gcc -o pgms/arithoh -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Darithoh src/arith.c 
gcc -o pgms/register -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum="register int" src/arith.c 
gcc -o pgms/short -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum=short src/arith.c 
gcc -o pgms/int -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum=int src/arith.c 
gcc -o pgms/long -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum=long src/arith.c 
gcc -o pgms/float -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum=float src/arith.c 
gcc -o pgms/double -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -Ddatum=double src/arith.c 
gcc -o pgms/hanoi -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/hanoi.c 
gcc -o pgms/syscall -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/syscall.c 
gcc -o pgms/context1 -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/context1.c 
gcc -o pgms/pipe -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/pipe.c 
src/pipe.c: In function xe2x80x98mainxe2x80x99:
src/pipe.c:52:2: warning: ignoring return value of xe2x80x98pipexe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
  pipe(pvec);
  ^
gcc -o pgms/spawn -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/spawn.c 
gcc -o pgms/execl -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/execl.c 
In file included from src/execl.c:34:0:
src/big.c: In function xe2x80x98dummyxe2x80x99:
src/big.c:109:5: warning: ignoring return value of xe2x80x98freopenxe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
     freopen("masterlog.00", "a", stderr);
     ^
src/big.c:197:6: warning: ignoring return value of xe2x80x98freopenxe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
      freopen(logname, "w", stderr);
      ^
src/big.c:221:3: warning: ignoring return value of xe2x80x98dupxe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
   dup(pvec[0]);
   ^
src/big.c:225:6: warning: ignoring return value of xe2x80x98freopenxe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
      freopen(logname, "w", stderr);
      ^
src/big.c:318:4: warning: ignoring return value of xe2x80x98writexe2x80x99, declared with attribute warn_unused_result [-Wunused-result]
    write(fcopy, cp->line, p - cp->line + 1);
    ^
gcc -o pgms/dhry2 -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -DHZ= ./src/dhry_1.c ./src/dhry_2.c
gcc -o pgms/dhry2reg -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -DHZ= -DREG=register ./src/dhry_1.c ./src/dhry_2.c
gcc -o pgms/looper -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/looper.c 
gcc -o pgms/fstime -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME src/fstime.c 
gcc -o pgms/whetstone-double -Wall -pedantic -O3 -ffast-math -march=native -mtune=native -I ./src -DTIME -DDP -DUNIX -DUNIXBENCH src/whets.c -lm
make all
make[1]: Entering directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
make distr
make[2]: Entering directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
Checking distribution of files
./pgms  exists
./src  exists
./testdir  exists
make[2]: Leaving directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
make programs
make[2]: Entering directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
make[2]: Nothing to be done for "programs".
make[2]: Leaving directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
make[1]: Leaving directory "/serverscope-1aQyHW/byte-unixbench/UnixBench"
sh: 1: 3dinfo: not found
   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #
   Version 5.1.3                      Based on the Byte Magazine Unix Benchmark
   Multi-CPU version                  Version 5 revisions by Ian Smith,
                                      Sunnyvale, CA, USA
   January 13, 2011                   johantheghost at yahoo period com
1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
1 x Execl Throughput  1 2 3
1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
1 x File Copy 256 bufsize 500 maxblocks  1 2 3
1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
1 x Process Creation  1 2 3
1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
1 x Shell Scripts (1 concurrent)  1 2 3
1 x Shell Scripts (8 concurrent)  1 2 3
16 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10
16 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10
16 x Execl Throughput  1 2 3
16 x File Copy 1024 bufsize 2000 maxblocks  1 2 3
16 x File Copy 256 bufsize 500 maxblocks  1 2 3
16 x File Copy 4096 bufsize 8000 maxblocks  1 2 3
16 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10
16 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10
16 x Process Creation  1 2 3
16 x System Call Overhead  1 2 3 4 5 6 7 8 9 10
16 x Shell Scripts (1 concurrent)  1 2 3
16 x Shell Scripts (8 concurrent)  1 2 3
========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)
   System: nc1: GNU/Linux
   OS: GNU/Linux -- 4.4.0-64-generic -- #85-Ubuntu SMP Mon Feb 20 11:50:30 UTC 2017
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 4: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 5: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 6: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 7: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 8: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 9: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 10: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 11: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 12: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 13: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 14: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 15: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4533.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   16:03:54 up 8 days, 17:33,  1 user,  load average: 7.80, 4.77, 2.08; runlevel 2017-03-27
------------------------------------------------------------------------
Benchmark Run: Wed Apr 05 2017 16:03:54 - 16:32:35
16 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables       25643881.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3354.8 MWIPS (9.9 s, 7 samples)
