iwinV 가상서버호스팅(VPS) 벤치마크 – rCore.Q1 Unixbench

(Last Updated On: September 19, 2018)

제공 정보

  • iwinv.kr rCore.Q1 (스마일서브)
  • 2 Core
  • 4 GB RAM
  • 25 GB SSD
  • 10 Gbps 네트워크
  • 공인 IPv4 1개
  • 트래픽 인바운드 무료
  • 아웃바운드 약 300 GB (1일 10GB)
  • 월 17000원 (혹은 1일 610원) 부가세별도

서버 스펙

  • AMD FX(tm)-8300 Eight-Core Processor 3314.660MHz ( x 2 )
  • 25 GB SSD
  • 3790 MB RAM
  • 사설아이피 NAT (통신은 공인아이피로 하는듯)

bench.sh

----------------------------------------------------------------------
CPU model            : AMD FX(tm)-8300 Eight-Core Processor
Number of cores      : 2
CPU frequency        : 3314.660 MHz
Total size of Disk   : 25.0 GB (6.9 GB Used)
Total amount of Mem  : 3790 MB (88 MB Used)
Total amount of Swap : 0 MB (0 MB Used)
System uptime        : 0 days, 3 hour 10 min
Load average         : 0.08, 0.03, 0.37
OS                   : CentOS 7.5.1804
Arch                 : x86_64 (64 Bit)
Kernel               : 3.10.0-693.11.1.el7.x86_64
----------------------------------------------------------------------
I/O speed(1st run)   : 89.8 MB/s
I/O speed(2nd run)   : 118 MB/s
I/O speed(3rd run)   : 121 MB/s
Average I/O speed    : 109.6 MB/s
----------------------------------------------------------------------
Node Name                       IPv4 address            Download Speed
CacheFly
Linode, Tokyo, JP               106.187.96.148          4.62MB/s
Linode, Singapore, SG           139.162.23.4            1.48MB/s
Linode, London, UK              176.58.107.39           5.45MB/s
Linode, Frankfurt, DE           139.162.130.8           1.02MB/s
Linode, Fremont, CA             50.116.14.9             1.31MB/s
Softlayer, Dallas, TX           173.192.68.18           1.71MB/s
Softlayer, Seattle, WA          67.228.112.250          647KB/s
Softlayer, Frankfurt, DE        159.122.69.4            1.70MB/s
Softlayer, Singapore, SG        119.81.28.170           41.1KB/s
Softlayer, HongKong, CN         119.81.130.170          208KB/s
----------------------------------------------------------------------

 

WGET 다음카카오 FTP (?)

[root@"kerus.net" ~]# wget -O /dev/null http://mirror.kakao.com/ubuntu-releases/18.04.1/ubuntu-18.04.1-desktop-amd64.iso
--2018-09-19 18:42:56--  http://mirror.kakao.com/ubuntu-releases/18.04.1/ubuntu-18.04.1-desktop-amd64.iso
Resolving mirror.kakao.com (mirror.kakao.com)... 113.29.189.165
Connecting to mirror.kakao.com (mirror.kakao.com)|113.29.189.165|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1953349632 (1.8G) [application/octet-stream]
Saving to: ‘/dev/null’

100%[====================================>] 1,953,349,632  105MB/s   in 17s

2018-09-19 18:43:14 (107 MB/s) - ‘/dev/null’ saved [1953349632/1953349632]

fio IOPS

[root@"kerus.net" fio-2.0.9]# ./fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 --name=test --filename=test --bs=4k --iodepth=64 --size=4G --readwrite=randrw --rwmixread=75
test: (g=0): rw=randrw, bs=4K-4K/4K-4K, ioengine=libaio, iodepth=64
fio-2.0.9
Starting 1 process
Jobs: 1 (f=1): [m] [98.5% done] [65736K/21724K /s] [16.5K/5431  iops] [eta 00m:01s]
test: (groupid=0, jobs=1): err= 0: pid=27664: Wed Sep 19 15:19:17 2018
  read : io=3072.1MB, bw=47770KB/s, iops=11942 , runt= 65871msec
  write: io=1023.2MB, bw=15905KB/s, iops=3976 , runt= 65871msec
  cpu          : usr=4.13%, sys=17.98%, ctx=461414, majf=0, minf=18
  IO depths    : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
     issued    : total=r=786660/w=261916/d=0, short=r=0/w=0/d=0

Run status group 0 (all jobs):
   READ: io=3072.1MB, aggrb=47769KB/s, minb=47769KB/s, maxb=47769KB/s, mint=65871msec, maxt=65871msec
  WRITE: io=1023.2MB, aggrb=15904KB/s, minb=15904KB/s, maxb=15904KB/s, mint=65871msec, maxt=65871msec

Disk stats (read/write):
  vda: ios=783718/260946, merge=0/1, ticks=3177431/996317, in_queue=4173667, util=99.90%

 

