【ECS/鲲鹏】横向对云服务器 unixbench测试

April 4, 2022 · Other · 136次阅读

unixbench测评方法
unixbench用来测试服务器跑分也算比较常见,但是受影响的因素较多,也没时间测单核多核其他因素
仅供参考、仅供参考、仅供参考,图一乐!

1.阿里云的ECS c5型

配置2核4G
13017-9cohf6u7c0o.png
git到unixbench代码

[root@iZbp14j2amyqheetigvagtZ ~]# git clone https://github.com/kdlucas/byte-unixbench.git
Cloning into 'byte-unixbench'...
remote: Enumerating objects: 222, done.
remote: Counting objects: 100% (17/17), done.
remote: Compressing objects: 100% (12/12), done.
remote: Total 222 (delta 7), reused 12 (delta 5), pack-reused 205
Receiving objects: 100% (222/222), 225.58 KiB | 632.00 KiB/s, done.
Resolving deltas: 100% (113/113), done.

对unixbench进行make,后面就不重复了

[root@iZbp14j2amyqheetigvagtZ byte-unixbench]# cd UnixBench/
[root@iZbp14j2amyqheetigvagtZ UnixBench]# make

ECS服务器需要安装perl-time-hies组件

[root@iZbp14j2amyqheetigvagtZ UnixBench]# yum -y  install perl-Time-HiRes

运行Run

[root@iZbp14j2amyqheetigvagtZ UnixBench]# ./Run

测试结果
可以参考最后的System Benchmarks Index Score 数值

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)
 
   System: iZbp14j2amyqheetigvagtZ: GNU/Linux
   OS: GNU/Linux -- 5.10.84-10.2.al8.x86_64 -- #1 SMP Thu Feb 10 15:03:09 CST 2022
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   23:11:07 up 1 day,  7:08, 4 users,  load average: 0.10, 0.09, 0.05; runlevel 2022-03-31
 
------------------------------------------------------------------------
Benchmark Run: Fri Apr 01 2022 23:11:07 - 23:39:12
2 CPUs in system; running 1 parallel copy of tests
 
Dhrystone 2 using register variables       34381345.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     5587.9 MWIPS (9.9 s, 7 samples)
Execl Throughput                              3572.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        627665.4 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          166712.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1735567.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                              771403.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 217316.8 lps   (10.0 s, 7 samples)
Process Creation                              9249.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5575.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    928.2 lpm   (60.0 s, 2 samples)
System Call Overhead                         415531.6 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   34381345.8  2946.1
Double-Precision Whetstone                       55.0       5587.9  1016.0
Execl Throughput                                43.0       3572.5    830.8
File Copy 1024 bufsize 2000 maxblocks         3960.0     627665.4   1585.0
File Copy 256 bufsize 500 maxblocks           1655.0     166712.0   1007.3
File Copy 4096 bufsize 8000 maxblocks         5800.0    1735567.3   2992.4
Pipe Throughput                               12440.0     771403.2   620.1
Pipe-based Context Switching                   4000.0     217316.8   543.3
Process Creation                               126.0       9249.5    734.1
Shell Scripts (1 concurrent)                     42.4       5575.2  1314.9
Shell Scripts (8 concurrent)                      6.0        928.2  1547.0
System Call Overhead                         15000.0     415531.6    277.0
                                                                  ========
System Benchmarks Index Score                                        1042.9
 
------------------------------------------------------------------------
Benchmark Run: Fri Apr 01 2022 23:39:12 - 00:07:18
2 CPUs in system; running 2 parallel copies of tests
 
Dhrystone 2 using register variables       50495548.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     9919.2 MWIPS (9.9 s, 7 samples)
Execl Throughput                              5222.0 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        821152.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          216521.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2339138.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1034483.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 241128.0 lps   (10.0 s, 7 samples)
Process Creation                             15576.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6683.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    949.2 lpm   (60.1 s, 2 samples)
System Call Overhead                         530123.4 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   50495548.8  4327.0
Double-Precision Whetstone                       55.0       9919.2  1803.5
Execl Throughput                                43.0       5222.0   1214.4
File Copy 1024 bufsize 2000 maxblocks         3960.0     821152.3   2073.6
File Copy 256 bufsize 500 maxblocks           1655.0     216521.0   1308.3
File Copy 4096 bufsize 8000 maxblocks         5800.0    2339138.3   4033.0
Pipe Throughput                               12440.0    1034483.9   831.6
Pipe-based Context Switching                   4000.0     241128.0   602.8
Process Creation                               126.0      15576.3   1236.2
Shell Scripts (1 concurrent)                     42.4       6683.2  1576.2
Shell Scripts (8 concurrent)                      6.0        949.2  1582.0
System Call Overhead                         15000.0     530123.4    353.4
                                                                  ========
System Benchmarks Index Score                                        1399.9

2.H3C的CAS虚拟化平台

PS:好玩而已,手上刚好有这台集群的使用权限,私有云硬件配置没有可比性
使用同等规格的配置,2核4G,构建虚拟机,使用Rocky系统
刀片式集群服务器H3C UIS B390 G3,硬盘是机械非SSD
39682-s7u0i7yk22m.png
虚拟化底座KVM

