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% |

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