Aller au contenu

byte-unixbench : tester sous Linux les performances de votre serveur dédié ou VPS

Ldfa

Par Ldfa
dans Mon Wallabag

Messages recommandés

Ldfa Grand Maître

Ldfa

Posté(e)
Posté(e)

Byte-unixbench permet de fournir un indicateur global sur la performance d’un système de type Unix/Linux. Pour ce faire, plusieurs tests sont exécutés pour mesurer les différents aspects de la performance du système.

unixbeach

Une fois que byte-unixbench a fini d’exécuter tous les tests, il affiche une note globale de la performance du système, qui permet de comparer plusieurs types de serveurs.

La liste de la série de tests qu’exécute byte-unixbench :

  • Dhrystone: test de performance Cpu sur les chaînes de caractères.
  • Whetstone: test de performance Cpu sur valeurs flottantes.
  • Execl Throughput: mesure le nombre d’appels execl, qui peuvent être effectués par seconde.
  • File Copy: test de performance disque dur sur la vitesse de copie de données.
  • Pipe Throughput: test sur la bande passante
  • Pipe-based Context Switching: test sur le nombre de fois où deux processus peuvent échanger pour effectuer un calcul
  • Process Creation: test sur le nombre de fois qu’un processus peut créer différentes implémentations systèmes
  • Shell Scripts: test sur le temps d’exécution d’un script tout en simulant des opérations courantes
  • System Call Overhead: test le temps de latence induit par un appel système
  • Graphical Tests: test sur le performances graphiques 2D et 3D (inutile sur un serveur)

Dans le cas de l’article, je vais comparer 4 serveurs d’architectures différentes sauf le système d’exploitation, qui sera commun à tous : Debian.

Installer et éxécuter byte-unixbench sous Debian

  • Installation des pré-requis :
apt-get install libx11-dev libgl1-mesa-dev libxext-dev perl perl-modules make gcc unzip
Téléchargement de byte-unixbench :
cd /opt
wget https://github.com/kdlucas/byte-unixbench/archive/master.zip
Décompression de byte-unixbench :
unzip master.zip
Exécution de byte-unixbench :
cd byte-unixbench-master/UnixBench/
./Run

Comparaison entre 3 offres du marché et un serveur local avec byte-unixbench

Pour chaque serveur, il est indiqué l’hébergeur et toutes les infos utiles du système via inxi.

  • VPS OpenVZ de chez Dyjix:
System:    Host: memolinux Kernel: 2.6.32-042stab108.8 x86_64 (64 bit) Console: tty 0 Distro: Debian GNU/Linux 8
Machine:   No /sys/class/dmi; using dmidecode: unknown error occured
CPU:       Quad core Intel Xeon E3-1245 V2 (-HT-MCP-) cache: 8192 KB 
           clock speeds: max: 3392 MHz 1: 3392 MHz 2: 3392 MHz 3: 3392 MHz 4: 3392 MHz
Graphics:  Card: Failed to Detect Video Card!
           Display Server: N/A driver: N/A tty size: 140x51 Advanced Data: N/A for root out of X
Network:   Card: Failed to Detect Network Card!
Partition: ID-1: / size: 99G used: 1.1G (2%) fs: ext4 dev: /dev/ploop46710p1
Sensors:   None detected - is lm-sensors installed and configured?
Info:      Processes: 24 Uptime: 3 days Memory: 43.1/5120.0MB Init: systemd runlevel: 3
           Client: Shell (bash) inxi: 2.2.28

