Skip to content

Instantly share code, notes, and snippets.

@ayosec
Last active May 9, 2017 15:30
Show Gist options
  • Star 4 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ayosec/d539586209105d240ce4 to your computer and use it in GitHub Desktop.
Save ayosec/d539586209105d240ce4 to your computer and use it in GitHub Desktop.
AWS C3 vs C4: UNIX Benchmarks

BYTE UNIX Benchmarks

Summary

                                             c3.large           c4.large          c4 / c3
===========================================================================================
Dhrystone 2 using register variables       34752053.9 lps     43996767.0 lps       1.2660
Double-Precision Whetstone                     4459.8 MWIPS       8113.5 MWIPS     1.8193
Execl Throughput                               4110.8 lps         7697.1 lps       1.8724
File Copy 1024 bufsize 2000 maxblocks       1111057.6 KBps     1444349.5 KBps      1.3000
File Copy 256 bufsize 500 maxblocks          302648.1 KBps      378783.7 KBps      1.2516
File Copy 4096 bufsize 8000 maxblocks       3239051.2 KBps     4386697.5 KBps      1.3543
Pipe Throughput                             2237313.6 lps      2929960.4 lps       1.3096
Pipe-based Context Switching                  36322.9 lps       458585.6 lps      12.6252
Process Creation                              10538.6 lps        20714.0 lps       1.9655
Shell Scripts (1 concurrent)                   9258.2 lpm        12153.0 lpm       1.3127
Shell Scripts (8 concurrent)                   1474.0 lpm         1771.7 lpm       1.2020
System Call Overhead                        3812555.7 lps      6265381.4 lps       1.6434

AWS c3.large

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

   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: ip-10-182-106-86: GNU/Linux
   OS: GNU/Linux -- 3.13.0-36-generic -- #63-Ubuntu SMP Wed Sep 3 21:30:07 UTC 2014
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz (5600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz (5600.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   09:34:47 up 2 min,  1 user,  load average: 0.24, 0.24, 0.11; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Wed Jan 14 2015 09:34:47 - 10:02:49
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       34752053.9 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4459.8 MWIPS (9.8 s, 7 samples)
Execl Throughput                               4110.8 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1111057.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          302648.1 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       3239051.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2237313.6 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  36322.9 lps   (10.0 s, 7 samples)
Process Creation                              10538.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   9258.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1474.0 lpm   (60.0 s, 2 samples)
System Call Overhead                        3812555.7 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   34752053.9   2977.9
Double-Precision Whetstone                       55.0       4459.8    810.9
Execl Throughput                                 43.0       4110.8    956.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    1111057.6   2805.7
File Copy 256 bufsize 500 maxblocks            1655.0     302648.1   1828.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    3239051.2   5584.6
Pipe Throughput                               12440.0    2237313.6   1798.5
Pipe-based Context Switching                   4000.0      36322.9     90.8
Process Creation                                126.0      10538.6    836.4
Shell Scripts (1 concurrent)                     42.4       9258.2   2183.5
Shell Scripts (8 concurrent)                      6.0       1474.0   2456.7
System Call Overhead                          15000.0    3812555.7   2541.7
                                                                   ========
System Benchmarks Index Score                                        1493.5

------------------------------------------------------------------------
Benchmark Run: Wed Jan 14 2015 10:02:49 - 10:30:56
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       37580935.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     7433.8 MWIPS (9.9 s, 7 samples)
Execl Throughput                               6568.4 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1170571.1 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          308905.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       3544794.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2727548.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 404963.4 lps   (10.0 s, 7 samples)
Process Creation                              17412.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  10615.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1542.0 lpm   (60.0 s, 2 samples)
System Call Overhead                        6036488.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   37580935.4   3220.3
Double-Precision Whetstone                       55.0       7433.8   1351.6
Execl Throughput                                 43.0       6568.4   1527.5
File Copy 1024 bufsize 2000 maxblocks          3960.0    1170571.1   2956.0
File Copy 256 bufsize 500 maxblocks            1655.0     308905.0   1866.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    3544794.3   6111.7
Pipe Throughput                               12440.0    2727548.4   2192.6
Pipe-based Context Switching                   4000.0     404963.4   1012.4
Process Creation                                126.0      17412.7   1382.0
Shell Scripts (1 concurrent)                     42.4      10615.3   2503.6
Shell Scripts (8 concurrent)                      6.0       1542.0   2570.0
System Call Overhead                          15000.0    6036488.2   4024.3
                                                                   ========
System Benchmarks Index Score                                        2260.6

