Alibaba Cloud のベンチマーク

More than 1 year has passed since last update.

夏のキャンペーンがありましたので、それを利用して VPS を契約・試用してみました。

ベンチマーク対象機のスペックは以下のとおりです。


  • Tokyo Zone

  • 2 vCPU

  • 4 GB

  • SSD 40GB

  • Network 100 Mbps (ピーク値)

ping increments.co.jp の結果は以下のとおりです。

PING increments.co.jp (54.230.108.135) 56(84) bytes of data.

64 bytes from server-54-230-108-135.nrt53.r.cloudfront.net (54.230.108.135): icmp_seq=1 ttl=246 time=1.69 ms
64 bytes from server-54-230-108-135.nrt53.r.cloudfront.net (54.230.108.135): icmp_seq=2 ttl=246 time=1.72 ms
64 bytes from server-54-230-108-135.nrt53.r.cloudfront.net (54.230.108.135): icmp_seq=3 ttl=246 time=1.76 ms
64 bytes from server-54-230-108-135.nrt53.r.cloudfront.net (54.230.108.135): icmp_seq=4 ttl=246 time=1.74 ms
^C
--- increments.co.jp ping statistics ---
4 packets transmitted, 4 received, 0% packet loss, time 3004ms
rtt min/avg/max/mdev = 1.697/1.735/1.767/0.026 ms

/proc/cpuinfo の内容は以下のとおりです。

vendor_id       : GenuineIntel

cpu family : 6
model : 79
model name : Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
stepping : 1
microcode : 0x1
cpu MHz : 2500.030
cache size : 40960 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 2
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 mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl
eagerfpu pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer
aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch fsgsbase tsc_adjust bmi1 hle avx2
smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt
bugs :
bogomips : 5000.06
clflush size : 64
cache_alignment : 64
address sizes : 46 bits physical, 48 bits virtual
power management:

UnixBench は以下のとおりです。

========================================================================

BYTE UNIX Benchmarks (Version 5.1.3)

System: iZ6we8ny8qalmyqjcqso8xZ: GNU/Linux
OS: GNU/Linux -- 4.4.0-82-generic -- #105-Ubuntu SMP Tue Jun 20 15:23:02 UTC 2017
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz (5000.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz (5000.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
18:15:18 up 1 min, 1 user, load average: 0.16, 0.05, 0.01; runlevel 5

------------------------------------------------------------------------
Benchmark Run: Thu Jul 13 2017 18:15:18 - 18:43:12
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 28933207.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2327.6 MWIPS (10.0 s, 7 samples)
Execl Throughput 3888.0 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 986498.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 260182.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2991999.1 KBps (30.0 s, 2 samples)
Pipe Throughput 1746891.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 40088.8 lps (10.0 s, 7 samples)
Process Creation 9236.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 10159.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2051.7 lpm (60.0 s, 2 samples)
System Call Overhead 3121796.6 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 28933207.5 2479.3
Double-Precision Whetstone 55.0 2327.6 423.2
Execl Throughput 43.0 3888.0 904.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 986498.5 2491.2
File Copy 256 bufsize 500 maxblocks 1655.0 260182.3 1572.1
File Copy 4096 bufsize 8000 maxblocks 5800.0 2991999.1 5158.6
Pipe Throughput 12440.0 1746891.8 1404.3
Pipe-based Context Switching 4000.0 40088.8 100.2
Process Creation 126.0 9236.8 733.1
Shell Scripts (1 concurrent) 42.4 10159.8 2396.2
Shell Scripts (8 concurrent) 6.0 2051.7 3419.5
System Call Overhead 15000.0 3121796.6 2081.2
========
System Benchmarks Index Score 1340.7

------------------------------------------------------------------------
Benchmark Run: Thu Jul 13 2017 18:43:12 - 19:11:02
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables 57684644.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 4639.0 MWIPS (9.9 s, 7 samples)
Execl Throughput 8801.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1084461.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 285730.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 3282620.0 KBps (30.0 s, 2 samples)
Pipe Throughput 3513447.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 478872.0 lps (10.0 s, 7 samples)
Process Creation 23123.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 16775.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2202.6 lpm (60.0 s, 2 samples)
System Call Overhead 4284159.6 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 57684644.5 4943.0
Double-Precision Whetstone 55.0 4639.0 843.5
Execl Throughput 43.0 8801.6 2046.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 1084461.5 2738.5
File Copy 256 bufsize 500 maxblocks 1655.0 285730.3 1726.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 3282620.0 5659.7
Pipe Throughput 12440.0 3513447.0 2824.3
Pipe-based Context Switching 4000.0 478872.0 1197.2
Process Creation 126.0 23123.8 1835.2
Shell Scripts (1 concurrent) 42.4 16775.1 3956.4
Shell Scripts (8 concurrent) 6.0 2202.6 3671.0
System Call Overhead 15000.0 4284159.6 2856.1
========
System Benchmarks Index Score 2497.1

数字としては他の VPS に引けはとらないようです‥が、では敢えて Alibaba Cloud を選択すべきかというと

理由が難しいところではありますね。