Benchmark de vos serveurs

Message par **sumfvm** » lun. 16 mars 2009 09:55

Hello les gens,

J'ai trouvé un petit script qui permet de bencher facilement vos bécanes sous Linux :

#wget http://members.dslextreme.com/users/and ... wht.tar.gz
# gunzip -dvc unixbench-4.1.0-wht.tar.gz | tar xvf -
# cd unixbench-4.1.0-wht
# make
# ./Run

Pour compiler, il vous sera peut-être nécessaire d'installer le paquetage "build-essential".

Résultat chez moi :

- C2D E6300 @ 2.33 Ghz, 4 Go de PC6400 :

Start Benchmark Run: Mon Mar 16 08:30:43 CET 2009
08:30:43 up 14:37, 1 user, load average: 0.12, 0.18, 0.88

End Benchmark Run: Mon Mar 16 08:41:14 CET 2009
08:41:14 up 14:47, 1 user, load average: 12.68, 5.55, 2.92

INDEX VALUES
TEST BASELINE RESULT INDEX

Dhrystone 2 using register variables 376783.7 10895075.6 289.2
Double-Precision Whetstone 83.1 1350.3 162.5
Execl Throughput 188.3 5546.7 294.6
File Copy 1024 bufsize 2000 maxblocks 2672.0 183887.0 688.2
File Copy 256 bufsize 500 maxblocks 1077.0 57181.0 530.9
File Read 4096 bufsize 8000 maxblocks 15382.0 1022121.0 664.5
Pipe-based Context Switching 15448.6 526983.0 341.1
Pipe Throughput 111814.6 2331359.4 208.5
Process Creation 569.3 15180.9 266.7
Shell Scripts (8 concurrent) 44.8 963.7 215.1
System Call Overhead 114433.5 2938163.6 256.8
=========
FINAL SCORE 319.3

- XeonE5440 @ 2.83 Ghz, 8 Go de PC8500 :

Start Benchmark Run: lundi 16 mars 2009, 09:04:38 (UTC+0100)
09:04:38 up 9 days, 22:39, 1 user, load average: 1.51, 1.42, 1.86

End Benchmark Run: lundi 16 mars 2009, 09:14:59 (UTC+0100)
09:14:59 up 9 days, 22:50, 1 user, load average: 14.76, 7.28, 4.23

INDEX VALUES
TEST BASELINE RESULT INDEX

Dhrystone 2 using register variables 376783.7 19694322.8 522.7
Double-Precision Whetstone 83.1 1491.6 179.5
Execl Throughput 188.3 6536.7 347.1
File Copy 1024 bufsize 2000 maxblocks 2672.0 193476.0 724.1
File Copy 256 bufsize 500 maxblocks 1077.0 50925.0 472.8
File Read 4096 bufsize 8000 maxblocks 15382.0 1220712.0 793.6
Pipe-based Context Switching 15448.6 1127958.3 730.1
Pipe Throughput 111814.6 4584537.8 410.0
Process Creation 569.3 16737.0 294.0
Shell Scripts (8 concurrent) 44.8 1537.7 343.2
System Call Overhead 114433.5 5935766.0 518.7
=========
FINAL SCORE 445.9

A vos benchs

Message par **Alucardfh** » lun. 16 mars 2009 10:45

Bi PIII @ 1ghz ,1go sdram pc133 :

Start Benchmark Run: lundi 16 mars 2009, 10:14:47 (UTC+0100)
10:14:47 up 6 days, 19:39, 1 user, load average: 0.35, 0.14, 0.05

End Benchmark Run: lundi 16 mars 2009, 10:25:15 (UTC+0100)
10:25:15 up 6 days, 19:50, 1 user, load average: 13.72, 5.87, 2.62

INDEX VALUES
TEST BASELINE RESULT INDEX

Dhrystone 2 using register variables 376783.7 3235129.2 85.9
Double-Precision Whetstone 83.1 451.4 54.3
Execl Throughput 188.3 1100.5 58.4
File Copy 1024 bufsize 2000 maxblocks 2672.0 30144.0 112.8
File Copy 256 bufsize 500 maxblocks 1077.0 12983.0 120.5
File Read 4096 bufsize 8000 maxblocks 15382.0 117568.0 76.4
Pipe-based Context Switching 15448.6 140817.9 91.2
Pipe Throughput 111814.6 610337.6 54.6
Process Creation 569.3 3533.5 62.1
Shell Scripts (8 concurrent) 44.8 213.6 47.7
System Call Overhead 114433.5 1030781.8 90.1
=========
FINAL SCORE 74.2

Message par **shreckbull** » mer. 18 mars 2009 21:58

quand on est sous windows on peut pas jouer ... snif !

