Unix Bench

L

lostincable

Active member
Hi all, I have been with my hosting provider for a while but I am making some decisions around whether to move to another provider or stay with them.

Essentially I have been looking at unix bench results and a few others and I am not quite happy with the amount of scoring I am getting out of unix bench for CPU.

I was wondering what others use to benchmark there VPS' and if you would give any rating to a unix bench result?

The server itself is quite good and has the right amount of disk io under load which is good but I am slightly concerned with the low results on unix bench.

Code: 
 #    #  #    #  #  #    #          #####  ######  #    #  ####  #    #
  #    #  ##  #  #  #  #          #    #  #      ##  #  #    #  #    #
  #    #  # #  #  #    ##            #####  #####  # #  #  #      ######
  #    #  #  # #  #    ##            #    #  #      #  # #  #      #    #
  #    #  #  ##  #  #  #          #    #  #      #  ##  #    #  #    #
    ####  #    #  #  #    #          #####  ######  #    #  ####  #    #

  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

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
  BYTE UNIX Benchmarks (Version 5.1.3)

  System: ******************
  OS: GNU/Linux -- 2.6.32-358.0.1.el6.x86_64 -- #1 SMP Wed Feb 27 06:06:45 UTC 2013
  Machine: x86_64 (x86_64)
  Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
  CPU 0: Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz (4600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  CPU 1: Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz (4600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  08:05:16 up  4:05,  1 user,  load average: 0.08, 0.02, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Mon Jul 29 2013 08:05:16 - 08:33:00
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables      16009551.9 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    1875.1 MWIPS (8.4 s, 7 samples)
Execl Throughput                                575.1 lps  (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        102703.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          26237.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        299356.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                              141656.4 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                  26976.5 lps  (10.0 s, 7 samples)
Process Creation                              1263.5 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  1361.1 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    307.6 lpm  (60.2 s, 2 samples)
System Call Overhead                        155019.0 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  16009551.9  1371.9
Double-Precision Whetstone                      55.0      1875.1    340.9
Execl Throughput                                43.0        575.1    133.8
File Copy 1024 bufsize 2000 maxblocks          3960.0    102703.0    259.4
File Copy 256 bufsize 500 maxblocks            1655.0      26237.9    158.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    299356.2    516.1
Pipe Throughput                              12440.0    141656.4    113.9
Pipe-based Context Switching                  4000.0      26976.5    67.4
Process Creation                                126.0      1263.5    100.3
Shell Scripts (1 concurrent)                    42.4      1361.1    321.0
Shell Scripts (8 concurrent)                      6.0        307.6    512.7
System Call Overhead                          15000.0    155019.0    103.3
                                                                  ========
System Benchmarks Index Score                                        225.6

------------------------------------------------------------------------
Benchmark Run: Mon Jul 29 2013 08:33:00 - 09:00:46
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables      36119926.5 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    3203.2 MWIPS (8.1 s, 7 samples)
Execl Throughput                              1694.5 lps  (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        233410.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          51988.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        587580.8 KBps  (30.1 s, 2 samples)
Pipe Throughput                              400057.2 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                  63152.8 lps  (10.0 s, 7 samples)
Process Creation                              3499.6 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  2802.8 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    343.0 lpm  (60.4 s, 2 samples)
System Call Overhead                        337441.6 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  36119926.5  3095.1
Double-Precision Whetstone                      55.0      3203.2    582.4
Execl Throughput                                43.0      1694.5    394.1
File Copy 1024 bufsize 2000 maxblocks          3960.0    233410.2    589.4
File Copy 256 bufsize 500 maxblocks            1655.0      51988.0    314.1
File Copy 4096 bufsize 8000 maxblocks          5800.0    587580.8  1013.1
Pipe Throughput                              12440.0    400057.2    321.6
Pipe-based Context Switching                  4000.0      63152.8    157.9
Process Creation                                126.0      3499.6    277.7
Shell Scripts (1 concurrent)                    42.4      2802.8    661.0
Shell Scripts (8 concurrent)                      6.0        343.0    571.6
System Call Overhead                          15000.0    337441.6    225.0
                                                                  ========
System Benchmarks Index Score                                        482.6
 
Is your site slow? Are you maxing out your CPU usage? If not, it doesn't really matter what the benchmark is.

Those scores are probably fairly normal for 2 shared cores on a E5-2630. The server itself is going to score WAY higher than the benchmarks you list. The problem is that you are only allowed to use 2 of the 12 cores, and perhaps not even 100% of those cores.
 
WSWD said:
Is your site slow? Are you maxing out your CPU usage? If not, it doesn't really matter what the benchmark is.

Those scores are probably fairly normal for 2 shared cores on a E5-2630. The server itself is going to score WAY higher than the benchmarks you list. The problem is that you are only allowed to use 2 of the 12 cores, and perhaps not even 100% of those cores.
Click to expand...
Yep, here is my base L5520 I have sitting back as a spare (and it's an older processor so the newer stuff should be better).

Code: 
========================================================================
  BYTE UNIX Benchmarks (Version 5.1.2)

  System: draco: GNU/Linux
  OS: GNU/Linux -- 3.2.0-4-amd64 -- #1 SMP Debian 3.2.46-1
  Machine: x86_64 (unknown)
  Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
  CPU 0: Intel(R) Xeon(R) CPU L5520 @ 2.27GHz (4534.0 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 (4533.3 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 (4533.3 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 (4533.4 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 (4533.3 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 (4533.4 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 (4533.4 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 (4533.4 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 (4533.4 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
  20:57:52 up 13 days, 22:36,  1 user,  load average: 0.68, 0.26, 0.13; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Mon Jul 29 2013 20:57:52 - 21:26:24
16 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables      24072135.1 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    2845.9 MWIPS (10.0 s, 7 samples)
Execl Throughput                              2005.6 lps  (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        794748.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          215123.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks      1711930.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                            1729955.6 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                125265.5 lps  (10.0 s, 7 samples)
Process Creation                              4157.6 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  5944.3 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                  3271.7 lpm  (60.0 s, 2 samples)
System Call Overhead                        3098338.8 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  24072135.1  2062.7
Double-Precision Whetstone                      55.0      2845.9    517.4
Execl Throughput                                43.0      2005.6    466.4
File Copy 1024 bufsize 2000 maxblocks          3960.0    794748.7  2006.9
File Copy 256 bufsize 500 maxblocks            1655.0    215123.9  1299.8
File Copy 4096 bufsize 8000 maxblocks          5800.0    1711930.2  2951.6
Pipe Throughput                              12440.0    1729955.6  1390.6
Pipe-based Context Switching                  4000.0    125265.5    313.2
Process Creation                                126.0      4157.6    330.0
Shell Scripts (1 concurrent)                    42.4      5944.3  1402.0
Shell Scripts (8 concurrent)                      6.0      3271.7  5452.9
System Call Overhead                          15000.0    3098338.8  2065.6
                                                                  ========
System Benchmarks Index Score                                        1197.5

------------------------------------------------------------------------
Benchmark Run: Mon Jul 29 2013 21:26:24 - 21:54:51
16 CPUs in system; running 16 parallel copies of tests

Dhrystone 2 using register variables      205404886.2 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    38912.5 MWIPS (10.0 s, 7 samples)
Execl Throughput                              32955.2 lps  (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        607598.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          180273.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks      1712794.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                            15989466.5 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                2749083.6 lps  (10.0 s, 7 samples)
Process Creation                              87122.7 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  66957.0 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                  8966.2 lpm  (60.1 s, 2 samples)
System Call Overhead                        7842777.9 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  205404886.2  17601.1
Double-Precision Whetstone                      55.0      38912.5  7075.0
Execl Throughput                                43.0      32955.2  7664.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    607598.8  1534.3
File Copy 256 bufsize 500 maxblocks            1655.0    180273.8  1089.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    1712794.7  2953.1
Pipe Throughput                              12440.0  15989466.5  12853.3
Pipe-based Context Switching                  4000.0    2749083.6  6872.7
Process Creation                                126.0      87122.7  6914.5
Shell Scripts (1 concurrent)                    42.4      66957.0  15791.7
Shell Scripts (8 concurrent)                      6.0      8966.2  14943.7
System Call Overhead                          15000.0    7842777.9  5228.5
                                                                  ========
System Benchmarks Index Score                                        6249.6
 
Thanks all, in terms of speed my VPS provider had me on a node that was experiencing some slow downs.

Nothing significant but enough for me to start poking around.

They where very kind and offered to move to another node that was apparently better spec'd better CPU and better disks.

So I benchmarked them both to test them as you can see from the rsults old vs new below the unix bench is very low on the new node but the disk IOP's is much better.

The old node had better CPU but the disk IOP's is much worse.

So I need to decide I can either go back to my old node, stay where I am or move to another provider all together!!!!

