 104501, mean = 32 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 28, 37, 61, 92, 250, 350, 619 ns/op
Iteration   8: n = 104518, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 35, 60, 88, 254, 346, 10224 ns/op
Iteration   9: n = 104517, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 35, 58, 88, 230, 339, 1560 ns/op
Iteration  10: n = 104407, mean = 29 ns/op, p{0.00, 0.50, 0.90, 0.95, 0.99, 0.999, 0.9999, 1.00} = 17, 26, 34, 60, 88, 264, 353, 14816 ns/op


Result: 29.025 ±(99.9%) 0.098 ns/op [Average]
  Statistics: (min, avg, max) = (17.000, 29.025, 14816.000), stdev = 30.428
  Confidence interval (99.9%): [28.927, 29.123]
  Samples, N = 1045454
        mean =     29.025 ±(99.9%) 0.098 ns/op
         min =     17.000 ns/op
  p( 0.0000) =     17.000 ns/op
  p(50.0000) =     26.000 ns/op
  p(90.0000) =     35.000 ns/op
  p(95.0000) =     60.000 ns/op
  p(99.0000) =     88.000 ns/op
  p(99.9000) =    240.000 ns/op
  p(99.9900) =    346.000 ns/op
  p(99.9990) =   4090.542 ns/op
  p(99.9999) =  14607.271 ns/op
         max =  14816.000 ns/op


# Run complete. Total time: 00:03:40

Benchmark                               Mode      Cnt   Score   Error  Units
Simulation.claimReleaseWithoutReturn  sample  1870405  47.734 ± 0.022  ns/op
Simulation.newObject                  sample  1045454  29.025 ± 0.098  ns/op
nitsan:object-pool-benchmarks%