Message par **poulpito** » mer. 18 mars 2009 22:40

avec cygwin ca doit passer remarque

Message par **nicodache** » jeu. 19 mars 2009 00:15

BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux korsakov 2.6.27-gentoo-r3 #2 SMP Tue Dec 9 23:27:22 CET 2008 x86_64 Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz GenuineIntel GNU/Linux
/dev/mapper/vg-home  1442148412 1354282308  14609144  99% /home

Start Benchmark Run: jeu mar 19 00:04:22 CET 2009
 00:04:22 up  3:42,  1 user,  load average: 0.69, 2.38, 6.61

End Benchmark Run: jeu mar 19 00:14:35 CET 2009
 00:14:35 up  3:53,  1 user,  load average: 13.76, 6.20, 5.99


                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7 20173939.6      535.4
Double-Precision Whetstone                      83.1     1668.1      200.7
Execl Throughput                               188.3    11593.7      615.7
File Copy 1024 bufsize 2000 maxblocks         2672.0   238196.0      891.5
File Copy 256 bufsize 500 maxblocks           1077.0    72182.0      670.2
File Read 4096 bufsize 8000 maxblocks        15382.0  1379492.0      896.8
Pipe-based Context Switching                 15448.6  1157639.7      749.3
Pipe Throughput                             111814.6  4808244.4      430.0
Process Creation                               569.3    39936.0      701.5
Shell Scripts (8 concurrent)                    44.8     1832.7      409.1
System Call Overhead                        114433.5  6704987.2      585.9
                                                                 =========
     FINAL SCORE                                                     566.3

[edit]et je vous propose plutot la 5.1.2 :
http://www.hermit.org/Linux/Benchmarking/

Message par **Zedoune** » jeu. 19 mars 2009 00:32

Bi E5420 - 8 Go de ram pc5300

Score de merde

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- FreeBSD smp 7.1-RELEASE FreeBSD 7.1-RELEASE #6: Wed Mar 18 22:02:31 UTC 2009 root@smp:/usr/obj/usr/src/sys/BIXEON i386
/dev/ad6s1a 32977462 12456868 17882398 41% /

Start Benchmark Run: Jeu 19 mar 2009 00:20:16 UTC
0:20 up 1:48, 3 users, load averages: 0,22 0,32 0,29

End Benchmark Run: Jeu 19 mar 2009 00:30:20 UTC
0:30 up 1:58, 3 users, load averages: 10,65 4,78 2,39

INDEX VALUES
TEST BASELINE RESULT INDEX

Dhrystone 2 using register variables 376783,0 22263316,2 590,9
Double-Precision Whetstone 83,0 1552,0 187,0
Execl Throughput 188,0 2207,0 117,4
File Copy 1024 bufsize 2000 maxblocks 2672,0 31386,0 117,5
File Copy 256 bufsize 500 maxblocks 1077,0 25088,0 232,9
File Read 4096 bufsize 8000 maxblocks 15382,0 742967,0 483,0
Pipe Throughput 111814,0 3165985,3 283,1
Pipe-based Context Switching 15448,0 435874,1 282,2
Process Creation 569,0 5824,2 102,4
Shell Scripts (8 concurrent) 44,0 497,7 113,1
System Call Overhead 114433,0 2251857,3 196,8
=========
FINAL SCORE 207,8

Message par **batoub** » jeu. 19 mars 2009 09:37

Score de fou pour ton Q6600 nicodache!

Sur mon portable (T2300)

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux bastien 2.6.24-23-generic #1 SMP Mon Jan 26 00:13:11 UTC 2009 i686 GNU/Linux
/dev/sda5 33908712 28908840 3290960 90% /

Start Benchmark Run: jeudi 19 mars 2009, 09:16:25 (UTC+0100)
09:16:25 up 19 min, 2 users, load average: 0.21, 0.17, 0.17

End Benchmark Run: jeudi 19 mars 2009, 09:27:06 (UTC+0100)
09:27:06 up 30 min, 2 users, load average: 14.40, 6.37, 2.93

INDEX VALUES
TEST BASELINE RESULT INDEX

Dhrystone 2 using register variables 376783.7 5827669.1 154.7
Double-Precision Whetstone 83.1 837.1 100.7
Execl Throughput 188.3 5302.4 281.6
File Copy 1024 bufsize 2000 maxblocks 2672.0 117920.0 441.3
File Copy 256 bufsize 500 maxblocks 1077.0 37218.0 345.6
File Read 4096 bufsize 8000 maxblocks 15382.0 720415.0 468.3
Pipe-based Context Switching 15448.6 356272.6 230.6
Pipe Throughput 111814.6 1033256.9 92.4
Process Creation 569.3 17073.4 299.9
Shell Scripts (8 concurrent) 44.8 530.6 118.4
System Call Overhead 114433.5 2180542.4 190.6
=========
FINAL SCORE 214.9

Message par **nicodache** » jeu. 19 mars 2009 11:56

boah, c'est un q6600 sur une p5e ws pro

Message par **nicodache** » ven. 20 mars 2009 22:20

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

   System: korsakov: GNU/Linux
   OS: GNU/Linux -- 2.6.27-gentoo-r3 -- #2 SMP Tue Dec 9 23:27:22 CET 2008
   Machine: x86_64 (GenuineIntel)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz (4810.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz (4811.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz (4811.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz (4811.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   20:21:37 up 11 min,  1 user,  load average: 0.57, 0.47, 0.29; runlevel

------------------------------------------------------------------------
Benchmark Run: ven mar 20 2009 20:21:38 - 21:02:10
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       17873524.5 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2780.2 MWIPS (10.0 s, 7 samples)
Execl Throughput                               2302.6 lps   (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        539011.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          158548.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1068574.4 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1176211.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 279399.0 lps   (10.0 s, 7 samples)
Process Creation                               8290.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3241.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1076.8 lpm   (60.1 s, 2 samples)
System Call Overhead                        1675732.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   17873524.5   1531.6
Double-Precision Whetstone                       55.0       2780.2    505.5
Execl Throughput                                 43.0       2302.6    535.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     539011.2   1361.1
File Copy 256 bufsize 500 maxblocks            1655.0     158548.6    958.0
File Copy 4096 bufsize 8000 maxblocks          5800.0    1068574.4   1842.4
Pipe Throughput                               12440.0    1176211.4    945.5
Pipe-based Context Switching                   4000.0     279399.0    698.5
Process Creation                                126.0       8290.3    658.0
Shell Scripts (1 concurrent)                     42.4       3241.9    764.6
Shell Scripts (8 concurrent)                      6.0       1076.8   1794.7
System Call Overhead                          15000.0    1675732.1   1117.2
                                                                   ========
System Benchmarks Index Score                                         966.4

------------------------------------------------------------------------
Benchmark Run: ven mar 20 2009 21:02:11 - 22:14:35
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       65186950.1 lps   (10.1 s, 7 samples)
Double-Precision Whetstone                    11253.5 MWIPS (10.0 s, 7 samples)
Execl Throughput                              11013.0 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        273908.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           76050.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        701090.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             4707258.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                1148491.2 lps   (10.0 s, 7 samples)
Process Creation                              38211.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  10270.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1338.3 lpm   (60.1 s, 2 samples)
System Call Overhead                        2991738.7 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   65186950.1   5585.9
Double-Precision Whetstone                       55.0      11253.5   2046.1
Execl Throughput                                 43.0      11013.0   2561.2
File Copy 1024 bufsize 2000 maxblocks          3960.0     273908.2    691.7
File Copy 256 bufsize 500 maxblocks            1655.0      76050.5    459.5
File Copy 4096 bufsize 8000 maxblocks          5800.0     701090.7   1208.8
Pipe Throughput                               12440.0    4707258.5   3784.0
Pipe-based Context Switching                   4000.0    1148491.2   2871.2
Process Creation                                126.0      38211.5   3032.7
Shell Scripts (1 concurrent)                     42.4      10270.4   2422.3
Shell Scripts (8 concurrent)                      6.0       1338.3   2230.5
System Call Overhead                          15000.0    2991738.7   1994.5
                                                                   ========
System Benchmarks Index Score                                        1995.8

avec la version trouvée sur http://www.hermit.org/Linux/Benchmarkin ... 1.2.tar.gz

Message par **sumfvm** » ven. 20 mars 2009 22:52

Ah bien ça, merci

Message par **ZEPsikopat** » ven. 20 mars 2009 22:56

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux karpette 2.6.28-1-amd64 #1 SMP Wed Feb 18 17:16:12 UTC 2009 x86_64 GNU/Linux
                      30963708   6257416  24391720  21% /

Start Benchmark Run: Fri Mar 20 22:44:10 CET 2009
 22:44:10 up 5 days,  3:36,  7 users,  load average: 0.59, 1.66, 1.14

End Benchmark Run: Fri Mar 20 22:54:19 CET 2009
 22:54:19 up 5 days,  3:46,  7 users,  load average: 12.21, 5.77, 3.08


                     INDEX VALUES            
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7 15119337.9      401.3
Double-Precision Whetstone                      83.1     1307.2      157.3
Execl Throughput                               188.3     9771.9      519.0
File Copy 1024 bufsize 2000 maxblocks         2672.0   181355.0      678.7
File Copy 256 bufsize 500 maxblocks           1077.0    54839.0      509.2
File Read 4096 bufsize 8000 maxblocks        15382.0  1190205.0      773.8
Pipe-based Context Switching                 15448.6   887290.7      574.4
Pipe Throughput                             111814.6  3072600.6      274.8
Process Creation                               569.3    31172.7      547.6
Shell Scripts (8 concurrent)                    44.8     1539.7      343.7
System Call Overhead                        114433.5  7836050.3      684.8
                                                                 =========
     FINAL SCORE                                                     456.2

Message par **nicodache** » ven. 20 mars 2009 23:14

petite comparaison (en cours) de mes FS

(avec la commande ./Run oldsystem)

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux korsakov 2.6.27-gentoo-r3 #2 SMP Tue Dec 9 23:27:22 CET 2008 x86_64 Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz GenuineIntel GNU/Linux
/dev/mapper/vg-home  1442148412 1340486464  28404988  98% /home

Start Benchmark Run: ven mar 20 23:04:32 CET 2009
 23:04:32 up  2:54,  1 user,  load average: 0.28, 2.04, 5.06

End Benchmark Run: ven mar 20 23:12:46 CET 2009
 23:12:46 up  3:02,  1 user,  load average: 4.45, 3.47, 4.48


                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Execl Throughput                               188.3    11328.1      601.6
File Copy 1024 bufsize 2000 maxblocks         2672.0   232684.0      870.8
File Copy 256 bufsize 500 maxblocks           1077.0    68477.0      635.8
File Read 4096 bufsize 8000 maxblocks        15382.0  1313877.0      854.2
Pipe-based Context Switching                 15448.6  1146315.1      742.0
Pipe Throughput                             111814.6  4772294.4      426.8
Process Creation                               569.3    39965.8      702.0
System Call Overhead                        114433.5  6666799.9      582.6
                                                                 =========
     FINAL SCORE                                                     661.9

lvm agrégat de 2 raid 1 soft, 2x500 et 2x1000 mdadm.
ext3

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux korsakov 2.6.27-gentoo-r3 #2 SMP Tue Dec 9 23:27:22 CET 2008 x86_64 Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz GenuineIntel GNU/Linux
/dev/root             29280224  18685176  10595048  64% /

Start Benchmark Run: ven mar 20 23:14:45 CET 2009
 23:14:45 up  3:04,  1 user,  load average: 0.86, 2.43, 3.97

End Benchmark Run: ven mar 20 23:23:00 CET 2009
 23:23:00 up  3:13,  1 user,  load average: 4.79, 3.57, 3.82


                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Execl Throughput                               188.3    11116.1      590.3
File Copy 1024 bufsize 2000 maxblocks         2672.0   498069.0     1864.0
File Copy 256 bufsize 500 maxblocks           1077.0   181351.0     1683.9
File Read 4096 bufsize 8000 maxblocks        15382.0  1322352.0      859.7
Pipe-based Context Switching                 15448.6  1154249.0      747.2
Pipe Throughput                             111814.6  4816172.5      430.7
Process Creation                               569.3    39571.0      695.1
System Call Overhead                        114433.5  6680501.4      583.8
                                                                 =========
     FINAL SCORE                                                     821.8

raid 5 hardware ; 3x36go sur acceleraid 352 w/ 64mo de cache (i960)
xfs

ca poutre quand même, le scsi, en fait

Message par **ZEPsikopat** » ven. 20 mars 2009 23:23

J'ai honte, je fais moins en passant sur l'areca

Message par **Zedoune** » ven. 20 mars 2009 23:44

Pourquoi mon ordi il a un score si merdique ??

