Server Benchmark mit UnixBench

In einem früheren Post hatte ich ja schon auf ein einfaches PHP-Benchmark-Skript hingewiesen. Jetzt habe ich einen richtigen Unix Benchmark gefunden und damit gleich mal meine Server durchgemessen.

Das nette Benchmark-Tool für Linux, welches schon seit 30 Jahren existiert, hat hier seine Projekt-Seite: https://code.google.com/p/byte-unixbench/

Ein Tutorial zu dessen Einsatz steht hier: http://blog.serverbear.com/tutorials/unixbench-ubuntu/

Eine Liste mit Benchmarks vieler verschiedener Systeme findet sich hier: http://serverbear.com/benchmarks

Hier kann man seine eigenen Benchmarks erstellen: http://serverbear.com/add-benchmark

Generelles zum Benchmarking einer VPS

Richtig sinnvoll sind diese Benchmarks eigentlich nur für dedizierte Server, da deren Leistung exklusiv zur Verfügung steht.

Bei einer VPS muss man sich klar sein, dass man mit vielen anderen Usern gemeinsame Hardware teilt, wodurch die günstigen Preise ermöglicht werden. Die Leistung eines solchen Systems ist also immer davon abhängig, wie viele Benutzer noch mit drauf sind und welche Ressourcen diese gerade benötigen. Gerade frisch angelegte Server tendieren dazu, viel mehr Leistungs-Reserven zu haben, als jene, die schon „voll“ sind. Man muss die Performance also grundsätzlich im Verlauf der Zeit betrachten.

Ich führe diese Benchmarks auf einem shared host trotzdem durch, weil ich daran zumindest ablesen kann, ob es irgendeine Leistungsdrossel gibt (heißt: Wenn nichts los ist, kann ich dann die Ressourcen haben?) und mir Hinweise gibt, wie voll ein System bereits belegt wurde.

Meine Benchmarks

Hier die Benchmarks, die ich damit durchgeführt habe:

myVirtualserver KVM-2 -> 1200

Dauerhaft 6.99 € / Monat

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

   System: ******************
   OS: GNU/Linux -- 3.2.0-4-amd64 -- #1 SMP Debian 3.2.60-1+deb7u3
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
   CPU 0: Common KVM processor (6399.9 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   14:31:48 up  1:34,  1 user,  load average: 0.00, 0.01, 0.05; runlevel 2

------------------------------------------------------------------------
Benchmark Run: So Okt 12 2014 14:31:48 - 14:59:50  
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       23735202.7 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     3133.7 MWIPS (9.0 s, 7 samples)  
Execl Throughput                               3340.3 lps   (29.8 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        838115.7 KBps  (30.1 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          229635.0 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1268447.4 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1733802.6 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 291352.4 lps   (10.0 s, 7 samples)  
Process Creation                               7713.0 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                   4993.1 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                    649.4 lpm   (60.1 s, 2 samples)  
System Call Overhead                        2960754.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   23735202.7   2033.9  
Double-Precision Whetstone                       55.0       3133.7    569.8  
Execl Throughput                                 43.0       3340.3    776.8  
File Copy 1024 bufsize 2000 maxblocks          3960.0     838115.7   2116.5  
File Copy 256 bufsize 500 maxblocks            1655.0     229635.0   1387.5  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1268447.4   2187.0  
Pipe Throughput                               12440.0    1733802.6   1393.7  
Pipe-based Context Switching                   4000.0     291352.4    728.4  
Process Creation                                126.0       7713.0    612.1  
Shell Scripts (1 concurrent)                     42.4       4993.1   1177.6  
Shell Scripts (8 concurrent)                      6.0        649.4   1082.3  
System Call Overhead                          15000.0    2960754.0   1973.8  
                                                                   ========
System Benchmarks Index Score                                        1201.4

------------------------------------------------------------------------
Benchmark Run: So Okt 12 2014 14:59:50 - 15:30:26  
1 CPU in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       22432317.5 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     4762.4 MWIPS (10.1 s, 7 samples)  
Execl Throughput                               2672.9 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        740544.8 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          225758.7 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1254954.5 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1708202.7 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 281309.7 lps   (10.0 s, 7 samples)  
Process Creation                               7546.2 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                   4967.6 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                    643.9 lpm   (60.1 s, 2 samples)  
System Call Overhead                        2953762.8 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   22432317.5   1922.2  
Double-Precision Whetstone                       55.0       4762.4    865.9  
Execl Throughput                                 43.0       2672.9    621.6  
File Copy 1024 bufsize 2000 maxblocks          3960.0     740544.8   1870.1  
File Copy 256 bufsize 500 maxblocks            1655.0     225758.7   1364.1  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1254954.5   2163.7  
Pipe Throughput                               12440.0    1708202.7   1373.2  
Pipe-based Context Switching                   4000.0     281309.7    703.3  
Process Creation                                126.0       7546.2    598.9  
Shell Scripts (1 concurrent)                     42.4       4967.6   1171.6  
Shell Scripts (8 concurrent)                      6.0        643.9   1073.2  
System Call Overhead                          15000.0    2953762.8   1969.2  
                                                                   ========
System Benchmarks Index Score                                        1191.4  

Link zur Online-Seite: http://serverbear.com/benchmark/2014/10/12/934j3NvKt89Wx0nN

Linevast VPS Starter -> 1500 bis 2200

Link zum Angebot (25€ / Jahr) – Gerade für 2.08 € / Monat zu haben.

Ob die Leistung dieses OpenVZ-Systems konstant so gut bleibt, wird das kommende Jahr zeigen. Ich bin da mal guter Dinge. 🙂

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

   System: ******************
   OS: GNU/Linux -- 2.6.32-042stab093.5 -- #1 SMP Wed Sep 10 17:39:49 MSK 2014
   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 E3-1230 v3 @ 3.30GHz (6600.6 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E3-1230 v3 @ 3.30GHz (6600.6 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   17:02:13 up 20:35,  0 users,  load average: 0.14, 0.03, 0.01; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Sun Oct 12 2014 17:02:13 - 17:30:17  
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       33872094.1 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     4545.0 MWIPS (9.9 s, 7 samples)  
Execl Throughput                               4348.8 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        728866.2 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          216525.9 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1855778.6 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1571014.9 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 291269.2 lps   (10.0 s, 7 samples)  
Process Creation                              11946.0 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                   8559.5 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1583.2 lpm   (60.0 s, 2 samples)  
System Call Overhead                        2540485.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   33872094.1   2902.5  
Double-Precision Whetstone                       55.0       4545.0    826.4  
Execl Throughput                                 43.0       4348.8   1011.3  
File Copy 1024 bufsize 2000 maxblocks          3960.0     728866.2   1840.6  
File Copy 256 bufsize 500 maxblocks            1655.0     216525.9   1308.3  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1855778.6   3199.6  
Pipe Throughput                               12440.0    1571014.9   1262.9  
Pipe-based Context Switching                   4000.0     291269.2    728.2  
Process Creation                                126.0      11946.0    948.1  
Shell Scripts (1 concurrent)                     42.4       8559.5   2018.8  
Shell Scripts (8 concurrent)                      6.0       1583.2   2638.7  
System Call Overhead                          15000.0    2540485.2   1693.7  
                                                                   ========
System Benchmarks Index Score                                        1515.7

------------------------------------------------------------------------
Benchmark Run: Sun Oct 12 2014 17:30:17 - 17:58:37  
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       58637982.3 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     8916.6 MWIPS (9.8 s, 7 samples)  
Execl Throughput                               8665.0 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        800448.9 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          215209.1 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       2241133.1 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             2459364.7 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 482231.0 lps   (10.0 s, 7 samples)  
Process Creation                              20436.5 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  13686.8 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1841.2 lpm   (60.1 s, 2 samples)  
System Call Overhead                        3373133.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   58637982.3   5024.7  
Double-Precision Whetstone                       55.0       8916.6   1621.2  
Execl Throughput                                 43.0       8665.0   2015.1  
File Copy 1024 bufsize 2000 maxblocks          3960.0     800448.9   2021.3  
File Copy 256 bufsize 500 maxblocks            1655.0     215209.1   1300.4  
File Copy 4096 bufsize 8000 maxblocks          5800.0    2241133.1   3864.0  
Pipe Throughput                               12440.0    2459364.7   1977.0  
Pipe-based Context Switching                   4000.0     482231.0   1205.6  
Process Creation                                126.0      20436.5   1621.9  
Shell Scripts (1 concurrent)                     42.4      13686.8   3228.0  
Shell Scripts (8 concurrent)                      6.0       1841.2   3068.7  
System Call Overhead                          15000.0    3373133.3   2248.8  
                                                                   ========
System Benchmarks Index Score                                        2220.3  