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

   System: memolinux: GNU/Linux
   OS: GNU/Linux -- 2.6.32-042stab108.8 -- #1 SMP Wed Jul 22 17:23:23 MSK 2015
   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 E3-1245 V2 @ 3.40GHz (6784.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz (6784.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz (6784.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz (6784.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   09:58:44 up 1 day, 17:51,  1 user,  load average: 0.54, 0.29, 0.12; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Mon Aug 31 2015 09:58:44 - 10:27:16
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       38684684.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4605.5 MWIPS (10.2 s, 7 samples)
Execl Throughput                               4694.3 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        881848.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          233133.2 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2332929.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1806721.0 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 172914.2 lps   (10.0 s, 7 samples)
Process Creation                              13739.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  13440.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   3859.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        2603140.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   38684684.7   3314.9
Double-Precision Whetstone                       55.0       4605.5    837.4
Execl Throughput                                 43.0       4694.3   1091.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     881848.7   2226.9
File Copy 256 bufsize 500 maxblocks            1655.0     233133.2   1408.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    2332929.6   4022.3
Pipe Throughput                               12440.0    1806721.0   1452.3
Pipe-based Context Switching                   4000.0     172914.2    432.3
Process Creation                                126.0      13739.4   1090.4
Shell Scripts (1 concurrent)                     42.4      13440.9   3170.0
Shell Scripts (8 concurrent)                      6.0       3859.2   6432.0
System Call Overhead                          15000.0    2603140.2   1735.4
                                                                   ========
System Benchmarks Index Score                                        1767.0

------------------------------------------------------------------------
Benchmark Run: Mon Aug 31 2015 10:27:16 - 10:55:47
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables      145346341.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    18682.6 MWIPS (9.8 s, 7 samples)
Execl Throughput                              21025.9 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1076905.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          289794.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       3089519.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             6920298.6 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                1157901.0 lps   (10.0 s, 7 samples)
Process Creation                              37353.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  33455.3 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                   4616.0 lpm   (60.1 s, 2 samples)
System Call Overhead                        8128941.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  145346341.1  12454.7
Double-Precision Whetstone                       55.0      18682.6   3396.8
Execl Throughput                                 43.0      21025.9   4889.7
File Copy 1024 bufsize 2000 maxblocks          3960.0    1076905.3   2719.5
File Copy 256 bufsize 500 maxblocks            1655.0     289794.4   1751.0
File Copy 4096 bufsize 8000 maxblocks          5800.0    3089519.7   5326.8
Pipe Throughput                               12440.0    6920298.6   5562.9
Pipe-based Context Switching                   4000.0    1157901.0   2894.8
Process Creation                                126.0      37353.6   2964.6
Shell Scripts (1 concurrent)                     42.4      33455.3   7890.4
Shell Scripts (8 concurrent)                      6.0       4616.0   7693.3
System Call Overhead                          15000.0    8128941.5   5419.3
                                                                   ========
System Benchmarks Index Score                                        4567.3

score final : 1767.0/4567.3

VPS OpenVZ de chez Pulseheberg :
System:    Host: memolinux Kernel: 2.6.32-042stab105.14 x86_64 (64 bit) Console: tty 0 Distro: Debian GNU/Linux 8
Machine:   No /sys/class/dmi; using dmidecode: unknown error occured
CPU:       Quad core Intel Xeon E5520 (-HT-MCP-) cache: 8192 KB 
           clock speeds: max: 1699 MHz 1: 1699 MHz 2: 1699 MHz 3: 1699 MHz 4: 1699 MHz
Graphics:  Card: Failed to Detect Video Card!
           Display Server: N/A driver: N/A tty size: 140x51 Advanced Data: N/A for root out of X
Network:   Card: Failed to Detect Network Card!
Partition: ID-1: / size: 200G used: 5.4G (4%) fs: simfs dev: /dev/simfs
           ID-2: swap-1 size: 4.29GB used: 0.07GB (2%) fs: swap dev: /dev/null
Sensors:   None detected - is lm-sensors installed and configured?
Info:      Processes: 38 Uptime: 1 day Memory: 418.9/4096.0MB Init: systemd runlevel: 5
           Client: Shell (bash) inxi: 2.2.28

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

   System: memolinux: GNU/Linux
   OS: GNU/Linux -- 2.6.32-042stab105.14 -- #1 SMP Fri Mar 13 20:06:37 MSK 2015
   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 (4533.1 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 (4533.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz (4533.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz (4533.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   15:47:48 up 16 min,  1 user,  load average: 0.59, 0.28, 0.10; runlevel 5