Unixbench

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #

   Version 5.1.3                      Based on the Byte Magazine Unix Benchmark

   Multi-CPU version                  Version 5 revisions by Ian Smith,
                                      Sunnyvale, CA, USA
   January 13, 2011                   johantheghost at yahoo period com

------------------------------------------------------------------------------
   Use directories for:
      * File I/O tests (named fs***) = /root/byte-unixbench/UnixBench/tmp
      * Results                      = /root/byte-unixbench/UnixBench/results
------------------------------------------------------------------------------


1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput  1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

1 x File Copy 256 bufsize 500 maxblocks  1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

1 x Process Creation  1 2 3

1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent)  1 2 3

1 x Shell Scripts (8 concurrent)  1 2 3

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

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

   System: "kerus.net".novalocal: GNU/Linux
   OS: GNU/Linux -- 3.10.0-693.11.1.el7.x86_64 -- #1 SMP Mon Dec 4 23:52:40 UTC 2017
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: AMD FX(tm)-8300 Eight-Core Processor (6629.3 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   CPU 1: AMD FX(tm)-8300 Eight-Core Processor (6629.3 bogomips)
          Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
   16:44:58 up  1:37,  1 user,  load average: 0.00, 0.07, 0.87; runlevel 2018-09-19

------------------------------------------------------------------------
Benchmark Run: Wed Sep 19 2018 16:44:58 - 17:13:41
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       32818303.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3672.8 MWIPS (13.5 s, 7 samples)
Execl Throughput                               1784.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        591289.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          167043.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1228206.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1010710.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  92554.0 lps   (10.0 s, 7 samples)
Process Creation                               8169.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4312.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1010.1 lpm   (60.1 s, 2 samples)
System Call Overhead                        1007002.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   32818303.8   2812.2
Double-Precision Whetstone                       55.0       3672.8    667.8
Execl Throughput                                 43.0       1784.3    415.0
File Copy 1024 bufsize 2000 maxblocks          3960.0     591289.6   1493.2
File Copy 256 bufsize 500 maxblocks            1655.0     167043.3   1009.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    1228206.6   2117.6
Pipe Throughput                               12440.0    1010710.5    812.5
Pipe-based Context Switching                   4000.0      92554.0    231.4
Process Creation                                126.0       8169.3    648.4
Shell Scripts (1 concurrent)                     42.4       4312.5   1017.1
Shell Scripts (8 concurrent)                      6.0       1010.1   1683.5
System Call Overhead                          15000.0    1007002.2    671.3
                                                                   ========
System Benchmarks Index Score                                         915.9

------------------------------------------------------------------------
Benchmark Run: Wed Sep 19 2018 17:13:41 - 17:41:49
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       46500419.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8630.2 MWIPS (9.7 s, 7 samples)
Execl Throughput                               5094.8 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        850132.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          243000.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1846994.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1365405.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 265892.3 lps   (10.0 s, 7 samples)
Process Creation                              12694.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6700.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    994.7 lpm   (60.0 s, 2 samples)
System Call Overhead                        1368706.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   46500419.4   3984.6
Double-Precision Whetstone                       55.0       8630.2   1569.1
Execl Throughput                                 43.0       5094.8   1184.8
File Copy 1024 bufsize 2000 maxblocks          3960.0     850132.8   2146.8
File Copy 256 bufsize 500 maxblocks            1655.0     243000.0   1468.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    1846994.5   3184.5
Pipe Throughput                               12440.0    1365405.8   1097.6
Pipe-based Context Switching                   4000.0     265892.3    664.7
Process Creation                                126.0      12694.0   1007.5
Shell Scripts (1 concurrent)                     42.4       6700.1   1580.2
Shell Scripts (8 concurrent)                      6.0        994.7   1657.8
System Call Overhead                          15000.0    1368706.2    912.5
                                                                   ========
System Benchmarks Index Score                                        1500.9

 

잡론

이 VPS는 vCore(가상코어)와 rCore(리얼코어) 가 나뉘어있다. vCore는 CPU 점유율 20%가 초과되면 프로그램에 의해 제약이 생길 수 있다. 리얼코어는 CPU 를 100%로 지속되어도 어떠한 제약없이 독립적으로 쓸 수 있는건가? 코어 1개가 Guarantee 되는건가? 아니면 어떤 스케쥴링에 의해 쓰로틀링이 가해질까? 이건 문의를 안해서 모르겠다. 다만 스펙에 매우 저렴하다는 것은 사실이다. 국내 최저가라고 부를 수 밖에 없다. 8 스레드 제품에는 E3-1230 v5 (스카이레이크) CPU가 들어간다고 하다. 이 정도면 VPS에선 매우 빠른 CPU이다.

인터넷 카더라통신에 의하면 해외망을 써보면 뭔가 ~ 하다는데, 일단 해외망이 어떤지를 해외서비스를 해야 알기때문에 난 모르겠다. Softlayer SG 가 41KB/s 나온 벤치를 보면 유감.