Home > Hyper-V, Hyper-V R2, SCVMM, SCVMM R2, Virtualization, Windows 2008 R2, Windows Server 2008 > Micorosft Lab Validation Report for Hyper-V

Micorosft Lab Validation Report for Hyper-V

Microsoft Hyper-V : Scalable, Native Server Virtualization for the Enterprise

Microsoft just published a Lab Validation Report for Windows Server 2008 Hyper-V, which was written by Enterprise Strategy Group.  This report goes over the installation and configuration of Windows Server 2008 Hyper-V and management of those servers with Virtual Machine Manager 2008.

The report reviews the performance of Windows Server 2008 Hyper-V in comparison with physical systems.

Performance

In this section, we’ll take a look at the results of ESG Lab testing of the performance of applications running on a physical server and on a Hyper-V virtual machine.

ESG Lab Testing

ESG Lab used four real-world application workloads to evaluate the physical and virtual performance of Microsoft Windows 2008 Data Center Edition R1:

1.  Application Install:  a timed installation of Visio 2007 using a distribution image stored on a network

attached shared drive within a private network.

2.  Directory level copy:  a timed copy an 860 MB directory with 2,014 files to a temporary directory.  The c:\windows\win32 directory was copied to a temporary directory on the same C: drive.

3.  Subsequent copies:  the directory level copy was repeated with much of the IO activity happening in cache. The average of three cached copy operations was recorded.

4.  SQL query:  a long running SQL select statement using a 25,000 row production database from ESG’s

internal IT operation was timed.  The SQL query performed a join of three tables. The average duration of three select statements was recorded.

The HP blade server used for this test was equipped with four 2.2 GHz dual-core AMD Opteron processors and eight gigabytes of RAM.   Comparing physical and virtual performance on the same server was accomplished after a reboot with Hyper-V role enabled and disabled.   During the virtual server testing, the server was configured with a  single virtual server, which used nearly all of the physically available hardware resources (all eight CPU cores, seven out of eight GB of RAM).

Physical and virtual testing was performed within a 40 GB logical C: drive.  The C: drive was built using a single LUN presented by a FC attached HP MSA storage array with six 15K SAS drives configured as a single RAID-5 group (5+1).

The Hyper-V C: drive was configured as a basic virtual hard disk (VHD).  The results are shown in Table 1.

Table 1. ESG Lab Performance Results

Operation Physical Virtual Difference
Application install 00:05:52.000 00:06:09.000 4.8%
Directory level copy 00:00:41.680 00:00:33.660 7.1%
Subsequent copies 00:00:05.660 00:00:05.830 3.0%
SQL query 00:00:47.566 00:00:53.630 12.7%

Hyper-V Preformance

What the Numbers Mean

It took five minutes and 52 seconds to install an application on the physical  server running Windows 2008 Data Center Edition SP1   It took six minutes and nine seconds to install the same application on the same hardware running the same operating system running within a Hyper-V enabled virtual machine  The difference in performance is relatively low (4.8%) The directory level copy and subsequent copies were also relatively low (7.1% and 3.0% respectively)  A long running Microsoft SQL query took 12.7% longer when running in a virtual server  The manageably low performance impact of Hyper-V won’t be detected by the vast majority of end-users and applications

Advertisements
  1. No comments yet.
  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: