I5-2520M在VMWARE下面和J2850在PVE下面的ubuntu虚拟机性能对比

 

J2850 CPU,ITX主板,宿主机安装PVE,然后虚拟UBUNTU系统。

========================================================================
BYTE UNIX Benchmarks (Version 5.1.2)

System: pve-gcc: GNU/Linux
OS: GNU/Linux — 4.15.0-135-generic — #139-Ubuntu SMP Mon Jan 18 17:38:24 UTC 2021
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap=”UTF-8″, collate=”UTF-8″)
CPU 0: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 3: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
04:08:48 up 1:53, 2 users, load average: 0.08, 0.10, 0.37; runlevel 5


Dhrystone 2 using register variables 13209582.8 lps (9.2 s, 7 samples)
Double-Precision Whetstone 1960.8 MWIPS (10.0 s, 7 samples)
Execl Throughput 1318.8 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 128961.9 KBps (28.7 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 34740.4 KBps (28.7 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 418859.9 KBps (28.7 s, 2 samples)
Pipe Throughput 197064.3 lps (9.6 s, 7 samples)
Pipe-based Context Switching 13855.3 lps (9.6 s, 7 samples)
Process Creation 2625.9 lps (28.7 s, 2 samples)
Shell Scripts (1 concurrent) 3280.7 lpm (57.4 s, 2 samples)
Shell Scripts (8 concurrent) 881.2 lpm (58.7 s, 2 samples)
System Call Overhead 153048.1 lps (9.8 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 13209582.8 1131.9
Double-Precision Whetstone 55.0 1960.8 356.5
Execl Throughput 43.0 1318.8 306.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 128961.9 325.7
File Copy 256 bufsize 500 maxblocks 1655.0 34740.4 209.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 418859.9 722.2
Pipe Throughput 12440.0 197064.3 158.4
Pipe-based Context Switching 4000.0 13855.3 34.6
Process Creation 126.0 2625.9 208.4
Shell Scripts (1 concurrent) 42.4 3280.7 773.8
Shell Scripts (8 concurrent) 6.0 881.2 1468.7
System Call Overhead 15000.0 153048.1 102.0
========
System Benchmarks Index Score 310.7

————————————————————————
Benchmark Run: Wed Feb 17 2021 04:35:41 – 05:02:35
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 49484335.0 lps (9.4 s, 7 samples)
Double-Precision Whetstone 7552.0 MWIPS (9.9 s, 7 samples)
Execl Throughput 3561.7 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 217787.1 KBps (28.7 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 63414.2 KBps (28.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 634896.2 KBps (28.7 s, 2 samples)
Pipe Throughput 718470.2 lps (9.8 s, 7 samples)
Pipe-based Context Switching 151040.1 lps (9.6 s, 7 samples)
Process Creation 7063.3 lps (28.7 s, 2 samples)
Shell Scripts (1 concurrent) 6827.5 lpm (57.4 s, 2 samples)
Shell Scripts (8 concurrent) 1017.8 lpm (58.2 s, 2 samples)
System Call Overhead 556278.4 lps (9.9 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 49484335.0 4240.3
Double-Precision Whetstone 55.0 7552.0 1373.1
Execl Throughput 43.0 3561.7 828.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 217787.1 550.0
File Copy 256 bufsize 500 maxblocks 1655.0 63414.2 383.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 634896.2 1094.6
Pipe Throughput 12440.0 718470.2 577.5
Pipe-based Context Switching 4000.0 151040.1 377.6
Process Creation 126.0 7063.3 560.6
Shell Scripts (1 concurrent) 42.4 6827.5 1610.3
Shell Scripts (8 concurrent) 6.0 1017.8 1696.4
System Call Overhead 15000.0 556278.4 370.9
========
System Benchmarks Index Score 847.7

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

下面是J2850,直接在宿主机PVE下面运行Unixbench的分数

========================================================================
BYTE UNIX Benchmarks (Version 5.1.2)

System: pve: GNU/Linux
OS: GNU/Linux — 5.4.73-1-pve — #1 SMP PVE 5.4.73-1 (Mon, 16 Nov 2020 10:52:16 +0100)
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap=”UTF-8″, collate=”UTF-8″)
CPU 0: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Pentium(R) CPU J2850 @ 2.41GHz (4640.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
13:52:13 up 4:55, 1 user, load average: 0.45, 0.39, 0.44; runlevel 5

————————————————————————
Benchmark Run: Wed Feb 17 2021 13:52:13 – 14:19:00
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 12790478.3 lps (9.5 s, 7 samples)
Double-Precision Whetstone 2239.4 MWIPS (9.8 s, 7 samples)
Execl Throughput 1709.5 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 210135.0 KBps (28.7 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 56914.5 KBps (28.7 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 637105.3 KBps (26.8 s, 2 samples)
Pipe Throughput 403454.0 lps (9.5 s, 7 samples)
Pipe-based Context Switching 48704.3 lps (9.5 s, 7 samples)
Process Creation 3549.7 lps (28.7 s, 2 samples)
Shell Scripts (1 concurrent) 3652.3 lpm (57.4 s, 2 samples)
Shell Scripts (8 concurrent) 1077.3 lpm (57.5 s, 2 samples)
System Call Overhead 404600.9 lps (9.8 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 12790478.3 1096.0
Double-Precision Whetstone 55.0 2239.4 407.2
Execl Throughput 43.0 1709.5 397.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 210135.0 530.6
File Copy 256 bufsize 500 maxblocks 1655.0 56914.5 343.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 637105.3 1098.5
Pipe Throughput 12440.0 403454.0 324.3
Pipe-based Context Switching 4000.0 48704.3 121.8
Process Creation 126.0 3549.7 281.7
Shell Scripts (1 concurrent) 42.4 3652.3 861.4
Shell Scripts (8 concurrent) 6.0 1077.3 1795.5
System Call Overhead 15000.0 404600.9 269.7
========
System Benchmarks Index Score 483.9

————————————————————————
Benchmark Run: Wed Feb 17 2021 14:19:00 – 14:45:55
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 46690834.3 lps (9.8 s, 7 samples)
Double-Precision Whetstone 8947.9 MWIPS (9.8 s, 7 samples)
Execl Throughput 4481.0 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 287149.1 KBps (28.7 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 87767.0 KBps (26.8 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 820282.5 KBps (28.7 s, 2 samples)
Pipe Throughput 1530791.1 lps (9.6 s, 7 samples)
Pipe-based Context Switching 183713.7 lps (9.5 s, 7 samples)
Process Creation 7753.4 lps (28.7 s, 2 samples)
Shell Scripts (1 concurrent) 8290.7 lpm (58.7 s, 2 samples)
Shell Scripts (8 concurrent) 1214.6 lpm (56.2 s, 2 samples)
System Call Overhead 1472732.1 lps (9.5 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 46690834.3 4000.9
Double-Precision Whetstone 55.0 8947.9 1626.9
Execl Throughput 43.0 4481.0 1042.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 287149.1 725.1
File Copy 256 bufsize 500 maxblocks 1655.0 87767.0 530.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 820282.5 1414.3
Pipe Throughput 12440.0 1530791.1 1230.5
Pipe-based Context Switching 4000.0 183713.7 459.3
Process Creation 126.0 7753.4 615.3
Shell Scripts (1 concurrent) 42.4 8290.7 1955.3
Shell Scripts (8 concurrent) 6.0 1214.6 2024.3
System Call Overhead 15000.0 1472732.1 981.8
========
System Benchmarks Index Score 1143.3

下面是I5-2520M的CPU,宿主机是X220安装WIN8系统,使用VMWARE虚拟ubuntu。

========================================================================
BYTE UNIX Benchmarks (Version 5.1.2)

System: gcc-x64: GNU/Linux
OS: GNU/Linux — 4.15.0-128-generic — #131-Ubuntu SMP Wed Dec 9 06:57:35 UTC 2020
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap=”UTF-8″, collate=”UTF-8″)
CPU 0: Intel(R) Core(TM) i5-2520M CPU @ 2.50GHz (4983.8 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Core(TM) i5-2520M CPU @ 2.50GHz (4983.8 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: Intel(R) Core(TM) i5-2520M CPU @ 2.50GHz (4983.8 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 3: Intel(R) Core(TM) i5-2520M CPU @ 2.50GHz (4983.8 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
12:10:36 up 13 days, 12:12, 1 user, load average: 0.04, 0.02, 0.00; runlevel 5

————————————————————————
Benchmark Run: Wed Feb 17 2021 12:10:36 – 12:38:43
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 35142638.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 4181.3 MWIPS (9.9 s, 7 samples)
Execl Throughput 3154.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 496998.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 138168.6 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1333249.8 KBps (30.0 s, 2 samples)
Pipe Throughput 784883.4 lps (10.0 s, 7 samples)
Pipe-based Context Switching 26146.4 lps (10.0 s, 7 samples)
Process Creation 6320.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 7542.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1740.1 lpm (60.0 s, 2 samples)
System Call Overhead 601614.0 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 35142638.2 3011.4
Double-Precision Whetstone 55.0 4181.3 760.2
Execl Throughput 43.0 3154.8 733.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 496998.2 1255.0
File Copy 256 bufsize 500 maxblocks 1655.0 138168.6 834.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 1333249.8 2298.7
Pipe Throughput 12440.0 784883.4 630.9
Pipe-based Context Switching 4000.0 26146.4 65.4
Process Creation 126.0 6320.5 501.6
Shell Scripts (1 concurrent) 42.4 7542.6 1778.9
Shell Scripts (8 concurrent) 6.0 1740.1 2900.1
System Call Overhead 15000.0 601614.0 401.1
========
System Benchmarks Index Score 864.1

————————————————————————
Benchmark Run: Wed Feb 17 2021 12:38:43 – 13:06:57
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 75534547.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 13099.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 7212.7 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 592695.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 164894.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1757109.6 KBps (30.0 s, 2 samples)
Pipe Throughput 1745436.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 232067.0 lps (10.0 s, 7 samples)
Process Creation 12276.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 13974.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1867.7 lpm (60.1 s, 2 samples)
System Call Overhead 1727416.8 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 75534547.1 6472.5
Double-Precision Whetstone 55.0 13099.2 2381.7
Execl Throughput 43.0 7212.7 1677.4
File Copy 1024 bufsize 2000 maxblocks 3960.0 592695.1 1496.7
File Copy 256 bufsize 500 maxblocks 1655.0 164894.1 996.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 1757109.6 3029.5
Pipe Throughput 12440.0 1745436.9 1403.1
Pipe-based Context Switching 4000.0 232067.0 580.2
Process Creation 126.0 12276.4 974.3
Shell Scripts (1 concurrent) 42.4 13974.3 3295.8
Shell Scripts (8 concurrent) 6.0 1867.7 3112.9
System Call Overhead 15000.0 1727416.8 1151.6
========
System Benchmarks Index Score 1791.7

J2850在PVE虚拟机得分847 ,在PVE宿主机里面的性能1143

I5-2520M在VMWARE下面的得分 1791

结论:虚拟机肯定会损失一些性能,但是PVE下面的虚拟机性能,要比VMWARE下面的性能损失小很多。

unixbench安装,参考文章 https://blog.csdn.net/weixin_36628778/article/details/100263115

发表评论

电子邮件地址不会被公开。 必填项已用*标注