[root@localhost ~]# hostnamectl
   Static hostname: localhost.localdomain
         Icon name: computer-vm
           Chassis: vm
        Machine ID: dc7cd03c1bd44c7a85aacf1d61414db0
           Boot ID: 91a8905e0b2b4570ad21fa9d91e1909e
    Virtualization: kvm
  Operating System: Rocky Linux 8.5 (Green Obsidian)
       CPE OS Name: cpe:/o:rocky:rocky:8.5:GA
            Kernel: Linux 4.18.0-348.el8.0.2.x86_64
      Architecture: x86-64

看一下CPU

[root@localhost ~]# cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 15
model           : 6
model name      : Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz
stepping        : 3
microcode       : 0x1
cpu MHz         : 2095.074
cache size      : 16384 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 de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx lm constant_tsc nopl xtopology cpuid tsc_known_freq pni cx16 x2apic hypervisor lahf_lm cpuid_fault pti
bugs            : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit
bogomips        : 4190.14
clflush size    : 64
cache_alignment : 128
address sizes   : 46 bits physical, 48 bits virtual
power management:
 
processor       : 1
vendor_id       : GenuineIntel
cpu family      : 15
model           : 6
model name      : Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz
stepping        : 3
microcode       : 0x1
cpu MHz         : 2095.074
cache size      : 16384 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx lm constant_tsc nopl xtopology cpuid tsc_known_freq pni cx16 x2apic hypervisor lahf_lm cpuid_fault pti
bugs            : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit
bogomips        : 4190.14
clflush size    : 64
cache_alignment : 128
address sizes   : 46 bits physical, 48 bits virtual
power management:

测试结果
不言而喻了啊

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)
 
   System: localhost.localdomain: GNU/Linux
   OS: GNU/Linux -- 4.18.0-348.el8.0.2.x86_64 -- #1 SMP Sun Nov 14 00:51:12 UTC 2021
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz (4190.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz (4190.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   22:24:48 up 18 min,  1 user, load average: 0.14, 0.63, 0.60; runlevel 2022-04-02
 
------------------------------------------------------------------------
Benchmark Run: Sat Apr 02 2022 22:24:48 - 22:52:51
2 CPUs in system; running 1 parallel copy of tests
 
Dhrystone 2 using register variables       36507208.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     5156.9 MWIPS (9.3 s, 7 samples)
Execl Throughput                              3344.5 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        353344.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           88893.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1097282.0 KBps  (30.0 s, 2 samples)
Pipe Throughput                              482971.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  49232.5 lps   (10.0 s, 7 samples)
Process Creation                              9286.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4518.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    880.4 lpm   (60.0 s, 2 samples)
System Call Overhead                         289751.1 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   36507208.1  3128.3
Double-Precision Whetstone                       55.0       5156.9   937.6
Execl Throughput                                43.0       3344.5    777.8
File Copy 1024 bufsize 2000 maxblocks         3960.0     353344.0    892.3
File Copy 256 bufsize 500 maxblocks           1655.0      88893.9    537.1
File Copy 4096 bufsize 8000 maxblocks         5800.0    1097282.0   1891.9
Pipe Throughput                               12440.0     482971.4   388.2
Pipe-based Context Switching                   4000.0      49232.5   123.1
Process Creation                               126.0       9286.3    737.0
Shell Scripts (1 concurrent)                     42.4       4518.6  1065.7
Shell Scripts (8 concurrent)                      6.0        880.4  1467.3
System Call Overhead                         15000.0     289751.1    193.2
                                                                  ========
System Benchmarks Index Score                                         727.6
 
------------------------------------------------------------------------
Benchmark Run: Sat Apr 02 2022 22:52:51 - 23:20:57
2 CPUs in system; running 2 parallel copies of tests
 
Dhrystone 2 using register variables       68622501.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     9653.6 MWIPS (9.4 s, 7 samples)
Execl Throughput                              4093.6 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        512635.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          132983.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1593856.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                              981623.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 239091.2 lps   (10.0 s, 7 samples)
Process Creation                             12172.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6087.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    901.7 lpm   (60.1 s, 2 samples)
System Call Overhead                         555546.5 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   68622501.4  5880.2
Double-Precision Whetstone                       55.0       9653.6  1755.2
Execl Throughput                                43.0       4093.6    952.0
File Copy 1024 bufsize 2000 maxblocks         3960.0     512635.8   1294.5
File Copy 256 bufsize 500 maxblocks           1655.0     132983.5    803.5
File Copy 4096 bufsize 8000 maxblocks         5800.0    1593856.2   2748.0
Pipe Throughput                               12440.0     981623.3   789.1
Pipe-based Context Switching                   4000.0     239091.2   597.7
Process Creation                               126.0      12172.7    966.1
Shell Scripts (1 concurrent)                     42.4       6087.4  1435.7
Shell Scripts (8 concurrent)                      6.0        901.7  1502.8
System Call Overhead                         15000.0     555546.5    370.4
                                                                  ========
System Benchmarks Index Score                                        1213.8