------------------------------------------------------------------------
Benchmark Run: Mon Aug 31 2015 15:47:48 - 16:16:02
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       21754677.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2878.6 MWIPS (9.9 s, 7 samples)
Execl Throughput                               2317.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        441494.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          127189.1 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1047926.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1094143.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 112689.7 lps   (10.0 s, 7 samples)
Process Creation                               4733.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6842.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1894.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        1463080.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   21754677.0   1864.2
Double-Precision Whetstone                       55.0       2878.6    523.4
Execl Throughput                                 43.0       2317.5    539.0
File Copy 1024 bufsize 2000 maxblocks          3960.0     441494.6   1114.9
File Copy 256 bufsize 500 maxblocks            1655.0     127189.1    768.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    1047926.6   1806.8
Pipe Throughput                               12440.0    1094143.4    879.5
Pipe-based Context Switching                   4000.0     112689.7    281.7
Process Creation                                126.0       4733.8    375.7
Shell Scripts (1 concurrent)                     42.4       6842.3   1613.8
Shell Scripts (8 concurrent)                      6.0       1894.5   3157.5
System Call Overhead                          15000.0    1463080.3    975.4
                                                                   ========
System Benchmarks Index Score                                         921.8

------------------------------------------------------------------------
Benchmark Run: Mon Aug 31 2015 16:16:02 - 16:45:22
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       63423235.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    11431.3 MWIPS (9.7 s, 7 samples)
Execl Throughput                               9021.0 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        526485.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          143709.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1377746.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                             3235031.7 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 533160.2 lps   (10.0 s, 7 samples)
Process Creation                              16902.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  15701.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   2228.7 lpm   (60.0 s, 2 samples)
System Call Overhead                        3208824.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   63423235.4   5434.7
Double-Precision Whetstone                       55.0      11431.3   2078.4
Execl Throughput                                 43.0       9021.0   2097.9
File Copy 1024 bufsize 2000 maxblocks          3960.0     526485.9   1329.5
File Copy 256 bufsize 500 maxblocks            1655.0     143709.6    868.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    1377746.8   2375.4
Pipe Throughput                               12440.0    3235031.7   2600.5
Pipe-based Context Switching                   4000.0     533160.2   1332.9
Process Creation                                126.0      16902.4   1341.5
Shell Scripts (1 concurrent)                     42.4      15701.5   3703.2
Shell Scripts (8 concurrent)                      6.0       2228.7   3714.4
System Call Overhead                          15000.0    3208824.0   2139.2
                                                                   ========
System Benchmarks Index Score                                        2133.4

Score final : 921.8/2133.4

Serveur dédié Cpu ARM D525 2*1,80 4Go RAM de chez FirstHeberg :
System:    Host: srv30.firstheberg.net Kernel: 3.2.0-4-amd64 x86_64 (64 bit) Console: tty 4
           Distro: Debian GNU/Linux 7
Machine:   Mobo: ASRock model: AD525PV3 Bios: American Megatrends v: P1.20 date: 04/01/2011
CPU:       Dual core Intel Atom D525 (-HT-MCP-) cache: 512 KB 
           clock speeds: max: 1795 MHz 1: 1795 MHz 2: 1795 MHz 3: 1795 MHz 4: 1795 MHz
Graphics:  Card: Intel Atom Processor D4xx/D5xx/N4xx/N5xx Integrated Graphics Controller
           Display Server: N/A driver: N/A tty size: 140x51 Advanced Data: N/A for root out of X
Audio:     Card Intel NM10/ICH7 Family High Definition Audio Controller driver: snd_hda_intel
           Sound: Advanced Linux Sound Architecture v: 1.0.24
Network:   Card: Atheros AR8151 v2.0 Gigabit Ethernet driver: atl1c
           IF: eth0 state: up speed: 1000 Mbps duplex: full mac: 00:25:22:d8:ef:8d
Drives:    HDD Total Size: 1000.2GB (1.3% used) ID-1: /dev/sdb model: WDC_WD5000AAKX size: 500.1GB
           ID-2: /dev/sda model: WDC_WD5000AAKX size: 500.1GB
Partition: ID-1: / size: 9.7G used: 4.9G (54%) fs: ext4 dev: /dev/sda1
           ID-2: /var size: 447G used: 5.0G (2%) fs: ext4 dev: /dev/sda3
           ID-3: swap-1 size: 2.10GB used: 0.00GB (0%) fs: swap dev: /dev/sda2
Sensors:   System Temperatures: cpu: 36.0C mobo: 34.0C
           Fan Speeds (in rpm): cpu: 5625 fan-1: 0 fan-3: 0 fan-5: 0
Info:      Processes: 129 Uptime: 11 days Memory: 556.4/3956.8MB Init: SysVinit runlevel: 2
           Client: Shell (bash) inxi: 2.2.28

