Benchmark for KVM Under Dell PowerEdge R710

From Leo's Notes
Revision as of 21:31, 25 November 2014 by Leo (talk | contribs) (Created page with " Here is the benchmark result for a single-core virtual machine using Qemu-KVM hypervisor (in an OpenStack setup). The benchmark was performed under CentOS 7. The disk is serv...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
This page was last edited on 25 November 2014, at 21:31.

Here is the benchmark result for a single-core virtual machine using Qemu-KVM hypervisor (in an OpenStack setup). The benchmark was performed under CentOS 7. The disk is served as a volume from cinder on the same machine serving data from a LVM volume on a Raid10.

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

   System: centos-2: GNU/Linux
   OS: GNU/Linux -- 3.10.0-123.8.1.el7.x86_64 -- #1 SMP Mon Sep 22 19:06:58 UTC 2014
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Westmere E56xx/L56xx/X56xx (Nehalem-C) (5320.0 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   20:57:57 up 39 min,  1 user,  load average: 0.00, 0.01, 0.05; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Tue Nov 25 2014 20:57:57 - 21:26:03
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       30583798.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3929.5 MWIPS (10.0 s, 7 samples)
Execl Throughput                               3881.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1073559.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          295659.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2292778.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1643236.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 312382.7 lps   (10.0 s, 7 samples)
Process Creation                              14438.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3471.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    775.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        2217174.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   30583798.8   2620.7
Double-Precision Whetstone                       55.0       3929.5    714.4
Execl Throughput                                 43.0       3881.5    902.7
File Copy 1024 bufsize 2000 maxblocks          3960.0    1073559.0   2711.0
File Copy 256 bufsize 500 maxblocks            1655.0     295659.6   1786.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    2292778.7   3953.1
Pipe Throughput                               12440.0    1643236.5   1320.9
Pipe-based Context Switching                   4000.0     312382.7    781.0
Process Creation                                126.0      14438.5   1145.9
Shell Scripts (1 concurrent)                     42.4       3471.1    818.7
Shell Scripts (8 concurrent)                      6.0        775.5   1292.5
System Call Overhead                          15000.0    2217174.2   1478.1
                                                                   ========
System Benchmarks Index Score                                        1406.3