3.华为云的鲲鹏ECS kc1型

相同配置,2核4G,使用CentOS7 ARM
96710-tii2r9aavae.png

[root@ecs-kc1-large-2-linux-20211012164825 ~]# hostnamectl
   Static hostname: ecs-kc1-large-2-linux-20211012164825
         Icon name: computer
        Machine ID: 9be71ad18fa04211933d37d9f75b05e8
           Boot ID: 3383ad9765f0446998a4b1db87178135
  Operating System: CentOS Linux 7 (AltArch)
       CPE OS Name: cpe:/o:centos:centos:7
            Kernel: Linux 4.18.0-80.7.2.el7.aarch64
      Architecture: arm64
[root@ecs-kc1-large-2-linux-20211012164825 ~]# cat /proc/cpuinfo
processor       : 0
BogoMIPS        : 200.00
Features        : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma dcpop asimddp asimdfhm
CPU implementer : 0x48
CPU architecture: 8
CPU variant     : 0x1
CPU part        : 0xd01
CPU revision    : 0
 
processor       : 1
BogoMIPS        : 200.00
Features        : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma dcpop asimddp asimdfhm
CPU implementer : 0x48
CPU architecture: 8
CPU variant     : 0x1
CPU part        : 0xd01
CPU revision    : 0

测试结果
这个嘛.....华为牛逼!

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)
 
   System: ecs-kc1-large-2-linux-20211012164825: GNU/Linux
   OS: GNU/Linux -- 4.18.0-80.7.2.el7.aarch64 -- #1 SMP Thu Sep 12 16:13:20 UTC 2019
   Machine: aarch64 (aarch64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: (200.0 bogomips)
 
   CPU 1: (200.0 bogomips)
 
   23:34:11 up 31 min,  3 users, load average: 0.08, 0.47, 0.47; runlevel 2022-04-02
 
------------------------------------------------------------------------
Benchmark Run: Sat Apr 02 2022 23:34:11 - 00:02:20
2 CPUs in system; running 1 parallel copy of tests
 
Dhrystone 2 using register variables       25784740.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3545.8 MWIPS (10.0 s, 7 samples)
Execl Throughput                              4839.3 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        514079.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          140389.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1559502.4 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1171578.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 118797.1 lps   (10.0 s, 7 samples)
Process Creation                              9589.2 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   7641.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1506.2 lpm   (60.0 s, 2 samples)
System Call Overhead                         858605.9 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   25784740.7  2209.5
Double-Precision Whetstone                       55.0       3545.8   644.7
Execl Throughput                                43.0       4839.3   1125.4
File Copy 1024 bufsize 2000 maxblocks         3960.0     514079.8   1298.2
File Copy 256 bufsize 500 maxblocks           1655.0     140389.0    848.3
File Copy 4096 bufsize 8000 maxblocks         5800.0    1559502.4   2688.8
Pipe Throughput                               12440.0    1171578.3   941.8
Pipe-based Context Switching                   4000.0     118797.1   297.0
Process Creation                               126.0       9589.2    761.0
Shell Scripts (1 concurrent)                     42.4       7641.9  1802.3
Shell Scripts (8 concurrent)                      6.0       1506.2  2510.4
System Call Overhead                         15000.0     858605.9    572.4
                                                                  ========
System Benchmarks Index Score                                        1083.5
 
------------------------------------------------------------------------
Benchmark Run: Sun Apr 03 2022 00:02:20 - 00:30:28
2 CPUs in system; running 2 parallel copies of tests
 
Dhrystone 2 using register variables       51494422.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     7085.7 MWIPS (10.0 s, 7 samples)
Execl Throughput                              7237.2 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        680235.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          185055.1 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2245821.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2331956.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 434571.5 lps   (10.0 s, 7 samples)
Process Creation                             16695.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  11076.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1563.8 lpm   (60.0 s, 2 samples)
System Call Overhead                        1607332.0 lps   (10.0 s, 7 samples)
 
System Benchmarks Index Values               BASELINE       RESULT   INDEX
Dhrystone 2 using register variables         116700.0   51494422.1  4412.5
Double-Precision Whetstone                       55.0       7085.7  1288.3
Execl Throughput                                43.0       7237.2   1683.1
File Copy 1024 bufsize 2000 maxblocks         3960.0     680235.2   1717.8
File Copy 256 bufsize 500 maxblocks           1655.0     185055.1   1118.2
File Copy 4096 bufsize 8000 maxblocks         5800.0    2245821.9   3872.1
Pipe Throughput                               12440.0    2331956.5  1874.6
Pipe-based Context Switching                   4000.0     434571.5  1086.4
Process Creation                               126.0      16695.0   1325.0
Shell Scripts (1 concurrent)                     42.4      11076.0  2612.3
Shell Scripts (8 concurrent)                      6.0       1563.8  2606.4
System Call Overhead                         15000.0    1607332.0   1071.6
                                                                  ========
System Benchmarks Index Score                                        1828.9

咱就图一乐,也没测试多次取个平均值啥的,也没停服务器上的一些业务,哎!就是玩儿

喝杯水

none

最后编辑于3个月前

添加新评论