Execl Throughput                               2004.2 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        818010.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          229091.7 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1655396.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1674768.0 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 150512.8 lps   (10.0 s, 7 samples)
Process Creation                               4767.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5736.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   3669.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        3312608.8 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   25643881.8   2197.4
Double-Precision Whetstone                       55.0       3354.8    610.0
Execl Throughput                                 43.0       2004.2    466.1
File Copy 1024 bufsize 2000 maxblocks          3960.0     818010.9   2065.7
File Copy 256 bufsize 500 maxblocks            1655.0     229091.7   1384.2
File Copy 4096 bufsize 8000 maxblocks          5800.0    1655396.7   2854.1
Pipe Throughput                               12440.0    1674768.0   1346.3
Pipe-based Context Switching                   4000.0     150512.8    376.3
Process Creation                                126.0       4767.8    378.4
Shell Scripts (1 concurrent)                     42.4       5736.5   1352.9
Shell Scripts (8 concurrent)                      6.0       3669.2   6115.4
System Call Overhead                          15000.0    3312608.8   2208.4
                                                                   ========
System Benchmarks Index Score                                        1271.5
------------------------------------------------------------------------
Benchmark Run: Wed Apr 05 2017 16:32:35 - 17:01:31
16 CPUs in system; running 16 parallel copies of tests
Dhrystone 2 using register variables      212536092.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    43144.3 MWIPS (10.0 s, 7 samples)
Execl Throughput                              24808.4 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        583005.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          164279.2 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1718011.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                            14565886.0 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                2157867.8 lps   (10.0 s, 7 samples)
Process Creation                              57612.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  63070.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   8470.1 lpm   (60.0 s, 2 samples)
System Call Overhead                        6369219.4 lps   (10.0 s, 7 samples)
System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  212536092.1  18212.2
Double-Precision Whetstone                       55.0      43144.3   7844.4
Execl Throughput                                 43.0      24808.4   5769.4
File Copy 1024 bufsize 2000 maxblocks          3960.0     583005.2   1472.2
File Copy 256 bufsize 500 maxblocks            1655.0     164279.2    992.6
File Copy 4096 bufsize 8000 maxblocks          5800.0    1718011.7   2962.1
Pipe Throughput                               12440.0   14565886.0  11708.9
Pipe-based Context Switching                   4000.0    2157867.8   5394.7
Process Creation                                126.0      57612.8   4572.4
Shell Scripts (1 concurrent)                     42.4      63070.6  14875.1
Shell Scripts (8 concurrent)                      6.0       8470.1  14116.8
System Call Overhead                          15000.0    6369219.4   4246.1
                                                                   ========
System Benchmarks Index Score                                        5583.9
dd if=/dev/zero of=benchmark bs=64K count=32K conv=fdatasync 32768+0 records in 32768+0 records out 2147483648 bytes (2.1 GB, 2.0 GiB) copied, 11.3033 s, 190 MB/s dd if=/dev/zero of=benchmark bs=1M count=2048 conv=fdatasync 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB, 2.0 GiB) copied, 11.0976 s, 194 MB/s
./fio --time_based --name=benchmark --size=256M --runtime=60 --randrepeat=1 --iodepth=32 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=8 --rw=randread --blocksize=4k --group_reporting
benchmark: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=32
...
fio-2.8
Starting 8 processes
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: (groupid=0, jobs=8): err= 0: pid=3098: Wed Apr  5 16:00:50 2017
  read : io=184616KB, bw=3076.2KB/s, iops=769, runt= 60016msec
    clat (usec): min=197, max=203992, avg=10394.32, stdev=7602.83
     lat (usec): min=198, max=203993, avg=10394.85, stdev=7602.83
    clat percentiles (usec):
     |  1.00th=[ 1784],  5.00th=[ 2544], 10.00th=[ 3376], 20.00th=[ 4896],
     | 30.00th=[ 6240], 40.00th=[ 7392], 50.00th=[ 8640], 60.00th=[ 9792],
     | 70.00th=[11712], 80.00th=[14528], 90.00th=[18816], 95.00th=[24960],
     | 99.00th=[38144], 99.50th=[44288], 99.90th=[59648], 99.95th=[68096],
     | 99.99th=[104960]
    bw (KB  /s): min=  229, max=  520, per=12.50%, avg=384.60, stdev=42.42
    lat (usec) : 250=0.04%, 500=0.10%, 750=0.01%, 1000=0.01%
    lat (msec) : 2=1.69%, 4=12.23%, 10=47.53%, 20=29.49%, 50=8.58%
    lat (msec) : 100=0.31%, 250=0.01%
  cpu          : usr=0.11%, sys=0.31%, ctx=46426, majf=0, minf=95
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=46154/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
   READ: io=184616KB, aggrb=3076KB/s, minb=3076KB/s, maxb=3076KB/s, mint=60016msec, maxt=60016msec
Disk stats (read/write):
  sda: ios=46121/111, merge=0/264, ticks=478096/11124, in_queue=489276, util=99.92%
./fio --time_based --name=benchmark --size=256M --runtime=60 --randrepeat=1 --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=8 --rw=randread --blocksize=4k --group_reporting
benchmark: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=32
...