Message par **ZEPsikopat** » ven. 20 mars 2009 23:46

Pourquoi mon areca elle a un score si merdique ??

Message par **syno** » sam. 21 mars 2009 01:30

Pourquoi ma vie elle a un score si merdique ??

Message par **Zedoune** » sam. 21 mars 2009 09:58

sérieusement, le portable avec un T2300 il fait plus que mon 2x 5420 !

Vive FreeBSD

Et vous avez des scores pourris parce que vous le valez bien

Message par **ZEPsikopat** » sam. 21 mars 2009 10:25

Pourquoi ma vie elle a un score si merdique ??

On est là pour t'optimiser pour te faire péter le score

Message par **nicodache** » dim. 22 mars 2009 22:23

'tain, le score de merde de mon laptop :'(

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux rachmaninov 2.6.28.4 #2 SMP Tue Feb 10 00:05:38 UTC 2009 i686 GNU/Linux
/dev/sda5             14640960   8593652   6047308  59% /

Start Benchmark Run: dimanche 22 mars 2009, 22:10:59 (UTC+0000)
 22:10:59 up  3:18,  1 user,  load average: 5.57, 5.63, 3.03

End Benchmark Run: dimanche 22 mars 2009, 22:21:54 (UTC+0000)
 22:21:54 up  3:29,  1 user,  load average: 20.03, 8.75, 4.98


                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7  9007875.7      239.1
Double-Precision Whetstone                      83.1     1092.7      131.5
Execl Throughput                               188.3     4340.3      230.5
File Copy 1024 bufsize 2000 maxblocks         2672.0    89132.0      333.6
File Copy 256 bufsize 500 maxblocks           1077.0    24261.0      225.3
File Read 4096 bufsize 8000 maxblocks        15382.0   668149.0      434.4
Pipe-based Context Switching                 15448.6   144218.9       93.4
Pipe Throughput                             111814.6   438222.5       39.2
Process Creation                               569.3    12126.6      213.0
Shell Scripts (8 concurrent)                    44.8      296.8       66.2
System Call Overhead                        114433.5  1160035.4      101.4
                                                                 =========
     FINAL SCORE                                                     155.0

Message par **poulpito** » dim. 22 mars 2009 22:39

190 mon laptop moi

un versa M360 avec un T5500

Message par **ZEPsikopat** » dim. 22 mars 2009 22:43

J'ose pas le faire sur mon thinkpad, il chauffe trop

Message par **nicodache** » mar. 24 mars 2009 00:02

Bon, je suis déçu par le dual opteron 2212 et 4x512M de ram

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux debian 2.6.26-1-amd64 #1 SMP Fri Mar 13 17:46:45 UTC 2009 x86_64 GNU/Linux
/dev/sda5             35570536    189848  33573780   1% /home

Start Benchmark Run: mardi 24 mars 2009, 20:31:48 (UTC+0100)
 20:31:48 up 4 min,  2 users,  load average: 0.75, 0.28, 0.11

End Benchmark Run: mardi 24 mars 2009, 20:41:57 (UTC+0100)
 20:41:57 up 14 min,  2 users,  load average: 13.45, 5.88, 2.65


                     INDEX VALUES            
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7 13694359.0      363.5
Double-Precision Whetstone                      83.1     1078.3      129.8
Execl Throughput                               188.3     7962.8      422.9
File Copy 1024 bufsize 2000 maxblocks         2672.0   137046.0      512.9
File Copy 256 bufsize 500 maxblocks           1077.0    42383.0      393.5
File Read 4096 bufsize 8000 maxblocks        15382.0  1078296.0      701.0
Pipe-based Context Switching                 15448.6   301291.1      195.0
Pipe Throughput                             111814.6  2010313.3      179.8
Process Creation                               569.3    24656.7      433.1
Shell Scripts (8 concurrent)                    44.8     1462.5      326.5
System Call Overhead                        114433.5  4653759.8      406.7
                                                                 =========
     FINAL SCORE                                                     333.6

