Unixbench Score on Core i5 750 with OpenVZ Kernel vs Xen/Openvz

This was unbelievable how much the Xen kernel slows things down, keep in mind both tests were done on the hostnode, one was with the Openvz-Xen hybrid kernel and the other was just OpenVZ.  You can see the performance difference is nearly 300% better when not using the Xen kernel.

OpenVZ-Xen Kernel Test Results (I was wondering what was wrong/so slow with my Core i5!)


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

                 4        1           Based on the Byte Magazine Unix Benchmark
                44       11
   v   v       4 4        1
    v v       44444       1           v4.1 revisions mostly by David C. Niemi,
     v           4   o   111 - WHT.2  Reston, VA, USA  <niemi@tux.org>
 
WHT Variant by Andy A. Lee <andylee@dslextreme.com>
See: http://www.webhostingtalk.com/showthread.php?s=&threadid=308055


Dhrystone 2 using register variables  1 2

Double-Precision Whetstone  1 2

Execl Throughput  1

Filesystem Throughput 1024 bufsize 2000 maxblocks  1

Filesystem Throughput 256 bufsize 500 maxblocks  1

Filesystem Throughput 4096 bufsize 8000 maxblocks  1

Pipe Throughput  1 2

Pipe-based Context Switching  1 2

Process Creation  1

System Call Overhead  1 2

Shell Scripts (8 concurrent)  1

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux localhost.localdomain 2.6.18-194.3.1.el5.028stab069.5xen #1 SMP Tue May 18 18:33:35 MSD 2010 i686 i686 i386 GNU/Linux
/dev/sda3             19236340    177016  18082172   1% /mnt/sda3

Start Benchmark Run: Sat May 29 01:28:00 EDT 2010
 01:28:00 up  2:38,  2 users,  load average: 0.32, 0.10, 0.02

End Benchmark Run: Sat May 29 01:38:35 EDT 2010
 01:38:35 up  2:48,  2 users,  load average: 12.47, 5.83, 2.66


                     INDEX VALUES           
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7 24942262.7      662.0
Double-Precision Whetstone                      83.1     1518.5      182.7
Execl Throughput                               188.3     4822.1      256.1
File Copy 1024 bufsize 2000 maxblocks         2672.0    69636.0      260.6
File Copy 256 bufsize 500 maxblocks           1077.0    25286.0      234.8
File Read 4096 bufsize 8000 maxblocks        15382.0   829674.0      539.4
Pipe-based Context Switching                 15448.6   149570.1       96.8
Pipe Throughput                             111814.6   416802.5       37.3
Process Creation                               569.3     7657.1      134.5
Shell Scripts (8 concurrent)                    44.8     1084.6      242.1
System Call Overhead                        114433.5  3620305.9      316.4
                                                                 =========
     FINAL SCORE                                                     211.6

OpenVZ only Kernel,now the Core i5 shows its performance!


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

                 4        1           Based on the Byte Magazine Unix Benchmark
                44       11
   v   v       4 4        1
    v v       44444       1           v4.1 revisions mostly by David C. Niemi,
     v           4   o   111 - WHT.2  Reston, VA, USA  <niemi@tux.org>
 
WHT Variant by Andy A. Lee <andylee@dslextreme.com>
See: http://www.webhostingtalk.com/showthread.php?s=&threadid=308055


Dhrystone 2 using register variables  1 2

Double-Precision Whetstone  1 2

Execl Throughput  1

Filesystem Throughput 1024 bufsize 2000 maxblocks  1

Filesystem Throughput 256 bufsize 500 maxblocks  1

Filesystem Throughput 4096 bufsize 8000 maxblocks  1

Pipe Throughput  1 2

Pipe-based Context Switching  1 2

Process Creation  1

System Call Overhead  1 2

Shell Scripts (8 concurrent)  1

==============================================================
BYTE UNIX Benchmarks (Version 4.1-wht.2)
System -- Linux localhost.localdomain 2.6.18-194.3.1.el5.028stab069.5PAE #1 SMP Tue May 18 18:26:13 MSD 2010 i686 i686 i386 GNU/Linux
/dev/md0             297581760   1276412 280945208   1% /

Start Benchmark Run: Sat May 29 01:55:39 EDT 2010
 01:55:39 up 2 min,  1 user,  load average: 0.57, 0.30, 0.11

End Benchmark Run: Sat May 29 02:06:06 EDT 2010
 02:06:06 up 13 min,  2 users,  load average: 15.13, 6.61, 2.95


                     INDEX VALUES           
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        376783.7 24876280.4      660.2
Double-Precision Whetstone                      83.1     1515.2      182.3
Execl Throughput                               188.3    17397.6      923.9
File Copy 1024 bufsize 2000 maxblocks         2672.0   379937.0     1421.9
File Copy 256 bufsize 500 maxblocks           1077.0   107354.0      996.8
File Read 4096 bufsize 8000 maxblocks        15382.0  2918897.0     1897.6
Pipe-based Context Switching                 15448.6   973442.9      630.1
Pipe Throughput                             111814.6  3216279.5      287.6
Process Creation                               569.3    50262.7      882.9
Shell Scripts (8 concurrent)                    44.8     3636.8      811.8
System Call Overhead                        114433.5  3680141.7      321.6
                                                                 =========
     FINAL SCORE                                                     671.4

The difference is easy to see

Xen Kernel=211.6

OpenVZ Kernel=671.4

OpenVZ is more than 3x faster.  I would hate to see the poor results inside a Xen container.  How can Xen claim such high performance when this is clearly not the case?