Link zur Online-Seite: http://serverbear.com/benchmark/2014/10/12/g1kM88kpqVn72XMK

Ergänzend dazu der sysbench-Wert:

root@localhost:~# sysbench --test=cpu --cpu-max-prime=20000 run  
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:  
Number of threads: 1

Doing CPU performance benchmark

Threads started!  
Done.

Maximum prime number checked in CPU test: 20000

Test execution summary:  
    total time:                          25.5892s
    total number of events:              10000
    total time taken by event execution: 25.5866
    per-request statistics:
         min:                                  2.41ms
         avg:                                  2.56ms
         max:                                 35.08ms
         approx.  95 percentile:               2.96ms

Threads fairness:  
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   25.5866/0.00

MonsterVPS VPS Level 1 -> 1600

Preis: 2.50 / Monat

  • Der Test war nicht anonym. Der Hoster MonsterVPS hat mir angeboten sein System aus Interesse am Ergebnis zu benchmarken und mir dafür einen Gutschein-Code gegeben. Ich kann daher nicht garantieren, ein repärsentatives System erhalten zu haben. Davon gehe ich einfach mal aus.
  • Die Firma ist noch sehr sehr jung und gerade erst gestartet. Daher steht hier quasi die gesamte Leistung des Systems zur Verfügung. Ein starkes Indiz dafür war, dass mein Login „user30“ lautete. 😉 Ob die Performance zukünftig auch so bleiben wird oder die Leistung aufgrund von Überbuchung sinken wird, kann ich unmöglich sagen. Dieser Test ist eine Momentaufnahme.
  • Die Server stehen in Frankreich! Wer einen deutschen Standort möchte, ist mit linevast besser beraten.
========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: ******************
   OS: GNU/Linux -- 2.6.32-042stab093.5 -- #1 SMP Wed Sep 10 17:39:49 MSK 2014
   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 E5-1620 v2 @ 3.70GHz (7399.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   15:22:16 up 22 min,  0 users,  load average: 0.13, 0.08, 0.03; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Wed Oct 15 2014 15:22:16 - 15:51:00  
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       42535907.8 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     3564.1 MWIPS (14.0 s, 7 samples)  
Execl Throughput                               5826.9 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        794945.7 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          201269.2 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1956579.1 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1688405.8 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 313536.6 lps   (10.0 s, 7 samples)  
Process Creation                              15020.8 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  10758.9 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1403.7 lpm   (60.0 s, 2 samples)  
System Call Overhead                        2586105.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   42535907.8   3644.9  
Double-Precision Whetstone                       55.0       3564.1    648.0  
Execl Throughput                                 43.0       5826.9   1355.1  
File Copy 1024 bufsize 2000 maxblocks          3960.0     794945.7   2007.4  
File Copy 256 bufsize 500 maxblocks            1655.0     201269.2   1216.1  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1956579.1   3373.4  
Pipe Throughput                               12440.0    1688405.8   1357.2  
Pipe-based Context Switching                   4000.0     313536.6    783.8  
Process Creation                                126.0      15020.8   1192.1  
Shell Scripts (1 concurrent)                     42.4      10758.9   2537.5  
Shell Scripts (8 concurrent)                      6.0       1403.7   2339.5  
System Call Overhead                          15000.0    2586105.0   1724.1  
                                                                   ========
System Benchmarks Index Score                                        1626.2