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

   System: srv30.firstheberg.net: GNU/Linux
   OS: GNU/Linux -- 3.2.0-4-amd64 -- #1 SMP Debian 3.2.68-1+deb7u3
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
   CPU 0: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.3 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 2: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.3 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 3: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.3 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   15:53:20 up 9 days, 20:13,  4 users,  load average: 0.43, 0.29, 0.20; runlevel 2

------------------------------------------------------------------------
Benchmark Run: lun. août 31 2015 15:53:20 - 16:22:03
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables        6635293.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     1002.7 MWIPS (9.8 s, 7 samples)
Execl Throughput                                985.0 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        152864.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           42462.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        426128.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                              479323.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  26757.8 lps   (10.0 s, 7 samples)
Process Creation                               2599.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2539.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    588.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        1028551.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0    6635293.8    568.6
Double-Precision Whetstone                       55.0       1002.7    182.3
Execl Throughput                                 43.0        985.0    229.1
File Copy 1024 bufsize 2000 maxblocks          3960.0     152864.9    386.0
File Copy 256 bufsize 500 maxblocks            1655.0      42462.6    256.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     426128.5    734.7
Pipe Throughput                               12440.0     479323.4    385.3
Pipe-based Context Switching                   4000.0      26757.8     66.9
Process Creation                                126.0       2599.6    206.3
Shell Scripts (1 concurrent)                     42.4       2539.5    598.9
Shell Scripts (8 concurrent)                      6.0        588.2    980.3
System Call Overhead                          15000.0    1028551.5    685.7
                                                                   ========
System Benchmarks Index Score                                         352.6

------------------------------------------------------------------------
Benchmark Run: lun. août 31 2015 16:22:03 - 16:51:04
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       17318290.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3588.3 MWIPS (9.8 s, 7 samples)
Execl Throughput                               2617.0 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        150471.4 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           41316.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        455420.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                              841075.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 152223.0 lps   (10.0 s, 7 samples)
Process Creation                               6924.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4643.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    644.0 lpm   (60.2 s, 2 samples)
System Call Overhead                        2490650.7 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   17318290.7   1484.0
Double-Precision Whetstone                       55.0       3588.3    652.4
Execl Throughput                                 43.0       2617.0    608.6
File Copy 1024 bufsize 2000 maxblocks          3960.0     150471.4    380.0
File Copy 256 bufsize 500 maxblocks            1655.0      41316.5    249.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     455420.8    785.2
Pipe Throughput                               12440.0     841075.2    676.1
Pipe-based Context Switching                   4000.0     152223.0    380.6
Process Creation                                126.0       6924.5    549.6
Shell Scripts (1 concurrent)                     42.4       4643.0   1095.1
Shell Scripts (8 concurrent)                      6.0        644.0   1073.3
System Call Overhead                          15000.0    2490650.7   1660.4
                                                                   ========
System Benchmarks Index Score                                         692.3