 


/proc/cpuinfo

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 30
model name      : Intel(R) Core(TM) i5 CPU         750  @ 2.67GHz
stepping        : 5
cpu MHz         : 2666.780
cache size      : 8192 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 4
apicid          : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm [8]
bogomips        : 5333.56

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 30
model name      : Intel(R) Core(TM) i5 CPU         750  @ 2.67GHz
stepping        : 5
cpu MHz         : 2666.780
cache size      : 8192 KB
physical id     : 0
siblings        : 4
core id         : 1
cpu cores       : 4
apicid          : 2
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm [8]
bogomips        : 5333.21

processor       : 2
vendor_id       : GenuineIntel
cpu family      : 6
model           : 30
model name      : Intel(R) Core(TM) i5 CPU         750  @ 2.67GHz
stepping        : 5
cpu MHz         : 2666.780
cache size      : 8192 KB
physical id     : 0
siblings        : 4
core id         : 2
cpu cores       : 4
apicid          : 4
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm [8]
bogomips        : 5333.24

processor       : 3
vendor_id       : GenuineIntel
cpu family      : 6
model           : 30
model name      : Intel(R) Core(TM) i5 CPU         750  @ 2.67GHz
stepping        : 5
cpu MHz         : 2666.780
cache size      : 8192 KB
physical id     : 0
siblings        : 4
core id         : 3
cpu cores       : 4
apicid          : 6
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm [8]
bogomips        : 5333.24
 

This system has a GA-H57M-USB3 motherboard, 4Gigs of DDR3 and a RAID1 Western Digital 2TB 64Meg cache disk array, running Centos 5.5 32 bit.


Tags:

unixbench, openvz, kernel, vs, xen, openvzthis, slows, hostnode, hybrid, byte, unix, benchmark, revisions, niemi, wht, reston, va, usa, tux, org, variant, andylee, dslextreme, http, www, webhostingtalk, showthread, php, threadid, dhrystone, register, variables, precision, whetstone, execl, throughput, filesystem, bufsize, maxblocks, context, switching, creation, overhead, shell, scripts, concurrent, benchmarks, linux, localhost, localdomain, smp, tue, msd, gnu, dev, sda, mnt, edt, users, index, baseline, pae, md, min, user, container, proc, cpuinfo, processor, vendor_id, genuineintel, cpu, intel, tm, ghz, stepping, mhz, cache, kb, siblings, cores, apicid, fdiv_bug, hlt_bug, f_bug, coma_bug, fpu, fpu_exception, cpuid, wp, flags, vme, pse, tsc, msr, mce, cx, apic, sep, mtrr, pge, mca, cmov, clflush, dts, acpi, mmx, fxsr, sse, ss, ht, pbe, nx, rdtscp, lm, constant_tsc, ida, nonstop_tsc, pni, ds_cpl, vmx, smx, est, ssse, xtpr, _, popcnt, lahf_lm, bogomips, ga, usb, motherboard, gigs, ddr, raid, western, digital, tb, meg, disk, array, centos,

Latest Articles

  • ssh Too many authentication failures not prompting for password
  • LightDM Mint Ubuntu Debian won't start errors Nvidia Graphics
  • WARNING: Unable to determine the path to install the libglvnd EGL vendor library config files. Check that you have pkg-config and the libglvnd development libraries installed, or specify a path with --glvnd-egl-config-path. Linux Ubuntu Mint Debian E
  • How To Upgrade Linux Mint 18.2 to 18.3 to 19.x and 20.x
  • MP3s Won't Play / ID3 Version 2.4 Issues in Cars and Other MP3 Players/CDs/DVDs Solution
  • LXC Containers LXD How to Install and Configure Tutorial Ubuntu Debian Mint
  • GlusterFS HowTo Tutorial For Distributed Storage in Docker, Kubernetes, LXC, KVM, Proxmox
  • Ubuntu Mint audio output not working pulseaudio "pulseaudio[13710]: [pulseaudio] sink-input.c: Failed to create sink input: too many inputs per sink."
  • How To Shrink Dynamically Allocated VM QEMU KVM VMware Disk Image File
  • How To Enable Linux Swapfile Instead of Partition Ubuntu Mint Debian Centos
  • 404 Not Found [IP: 151.101.194.132 80] apt update Debian 11 Bullseye Solution The repository 'http://security.debian.org bullseye/updates Release' does not have a Release file.
  • WARNING: Can't download daily.cvd from db.local.clamav.net freshclam clamav error solution
  • (firefox:9562): LIBDBUSMENU-GLIB-WARNING **: Unable to get session bus: Failed to execute child process "dbus-launch" (No such file or directory) Solution
  • Debian Mint Ubuntu Which Package Provides missing top, ps and w Solution
  • Vbox Virtualbox DNS NAT Network Mode NOT working
  • Docker Tutorial HowTo Install Docker, Use and Create Docker Container Images Clustering Swarm Mode Monitoring Service Hosting Provider
  • Zoom Password Error 'That passcode was incorrect' - Solution Wrong Passcode Wrong Meeting Name
  • How To Startup and Open Remote/Local Folder/Directory in Ubuntu Linux Mint automatically upon login
  • How To Reset Windows Server Password 2019, 2022, 7, 8, 10, 11 Recovery and Removal Guide Using Linux Ubuntu Mint Debian
  • How To Create OpenVPN Server for Secure Remote Corporate Access in Linux Debian/Mint/Ubuntu with client public key authentication