タイトルの通り、GCE(Google Compute Engine)のf1-micro(無料枠で使えるもの)のベンチマークを取りましたので、 備忘録として貼っておきます。
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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***) = /home/xxx/byte-unixbench/UnixBench/tmp
* Results = /home/xxx/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
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: db: GNU/Linux
OS: GNU/Linux -- 4.15.0-1029-gcp -- #31-Ubuntu SMP Thu Mar 21 09:40:28 UTC 2019
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU @ 2.20GHz (4400.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
00:12:07 up 3 days, 11:23, 1 user, load average: 0.13, 0.03, 0.01; runlevel 2019-04-30
------------------------------------------------------------------------
Benchmark Run: Sat May 04 2019 00:12:07 - 00:43:23
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 19549752.8 lps (10.1 s, 7 samples)
Double-Precision Whetstone 965.7 MWIPS (33.6 s, 7 samples)
Execl Throughput 771.9 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 112448.3 KBps (30.1 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 37081.8 KBps (30.1 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 246207.9 KBps (30.1 s, 2 samples)
Pipe Throughput 281428.4 lps (10.2 s, 7 samples)
Pipe-based Context Switching 66004.8 lps (10.1 s, 7 samples)
Process Creation 2366.5 lps (30.2 s, 2 samples)
Shell Scripts (1 concurrent) 1486.9 lpm (60.2 s, 2 samples)
Shell Scripts (8 concurrent) 205.7 lpm (60.2 s, 2 samples)
System Call Overhead 202476.7 lps (10.1 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 19549752.8 1675.2
Double-Precision Whetstone 55.0 965.7 175.6
Execl Throughput 43.0 771.9 179.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 112448.3 284.0
File Copy 256 bufsize 500 maxblocks 1655.0 37081.8 224.1
File Copy 4096 bufsize 8000 maxblocks 5800.0 246207.9 424.5
Pipe Throughput 12440.0 281428.4 226.2
Pipe-based Context Switching 4000.0 66004.8 165.0
Process Creation 126.0 2366.5 187.8
Shell Scripts (1 concurrent) 42.4 1486.9 350.7
Shell Scripts (8 concurrent) 6.0 205.7 342.8
System Call Overhead 15000.0 202476.7 135.0
========
System Benchmarks Index Score 271.8
Amazon Lightsailのベンチマーク(UnixBench)とか貼っておきますね。と比べてみると、かなりパフォーマンスは低いようです。 最後のSystem Benchmarks Index Scoreでは、Lightsailの1971.6に対して、271.8と13%程度の性能です。
/proc/cpuinfoの内容は次の通りでした。
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 79
model name : Intel(R) Xeon(R) CPU @ 2.20GHz
stepping : 0
microcode : 0x1
cpu MHz : 2200.000
cache size : 56320 KB
physical id : 0
siblings : 1
core id : 0
cpu cores : 1
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 xtopology nonstop_tsc cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt
bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf
bogomips : 4400.00
clflush size : 64
cache_alignment : 64
address sizes : 46 bits physical, 48 bits virtual
power management:
この程度の性能だと、無料ならまだしも、お金を出して使う積極的な理由は見つかりませんね。 一番安い5USD/monthのAmazon Lightsailの方が圧倒的にコスパが良いと感じます。
2019/8/20追記
最後に、自宅のi5-8400上のUbuntuで実行した結果(SSDではなくHDDで実行したので、 その分は差し引いて考えてください)も貼っておきます。これと比較してみると、 上記Lightsailのベンチマークがあまりに良すぎる気がしました。 Pipe Throughput等一部の結果については、i5-8400の2倍以上の性能が出ている項目があります。
GCEの性能はCPUインテンシブな場合、下記i5-8400のシングルコアの1/3位の性能のようですね。
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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***) = /home/xxx/test/byte-unixbench/UnixBench/tmp
* Results = /home/xxx/test/byte-unixbench/UnixBench/results
------------------------------------------------------------------------------
Wide character in print at ./Run line 1643.
Wide character in printf at ./Run line 1674.
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
Wide character in printf at ./Run line 1574.
6 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
6 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
6 x Execl Throughput 1 2 3
6 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
6 x File Copy 256 bufsize 500 maxblocks 1 2 3
6 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
6 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
6 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
6 x Process Creation 1 2 3
6 x Process Creation 1 2 3
6 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
6 x Shell Scripts (1 concurrent) 1 2 3
6 x Shell Scripts (8 concurrent) 1 2 3
Wide character in printf at ./Run line 1574.
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: desktop: GNU/Linux
OS: GNU/Linux -- 4.15.0-55-generic -- #60-Ubuntu SMP Tue Jul 2 18:22:20 UTC 2019
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 4: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 5: Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz (5616.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
20:35:51 up 3 days, 21:35, 4 users, load average: 0.14, 0.35, 0.64; runlevel 2019-08-16
------------------------------------------------------------------------
Benchmark Run: 火 8月 20 2019 20:35:51 - 21:05:45
6 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 48461208.6 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3479.5 MWIPS (19.7 s, 7 samples)
Execl Throughput 5194.8 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 570326.6 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 153172.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1859454.1 KBps (30.0 s, 2 samples)
Pipe Throughput 1020818.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 198110.8 lps (10.0 s, 7 samples)
Process Creation 3754.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 8822.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1118.2 lpm (60.0 s, 2 samples)
System Call Overhead 606405.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 48461208.6 4152.6
Double-Precision Whetstone 55.0 3479.5 632.6
Execl Throughput 43.0 5194.8 1208.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 570326.6 1440.2
File Copy 256 bufsize 500 maxblocks 1655.0 153172.3 925.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 1859454.1 3206.0
Pipe Throughput 12440.0 1020818.3 820.6
Pipe-based Context Switching 4000.0 198110.8 495.3
Process Creation 126.0 3754.8 298.0
Shell Scripts (1 concurrent) 42.4 8822.3 2080.7
Shell Scripts (8 concurrent) 6.0 1118.2 1863.6
System Call Overhead 15000.0 606405.8 404.3
========
System Benchmarks Index Score 1082.0
------------------------------------------------------------------------
Benchmark Run: 火 8月 20 2019 21:05:45 - 21:35:38
6 CPUs in system; running 6 parallel copies of tests
Dhrystone 2 using register variables 282703793.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 20802.1 MWIPS (19.6 s, 7 samples)
Execl Throughput 27682.6 lps (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 841490.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 215572.2 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2927671.9 KBps (30.0 s, 2 samples)
Pipe Throughput 5898172.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 1455977.0 lps (10.0 s, 7 samples)
Process Creation 65219.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 11364.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 6600.7 lpm (60.0 s, 2 samples)
System Call Overhead 3353321.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 282703793.8 24224.8
Double-Precision Whetstone 55.0 20802.1 3782.2
Execl Throughput 43.0 27682.6 6437.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 841490.0 2125.0
File Copy 256 bufsize 500 maxblocks 1655.0 215572.2 1302.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 2927671.9 5047.7
Pipe Throughput 12440.0 5898172.1 4741.3
Pipe-based Context Switching 4000.0 1455977.0 3639.9
Process Creation 126.0 65219.2 5176.1
Shell Scripts (1 concurrent) 42.4 11364.6 2680.3
Shell Scripts (8 concurrent) 6.0 6600.7 11001.2
System Call Overhead 15000.0 3353321.0 2235.5
========
System Benchmarks Index Score 4370.2