Old Node -

Disks:

Code: 
FIO
Read IOPS    3796.0
Read Bandwidth    15.1 MB/second
Write IOPS    1694.0
Write Bandwidth    6.7 MB/second

CPU:

Code: 
  #    #  #    #  #  #    #          #####  ######  #    #  ####  #    #
  #    #  ##  #  #  #  #          #    #  #      ##  #  #    #  #    #
  #    #  # #  #  #    ##            #####  #####  # #  #  #      ######
  #    #  #  # #  #    ##            #    #  #      #  # #  #      #    #
  #    #  #  ##  #  #  #          #    #  #      #  ##  #    #  #    #
    ####  #    #  #  #    #          #####  ######  #    #  ####  #    #

  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

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
  BYTE UNIX Benchmarks (Version 5.1.3)

  System: ******************
  OS: GNU/Linux -- 2.6.32-279.22.1.el6.x86_64 -- #1 SMP Wed Feb 6 03:10:46 UTC 2013
  Machine: x86_64 (x86_64)
  Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
  CPU 0: Intel(R) Xeon(R) CPU E5-1620 0 @ 3.60GHz (7200.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
  CPU 1: Intel(R) Xeon(R) CPU E5-1620 0 @ 3.60GHz (7200.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
  05:56:00 up  9:59,  1 user,  load average: 0.08, 0.02, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Sun Mar 10 2013 05:56:01 - 06:24:03
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables      37426344.6 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    4175.5 MWIPS (9.9 s, 7 samples)
Execl Throughput                              1629.3 lps  (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        241363.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          62778.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        764498.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                              376279.7 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                  67008.2 lps  (10.0 s, 7 samples)
Process Creation                              3550.3 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  3647.4 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    673.9 lpm  (60.1 s, 2 samples)
System Call Overhead                        369947.9 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  37426344.6  3207.1
Double-Precision Whetstone                      55.0      4175.5    759.2
Execl Throughput                                43.0      1629.3    378.9
File Copy 1024 bufsize 2000 maxblocks          3960.0    241363.7    609.5
File Copy 256 bufsize 500 maxblocks            1655.0      62778.6    379.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    764498.6  1318.1
Pipe Throughput                              12440.0    376279.7    302.5
Pipe-based Context Switching                  4000.0      67008.2    167.5
Process Creation                                126.0      3550.3    281.8
Shell Scripts (1 concurrent)                    42.4      3647.4    860.2
Shell Scripts (8 concurrent)                      6.0        673.9  1123.1
System Call Overhead                          15000.0    369947.9    246.6
                                                                  ========
System Benchmarks Index Score                                        560.3

------------------------------------------------------------------------
Benchmark Run: Sun Mar 10 2013 06:24:03 - 06:52:08
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables      66724837.5 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    8164.6 MWIPS (9.9 s, 7 samples)
Execl Throughput                              2881.6 lps  (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        410251.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          101801.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks      1258608.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                              702996.7 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                118172.1 lps  (10.0 s, 7 samples)
Process Creation                              5938.5 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  4908.1 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    653.1 lpm  (60.2 s, 2 samples)
System Call Overhead                        695159.8 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  66724837.5  5717.6
Double-Precision Whetstone                      55.0      8164.6  1484.5
Execl Throughput                                43.0      2881.6    670.1
File Copy 1024 bufsize 2000 maxblocks          3960.0    410251.7  1036.0
File Copy 256 bufsize 500 maxblocks            1655.0    101801.0    615.1
File Copy 4096 bufsize 8000 maxblocks          5800.0    1258608.2  2170.0
Pipe Throughput                              12440.0    702996.7    565.1
Pipe-based Context Switching                  4000.0    118172.1    295.4
Process Creation                                126.0      5938.5    471.3
Shell Scripts (1 concurrent)                    42.4      4908.1  1157.6
Shell Scripts (8 concurrent)                      6.0        653.1  1088.6
System Call Overhead                          15000.0    695159.8    463.4
                                                                  ========
System Benchmarks Index Score                                        918.7
 
Last edited:
New Node -

Disks:


Code: 
Read IOPS    21834.0
Read Bandwidth    87.3 MB/second
Write IOPS    9708.0
Write Bandwidth    38.8 MB/second

CPU:

Code: 
System Specs
RAM    993 MB
HDD    26 GB
CPU Model    Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz
CPU Cores    2
CPU Speed    2300 MHz
CPU Cache    15360 KB
UnixBench
UnixBench (w/ all processors)    485.5
UnixBench (w/ one processor)    238.6
Raw UnixBench Output

  #    #  #    #  #  #    #          #####  ######  #    #  ####  #    #
  #    #  ##  #  #  #  #          #    #  #      ##  #  #    #  #    #
  #    #  # #  #  #    ##            #####  #####  # #  #  #      ######
  #    #  #  # #  #    ##            #    #  #      #  # #  #      #    #
  #    #  #  ##  #  #  #          #    #  #      #  ##  #    #  #    #
    ####  #    #  #  #    #          #####  ######  #    #  ####  #    #

  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

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
  BYTE UNIX Benchmarks (Version 5.1.3)

  System: ******************
  OS: GNU/Linux -- 2.6.32-279.22.1.el6.x86_64 -- #1 SMP Wed Feb 6 03:10:46 UTC 2013
  Machine: x86_64 (x86_64)
  Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
  CPU 0: Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz (4600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
  CPU 1: Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz (4600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
  08:05:33 up  1:00,  0 users,  load average: 0.08, 0.04, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Sun Jul 28 2013 08:05:33 - 08:33:12
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables      15410764.5 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    2001.4 MWIPS (7.4 s, 7 samples)
Execl Throughput                                563.3 lps  (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        106657.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          29106.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        345605.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                              163091.0 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                  31508.0 lps  (10.0 s, 7 samples)
Process Creation                              1249.2 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  1307.7 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    319.7 lpm  (60.1 s, 2 samples)
System Call Overhead                        171085.4 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  15410764.5  1320.5
Double-Precision Whetstone                      55.0      2001.4    363.9
Execl Throughput                                43.0        563.3    131.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    106657.7    269.3
File Copy 256 bufsize 500 maxblocks            1655.0      29106.3    175.9
File Copy 4096 bufsize 8000 maxblocks          5800.0    345605.9    595.9
Pipe Throughput                              12440.0    163091.0    131.1
Pipe-based Context Switching                  4000.0      31508.0    78.8
Process Creation                                126.0      1249.2    99.1
Shell Scripts (1 concurrent)                    42.4      1307.7    308.4
Shell Scripts (8 concurrent)                      6.0        319.7    532.9
System Call Overhead                          15000.0    171085.4    114.1
                                                                  ========
System Benchmarks Index Score                                        238.6

------------------------------------------------------------------------
Benchmark Run: Sun Jul 28 2013 08:33:12 - 09:00:55
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables      36855193.8 lps  (10.0 s, 7 samples)
Double-Precision Whetstone                    3818.3 MWIPS (8.1 s, 7 samples)
Execl Throughput                              1556.5 lps  (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        249001.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          53974.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        658907.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                              349591.2 lps  (10.0 s, 7 samples)
Pipe-based Context Switching                  63931.8 lps  (10.0 s, 7 samples)
Process Creation                              3292.6 lps  (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  2534.5 lpm  (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    358.1 lpm  (60.3 s, 2 samples)
System Call Overhead                        332624.0 lps  (10.0 s, 7 samples)

System Benchmarks Index Values              BASELINE      RESULT    INDEX
Dhrystone 2 using register variables        116700.0  36855193.8  3158.1
Double-Precision Whetstone                      55.0      3818.3    694.2
Execl Throughput                                43.0      1556.5    362.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    249001.8    628.8
File Copy 256 bufsize 500 maxblocks            1655.0      53974.9    326.1
File Copy 4096 bufsize 8000 maxblocks          5800.0    658907.8  1136.0
Pipe Throughput                              12440.0    349591.2    281.0
Pipe-based Context Switching                  4000.0      63931.8    159.8
Process Creation                                126.0      3292.6    261.3
Shell Scripts (1 concurrent)                    42.4      2534.5    597.8
Shell Scripts (8 concurrent)                      6.0        358.1    596.9
System Call Overhead                          15000.0    332624.0    221.7
                                                                  ========
System Benchmarks Index Score                                        485.5
 
In all my experience, aside from video encoding sites, and other very processor intensive application sites, clients almost never reach their CPU limitations. On any dedicated server, VPS, etc., disk i/o is almost always the limiting factor. That's almost always going to "run out" before the RAM or CPU does.

So personally, I think you would be better off staying on the node with the better disk i/o. That's what is going to make your site load faster. Like I said, if your site isn't experiencing slowdowns, I wouldn't worry about it one way or the other.
 
You must log in or register to reply here.

Similar threads

Hosh
  • Question Question
Unix Cron
Replies
5
Views
675
Mouth
Mouth
Zak Smith
Unix scripts to clarify template diffs
Replies
1
Views
2K
Zak Smith
Zak Smith
Back
Top Bottom