score final : 352.6/692.3

Serveur local Dell R710 :
System:    Host: proxmox-01 Kernel: 2.6.32-40-pve x86_64 (64 bit) Console: tty 0
           Distro: /etc/ corrupted, use -% to override
Machine:   System: Dell product: PowerEdge R710 serial: DM11S4J
           Mobo: Dell model: 0HYPX2 v: A09 serial: ..CN70821051001R. Bios: Dell v: 2.0.13 date: 04/06/2010
CPU(s):    2 Quad core Intel Xeon E5504s (-HT-MCP-SMP-) cache: 8192 KB 
           clock speeds: max: 1995 MHz 1: 1995 MHz 2: 1995 MHz 3: 1995 MHz 4: 1995 MHz 5: 1995 MHz 6: 1995 MHz
           7: 1995 MHz 8: 1995 MHz
Graphics:  Card: Matrox Systems MGA G200eW WPCM450
           Display Server: N/A driver: N/A tty size: 140x53 Advanced Data: N/A for root out of X
Audio:     Card pcsp driver: PC-Speaker Sound: ALSA v: 1.0.21
Network:   Card-1: Broadcom NetXtreme II BCM5709 Gigabit Ethernet driver: bnx2
           IF: eth0 state: up speed: 1000 Mbps duplex: full mac: b8:ac:6f:84:83:91
           Card-2: Broadcom NetXtreme II BCM5709 Gigabit Ethernet driver: bnx2
           IF: eth1 state: up speed: 1000 Mbps duplex: full mac: b8:ac:6f:84:83:93
           Card-3: Broadcom NetXtreme II BCM5709 Gigabit Ethernet driver: bnx2
           IF: eth2 state: up speed: 1000 Mbps duplex: full mac: b8:ac:6f:84:83:93
           Card-4: Broadcom NetXtreme II BCM5709 Gigabit Ethernet driver: bnx2
           IF: eth3 state: up speed: 1000 Mbps duplex: full mac: b8:ac:6f:84:83:93
           Card-5: Intel 82580 Gigabit Network Connection driver: igb
           IF: eth4 state: up speed: 1000 Mbps duplex: full mac: ac:16:2d:98:be:08
           Card-6: Intel 82580 Gigabit Network Connection driver: igb
           IF: eth5 state: up speed: 1000 Mbps duplex: full mac: ac:16:2d:98:be:08
           Card-7: Intel 82580 Gigabit Network Connection driver: igb
           IF: eth6 state: up speed: 1000 Mbps duplex: full mac: ac:16:2d:98:be:08
           Card-8: Intel 82580 Gigabit Network Connection driver: igb
           IF: eth7 state: down mac: ac:16:2d:98:be:0b
Drives:    HDD Total Size: 898.3GB (3.0% used) ID-1: /dev/sda model: PERC_6/i size: 898.3GB
           ID-2: /dev/sdb model: VIRTUAL size: 0.0GB
Partition: ID-1: / size: 95G used: 2.8G (4%) fs: ext3 dev: /dev/dm-0
           ID-2: /boot size: 494M used: 90M (20%) fs: ext3 dev: /dev/sda2
           ID-3: swap-1 size: 24.70GB used: 0.00GB (0%) fs: swap dev: /dev/dm-1
RAID:      No RAID devices: /proc/mdstat, md_mod kernel module present
Sensors:   None detected - is lm-sensors installed and configured?
Info:      Processes: 264 Uptime: 5 days Memory: 993.4/24094.9MB Init: SysVinit runlevel: 2
           Client: Shell (bash) inxi: 2.2.28

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

   System: proxmox-01: GNU/Linux
   OS: GNU/Linux -- 2.6.32-40-pve -- #1 SMP Fri Jul 24 11:16:05 CEST 2015
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3990.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3989.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3990.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3989.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 4: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3990.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 5: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3989.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 6: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3990.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 7: Intel(R) Xeon(R) CPU E5504 @ 2.00GHz (3989.4 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   10:28:55 up 4 days, 22:52,  1 user,  load average: 0.01, 0.07, 0.07; runlevel 2

