Blog

Benchmark SP 32G 2013 OVH

Écrit le 13 06 2013 par Kévin MET _

On continue avec le benchmark d'une nouvelle machine de chez OVH. Cette fois, il s'agit du modèle SP 32G qui a un proco un peu plus sympa que la gamme SP 16G et 32G de RAM. Sinon les performances disques sont les mêmes car ce sont les mêmes disques. Ce serveur dispose d'assez de RAM pour l'utiliser comme hyperviseur et il reste assez abordable à 70€ HT/Mois. Le seule handicap reste les disques SATA qui ont des performances assez médiocres. C'est du SATA quoi 😕

Caractéristiques techniques et informations supplémentaires

  • OS : Debian Squeeze, kernel OVH 3.8.13-xxxx-grs-ipv6-64
  • Disque : TOSHIBA DT01ACA200 (2 disques)
  • Raid : Raid1 avec les paramètres par défaut OVH
  • CPU : Intel(R) Xeon(R) CPU E3-1245 V2 @ 3.40GHz
  • RAM : 32Go

Benchmark du CPU


# sysbench --test=cpu --cpu-max-prime=20000 --num-threads=1 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:                          24.3759s
    total number of events:              10000
    total time taken by event execution: 24.3742
    per-request statistics:
         min:                                  2.21ms
         avg:                                  2.44ms
         max:                                  2.85ms
         approx.  95 percentile:               2.53ms

Threads fairness:
    events (avg/stddev):           10000.0000/0.00
    execution time (avg/stddev):   24.3742/0.00

# sysbench --test=cpu --cpu-max-prime=20000 --num-threads=8 run
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:
Number of threads: 8

Doing CPU performance benchmark

Threads started!
Done.

Maximum prime number checked in CPU test: 20000


Test execution summary:
    total time:                          3.3688s
    total number of events:              10000
    total time taken by event execution: 26.9357
    per-request statistics:
         min:                                  2.39ms
         avg:                                  2.69ms
         max:                                  7.02ms
         approx.  95 percentile:               2.70ms

Threads fairness:
    events (avg/stddev):           1250.0000/2.65
    execution time (avg/stddev):   3.3670/0.00

Benchmark et informations sur la partie Disque


# parted /dev/sda
GNU Parted 2.3
Using /dev/sda
Welcome to GNU Parted! Type 'help' to view a list of commands.
(parted) unit s print                                                     
Model: ATA TOSHIBA DT01ACA2 (scsi)
Disk /dev/sda: 3907029168s
Sector size (logical/physical): 512B/4096B
Partition Table: gpt

# tune2fs -l /dev/sda2
tune2fs 1.41.12 (17-May-2010)
Filesystem volume name:   /home
Last mounted on:          /home
Filesystem UUID:          a9e4b77c-8088-4bc5-94ce-75f7769fb95f
Filesystem magic number:  0xEF53
Filesystem revision #:    1 (dynamic)
Filesystem features:      has_journal ext_attr resize_inode dir_index filetype needs_recovery extent flex_bg sparse_super large_file huge_file uninit_bg dir_nlink extra_isize
Filesystem flags:         signed_directory_hash 
Default mount options:    user_xattr acl
Filesystem state:         clean
Errors behavior:          Continue
Filesystem OS type:       Linux
Inode count:              120758272
Block count:              483003120
Reserved block count:     24150156
Free blocks:              475373997
Free inodes:              120758261
First block:              0
Block size:               4096
Fragment size:            4096
Reserved GDT blocks:      908
Blocks per group:         32768
Fragments per group:      32768
Inodes per group:         8192
Inode blocks per group:   512
Flex block group size:    16
Filesystem created:       Thu Jun 13 12:52:00 2013
Last mount time:          Thu Jun 13 12:57:28 2013
Last write time:          Thu Jun 13 12:57:28 2013
Mount count:              3
Maximum mount count:      -1
Last checked:             Thu Jun 13 12:52:00 2013
Check interval:           0 ()
Lifetime writes:          688 MB
Reserved blocks uid:      0 (user root)
Reserved blocks gid:      0 (group root)
First inode:              11
Inode size:	          256
Required extra isize:     28
Desired extra isize:      28
Journal inode:            8
Default directory hash:   half_md4
Directory Hash Seed:      e43bf920-7602-4f22-95c1-a581e8da6151
Journal backup:           inode blocks

# sysbench --test=fileio --file-total-size=150G --file-test-mode=rndrw --init-rng=on --max-time=300 --max-requests=0 run
sysbench 0.4.12:  multi-threaded system evaluation benchmark

Running the test with following options:
Number of threads: 1
Initializing random number generator from timer.


Extra file open flags: 0
128 files, 1.1719Gb each
150Gb total file size
Block size 16Kb
Number of random requests for random IO: 0
Read/Write ratio for combined random IO test: 1.50
Periodic FSYNC enabled, calling fsync() each 100 requests.
Calling fsync() at the end of test, Enabled.
Using synchronous I/O mode
Doing random r/w test
Threads started!
Time limit exceeded, exiting...
Done.

Operations performed:  16980 Read, 11320 Write, 36121 Other = 64421 Total
Read 265.31Mb  Written 176.88Mb  Total transferred 442.19Mb  (1.474Mb/sec)
   94.33 Requests/sec executed

Test execution summary:
    total time:                          300.0001s
    total number of events:              28300
    total time taken by event execution: 152.9858
    per-request statistics:
         min:                                  0.00ms
         avg:                                  5.41ms
         max:                                113.85ms
         approx.  95 percentile:              13.43ms

Threads fairness:
    events (avg/stddev):           28300.0000/0.00
    execution time (avg/stddev):   152.9858/0.00
♥ Partage sur tes réseaux sociaux ♥
Kévin MET
Kévin MET

Auteur de ce blog et gérant de la société MNT-TECH, je publie sur ce blog lorsque le temps me le permet et lorsqu'un sujet qui me parait intéressant n'a pas encore été abordé en français. Toutes les informations techniques présentes sur cette page peuvent être réutilisées moyennant le fait de citer la source.