fio-2.8
Starting 8 processes
benchmark: (groupid=0, jobs=8): err= 0: pid=3165: Wed Apr  5 16:01:50 2017
  read : io=185880KB, bw=3097.5KB/s, iops=774, runt= 60011msec
    clat (usec): min=230, max=95949, avg=10322.62, stdev=7314.34
     lat (usec): min=231, max=95949, avg=10323.15, stdev=7314.34
    clat percentiles (usec):
     |  1.00th=[ 1816],  5.00th=[ 2544], 10.00th=[ 3344], 20.00th=[ 4832],
     | 30.00th=[ 6176], 40.00th=[ 7392], 50.00th=[ 8512], 60.00th=[ 9792],
     | 70.00th=[11712], 80.00th=[14528], 90.00th=[18816], 95.00th=[24704],
     | 99.00th=[37120], 99.50th=[42752], 99.90th=[56576], 99.95th=[63744],
     | 99.99th=[76288]
    bw (KB  /s): min=  267, max=  531, per=12.51%, avg=387.36, stdev=41.04
    lat (usec) : 250=0.01%, 500=0.05%, 750=0.01%, 1000=0.01%
    lat (msec) : 2=1.72%, 4=12.34%, 10=47.72%, 20=29.30%, 50=8.65%
    lat (msec) : 100=0.20%
  cpu          : usr=0.10%, sys=0.30%, ctx=46661, majf=0, minf=85
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=46470/w=0/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
   READ: io=185880KB, aggrb=3097KB/s, minb=3097KB/s, maxb=3097KB/s, mint=60011msec, maxt=60011msec
Disk stats (read/write):
  sda: ios=46433/34, merge=0/35, ticks=478164/2936, in_queue=481304, util=99.92%
./fio --time_based --name=benchmark --size=256M --runtime=60 --filename=benchmark --randrepeat=1 --iodepth=32 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=8 --rw=randwrite --blocksize=4k --group_reporting
benchmark: (g=0): rw=randwrite, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=32
...
fio-2.8
Starting 8 processes
benchmark: (groupid=0, jobs=8): err= 0: pid=3312: Wed Apr  5 16:03:51 2017
  write: io=75990MB, bw=1266.5MB/s, iops=324220, runt= 60001msec
    clat (usec): min=1, max=67324, avg=22.83, stdev=302.53
     lat (usec): min=1, max=67325, avg=23.08, stdev=302.54
    clat percentiles (usec):
     |  1.00th=[    3],  5.00th=[    4], 10.00th=[    6], 20.00th=[   10],
     | 30.00th=[   14], 40.00th=[   16], 50.00th=[   17], 60.00th=[   18],
     | 70.00th=[   18], 80.00th=[   19], 90.00th=[   20], 95.00th=[   21],
     | 99.00th=[   25], 99.50th=[   34], 99.90th=[ 1352], 99.95th=[ 4704],
     | 99.99th=[16064]
    bw (KB  /s): min=105212, max=237184, per=12.51%, avg=162195.77, stdev=18919.03
    lat (usec) : 2=0.01%, 4=4.04%, 10=15.05%, 20=70.61%, 50=9.94%
    lat (usec) : 100=0.15%, 250=0.03%, 500=0.02%, 750=0.02%, 1000=0.01%
    lat (msec) : 2=0.03%, 4=0.02%, 10=0.03%, 20=0.03%, 50=0.01%
    lat (msec) : 100=0.01%
  cpu          : usr=6.20%, sys=63.65%, ctx=2980693, majf=0, minf=2769
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=0/w=19453535/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
  WRITE: io=75990MB, aggrb=1266.5MB/s, minb=1266.5MB/s, maxb=1266.5MB/s, mint=60001msec, maxt=60001msec
Disk stats (read/write):
  sda: ios=0/6686, merge=0/2593, ticks=0/86756, in_queue=86748, util=92.92%
./fio --time_based --name=benchmark --size=256M --runtime=60 --filename=benchmark --randrepeat=1 --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=8 --rw=randwrite --blocksize=4k --group_reporting
benchmark: (g=0): rw=randwrite, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=32
...