------------------------------------------------------------------------
Benchmark Run: Wed Sep 02 2015 10:28:55 - 10:57:08
8 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       21168220.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2498.7 MWIPS (10.0 s, 7 samples)
Execl Throughput                               2142.4 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        474514.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          150728.1 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1246859.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1314410.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 140957.4 lps   (10.0 s, 7 samples)
Process Creation                               3102.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4602.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   2519.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        2516256.7 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   21168220.6   1813.9
Double-Precision Whetstone                       55.0       2498.7    454.3
Execl Throughput                                 43.0       2142.4    498.2
File Copy 1024 bufsize 2000 maxblocks          3960.0     474514.6   1198.3
File Copy 256 bufsize 500 maxblocks            1655.0     150728.1    910.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    1246859.3   2149.8
Pipe Throughput                               12440.0    1314410.2   1056.6
Pipe-based Context Switching                   4000.0     140957.4    352.4
Process Creation                                126.0       3102.4    246.2
Shell Scripts (1 concurrent)                     42.4       4602.2   1085.4
Shell Scripts (8 concurrent)                      6.0       2519.2   4198.6
System Call Overhead                          15000.0    2516256.7   1677.5
                                                                   ========
System Benchmarks Index Score                                         967.8

------------------------------------------------------------------------
Benchmark Run: Wed Sep 02 2015 10:57:08 - 11:25:45
8 CPUs in system; running 8 parallel copies of tests

Dhrystone 2 using register variables      168464731.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    19981.2 MWIPS (10.0 s, 7 samples)
Execl Throughput                              20133.8 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        411096.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          113098.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1199135.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                            10235072.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                1492403.9 lps   (10.0 s, 7 samples)
Process Creation                              46014.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  27569.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   4022.8 lpm   (60.1 s, 2 samples)
System Call Overhead                        4370269.6 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  168464731.8  14435.7
Double-Precision Whetstone                       55.0      19981.2   3632.9
Execl Throughput                                 43.0      20133.8   4682.3
File Copy 1024 bufsize 2000 maxblocks          3960.0     411096.8   1038.1
File Copy 256 bufsize 500 maxblocks            1655.0     113098.9    683.4
File Copy 4096 bufsize 8000 maxblocks          5800.0    1199135.8   2067.5
Pipe Throughput                               12440.0   10235072.8   8227.6
Pipe-based Context Switching                   4000.0    1492403.9   3731.0
Process Creation                                126.0      46014.3   3651.9
Shell Scripts (1 concurrent)                     42.4      27569.6   6502.3
Shell Scripts (8 concurrent)                      6.0       4022.8   6704.7
System Call Overhead                          15000.0    4370269.6   2913.5
                                                                   ========
System Benchmarks Index Score                                        3623.8

Score final : 967.8/3623.8

Résultat des courses du comparatif

Classement du benchmark :

  • Premier : VPS Dyjix 1767.0/4567.3
  • Second : Dell R710 967.8/3623.8
  • Trosième : VPS Pulseheberg 921.8/2133.4
  • Quatrième : Dédié base ARM Firstheberg 352.6/692.3

Pour conclure le comparatf, je suis assez impressioné par les performances du petit VPS de chez Dyjix ! Si j’ai le temps, je ferais bien un comparatif entre deux technologies de virtualisation, qui sont KVM et OpenVZ sur la même machine phisique (je pense qu’OpenVZ devrait gagner haut la main).
Bref, pour moi l’outil byte-unixbench est très intéressent pour faire des comparatifs entre plusieurs offres d’hébergement.


Afficher l’article complet

Lien vers le commentaire
Partager sur d’autres sites

Archivé

Ce sujet est désormais archivé et ne peut plus recevoir de nouvelles réponses.

Aller sur la liste des sujets
×
×
  • Créer...

Information importante

Nous avons placé des cookies sur votre appareil pour aider à améliorer ce site. Vous pouvez choisir d’ajuster vos paramètres de cookie, sinon nous supposerons que vous êtes d’accord pour continuer.