0 item | View Cart
img

KVM Performance: 1 CPU vs 2 CPUs vs 4 CPUs

Having multiple CPU cores can improve your Cloud Server performance substantially. We used industry leading BYTE UNIX Benchmarks tests to show how more CPU cores can improve the Benchmarks performance index scores:
1 CPU Core Index Score: 1031.0;
2 CPU Cores Index Score: 1532.6;
4 CPU Cores Index Score: 2331.50.

BYTE UNIX Benchmarks Test Results: KVM Cloud Server with 1 CPU core and 2GB RAM.:

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

System: kvm1cpu.cybercon.net: GNU/Linux
OS: GNU/Linux -- 2.6.32-71.29.1.el6.x86_64 -- #1 SMP Mon Jun 27 19:49:27 BST 2011
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
19:05:09 up 2 min, 1 user, load average: 0.21, 0.08, 0.02; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Fri Jul 22 2011 19:05:09 - 19:40:09
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 26063506.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2241.3 MWIPS (28.4 s, 7 samples)
Execl Throughput 2908.1 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 640886.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 178503.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1442123.3 KBps (30.0 s, 2 samples)
Pipe Throughput 1281880.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 249739.3 lps (10.0 s, 7 samples)
Process Creation 10237.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4048.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 545.3 lpm (60.1 s, 2 samples)
System Call Overhead 1785917.3 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 26063506.5 2233.4
Double-Precision Whetstone 55.0 2241.3 407.5
Execl Throughput 43.0 2908.1 676.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 640886.1 1618.4
File Copy 256 bufsize 500 maxblocks 1655.0 178503.0 1078.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 1442123.3 2486.4
Pipe Throughput 12440.0 1281880.8 1030.5
Pipe-based Context Switching 4000.0 249739.3 624.3
Process Creation 126.0 10237.5 812.5
Shell Scripts (1 concurrent) 42.4 4048.6 954.9
Shell Scripts (8 concurrent) 6.0 545.3 908.9
System Call Overhead 15000.0 1785917.3 1190.6
========
System Benchmarks Index Score 1031.0

 

BYTE UNIX Benchmarks Test Results: KVM Cloud Server with 2 CPU cores and 2GB RAM.:

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

System: kvm2cpu.cybercon.net: GNU/Linux
OS: GNU/Linux -- 2.6.32-71.29.1.el6.x86_64 -- #1 SMP Mon Jun 27 19:49:27 BST 2011
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 1: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
18:35:24 up 1 min, 1 user, load average: 0.11, 0.04, 0.01; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Mon Jul 25 2011 18:35:24 - 19:08:16

2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables 51690353.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 6151.2 MWIPS (17.4 s, 7 samples)
Execl Throughput 5440.3 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 421999.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 121100.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1408301.8 KBps (30.0 s, 2 samples)
Pipe Throughput 2437831.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 431102.4 lps (10.0 s, 7 samples)
Process Creation 16890.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 7611.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1053.6 lpm (60.0 s, 2 samples)
System Call Overhead 2378448.0 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 51690353.5 4429.3
Double-Precision Whetstone 55.0 6151.2 1118.4
Execl Throughput 43.0 5440.3 1265.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 421999.2 1065.7
File Copy 256 bufsize 500 maxblocks 1655.0 121100.1 731.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 1408301.8 2428.1
Pipe Throughput 12440.0 2437831.7 1959.7
Pipe-based Context Switching 4000.0 431102.4 1077.8
Process Creation 126.0 16890.9 1340.5
Shell Scripts (1 concurrent) 42.4 7611.1 1795.1
Shell Scripts (8 concurrent) 6.0 1053.6 1756.1
System Call Overhead 15000.0 2378448.0 1585.6
========
System Benchmarks Index Score 1532.6

 

BYTE UNIX Benchmarks Test Results: KVM Cloud Server with 4 CPU cores and 2GB RAM.:

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

System: kvm4cpu.cybercon.net: GNU/Linux
OS: GNU/Linux -- 2.6.32-71.29.1.el6.x86_64 -- #1 SMP Mon Jun 27 19:49:27 BST 2011
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 1: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 2: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 3: QEMU Virtual CPU version 0.9.1 (4788.1 bogomips)
x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
18:12:13 up 3 min, 1 user, load average: 0.08, 0.03, 0.01; runlevel 3


------------------------------------------------------------------------
Benchmark Run: Tue Jul 26 2011 18:45:39 - 19:20:50
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 102713666.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 8444.8 MWIPS (29.7 s, 7 samples)
Execl Throughput 10186.3 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 365067.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 101515.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1238934.3 KBps (30.0 s, 2 samples)
Pipe Throughput 4647352.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 850011.6 lps (10.0 s, 7 samples)
Process Creation 31824.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 14718.7 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2005.1 lpm (60.0 s, 2 samples)
System Call Overhead 4301845.1 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 102713666.8 8801.5
Double-Precision Whetstone 55.0 8444.8 1535.4
Execl Throughput 43.0 10186.3 2368.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 365067.2 921.9
File Copy 256 bufsize 500 maxblocks 1655.0 101515.0 613.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 1238934.3 2136.1
Pipe Throughput 12440.0 4647352.7 3735.8
Pipe-based Context Switching 4000.0 850011.6 2125.0
Process Creation 126.0 31824.9 2525.8
Shell Scripts (1 concurrent) 42.4 14718.7 3471.4
Shell Scripts (8 concurrent) 6.0 2005.1 3341.8
System Call Overhead 15000.0 4301845.1 2867.9
========
System Benchmarks Index Score 2331.5

© 1995 - 2011 vServerCenter.com All Rights Reserved. Telephone: 1.314.621.9991 (24x7), Web: www.vServerCenter.com
Powered by Cybercon Data Center | Privacy Policy
Follow Us   twitter   facebook