------------------------------------------------------------------------
Benchmark Run: Wed Oct 15 2014 15:51:00 - 16:19:44  
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       42824147.0 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     3491.6 MWIPS (14.3 s, 7 samples)  
Execl Throughput                               5743.6 lps   (29.9 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        785899.6 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          219372.3 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1999241.9 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1751542.1 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 319883.5 lps   (10.0 s, 7 samples)  
Process Creation                              15000.2 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  10803.6 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1417.2 lpm   (60.0 s, 2 samples)  
System Call Overhead                        2574918.9 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   42824147.0   3669.6  
Double-Precision Whetstone                       55.0       3491.6    634.8  
Execl Throughput                                 43.0       5743.6   1335.7  
File Copy 1024 bufsize 2000 maxblocks          3960.0     785899.6   1984.6  
File Copy 256 bufsize 500 maxblocks            1655.0     219372.3   1325.5  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1999241.9   3447.0  
Pipe Throughput                               12440.0    1751542.1   1408.0  
Pipe-based Context Switching                   4000.0     319883.5    799.7  
Process Creation                                126.0      15000.2   1190.5  
Shell Scripts (1 concurrent)                     42.4      10803.6   2548.0  
Shell Scripts (8 concurrent)                      6.0       1417.2   2361.9  
System Call Overhead                          15000.0    2574918.9   1716.6  
                                                                   ========
System Benchmarks Index Score                                        1644.3  

Link zur Online-Seite: http://serverbear.com/benchmark/2014/10/15/i96Og4HIiD2ORGAF

storage-base.de OpenVZ-Testsystem -> 400

1 vCore (100%), 256 MB ECC Ram

Preis: Als OpenVZ S für 3.99 € / Monat

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

   System: ******************
   OS: GNU/Linux -- 2.6.32-042stab093.5 -- #1 SMP Wed Sep 10 17:39:49 MSK 2014
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4987.5 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   13:46:51 up  1:40,  1 user,  load average: 0.12, 0.03, 0.01; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Wed Oct 15 2014 13:46:51 - 14:15:09  
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       22172483.4 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     2886.1 MWIPS (9.9 s, 7 samples)  
Execl Throughput                                469.2 lps   (29.9 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        438396.2 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          124688.6 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks        703904.9 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1040197.7 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                  67124.5 lps   (10.0 s, 7 samples)  
Process Creation                               1029.1 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                    818.5 lpm   (60.1 s, 2 samples)  
Shell Scripts (8 concurrent)                     99.3 lpm   (60.6 s, 2 samples)  
System Call Overhead                        1184305.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   22172483.4   1900.0  
Double-Precision Whetstone                       55.0       2886.1    524.7  
Execl Throughput                                 43.0        469.2    109.1  
File Copy 1024 bufsize 2000 maxblocks          3960.0     438396.2   1107.1  
File Copy 256 bufsize 500 maxblocks            1655.0     124688.6    753.4  
File Copy 4096 bufsize 8000 maxblocks          5800.0     703904.9   1213.6  
Pipe Throughput                               12440.0    1040197.7    836.2  
Pipe-based Context Switching                   4000.0      67124.5    167.8  
Process Creation                                126.0       1029.1     81.7  
Shell Scripts (1 concurrent)                     42.4        818.5    193.0  
Shell Scripts (8 concurrent)                      6.0         99.3    165.6  
System Call Overhead                          15000.0    1184305.4    789.5  
                                                                   ========
System Benchmarks Index Score                                         421.9

------------------------------------------------------------------------
Benchmark Run: Wed Oct 15 2014 14:15:09 - 14:43:28  
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       22371086.3 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     2886.0 MWIPS (9.9 s, 7 samples)  
Execl Throughput                                572.3 lps   (29.9 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        440539.8 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          127926.3 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks        705756.6 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1049049.6 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                  66658.1 lps   (10.0 s, 7 samples)  
Process Creation                               1009.9 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                    792.6 lpm   (60.1 s, 2 samples)  
Shell Scripts (8 concurrent)                     99.5 lpm   (60.1 s, 2 samples)  
System Call Overhead                        1219896.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   22371086.3   1917.0  
Double-Precision Whetstone                       55.0       2886.0    524.7  
Execl Throughput                                 43.0        572.3    133.1  
File Copy 1024 bufsize 2000 maxblocks          3960.0     440539.8   1112.5  
File Copy 256 bufsize 500 maxblocks            1655.0     127926.3    773.0  
File Copy 4096 bufsize 8000 maxblocks          5800.0     705756.6   1216.8  
Pipe Throughput                               12440.0    1049049.6    843.3  
Pipe-based Context Switching                   4000.0      66658.1    166.6  
Process Creation                                126.0       1009.9     80.1  
Shell Scripts (1 concurrent)                     42.4        792.6    186.9  
Shell Scripts (8 concurrent)                      6.0         99.5    165.8  
System Call Overhead                          15000.0    1219896.2    813.3  
                                                                   ========
System Benchmarks Index Score                                         429.8  

Link zur Online-Seite: http://serverbear.com/benchmark/2014/10/15/1TVR83iAcdtGJqST

Server 4 You Pro X5 SSD -> 1000

Preis: 8.85 € / Monat

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

   System: ******************
   OS: GNU/Linux -- 3.2.41-042stab092.3 -- #1 SMP Sun Jul 20 13:27:24 MSK 2014
   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 E5520 @ 2.27GHz (4533.7 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz (4533.7 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   19:34:23 up  1:52,  0 users,  load average: 0.02, 0.01, 0.00; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Thu Oct 16 2014 19:34:23 - 20:02:37  
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       21249549.2 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     2822.7 MWIPS (10.0 s, 7 samples)  
Execl Throughput                               2454.4 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        510747.5 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          146953.3 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1151818.3 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1375979.2 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 198655.7 lps   (10.0 s, 7 samples)  
Process Creation                               7485.3 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                   6207.9 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1270.2 lpm   (60.0 s, 2 samples)  
System Call Overhead                        2945072.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   21249549.2   1820.9  
Double-Precision Whetstone                       55.0       2822.7    513.2  
Execl Throughput                                 43.0       2454.4    570.8  
File Copy 1024 bufsize 2000 maxblocks          3960.0     510747.5   1289.8  
File Copy 256 bufsize 500 maxblocks            1655.0     146953.3    887.9  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1151818.3   1985.9  
Pipe Throughput                               12440.0    1375979.2   1106.1  
Pipe-based Context Switching                   4000.0     198655.7    496.6  
Process Creation                                126.0       7485.3    594.1  
Shell Scripts (1 concurrent)                     42.4       6207.9   1464.1  
Shell Scripts (8 concurrent)                      6.0       1270.2   2117.0  
System Call Overhead                          15000.0    2945072.0   1963.4  
                                                                   ========
System Benchmarks Index Score                                        1076.0

------------------------------------------------------------------------
Benchmark Run: Thu Oct 16 2014 20:02:37 - 20:30:52  
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       45681203.0 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     5632.2 MWIPS (10.0 s, 7 samples)  
Execl Throughput                               6228.3 lps   (29.8 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        533446.8 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          154315.7 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       1368004.7 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             2651894.2 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 402915.9 lps   (10.0 s, 7 samples)  
Process Creation                              14221.2 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  10271.1 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   1352.4 lpm   (60.0 s, 2 samples)  
System Call Overhead                        4894854.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   45681203.0   3914.4  
Double-Precision Whetstone                       55.0       5632.2   1024.0  
Execl Throughput                                 43.0       6228.3   1448.4  
File Copy 1024 bufsize 2000 maxblocks          3960.0     533446.8   1347.1  
File Copy 256 bufsize 500 maxblocks            1655.0     154315.7    932.4  
File Copy 4096 bufsize 8000 maxblocks          5800.0    1368004.7   2358.6  
Pipe Throughput                               12440.0    2651894.2   2131.7  
Pipe-based Context Switching                   4000.0     402915.9   1007.3  
Process Creation                                126.0      14221.2   1128.7  
Shell Scripts (1 concurrent)                     42.4      10271.1   2422.4  
Shell Scripts (8 concurrent)                      6.0       1352.4   2254.0  
System Call Overhead                          15000.0    4894854.5   3263.2  
                                                                   ========
System Benchmarks Index Score                                        1734.8  

Link zur Online-Seite: http://serverbear.com/benchmark/2014/10/16/PKrhGDwSeUDE26jW

Mein Desktop-PC

Unter Knoppix habe ich den Benchmark auch mit meinem Desktop PC durchgeführt, um eine bessere Einordnung der Gesamt-Leistung zu bekommen.

