The Need for a Standard Virtualization Benchmark

Conventional server benchmarks in use today were designed to measure the performance of a single application running on a single operating system, inside a single physical computer. However, these benchmarks cannot accurately measure the performance of a single application running inside a virtual machine, nor can they measure the performance of a single hardware platform used to run several virtual machines at once. As a result, there is increasing interest in a more effective solution for measuring the performance and scalability of virtualized IT environments.

VMmark: The Industry's First Virtualization Benchmark

VMmark is a free tool that hardware vendors, virtualization software vendors and other organizations use to measure the performance and scalability of applications running in virtualized environments. This virtualization benchmark software features a novel tile-based scheme for measuring application performance and provides a consistent methodology that captures both the overall scalability and individual application performance

Traditional Benchmarking vs. VMmark Tile-Based Benchmarking

VMmark: The First Industry-Standard Virtualization Benchmark

VMware developed VMmark as a standard methodology for comparing virtualized systems. The benchmark system in VMmark comprises a series of “sub-tests” that are derived from commonly used load-generation tools, as well as from benchmarks developed by the Standard Performance Evaluation Corporation (SPEC®). In parallel to VMmark, VMware is a member of the SPEC Virtualization subcommittee and is working with other SPEC members to create the next-generation virtualization benchmark.

 

 

 

FEATURES

Open Standards and Platform Neutrality

VMmark is not a commercial or proprietary product, but rather a product of our commitment to the development of open standards for virtualization benchmarks. As such, the VMmark software is agnostic towards individual hardware platforms and virtualization software systems so that users can get an objective measurement of virtualization performance.

VMware is working with the Standard Performance Evaluation Corporation (SPEC®) - a non profit organization that establishes, maintains and endorses standardized benchmarks - and members of the SPEC Virtualization subcommittee to develop standard methods of comparing virtualization performance for data center servers.

Other current participants include AMD, Dell, Fujitsu Siemens, Hewlett-Packard, Intel, IBM, Microsoft, Red Hat, Sun Microsystems and SWsoft.

Application-Centric Benchmarking of Real-World Workloads

VMmark uses workloads representative of those applications most often found in the data center, such as email servers, databases, etc. VMware has worked closely with its partners to design and implement the benchmark across various software and hardware platforms, and has also gathered extensive customer feedback to understand how these applications are typically used in virtualized environments.

To measure performance, VMmark leverages well-understood, existing benchmarks that customers are already familiar with.

VMmark incorporates 64-bit versions of three of the VMmark workloads—Java Server, Database Server and Web Server—to reflect the growing use of 64-bit applications and operating systems.

Unique Tile-Based Implementation

The unit of work for a benchmark of virtualized consolidation environments can be naturally defined as a collection of virtual machines executing a set of diverse workloads. The VMmark benchmark refers to this unit of work as a tile.

The total number of tiles that a system can accommodate provides a coarse-grain measure of that system's consolidation capacity. This concept is similar to some server benchmarks, such as TPC-C, that scale the workload in a step-wise fashion to increase the system load.

High-Precision Scoring Methodology

VMmark allows for the integration of the different component metrics into an overall score. Once a VMmark test completes, each individual workload reports its relevant performance metric. These metrics are collected at frequent intervals during the course of a run. A VMmark benchmark test is designed to run for at least three hours with workload metrics reported every 60 seconds.

After a benchmark run, the workload metrics for each tile are computed and aggregated into a score for that tile. This aggregation is performed by first normalizing the different performance metrics such as MB/second and database commits/second with respect to a reference system. Then, a geometric mean of the normalized scores is computed as the final score for the tile. The resulting per-tile scores are then summed to create the final metric.

This approach helps users measure the virtualization overhead of the individual application workloads, as well as the scalability of the entire system.

VMMARK SYSTEM REQUIREMENTS

Here is the minimum hardware setup you will need

  • One server with 2 CPUs, 6GB RAM, 80G disk space and a 1Gb NIC
  • One client PC for every tile, each with 2 CPUs, 2GB RAM and 15G available disk space
  • A private network for connecting clients to the server

You can also optionally connect a SAN, iSCSI or NFS storage.

Workload Software

Operating systems: Microsoft Windows Server 2003 Release 2 Enterprise Edition (32-bit and 64-bit); SUSE Linux Enterprise Server 10 (32-bit and 64-bit)

Applications: Microsoft Exchange 2003; SPECjbb2005; SPECweb2005; MySQL; dbench

Client Software

Each VMmark tile requires a client machine. These client machines run Microsoft Windows Server 2003 Release 2 Enterprise Edition (32-bit) with the following applications:VMmark harness

  • VMmark harness
  • STAF framework and STAX execution engine
  • LoadSim 2003
  • Microsoft Outlook 2003 (standalone or included in Microsoft Office 2003)
  • BEA JRockit 5.0 JVM JDK
  • SPECweb client (included with the SPECweb2005 package)
  • MySQL database server
  • SysBench database benchmark
  • SPECjbb monitor (included with the SPECjbb2005 package)

Software Licensing Considerations

Some of the software required to run VMmark is free, some is available in no-cost evaluation versions and some requires paid licenses. The following list summarizes these three categories.  

Free Software

You can download the following free software packages from the web:

  • SUSE Linux Enterprise Server 10
  • Apache Ant build tool
  • Apache HTTP Server
  • APC cache for PHP
  • BEA JRockit 5.0 JVM JDK
  • Cygwin environment
  • MySQL database server
  • SysBench database benchmark
  • Dbench (a customized version included with VMmark software)
  • FastCGI CGI extension
  • MySQL database
  • SysBench database benchmarking tool
  • PHP scripting language
  • STAF/STAX software
  • VMware VMmark Harness
  • VMware memory soaker

Evaluation Software

You can download evaluation versions of the following software packages from the web:

  • Microsoft Outlook 2003 (standalone or included in Microsoft Office 2003)

Purchased Software

You must purchase licenses for the following software packages if you do not already own them:

  • Microsoft Windows Server 2003 Release 2 Enterprise Edition (32-bit)—three 32-bit copies per tile (two for virtual machines and one for that tile’s client system), and one 64-bit copy per tile (for the Java server virtual machine)  
  • Microsoft Exchange Server 2003 Enterprise Edition (This is available as part of the Microsoft Developer’s Network (MSDN) Universal subscription.)   
  • SPECjbb2005 Benchmark   
  • SPECweb2005 Benchmark
See All

RESULTS

Get an accurate measurement of application performance in virtualized environments with VMware VMmark, the industry's first virtualization benchmark for x86-based computers. Measure virtual machine performance accurately and reliably.

64 Cores

TestSubmitter System Description VMmark Version & Score Processors Published Date
NEC NEC Express5800/A1160
VMware ESX v4.0
VMmark v1.1.1
48.23 @ 32 tiles
View Disclosure
16 sockets
64 total cores
64 total threads
11/17/09

 

48 Cores

Submitter System Description VMmark Version & Score Processors Published Date
Dell Dell PowerEdge R815
VMware ESX v4.0 Update 2
VMmark v1.1.1
59.74@41 tiles
View Disclosure
4 sockets
48 total cores
48 total threads
08/10/10
HP HP ProLiant DL785 G6
VMware ESX v4.0
VMmark v1.1.1
53.73 @ 35 tiles
View Disclosure
8 sockets
48 total cores
48 total threads
08/25/09
HP HP ProLiant DL785 G6
VMware ESX v4.0
VMmark v1.1.1
47.77 @ 30 tiles
View Disclosure
8 sockets
48 total cores
48 total threads
08/11/09
NEC NEC Express5800/A1160
VMware ESX v4.0
VMmark v1.1.1
34.05@24 tiles
View Disclosure
8 sockets
48 total cores
48 total threads
07/28/09
IBM IBM System x3950 M2
VMware ESX v4.0
VMmark v1.1
33.85@24 tiles
View Disclosure
8 sockets
48 total cores
48 total threads
06/16/09

 

32 Cores

Submitter System Description VMmark Version & Score Processors Published Date
Fujitsu Fujitsu RX600 S5
VMware ESX v4.0 Update 2
VMmark v1.1.1
77.29@51 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
10/19/10
Cisco Cisco UCS C460 M1
VMware ESX v4.0 Update 2
VMmark v1.1.1
76.10@51 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
09/07/10
Fujitsu Fujitsu RX600 S5
VMware ESX v4.0 Update 2
VMmark v1.1.1
75.77@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
06/29/10
HP HP ProLiant DL580 G7
VMware ESX v4.0 Update 2
VMmark v1.1.1
75.01@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
08/24/10
Dell Dell PowerEdge R910
VMware ESX v4.0 Update 2
VMmark v1.1.1
74.34@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
07/27/10
Cisco Cisco UCS C460 M1
VMware ESXi v4.0 Update 2
VMmark v1.1.1
73.82@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
05/04/10
Fujitsu Fujitsu RX600 S5
VMware ESX v4.0 Update 2
VMmark v1.1.1
73.69@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
06/15/10
Lenovo Lenovo WQ R680 G7
VMware ESXi v4.0 Update 2
VMmark v1.1.1
73.20@50 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
07/28/10
IBM IBM System x3850 X5
VMware ESXi v4.0 Update 2
VMmark v1.1.1
71.85@49 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
04/20/10
Cisco Cisco UCS B440 M1
VMware ESXi v4.1
VMmark v1.1.1
71.13@48 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
07/27/10
IBM IBM System x3850 X5
VMware ESXi v4.0 Update 2
VMmark v1.1.1
70.78@48 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
04/06/10
Dell Dell PowerEdge R810
VMware ESX v4.0 Update 2
VMmark v1.1.1
59.21@41 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
08/10/10
Dell Dell PowerEdge M910
VMware ESX v4.0 Update 2
VMmark v1.1.1
58.37@41 tiles
View Disclosure
4 sockets
32 total cores
64 total threads
08/24/10
HP HP ProLiant DL785 G5
VMware ESX v4.0
VMmark v1.1
31.56@21 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
06/02/09
Unisys Unisys ES7000 Model 7405R
VMware ESX v4.0
VMmark v1.1
30.86@20 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
05/19/09
HP HP ProLiant DL785 G5
VMware ESX v4.0
VMmark v1.1
30.50@21 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
04/21/09
Unisys Unisys ES7000 Model 7405R
VMware ESX v3.5.0 Update 3
VMmark v1.1
29.19@19 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
04/07/09
Sun Sun Fire X4600 M2
VMware ESX v3.5.0 Update 3
VMmark v1.1
29.11@19 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
03/10/09
Unisys Unisys ES7000 Model 7405R
VMware ESX v3.5.0 Update 3
VMmark v1.1
28.97@19 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
03/05/09
HP HP ProLiant DL785 G5
VMware ESX v3.5.0 Update 3
VMmark v1.1
27.71@19 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
12/19/08
IBM IBM System x3950 M2
VMware ESX v3.5.0 Update 2
VMmark v1.1
24.62@18 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
10/02/08
Unisys Unisys ES7000 Model 7405R G1
VMware ESX v3.5.0 Update 2
VMmark v1.1
21.96@15 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
11/05/08
HP HP ProLiant DL785 G5
VMware ESX v3.5.0 Update 1
VMmark v1.1
21.88@16 tiles
View Disclosure
8 sockets
32 total cores
32 total threads
08/18/08

24 Cores

Submitter System Description VMmark Version & Score Processors Published Date
Fujitsu Fujitsu RX600 S5
VMware ESX v4.0 Update 2
VMmark v1.1.1
55.88@ 39 tiles
View Disclosure
4 sockets
24 total cores
48 total threads
10/19/10
Fujitsu Fujitsu BX960 S1
VMware ESX v4.0 Update 2
VMmark v1.1.1
52.27@35 tiles
View Disclosure
4 sockets
24 total cores
48 total threads
06/29/10
Dell Dell PowerEdge R715
VMware ESX v4.0 Update 2
VMmark v1.1.1
32.44@22 tiles
View Disclosure
2 sockets
24 total cores
24 total threads
09/21/10
HP HP ProLiant DL385 G7
VMware ESX v4.0 Update 1
VMmark v1.1.1
30.96@22 tiles
View Disclosure
2 sockets
24 total cores
24 total threads
05/04/10
HP HP ProLiant DL385 G7
VMware ESX v4.0 Update 1
VMmark v1.1.1
30.60@21 tiles
View Disclosure
2 sockets
24 total cores
24 total threads
04/20/10
HP HP ProLiant DL585 G6
VMware ESX v4.0
VMmark v1.1.1
29.95@20 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
07/14/09
Dell Dell PowerEdge R905
VMware ESX v4.0
VMmark v1.1.1
29.51@20 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
07/28/09
HP HP ProLiant BL685c G6
VMware ESX v4.0
VMmark v1.1.1
29.19@20 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
07/14/09
IBM IBM System x3850 M2
VMware ESX v3.5.0 Update 3
VMmark v1.1
20.50@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
03/24/09
IBM IBM System x3850 M2
VMware ESX v3.5.0 Update 3
VMmark v1.1
20.41@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
02/24/09
Dell Dell PowerEdge R900
VMware ESX v3.5.0 Update 3
VMmark v1.1
19.99@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
02/10/09
Inspur Inspur NF520D2
VMware ESX v3.5.0 Update 3
VMmark v1.1
19.67@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
01/27/09
Sun Sun Fire X4450
VMware ESX v3.5.0 Update 2
VMmark v1.1
19.47@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
01/13/09
IBM IBM System x3850 M2
VMware ESX v3.5.0 Update 2
VMmark v1.1
19.10@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
09/17/08
Dell Dell PowerEdge R900
VMware ESX v3.5.0 Update 3
VMmark v1.1
18.69@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
12/02/08
HP HP ProLiant BL680c G5
VMware ESX v3.5.0 Update 3
VMmark v1.1
18.64@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
03/30/09
HP HP ProLiant DL580 G5
VMware ESX v3.5.0 Update 2
VMmark v1.1
18.56@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
10/06/08
Dell Dell PowerEdge R900
VMware ESX v3.5.0 Update 2
VMmark v1.1
18.49@14 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
09/12/08
HP HP ProLiant BL680c G5
VMware ESX v3.5.0 Update 2
VMmark v1.1
16.05 @ 12 tiles
View Disclosure
4 sockets
24 total cores
24 total threads
09/23/08

 

16 Cores

Submitter
System Description VMmark Version & Score Processors Published Date
Fujitsu Fujitsu RX600 S5
VMware ESX v4.0 Update 2
VMmark v1.1.1
40.52@28 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
10/19/10
Fujitsu Fujitsu BX960 S1
VMware ESX v4.0 Update 2
VMmark v1.1.1
40.49@28 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
10/19/10
Cisco Cisco UCS B230 M1
VMware ESX v4.0 Update 2
VMmark v1.1.1
39.19@27 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
10/19/10
HP HP ProLiant BL620c G7
VMware ESX v4.0 Update 2
VMmark v1.1.1
37.92@28 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
10/19/10
Dell Dell PowerEdge R810
VMware ESX v4.0 Update 2
VMmark v1.1.1
37.28@26 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
07/27/10
Dell Dell PowerEdge M910
VMware ESX v4.0 Update 2
VMmark v1.1.1
37.11@26 tiles
View Disclosure
2 sockets
16 total cores
32 total threads
07/13/10
Fujitsu Fujitsu BX960 S1
VMware ESX v4.0 Update 2
VMmark v1.1.1
32.82@22 tiles
View Disclosure
4 sockets
16 total cores
32 total threads
06/29/10
Dell Dell PowerEdge M905
VMware ESX v4.0
VMmark v1.1.1
22.90@17 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
06/19/09
Dell Dell PowerEdge R905
VMware ESX v4.0
VMmark v1.1
22.70@16 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
05/19/09
HP HP ProLiant DL585 G5
VMware ESX v4.0
VMmark v1.1
22.11@15 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
04/24/09
HP HP ProLiant BL685 G6
VMware ESX v4.0
VMmark v1.1
20.87@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
04/24/09
HP HP ProLiant DL585 G5
VMware ESX v3.5.0 Update 3
VMmark v1.1
20.43@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
01/27/09
Dell Dell PowerEdge R905
VMware ESX v3.5.0 Update 3
VMmark v1.1
20.35@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
11/12/08
HP HP ProLiant BL685c G5
VMware ESX v3.5.0 Update 3
VMmark v1.1
19.96@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
12/09/08
Dell Dell PowerEdge M905
VMware ESX v3.5.0 Update 3
VMmark v1.1
19.91@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
11/12/08
IBM IBM Bladecenter LS42
VMware ESX v3.5.0 Update 3
VMmark v1.1
19.17@14 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
01/13/09
IBM IBM BladeCenter LS42
VMware ESX v3.5.0 Update 3
VMmark v1.1
16.81@11 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
11/12/08
Dell Dell PowerEdge R905
VMware ESX v3.5.0 Update 2
VMmark v1.1
15.35@11 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
10/08/08
Dell Dell PowerEdge M905
VMware ESX v3.5.0 Update 2
VMmark v1.1
15.09@11 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
10/01/08
Dell Dell PowerEdge R905
VMware ESX v3.5.0 Update 2
VMmark v1.1
14.84@10 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
09/17/08
HP HP ProLiant DL585 G5
VMware ESX v3.5.0 Update 1
VMmark v1.1
14.74@10 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
08/05/08
Dell Dell PowerEdge M905
VMware ESX v3.5.0 Update 2
VMmark v1.1
14.28@11 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
08/12/08
Dell Dell PowerEdge R905
VMware ESX v3.5.0 Update 1
VMmark v1.0
14.17@10 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
05/06/08
HP HP ProLiant DL580 G5
VMware ESX v3.5.0 Update 1
VMmark v1.1
14.14@10 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
09/05/08
Dell Dell PowerEdge R900
VMware ESX v3.5.0 Update 1
VMmark v1.0
14.05@10 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
07/08/08
IBM IBM System x3850 M2
VMware ESX v3.5.0
VMmark v1.0
13.16@9 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
03/26/08
Sun Sun Fire X4450
VMware ESX v3.5.0
VMmark v1.0
12.23 @ 8 Tiles
View Disclosure
4 sockets
16 total cores
16 total threads
04/25/08
Dell Dell PowerEdge R900
VMware ESX v3.5.0
VMmark v1.0
12.23@8 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
11/19/07
HP HP ProLiant DL580 G5
VMware ESX v3.0.2
VMmark v1.0
11.54@8 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
08/31/07
HP HP ProLiant BL680 G5
VMware ESX v3.0.2
VMmark v1.0
10.17@7 tiles
View Disclosure
4 sockets
16 total cores
16 total threads
08/31/07

 

12 Cores

Submitter System Description VMmark Version & Score Processors Published Date
Fujitsu Fujitsu BX924 S2
VMware ESX v4.0 Update 2
VMmark v1.1.1
40.86@30 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/19/10
HP HP ProLiant DL380 G7
VMware ESX v4.0 Update 2
VMmark v1.1.1
38.97@28 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/19/10
Dell Dell PowerEdge R710
VMware ESX v4.0 Update 2
VMmark v1.1.1
38.39@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/05/10
Fujitsu Fujitsu BX924 S2
VMware ESX v4.0 Update 2
VMmark v1.1.1
38.39@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
09/07/10
Dell Dell PowerEdge M610x
VMware ESX v4.0 Update 2
VMmark v1.1.1
38.38@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/19/10
Cisco Cisco UCS B250 M2
VMware ESX v4.0 Update 2
VMmark v1.1.1
38.04@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/19/10
SGI SGI C2005-TY15
VMware ESX v4.1
VMmark v1.1.1
36.76@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/05/10
Cisco Cisco UCS B250 M2
VMware ESX v4.0 Update 1
VMmark v1.1.1
35.83@26 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
04/06/10
Fujitsu Fujitsu RX200 S6
VMware ESX v4.0 Update 2
VMmark v1.1.1
35.09@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
08/10/10
Fujitsu Fujitsu RX300 S6
VMware ESX v4.0 Update 2
VMmark v1.1.1
35.07@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
08/10/10
Dell Dell PowerEdge M610x
VMware ESX v4.0 Update 2
VMmark v1.1.1
34.80@27 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/05/10
Dell Dell PowerEdge R710
VMware ESX v4.0 Update 2
VMmark v1.1.1
34.78@28 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
10/05/10
Dell Dell PowerEdge R710
VMware ESX v4.0 Update 2
VMmark v1.1.1
33.64@25 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
09/07/10
Fujitsu Fujitsu BX922 S2
VMware ESX v4.0 Update 1
VMmark v1.1.1
32.89@24 tiles
View Disclosure
2 sockets
12 total cores
24 total threads
04/06/10
HP HP ProLiant DL385 G6
VMware ESX v4.0
VMmark v1.1
15.54@11 tiles
View Disclosure
2 sockets
12 total cores
12 total threads
06/02/09

 

8 Cores

Submitter System Description VMmark Version & Score Processors Published Date
Fujitsu Fujitsu BX924 S2
VMware ESX v4.0 Update 2
VMmark v1.1.1
30.05@20 tiles
View Disclosure
2 sockets
8 total cores
16 total threads
10/19/10
HP HP ProLiant DL380 G7
VMware ESX v4.0 Update 2
VMmark v1.1.1
29.46@20 tiles
View Disclosure
2 sockets
8 total cores
16 total threads
10/19/10
Fujitsu Fujitsu RX300 S6
VMware ESX v4.0 Update 1
VMmark v1.1.1
28.02@18tiles
View Disclosure
2 sockets
8 total cores
16 total threads
05/04/10
Fujitsu Fujitsu BX922 S2
VMware ESX v4.0 Update 1
VMmark v1.1.1
27.99@18tiles
View Disclosure
2 sockets
8 total cores
16 total threads
05/04/10
SGI SGI C2104-TY3
VMware ESX v4.1
VMmark v1.1.1
25.67@18tiles
View Disclosure
2 sockets
8 total cores
16 total threads
09/21/10
HP HP ProLiant ML370 G6
VMware ESX v4.0 Update 1
VMmark v1.1.1
25.29@18tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/06/10
HP HP ProLiant BL490c G6
VMware ESX v4.0
VMmark v1.1.1
25.27@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/20/10
Fujitsu Fujitsu RX300 S5
VMware ESX v4.0
VMmark v1.1.1
25.16@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
11/09/09
Cisco Cisco UCS B200 M1
VMware ESX v4.0
VMmark v1.1.1
25.06@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
01/12/10
SGI SGI XE500
VMware ESX v4.0
Update 1
VMmark v1.1.1
24.56@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
03/09/10
HP HP ProLiant BL490c G6
VMware ESX v4.0
VMmark v1.1.1
24.54@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
09/22/09
SGI SGI XE270
VMware ESX v4.0 Update 1
VMmark v1.1.1
24.52@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/06/10
Lenovo Lenovo R525 G2
VMware ESX v4.0
VMmark v1.1.1
24.35@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
06/30/09
Dell Dell PowerEdge R710
VMware ESX v4.0
VMmark v1.1.1
24.27@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
09/08/09
HP HP ProLiant BL490 G6
VMware ESX v4.0
VMmark v1.1
24.24@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
05/19/09
Fujitsu Fujitsu RX200 S5
VMware ESX v4.0
VMmark v1.1.1
24.20@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
08/11/09
Sun Sun Fire X4270
VMware ESX v4.0
VMmark v1.1.1
24.18@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
09/28/09
HP HP ProLiant DL380 G6
VMware ESX v4.0
VMmark v1.1
24.15@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
05/19/09
Cisco Cisco B200-M1
VMware ESX v4.0
VMmark v1.1
24.14@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/21/09
IBM IBM Bladecenter HS22
VMware ESX v4.0
VMmark v1.1.1
24.05@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
06/30/09
Dell Dell PowerEdge R710
VMware ESX v4.0
VMmark v1.1
24.00@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/21/09
HP HP ProLiant DL370 G6
VMware ESX v4.0
VMmark v1.1
23.96@16tiles
View Disclosure
2 sockets
8 total cores
16 total threads
03/30/09
Dell Dell PowerEdge M610
VMware ESX v4.0
VMmark v1.1
23.90@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/21/09
IBM IBM System x3650 M2
VMware ESX v4.0
VMmark v1.1
23.89@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
04/27/09
Dell Dell PowerEdge R710
VMware ESX v4.0
VMmark v1.1
23.55@16tiles
View Disclosure
2 sockets
8 total cores
16 total threads
03/30/09
Inspur Inspur NF5280
VMware ESX v4.0
VMmark v1.1
23.45@17tiles
View Disclosure
2 sockets
8 total cores
16 total threads
03/30/09
Intel Supermicro 6026-NTR+
VMware ESX v3.5.0 Update 4
VMmark v1.1
14.22@10 tiles
View Disclosure
2 sockets
8 total cores
16 total threads
03/30/09
HP HP ProLiant385G5p
VMware ESX v3.5.0 Update 3
VMmark v1.1
11.28@8 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
12/30/08
HP HP ProLiant BL495cG5
VMware ESX v3.5.0 Update 3
VMmark v1.1
11.23@8 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
12/30/08
Dell Dell PowerEdge R805
VMware ESX v3.5.0 Update 3
VMmark v1.1
11.22@8 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
11/12/08
Dell Dell PowerEdge M805
VMware ESX v3.5.0 Update 3
VMmark v1.1
11.00@8 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
11/17/08
HP HP ProLiant ML370 G5
VMware ESX v3.5.0 Update 3
VMmark v1.1
9.15@7 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
10/09/08
Dell Dell PowerEdge M600
VMware ESX v3.5.0 Update 2
VMmark v1.1
8.97@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
09/24/08
Dell Dell PowerEdge 2950 III
VMware ESX v3.5.0 Update 2
VMmark v1.1
8.94@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
09/29/08
HP
HP ProLiant ML370 G5
VMware ESX v3.5.0 Update 2
VMmark v1.1
8.66@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
10/06/08
IBM IBM System x3650
VMware ESX v3.5.0 Update 1
VMmark v1.1
8.63@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
09/02/08
Dell Dell PowerEdge 2950 III
VMware ESX v3.5.0
VMmark v1.0
8.47@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
11/06/07
IBM IBM System BladeCenter HS21 XM
VMware ESX v3.5.0 Update 1
VMmark v1.1
8.44@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
09/05/08
Dell Dell PowerEdge M600
VMware ESX v3.5.0
VMmark v1.0
8.37@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
02/08/08
Sun Sun Fire X4240
VMware ESX v3.5.0 Update 1
VMmark v1.1
8.07@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
10/23/08
Dell Dell PowerEdge R805
VMware ESX v3.5.0 Update 1
VMmark v1.0
7.96@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
05/06/08
Sun Sun Fire X4240
VMware ESX v3.5.0 Update 1
VMmark v1.1
7.92@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
10/10/08
Dell Dell PowerEdge M805
VMware ESX v3.5.0 Update 2
VMmark v1.1
7.88@6 tiles
View Disclosure
2 sockets
8 total cores
8 total threads
08/12/08
Sun Sun Blade X8440
VMware ESX v3.5.0
VMmark v1.0
7.37@5 tiles
View Disclosure
4 sockets
8 total cores
8 total threads
02/04/08
Sun Sun Blade X8440
VMware ESX v3.0.2
VMmark v1.0
7.02@5 tiles
View Disclosure
4 sockets
8 total cores
8 total threads
1/08/08

 

View Historical VMmark Version 1 Results


View Withdrawn VMmark Version 1 Results


Fair Use Guidelines

  • Only official VMmark metrics and submetrics may be used in comparisons.
  • Any competitive comparison of VMmark metrics must also include a statement providing the basis for making the comparison and the date when the claim is first made. A published comparison could, for example, state the claim is based on having best VMmark result out of all results using four core systems, published as of the original publication date.
  • Comparisons of VMmark metrics and submetrics to any other benchmark metrics are not allowed. VMmark utilizes other benchmarking software as load generators and produces results which are not comparable to the original benchmark metrics.

VMmark FAQs

Note: VMmark 1.x is now permanently retired. It will remain available for download for academic purposes only. The VMmark 1.x results page will remain available for reference.

Get an accurate measurement of application performance in virtualized environments with VMmark, the industry's first virtualization benchmark for x86-based computers. For academic use only.

What is VMmark?

VMmark is the first benchmark that was designed specifically to quantify and measure the performance of virtualized environments. It features a novel tile-based scheme for measuring the scalability of consolidated workloads and provides a consistent methodology that captures both the overall scalability and individual application performance. The VMmark benchmark is built on our expertise in virtualization performance and incorporates popular workloads from application categories most commonly represented in customer data centers.

Why is there a need for a new benchmark?

Traditional server benchmarks that exist today were developed with neither virtual machines nor server consolidation in mind and focus on a single workload per server. These benchmarks do not capture the system behavior induced by multiple virtual machines and fail to provide sufficient insight into the scalability of virtual environments supporting multiple simultaneous workloads on the same server. Organizations implementing or evaluating virtualization platforms today also need a more realistic and specialized benchmark to help them compare performance and scalability of different virtualization platforms, make appropriate hardware choices and measure platform performance on an ongoing basis. Clearly, a more sophisticated approach is required to quantify a virtualization environment's performance and develop meaningful and precise metrics in order to effectively compare the suitability and performance of different hardware platforms for virtual environments. Also, there is a need for a common workload and methodology for virtualized systems so that benchmark results can be compared across different virtualization platforms.

What are some specific requirements for developing such a benchmark?

Besides the need to capture key performance characteristics of virtual systems, an appropriate virtual machine benchmark must employ realistic, diverse workloads running on multiple operating systems. Further, there is a need to define a single, easy to understand metric while ensuring that the benchmark is representative of various end user environments. The benchmark specification needs to be platform neutral and should also provide a methodical way to measure scalability so that the same benchmark can be used for small servers as well as larger servers from different hardware vendors.

Why did VMware develop VMmark?

VMware realized the need for a virtualization benchmark early on with more and more customers asking for metrics to compare different hardware platforms and configurations on which to run their virtualized environments. VMmark provides a standardized way to compare platforms that customers have come to expect from enterprise software.

Will VMmark be an industry standard? If so, what is VMware doing towards this goal?

VMware is actively working on open standards on virtualization benchmarks. In October 2006, SPEC formed a working group to develop a standard benchmark for measuring virtualization performance. This working group was formed at the request of VMware. By March 2007 the working group had agreed on the design goals and project plan, and was able to graduate to a subcommittee. Paula Smith of VMware was the chairperson of the working group and continues to chair the subcommittee. We are an active participant in the subcommittee, along with many of our major partners and a few of our competitors. Current participants include: AMD, Dell, Fujitsu Siemens, Hewlett-Packard, Intel, IBM, Microsoft, Red Hat, Sun Microsystems, SWsoft and VMware. Additional information on the subcommittee can be found at: http://www.spec.org/specvirtualization/

How was VMmark developed?

Nearly two years of engineering effort has gone into the design and implementation of the benchmark culminating in a private beta release in December, 2006 and the current public beta (launched in July 2007) as a part of VMware’s normal product release cycle. In the effort to build a reliable and robust benchmark that truly represents customer environments, VMware has taken into account extensive survey data from its customers to understand what types of applications and configurations are typically run in virtualized environments. VMware has also worked closely with its partners to design and implement the benchmark across various software and hardware platforms. Throughout the course of the benchmark development, VMware has also evaluated numerous workloads and run hundreds of experiments to make sure that the benchmark is reliable and robust.

What is a tile?

A tile is a collection of six diverse workloads concurrently executing specific software. Running on one of two separate operating systems, each workload runs in its own virtual machine and executes applications found in all the world's datacenters. Included in a single tile are a web server, file server, mail server, database, java server, as well as an idle machine. Each virtual machine in a tile is tuned to use only a fraction of the system's total resources. As a tile, the aggregate of all six workloads normally utilizes less than the full capacity of modern servers. Therefore, the complete saturation of a system's resources and accurate measurement of server performance with VMmark require the execution of multiple tiles simultaneously.

How does VMmark work?

VMmark is designed as a tile-based benchmark consisting of a diverse set of workloads commonly found in the datacenter, including database server, file server, web server, and Java server. The workloads comprising each tile are run simultaneously in separate virtual machines at load levels that are typical of virtualized environments. The performance of each workload is measured and then combined with the other workloads to form the score for the individual tile. Multiple tiles can be run simultaneously to increase the overall score. This approach allows smaller increases in system performance to be reflected by increased scores in a single tile and larger gains in system capacity to be captured to adding additional tiles. (Future work will present data to demonstrate the ability of multiple tiles to measure performance of larger multiprocessor systems using a well-defined reference score). Each workload within a VMmark tile is constrained to execute at less than full utilization of its virtual machine. However, the performance of each workload can vary to a degree with the speed and capabilities of the underlying system. For instance, disk-centric workloads might respond to the addition of a fast disk array with a more favorable score. These variations can capture system improvements that do not warrant the addition of another tile. However, the workload throttling will force the use of additional tiles for large jumps in system performance. When the number of` tiles is increased, workloads in existing tiles might measure lower performance. However, if the system has not been overcommitted, the aggregate score, including the new tile, should increase. The result is a flexible benchmark metric that provides a relative measure of the number of workloads that can be supported by a particular system as well as the overall performance level within the virtual machines.

Who will use VMmark?

VMmark was developed as a useful tool for hardware vendors, system integrators, and customers to evaluate the performance of their systems. Many customers will not run the benchmark themselves, but rather rely on published VMmark scores from their hardware vendors to make purchasing and configuration decisions for their virtualization infrastructure.

What are the use cases for VMmark?

The main use-case for VMmark is to compare the performance of different hardware platforms and configurations. Organizations implementing or evaluating virtualization platforms today will use VMmark for comparing performance and scalability of different virtualization platforms, making appropriate hardware choices and for measure platform performance on an ongoing basis. It is also important to note that VMmark is neither a capacity planning tool nor a sizing tool. It does not provide deployment guidelines for specific applications. Rather VMmark is meant to be representative of a general-purpose virtualization environment. The virtual machine configurations and the software stacks inside the virtual machines are fixed as part of the benchmark specification. Recommendations derived from VMmark results will capture many common cases; however, specialized scenarios will likely require individual measurement.

What are the benefits of VMmark?

With VMmark, organizations now have a robust and reliable and benchmark that captures the key performance characteristics of virtual systems; is representative of end user environments running multiple workloads; is platform neutral and provides a methodical way to measure scalability so that the same benchmark can be used across different hardware platforms. With VMmark, organizations now finally have a virtualization benchmark that works. With VMmark, organizations can compare performance and scalability of different virtualization platforms, make appropriate hardware choices and monitor virtual machine performance on an ongoing basis.

How do I interpret a VMmark score?

A VMmark score is a measure of the performance of both the hardware and virtualization layers of a virtualization platform. Each score represents the performance relative to a fixed reference platform. Though the reference platform is from a previous hardware generation, making comparisons between it and newer systems not very meaningful, its use allows for easy comparisons between various contemporary platforms and configurations. A score is obtained by measuring the aggregate throughput achieved by multiple workloads executing simultaneously on the virtualization platform. A set of six specific workloads, each in its own virtual machine, are run for a specific length of time. These six workload virtual machines are collectively defined as a VMmark tile. During a VMmark run each individual workload generates a raw throughput metric -- for example, the throughput of the database workload is measured in transactions per minute. Upon completion of a run each of these raw metrics is normalized with respect to the reference platform then the geometric mean of the normalized individual scores is computed. The resulting score is a measure of the throughput of the tested platform relative to the reference platform. In addition to this score, each VMmark result also includes the number of VMmark tiles used in the benchmark run. With increasing system resources (for example, more CPU cores) multiple VMmark tiles (that is, complete sets of the six workload virtual machines) can be run simultaneously in order to fully utilize a virtualization platform. After calculating the score for each tile the individual tile scores are added together to produce the VMmark score. A VMmark full disclosure report also includes the raw and normalized results for each underlying workload as well as complete details of the virtualization platform configuration. In some cases, studying the workload metrics along with the platform configuration can provide insight into system performance and scaling. For a more detailed description of the benchmark scoring methodology see the VMmark Benchmarking Guide.

How do I compare VMmark scores across different virtualization platforms?

A higher VMmark score implies that a virtualization platform is capable of sustaining greater throughput in a mixed workload consolidation environment. A larger number of VMmark tiles used to generate the benchmark means that the platform supported more virtual machines during the benchmark run. Typically, a higher benchmark score requires a higher number of tiles. If two different virtualization platforms achieve similar VMmark scores with a different number of tiles, the score with the lower tile count is generally preferred. The higher tile count could be a sign that the underlying hardware resources were not properly balanced. Studying the individual workload metrics is suggested in these cases.

How is VMmark version 1.1 different from version 1.0?

In order to address the growing prevalence of 64bit applications and OSs, in VMmark 1.1 the Java server, database server, and web server workloads within the tile are 64-bit. The mail server, file server, and standby server remain 32-bit and unchanged from VMmark 1.0.

Are VMmark 1.1 results comparable to VMmark 1.0 results?

Yes, the results are directly comparable. The underlying virtual hardware definitions and load levels for each workload have not changed in VMmark 1.1.

Performance Blog

Learn about the performance of virtualized environments at the VROOM! Blog

Read Now