fio-2.8
Starting 8 processes
benchmark: Laying out IO file(s) (1 file(s) / 256MB)
benchmark: (groupid=0, jobs=8): err= 0: pid=3232: Wed Apr  5 16:02:50 2017
  write: io=29528KB, bw=503382B/s, iops=122, runt= 60067msec
    clat (msec): min=2, max=13540, avg=65.06, stdev=696.19
     lat (msec): min=2, max=13540, avg=65.06, stdev=696.19
    clat percentiles (msec):
     |  1.00th=[    4],  5.00th=[    5], 10.00th=[    5], 20.00th=[    7],
     | 30.00th=[    7], 40.00th=[    8], 50.00th=[    9], 60.00th=[    9],
     | 70.00th=[   10], 80.00th=[   10], 90.00th=[   11], 95.00th=[   11],
     | 99.00th=[   34], 99.50th=[ 5735], 99.90th=[11207], 99.95th=[11863],
     | 99.99th=[13566]
    bw (KB  /s): min=    0, max=  537, per=64.41%, avg=316.27, stdev=232.08
    lat (msec) : 4=4.21%, 10=77.38%, 20=16.92%, 50=0.61%, 100=0.08%
    lat (msec) : 250=0.01%, 2000=0.04%, >=2000=0.75%
  cpu          : usr=0.03%, sys=0.18%, ctx=14879, majf=0, minf=94
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=0/w=7382/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=32
Run status group 0 (all jobs):
  WRITE: io=29528KB, aggrb=491KB/s, minb=491KB/s, maxb=491KB/s, mint=60067msec, maxt=60067msec
Disk stats (read/write):
  sda: ios=0/7484, merge=0/783, ticks=0/62848, in_queue=62840, util=99.11%
Downloaded 104857600 bytes in 1.236 sec Downloaded 104857600 bytes in 1.080 sec Downloaded 104857600 bytes in 1.174 sec Downloaded 104857600 bytes in 1.147 sec Downloaded 104857600 bytes in 1.254 sec Finished! Average download speed is 679.00 Mbit/s
Retrieving speedtest.net configuration... Retrieving speedtest.net server list... Testing from Centrilogic ... Selecting 15 servers that are not too close: 1. ColoCrossing (Buffalo, NY) [99.90 km]: 49.585 ms 2. Time Warner Cable (Syracuse, NY) [128.17 km]: 44.626 ms 3. Northland Communications (Syracuse, NY) [128.17 km]: 181.678 ms 4. TELUS (Toronto, ON) [146.41 km]: 53.94 ms 5. Rogers (Toronto, ON) [146.41 km]: 43.821 ms 6. Keewaytinook Okimakanak (Toronto, ON) [146.41 km]: 449.291 ms 7. TekSavvy Solutions (Toronto, ON) [146.41 km]: 552.65 ms 8. Beanfield Metroconnect (Toronto, ON) [146.41 km]: 214.589 ms 9. Speedtest.net (Toronto, ON) [146.41 km]: 1800000.0 ms 10. Nexicom Inc. (Toronto, ON) [146.41 km]: 51.288 ms 11. Start Communications (Toronto, ON) [146.41 km]: 299.69 ms 12. TeraGo Networks (Toronto, ON) [146.41 km]: 37.597 ms 13. ZEROFAIL (Toronto, ON) [146.41 km]: 69.788 ms 14. Connexxa Networks (Toronto, ON) [146.41 km]: 168.996 ms 15. Ravand Cybertech INC (Toronto, ON) [146.41 km]: 425.147 ms Testing upload speeds 1. ColoCrossing (Buffalo, NY): ......................... 85.91 Mbit/s 2. Time Warner Cable (Syracuse, NY): ......................... 55.64 Mbit/s 3. Northland Communications (Syracuse, NY): ......................... 209.86 Mbit/s 4. TELUS (Toronto, ON): ......................... 123.27 Mbit/s 5. Rogers (Toronto, ON): ......................... 146.83 Mbit/s 6. Keewaytinook Okimakanak (Toronto, ON): ......................... 65.47 Mbit/s 7. TekSavvy Solutions (Toronto, ON): ......................... 98.72 Mbit/s 8. Beanfield Metroconnect (Toronto, ON): ......................... 166.75 Mbit/s 9. Speedtest.net (Toronto, ON): ......................... 141.16 Mbit/s 10. Nexicom Inc. (Toronto, ON): ......................... 125.67 Mbit/s 11. Start Communications (Toronto, ON): ......................... 138.51 Mbit/s 12. TeraGo Networks (Toronto, ON): ......................... 11.77 Mbit/s 13. ZEROFAIL (Toronto, ON): ......................... 139.40 Mbit/s 14. Connexxa Networks (Toronto, ON): ......................... 188.99 Mbit/s 15. Ravand Cybertech INC (Toronto, ON): ......................... 164.37 Mbit/s Average upload speed is 124.15 Mbit/s