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

   System: Microknoppix: GNU/Linux
   OS: GNU/Linux -- 3.16.2-64 -- #6 SMP PREEMPT Tue Sep 9 16:12:33 CEST 2014
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM) i5-4670K CPU @ 3.40GHz (6798.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Core(TM) i5-4670K CPU @ 3.40GHz (6798.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Core(TM) i5-4670K CPU @ 3.40GHz (6798.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Core(TM) i5-4670K CPU @ 3.40GHz (6798.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   21:52:13 up 11 min,  3 users,  load average: 0,45, 0,76, 0,78; runlevel 5

------------------------------------------------------------------------
Benchmark Run: Di Okt 14 2014 21:52:13 - 22:20:17  
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       27760916.9 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                     4098.8 MWIPS (10.1 s, 7 samples)  
Execl Throughput                               6197.3 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks        747355.0 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          193534.3 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       2245506.8 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             1374183.9 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                 232356.1 lps   (10.0 s, 7 samples)  
Process Creation                              17865.8 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  10257.4 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   3034.5 lpm   (60.0 s, 2 samples)  
System Call Overhead                        1222898.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0   27760916.9   2378.8  
Double-Precision Whetstone                       55.0       4098.8    745.2  
Execl Throughput                                 43.0       6197.3   1441.2  
File Copy 1024 bufsize 2000 maxblocks          3960.0     747355.0   1887.3  
File Copy 256 bufsize 500 maxblocks            1655.0     193534.3   1169.4  
File Copy 4096 bufsize 8000 maxblocks          5800.0    2245506.8   3871.6  
Pipe Throughput                               12440.0    1374183.9   1104.6  
Pipe-based Context Switching                   4000.0     232356.1    580.9  
Process Creation                                126.0      17865.8   1417.9  
Shell Scripts (1 concurrent)                     42.4      10257.4   2419.2  
Shell Scripts (8 concurrent)                      6.0       3034.5   5057.5  
System Call Overhead                          15000.0    1222898.5    815.3  
                                                                   ========
System Benchmarks Index Score                                        1553.9

------------------------------------------------------------------------
Benchmark Run: Di Okt 14 2014 22:20:17 - 22:48:46  
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables      101033427.8 lps   (10.0 s, 7 samples)  
Double-Precision Whetstone                    16381.3 MWIPS (10.1 s, 7 samples)  
Execl Throughput                              20598.4 lps   (30.0 s, 2 samples)  
File Copy 1024 bufsize 2000 maxblocks       1022820.9 KBps  (30.0 s, 2 samples)  
File Copy 256 bufsize 500 maxblocks          268800.4 KBps  (30.0 s, 2 samples)  
File Copy 4096 bufsize 8000 maxblocks       3600623.4 KBps  (30.0 s, 2 samples)  
Pipe Throughput                             5439877.4 lps   (10.0 s, 7 samples)  
Pipe-based Context Switching                1348625.5 lps   (10.0 s, 7 samples)  
Process Creation                              55220.2 lps   (30.0 s, 2 samples)  
Shell Scripts (1 concurrent)                  26207.4 lpm   (60.0 s, 2 samples)  
Shell Scripts (8 concurrent)                   3525.3 lpm   (60.0 s, 2 samples)  
System Call Overhead                        4335341.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX  
Dhrystone 2 using register variables         116700.0  101033427.8   8657.5  
Double-Precision Whetstone                       55.0      16381.3   2978.4  
Execl Throughput                                 43.0      20598.4   4790.3  
File Copy 1024 bufsize 2000 maxblocks          3960.0    1022820.9   2582.9  
File Copy 256 bufsize 500 maxblocks            1655.0     268800.4   1624.2  
File Copy 4096 bufsize 8000 maxblocks          5800.0    3600623.4   6208.0  
Pipe Throughput                               12440.0    5439877.4   4372.9  
Pipe-based Context Switching                   4000.0    1348625.5   3371.6  
Process Creation                                126.0      55220.2   4382.6  
Shell Scripts (1 concurrent)                     42.4      26207.4   6181.0  
Shell Scripts (8 concurrent)                      6.0       3525.3   5875.5  
System Call Overhead                          15000.0    4335341.4   2890.2  
                                                                   ========
System Benchmarks Index Score                                        4088.5