[edit]le même serveur, bench en 5.1.2

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

   System: debian: GNU/Linux
   OS: GNU/Linux -- 2.6.26-1-amd64 -- #1 SMP Fri Mar 13 17:46:45 UTC 2009
   Machine: x86_64 (unknown)
   Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
   CPU 0: Dual-Core AMD Opteron(tm) Processor 2212 (1996.7 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   CPU 1: Dual-Core AMD Opteron(tm) Processor 2212 (1996.7 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   CPU 2: Dual-Core AMD Opteron(tm) Processor 2212 (3993.5 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   CPU 3: Dual-Core AMD Opteron(tm) Processor 2212 (3993.5 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   21:36:02 up 15 min,  2 users,  load average: 0.71, 0.47, 0.24; runlevel 

------------------------------------------------------------------------
Benchmark Run: mer mar 25 2009 21:36:02 - 22:03:29
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables        9613432.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     1880.7 MWIPS (6.7 s, 7 samples)
Execl Throughput                               1061.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        188937.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           53454.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        524669.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                              466686.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  52780.4 lps   (10.0 s, 7 samples)
Process Creation                               3062.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2127.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    729.7 lpm   (60.1 s, 2 samples)
System Call Overhead                        1479986.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0    9613432.0    823.8
Double-Precision Whetstone                       55.0       1880.7    341.9
Execl Throughput                                 43.0       1061.5    246.9
File Copy 1024 bufsize 2000 maxblocks          3960.0     188937.0    477.1
File Copy 256 bufsize 500 maxblocks            1655.0      53454.8    323.0
File Copy 4096 bufsize 8000 maxblocks          5800.0     524669.3    904.6
Pipe Throughput                               12440.0     466686.9    375.2
Pipe-based Context Switching                   4000.0      52780.4    132.0
Process Creation                                126.0       3062.8    243.1
Shell Scripts (1 concurrent)                     42.4       2127.3    501.7
Shell Scripts (8 concurrent)                      6.0        729.7   1216.1
System Call Overhead                          15000.0    1479986.1    986.7
                                                                   ========
System Benchmarks Index Score                                         450.7

------------------------------------------------------------------------
Benchmark Run: mer mar 25 2009 22:03:29 - 22:31:17
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       36365491.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     7433.5 MWIPS (7.4 s, 7 samples)
Execl Throughput                               7968.8 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks         77086.1 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           22775.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        222080.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1684253.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 299316.0 lps   (10.0 s, 7 samples)
Process Creation                              24194.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   9708.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1407.7 lpm   (60.1 s, 2 samples)
System Call Overhead                        2361343.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   36365491.4   3116.2
Double-Precision Whetstone                       55.0       7433.5   1351.5
Execl Throughput                                 43.0       7968.8   1853.2
File Copy 1024 bufsize 2000 maxblocks          3960.0      77086.1    194.7
File Copy 256 bufsize 500 maxblocks            1655.0      22775.6    137.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     222080.6    382.9
Pipe Throughput                               12440.0    1684253.2   1353.9
Pipe-based Context Switching                   4000.0     299316.0    748.3
Process Creation                                126.0      24194.4   1920.2
Shell Scripts (1 concurrent)                     42.4       9708.1   2289.6
Shell Scripts (8 concurrent)                      6.0       1407.7   2346.2
System Call Overhead                          15000.0    2361343.2   1574.2
                                                                   ========
System Benchmarks Index Score                                        1023.2

Message par **grandEST1** » sam. 28 mars 2009 20:04

3300 point furmark

oki je sort

Message par **Zedoune** » dim. 5 avr. 2009 00:39

Je reviens à l'assaut mais avec un autre système ce coup-ci

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux smp 2.6.29.1-custom-huhu-latest-de-la-mort #2 SMP PREEMPT Sat Apr 4 17:33:38 CEST 2009 x86_64 GNU/Linux
/dev/md0p1           961313356 155367400 805945956  17% /home

Start Benchmark Run: dimanche 5 avril 2009, 00:27:15 (UTC+0200)
 00:27:15 up  5:06,  4 users,  load average: 0.31, 0.38, 0.36

End Benchmark Run: dimanche 5 avril 2009, 00:37:35 (UTC+0200)
 00:37:35 up  5:17,  4 users,  load average: 14.32, 6.43, 3.05


                     INDEX VALUES            
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783,0 21485443,4      570,2
Double-Precision Whetstone                      83,0     1822,0      219,5
Execl Throughput                               188,0     8439,4      448,9
File Copy 1024 bufsize 2000 maxblocks         2672,0   174112,0      651,6
File Copy 256 bufsize 500 maxblocks           1077,0    47223,0      438,5
File Read 4096 bufsize 8000 maxblocks        15382,0  1409550,0      916,4
Pipe-based Context Switching                 15448,0  1118536,4      724,1
Pipe Throughput                             111814,0  4208117,8      376,3
Process Creation                               569,0    25665,0      451,1
System Call Overhead                        114433,0  6880235,1      601,2
                                                                 =========
     FINAL SCORE                                                     505,4

Message par **Zedoune** » dim. 5 avr. 2009 01:51

Version multi-CPU

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

   System: smp: GNU/Linux
   OS: GNU/Linux -- 2.6.29.1-custom-huhu-latest-de-la-mort -- #2 SMP PREEMPT Sat Apr 4 17:33:38 CEST 2009
   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 E5420 @ 2.50GHz (4987.7 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 1: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 2: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 3: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 4: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 5: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 6: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4986.8 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   CPU 7: Intel(R) Xeon(R) CPU E5420 @ 2.50GHz (4987.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
   00:40:47 up  5:20,  4 users,  load average: 0.89, 3.52, 2.54; runlevel 

------------------------------------------------------------------------
Benchmark Run: dim avr 05 2009 00:40:47 - 01:10:13
8 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       19004334.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2983.1 MWIPS (10.0 s, 7 samples)
Execl Throughput                               2126.3 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        418755.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          122172.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        805177.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1076217.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 278861.9 lps   (10.0 s, 7 samples)
Process Creation                               6033.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3888.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1591.6 lpm   (60.0 s, 2 samples)
System Call Overhead                        1731993.8 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   19004334.0   1628.5
Double-Precision Whetstone                       55.0       2983.1    542.4
Execl Throughput                                 43.0       2126.3    494.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     418755.3   1057.5
File Copy 256 bufsize 500 maxblocks            1655.0     122172.9    738.2
File Copy 4096 bufsize 8000 maxblocks          5800.0     805177.1   1388.2
Pipe Throughput                               12440.0    1076217.8    865.1
Pipe-based Context Switching                   4000.0     278861.9    697.2
Process Creation                                126.0       6033.7    478.9
Shell Scripts (1 concurrent)                     42.4       3888.5    917.1
Shell Scripts (8 concurrent)                      6.0       1591.6   2652.6
System Call Overhead                          15000.0    1731993.8   1154.7
                                                                   ========
System Benchmarks Index Score                                         923.3

------------------------------------------------------------------------
Benchmark Run: dim avr 05 2009 01:10:13 - 01:47:44
8 CPUs in system; running 8 parallel copies of tests

Dhrystone 2 using register variables      135008279.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    23645.6 MWIPS (10.0 s, 7 samples)
Execl Throughput                              14571.2 lps   (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        357539.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          101615.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        886863.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             6257509.6 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                1838585.1 lps   (10.0 s, 7 samples)
Process Creation                              35967.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  15480.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   2680.9 lpm   (60.1 s, 2 samples)
System Call Overhead                        2783264.6 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  135008279.0  11568.8
Double-Precision Whetstone                       55.0      23645.6   4299.2
Execl Throughput                                 43.0      14571.2   3388.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     357539.8    902.9
File Copy 256 bufsize 500 maxblocks            1655.0     101615.9    614.0
File Copy 4096 bufsize 8000 maxblocks          5800.0     886863.6   1529.1
Pipe Throughput                               12440.0    6257509.6   5030.2
Pipe-based Context Switching                   4000.0    1838585.1   4596.5
Process Creation                                126.0      35967.3   2854.5
Shell Scripts (1 concurrent)                     42.4      15480.9   3651.2
Shell Scripts (8 concurrent)                      6.0       2680.9   4468.2
System Call Overhead                          15000.0    2783264.6   1855.5
                                                                   ========
System Benchmarks Index Score                                        2848.6