AWS c4.large

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

   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: ip-172-30-1-185: GNU/Linux
   OS: GNU/Linux -- 3.13.0-36-generic -- #63-Ubuntu SMP Wed Sep 3 21:30:07 UTC 2014
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5-2666 v3 @ 2.90GHz (5786.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) CPU E5-2666 v3 @ 2.90GHz (5786.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   09:34:56 up 3 min,  1 user,  load average: 0.25, 0.18, 0.08; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Wed Jan 14 2015 09:34:56 - 10:02:59
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       37053293.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4714.0 MWIPS (9.9 s, 7 samples)
Execl Throughput                               4718.8 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1206030.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          322736.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       3355774.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2450151.7 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  45053.9 lps   (10.0 s, 7 samples)
Process Creation                              11995.9 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  10613.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1676.8 lpm   (60.0 s, 2 samples)
System Call Overhead                        4062320.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   37053293.4   3175.1
Double-Precision Whetstone                       55.0       4714.0    857.1
Execl Throughput                                 43.0       4718.8   1097.4
File Copy 1024 bufsize 2000 maxblocks          3960.0    1206030.0   3045.5
File Copy 256 bufsize 500 maxblocks            1655.0     322736.0   1950.1
File Copy 4096 bufsize 8000 maxblocks          5800.0    3355774.9   5785.8
Pipe Throughput                               12440.0    2450151.7   1969.6
Pipe-based Context Switching                   4000.0      45053.9    112.6
Process Creation                                126.0      11995.9    952.1
Shell Scripts (1 concurrent)                     42.4      10613.6   2503.2
Shell Scripts (8 concurrent)                      6.0       1676.8   2794.7
System Call Overhead                          15000.0    4062320.3   2708.2
                                                                   ========
System Benchmarks Index Score                                        1651.1

------------------------------------------------------------------------
Benchmark Run: Wed Jan 14 2015 10:02:59 - 10:31:04
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       43996767.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8113.5 MWIPS (10.0 s, 7 samples)
Execl Throughput                               7697.1 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1444349.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          378783.7 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       4386697.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2929960.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 458585.6 lps   (10.0 s, 7 samples)
Process Creation                              20714.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  12153.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1771.7 lpm   (60.0 s, 2 samples)
System Call Overhead                        6265381.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   43996767.0   3770.1
Double-Precision Whetstone                       55.0       8113.5   1475.2
Execl Throughput                                 43.0       7697.1   1790.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    1444349.5   3647.3
File Copy 256 bufsize 500 maxblocks            1655.0     378783.7   2288.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    4386697.5   7563.3
Pipe Throughput                               12440.0    2929960.4   2355.3
Pipe-based Context Switching                   4000.0     458585.6   1146.5
Process Creation                                126.0      20714.0   1644.0
Shell Scripts (1 concurrent)                     42.4      12153.0   2866.3
Shell Scripts (8 concurrent)                      6.0       1771.7   2952.8
System Call Overhead                          15000.0    6265381.4   4176.9
                                                                   ========
System Benchmarks Index Score                                        2607.2
@ayosec
Copy link
Author

ayosec commented Jan 14, 2015

@thbar
Copy link

thbar commented Jan 13, 2016

Thanks for sharing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment