Всем привет! Публикую тесты нескольких серверов от OVH которые я провел в октябре этого года. Все серверы для теста любезно предоставил alice2k
Если в прошлом посте у нас был более простой игровой сервер линейки SYS Game, то теперь у нас на тесте более крутой игровой сервер из линейки OVH Game.
Вот такой сервер: https://www.ovh.ie/dedicated_servers/game/
Здесь процессор Intel i7 4790K, 32 Gb RAM и SSD 2x240Gb.
Начнем тест.
Информация о сервере
Спецификация сервера:
Стоит такая конфигурация сейчас 69.99 евро. Стоит также отметить что здесь есть возможность покупки дополнительных IP (об этом в отдельном посте) до 256 штук и есть встроенный антиддос заточенный специально под игровые сервера.
С каждым сервером идет место на бэкап-сервере объемом 500 гигабайт.
На тесте сервер с Debian 8
CPU и RAM
root@ns30091xx:~# cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 60 model name : Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz stepping : 3 microcode : 0x19 cpu MHz : 854.687 cache size : 8192 KB physical id : 0 siblings : 8 core id : 0 cpu cores : 4 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm ida arat epb xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm bogomips : 7981.52 clflush size : 64 cache_alignment : 64 address sizes : 39 bits physical, 48 bits virtual power management: ... processor : 7 vendor_id : GenuineIntel cpu family : 6 model : 60 model name : Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz stepping : 3 microcode : 0x19 cpu MHz : 927.187 cache size : 8192 KB physical id : 0 siblings : 8 core id : 3 cpu cores : 4 apicid : 7 initial apicid : 7 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm ida arat epb xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm bogomips : 7981.52 clflush size : 64 cache_alignment : 64 address sizes : 39 bits physical, 48 bits virtual power management: root@ns30091xx:~# cat /proc/meminfo MemTotal: 32880772 kB MemFree: 32248616 kB MemAvailable: 32488360 kB Buffers: 25656 kB Cached: 267636 kB SwapCached: 0 kB Active: 167472 kB Inactive: 157308 kB Active(anon): 33016 kB Inactive(anon): 8236 kB Active(file): 134456 kB Inactive(file): 149072 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 1046520 kB SwapFree: 1046520 kB Dirty: 80 kB Writeback: 0 kB AnonPages: 31496 kB Mapped: 16640 kB Shmem: 9764 kB Slab: 58796 kB SReclaimable: 27036 kB SUnreclaim: 31760 kB KernelStack: 2672 kB PageTables: 1568 kB NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB CommitLimit: 17486904 kB Committed_AS: 166460 kB VmallocTotal: 34359738367 kB VmallocUsed: 132344 kB VmallocChunk: 34359400268 kB HardwareCorrupted: 0 kB DirectMap4k: 10884 kB DirectMap2M: 3010560 kB DirectMap1G: 30408704 kB
Диск примонтирован по-умолчанию вот так:
root@ns30091xx:~# df -H Filesystem Size Used Avail Use% Mounted on /dev/root 236G 645M 223G 1% / devtmpfs 17G 0 17G 0% /dev tmpfs 17G 0 17G 0% /dev/shm tmpfs 17G 10M 17G 1% /run tmpfs 5.3M 0 5.3M 0% /run/lock tmpfs 17G 0 17G 0% /sys/fs/cgroup
Более подробная информация о железе:
root@ns30091xx:~# inxi -b
System: Host: ns30091xx.ip-151-80-47.eu Kernel: 3.14.32-xxxx-grs-ipv6-64 x86_64 (64 bit) Console: tty 0
Distro: Debian 8
Machine: System: ASUS product: All Series
Mobo: ASUSTeK model: H97M-PLUS v: Rev X.0x serial: 141236406600719
Bios: American Megatrends v: 2404 date: 03/04/2015
CPU: Quad core Intel Core i7-4790K (-HT-MCP-) clocked at 3940 MHz
Graphics: Card: Intel Xeon E3-1200 v3/4th Gen Core Processor Integrated Graphics Controller
Display Server: N/A driver: N/A tty size: 182x31 Advanced Data: N/A for root out of X
Network: Card: Intel Ethernet Connection (2) I218-V driver: e1000e
Drives: HDD Total Size: 480.1GB (0.2% used)
RAID: Device: 1: /dev/md1
Info: Processes: 150 Uptime: 1:55 Memory: 374.0/32110.1MB Init: systemd runlevel: 5
Client: Shell (bash) inxi: 2.1.28
Материнка здесь точно такая же как на - SYS Game 1
Подробно об установленых SSD:
root@ns30091xx:~# hdparm -I /dev/sda1
/dev/sda1:
ATA device, with non-removable media
Model Number: SAMSUNG MZ7LM240HCGR-00003
Serial Number: S1YFNYAG500300
Firmware Revision: GXT3003Q
Transport: Serial, ATA8-AST, SATA 1.0a, SATA II Extensions, SATA Rev 2.5, SATA Rev 2.6, SATA Rev 3.0
Standards:
Used: unknown (minor revision code 0x0039)
Supported: 9 8 7 6 5
Likely used: 9
Configuration:
Logical max current
cylinders 16383 16383
heads 16 16
sectors/track 63 63
--
CHS current addressable sectors: 16514064
LBA user addressable sectors: 268435455
LBA48 user addressable sectors: 468862128
Logical Sector size: 512 bytes
Physical Sector size: 512 bytes
Logical Sector-0 offset: 0 bytes
device size with M = 1024*1024: 228936 MBytes
device size with M = 1000*1000: 240057 MBytes (240 GB)
cache/buffer size = unknown
Nominal Media Rotation Rate: Solid State Device
Capabilities:
LBA, IORDY(can be disabled)
Queue depth: 32
Standby timer values: spec'd by Standard, no device specific minimum
R/W multiple sector transfer: Max = 16 Current = 16
DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
Cycle time: min=120ns recommended=120ns
PIO: pio0 pio1 pio2 pio3 pio4
Cycle time: no flow control=120ns IORDY flow control=120ns
Commands/features:
Enabled Supported:
* SMART feature set
Security Mode feature set
* Power Management feature set
* Write cache
* Look-ahead
* Host Protected Area feature set
* WRITE_BUFFER command
* READ_BUFFER command
* NOP cmd
* DOWNLOAD_MICROCODE
SET_MAX security extension
* 48-bit Address feature set
* Device Configuration Overlay feature set
* Mandatory FLUSH_CACHE
* FLUSH_CACHE_EXT
* SMART error logging
* SMART self-test
* General Purpose Logging feature set
* WRITE_{DMA|MULTIPLE}_FUA_EXT
* 64-bit World wide name
Write-Read-Verify feature set
* WRITE_UNCORRECTABLE_EXT command
* {READ,WRITE}_DMA_EXT_GPL commands
* Segmented DOWNLOAD_MICROCODE
* Gen1 signaling speed (1.5Gb/s)
* Gen2 signaling speed (3.0Gb/s)
* Gen3 signaling speed (6.0Gb/s)
* Native Command Queueing (NCQ)
* Phy event counters
* unknown 76[15]
* DMA Setup Auto-Activate optimization
* Asynchronous notification (eg. media change)
* Software settings preservation
* SMART Command Transport (SCT) feature set
* SCT Write Same (AC2)
* SCT Error Recovery Control (AC3)
* SCT Features Control (AC4)
* SCT Data Tables (AC5)
* DOWNLOAD MICROCODE DMA command
* SET MAX SETPASSWORD/UNLOCK DMA commands
* WRITE BUFFER DMA command
* READ BUFFER DMA command
* Data Set Management TRIM supported (limit 8 blocks)
* Deterministic read ZEROs after TRIM
Security:
Master password revision code = 65534
supported
not enabled
not locked
frozen
not expired: security count
supported: enhanced erase
32min for SECURITY ERASE UNIT. 32min for ENHANCED SECURITY ERASE UNIT.
Logical Unit WWN Device Identifier: 5002538c000128f7
NAA : 5
IEEE OUI : 002538
Unique ID : c000128f7
Checksum: correct
Тесты и замеры производительности
Пинг из Ульяновска:
[rail@localhost ~]$ ping 151.80.47.xx PING 151.80.47.xx (151.80.47.xx) 56(84) bytes of data. 64 bytes from 151.80.47.xx: icmp_seq=1 ttl=55 time=79.2 ms 64 bytes from 151.80.47.xx: icmp_seq=2 ttl=55 time=79.0 ms 64 bytes from 151.80.47.xx: icmp_seq=3 ttl=55 time=78.9 ms 64 bytes from 151.80.47.xx: icmp_seq=4 ttl=55 time=78.9 ms 64 bytes from 151.80.47.xx: icmp_seq=5 ttl=55 time=86.8 ms 64 bytes from 151.80.47.xx: icmp_seq=6 ttl=55 time=82.5 ms 64 bytes from 151.80.47.xx: icmp_seq=7 ttl=55 time=81.1 ms 64 bytes from 151.80.47.xx: icmp_seq=8 ttl=55 time=79.1 ms 64 bytes from 151.80.47.xx: icmp_seq=9 ttl=55 time=79.2 ms 64 bytes from 151.80.47.xx: icmp_seq=10 ttl=55 time=79.3 ms 64 bytes from 151.80.47.xx: icmp_seq=11 ttl=55 time=79.4 ms 64 bytes from 151.80.47.xx: icmp_seq=12 ttl=55 time=79.3 ms 64 bytes from 151.80.47.xx: icmp_seq=13 ttl=55 time=79.2 ms ^C --- 151.80.47.xx ping statistics --- 13 packets transmitted, 13 received, 0% packet loss, time 12013ms rtt min/avg/max/mdev = 78.976/80.212/86.803/2.184 ms
SSD показывает результаты вдвое выше чем на SYS:
root@ns30091xx:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync 16384+0 records in 16384+0 records out 1073741824 bytes (1.1 GB) copied, 4.40238 s, 244 MB/s root@ns30091xx:~# rm test root@ns30091xx:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync 16384+0 records in 16384+0 records out 1073741824 bytes (1.1 GB) copied, 4.41008 s, 243 MB/s root@ns30091xx:~# rm test root@ns30091xx:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync 16384+0 records in 16384+0 records out 1073741824 bytes (1.1 GB) copied, 4.40448 s, 244 MB/s
Тесты Sysbench
Замеряем производительность процессора нагружая его вычислениями 64-разрядных чисел. Попробуем запустить вычисление в один поток.
root@ns30091xx:~# 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: 18.1742s
total number of events: 10000
total time taken by event execution: 18.1737
per-request statistics:
min: 1.81ms
avg: 1.82ms
max: 6.66ms
approx. 95 percentile: 1.82ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 18.1737/0.00
Теперь запустим 4 потока по числу физических ядер процессора.
root@ns30091xx:~# sysbench --test=cpu --cpu-max-prime=20000 --num-threads=4 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 4
Doing CPU performance benchmark
Threads started!
Done.
Maximum prime number checked in CPU test: 20000
Test execution summary:
total time: 4.9038s
total number of events: 10000
total time taken by event execution: 19.6111
per-request statistics:
min: 1.90ms
avg: 1.96ms
max: 9.79ms
approx. 95 percentile: 1.91ms
Threads fairness:
events (avg/stddev): 2500.0000/1.22
execution time (avg/stddev): 4.9028/0.00
Тестим процессор нагружая его большим количеством конкурирующих потоков:
root@ns30091xx:~# sysbench --test=threads --thread-locks=1 --max-time=20s run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 1
Doing thread subsystem performance test
Thread yields per test: 1000 Locks used: 1
Threads started!
Done.
Test execution summary:
total time: 1.0470s
total number of events: 10000
total time taken by event execution: 1.0462
per-request statistics:
min: 0.10ms
avg: 0.10ms
max: 0.43ms
approx. 95 percentile: 0.14ms
Threads fairness:
events (avg/stddev): 10000.0000/0.00
execution time (avg/stddev): 1.0462/0.00
root@ns30091xx:~# sysbench --test=mutex --num-threads=64 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 64
Doing mutex performance test
Threads started!
Done.
Test execution summary:
total time: 0.6075s
total number of events: 64
total time taken by event execution: 37.7957
per-request statistics:
min: 572.83ms
avg: 590.56ms
max: 606.87ms
approx. 95 percentile: 606.40ms
Threads fairness:
events (avg/stddev): 1.0000/0.00
execution time (avg/stddev): 0.5906/0.01
Теперь замерим производительность оперативной памяти:
root@ns30091xx:~# sysbench --test=memory --memory-total-size=32G --num-threads=4 run
sysbench 0.4.12: multi-threaded system evaluation benchmark
Running the test with following options:
Number of threads: 4
Doing memory operations speed test
Memory block size: 1K
Memory transfer size: 32768M
Memory operations type: write
Memory scope type: global
Threads started!
Done.
Operations performed: 33554432 (5964192.04 ops/sec)
32768.00 MB transferred (5824.41 MB/sec)
Test execution summary:
total time: 5.6260s
total number of events: 33554432
total time taken by event execution: 14.0642
per-request statistics:
min: 0.00ms
avg: 0.00ms
max: 0.04ms
approx. 95 percentile: 0.00ms
Threads fairness:
events (avg/stddev): 8388608.0000/160224.17
execution time (avg/stddev): 3.5160/0.03
Тест скорости чтения и записи на диск. Чтобы на тест не влиял кэш в ОЗУ зададим общий объем тестовых чуть больше чем установлено на сервере RAM.
root@ns30091xx:~# sysbench --test=fileio --file-total-size=36G prepare
sysbench 0.4.12: multi-threaded system evaluation benchmark
128 files, 294912Kb each, 36864Mb total
Creating files for the test...
root@ns30091xx:~# sysbench --test=fileio --file-total-size=36G --file-test-mode=rndrw --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
Extra file open flags: 0
128 files, 288Mb each
36Gb 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: 2160600 Read, 1440400 Write, 4609158 Other = 8210158 Total
Read 32.968Gb Written 21.979Gb Total transferred 54.947Gb (187.55Mb/sec)
12003.33 Requests/sec executed
Test execution summary:
total time: 300.0001s
total number of events: 3601000
total time taken by event execution: 123.3239
per-request statistics:
min: 0.00ms
avg: 0.03ms
max: 3.86ms
approx. 95 percentile: 0.16ms
Threads fairness:
events (avg/stddev): 3601000.0000/0.00
execution time (avg/stddev): 123.3239/0.00
Serverbear
Тесты Serverbear
Судя по которым этот сервер является довольно выгодным по сравнению с конкурентами.
Выводы
Это отличный сервер за свои деньги. Обычно с этими серверами практически не возникает проблем. Также в пользу этих серверов говорит и их популярность. Все мои знакомые с игровыми серверами уже давно переехали в OVH =)