Go Premium for a chance to win a PS4. Enter to Win

x
  • Status: Solved
  • Priority: Medium
  • Security: Public
  • Views: 135
  • Last Modified:

I have a VM and a Standalone server I want to compare performance. What is the best way/tool?

I have a VM and a Standalone server I want to compare performance.  What is the best way/tool?
The VM is acting a little slower than the standalone.  They are configured differently, but before I start changing the VM
configuration I'd like to confirm:

Standalone                                                   VM
2012 R2                                                        2012 R2
64GB RAM                                                   6GB RAM
2.60GHz 2 processor                                 2 virtual sockets and 2 cores per socket
0
operationsIT
Asked:
operationsIT
  • 3
  • 2
  • 2
  • +1
1 Solution
 
Lee W, MVPTechnology and Business Process AdvisorCommented:
Reduce the number of processors on the VM.

Please read:
http://www.zdnet.com/article/virtual-cpus-the-overprovisioning-penalty-of-vcpu-to-pcpu-ratios/

Personally, I start with 2 on everything and only increase them as performance needs dictate.
0
 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
You will ALWAYS find the Physical Computer performs better than the Virtual!

Also you should always use Sockets, not cores, unless you have a licensing requirement for cores!

What do you want to test, CPU, Memory, Disk, Networking?

Where is the bottleneck, and what is slower ?

vSMP (virtual SMP) can affect virtual machine performance, when adding too many vCPUs to virtual machines that cannot use the vCPUs effectly, e.g. Servers than can use vSMP correctly :- SQL Server, Exchange Server.

This is true, many VMware Administrators, think adding lots of processors, will increase performance - wrong! (and because they can, they just go silly!). Sometimes there is confusion between cores and processors. But what we are adding is additional processors in the virtual machine.

So 4 vCPU, to the VM is a 4 Way SMP (Quad Processor Server), if you have Enterprise Plus license you can add 8, (and only if you have the correct OS License will the OS recognise them all).

If applications, can take advantage e.g. Exchange, SQL, adding additional processors, can/may increase performance.

So usual rule of thumb is try 1 vCPU, then try 2 vCPU, knock back to 1 vCPU if performance is affected. and only use vSMP if the VM can take advantage.

Example, VM with 4 vCPUs allocated!

My simple laymans explaination of the "scheduler!"

As you have assigned 4 vCPUs, to this VM, the VMware scheulder, has to wait until 4 cores are free and available, to do this, it has to pause the first cores, until the 4th is available, during this timeframe, the paused cores are not available for processes, this is my simplistic view, but bottom line is adding more vCPUs to a VM, may not give you the performance benefits you think, unless the VM, it's applications are optimised for additional vCPUs.

See here
http://www.vmware.com/resources/techresources/10131

see here
http://www.gabesvirtualworld.com/how-too-many-vcpus-can-negatively-affect-your-performance/

http://www.zdnet.com/virtual-cpus-the-overprovisioning-penalty-of-vcpu-to-pcpu-ratios-4010025185/

also there is a document here about the CPU scheduler

www.vmware.com/files/pdf/perf-vsphere-cpu_scheduler.pdf

https://blogs.vmware.com/vsphere/2013/10/does-corespersocket-affect-performance.html
0
 
ZberteocCommented:
The most important parameter in that compare is 64GB memory vs 6GB memory. I know it can be changed on VM but SQL server needs as much memory as possible to the extent that all the databases can be actually stored in memory, which would be an ideal situation. Imagine never have to go to disc, really.

With VM the advantages are not in terms of performance but rather in high availability and disaster recovery. VMs can be moved around, they have automatic failover processes, scalability capabilities that come with the virtual environment configuration.
0
Has Powershell sent you back into the Stone Age?

If managing Active Directory using Windows Powershell® is making you feel like you stepped back in time, you are not alone.  For nearly 20 years, AD admins around the world have used one tool for day-to-day AD management: Hyena. Discover why.

 
Lee W, MVPTechnology and Business Process AdvisorCommented:
I don't see anything referencing SQL in the question... RAM does play a huge factor in performance, often more than CPU.  BUT, it depends on what the workload is.  

Also, another KEY advantage in virtualization is resource utilization.  OFTEN CPUs sit IDLE, doing NOTHING.  By virtualizing, you reduce overall hardware requirements (which reduces costs in terms of required space for systems, electric used, warranty requirements, overall system count, and other areas that in turn maximizes your investment).  

Virtualization, as previously stated, *WILL* be slower on equivalent hardware than a direct install, but the performance hit shouldn't be TOO much if things are properly configured.  If you have a workload that ABSOLUTELY REQUIRES high performance, then a direct install to hardware is preferable... but if you look at upgrades from older systems, most newer systems, virtualized will STILL be more powerful than the older system you upgraded from.  Again, if you configured it properly.
0
 
operationsITAuthor Commented:
Great input.  The two servers are each running Lotus Notes so a question would be if you think it can handle vSMP?  

We are noticing it more on things when interacting i.e opening windows explorer, etc.
Should I step back on processors first as it sounds like people are leaning toward processor?
0
 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
Yes, Lotus Notus is SMP aware.

If you are expecting the physical server to be faster than the virtual server - this is not correct.

Is the performance of the virtual server affecting service, e.g. Impacting Service ?

At present you are comparing Apples and Pear!

64GB versus 6GB Lotus Notes Server.

How many users ? (concurrent).

I would start with 4 CPUs (vCPU - sockets not cores) and at least 8GB-12GB RAM.

But comparing to a physical server, it's ALWAYS going to be faster!

You don't mention storage, what is the storage on the Host OS ?
0
 
operationsITAuthor Commented:
That is my concern as currently the VM is slower.  Both servers have half the mailboxes and roll over to the other for HA in the event of an issue.

The VM has a OS on a SAN data store

I will try your suggestions.  I wasn't sure if I should be looking at memory or processor first, but do understand Apple to Pear
0
 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
I would look at the performance charts in vCenter Server, are there any visible bottlenecks ?

Please see my EE Article

HOW TO:  Performance Monitor vSphere 4.x or 5.0

But comparing physical versus virtual, physical will always win! BUT, its whether it affects service!
0
 
ZberteocCommented:
Well, it came in my list even though it is set to be SQL related only. Sometimes it happens, EE glitch, and I assumed it is about SQL under VM environment. Fell free to ignore.
0

Featured Post

Simplify Active Directory Administration

Administration of Active Directory does not have to be hard.  Too often what should be a simple task is made more difficult than it needs to be.The solution?  Hyena from SystemTools Software.  With ease-of-use as well as powerful importing and bulk updating capabilities.

  • 3
  • 2
  • 2
  • +1
Tackle projects and never again get stuck behind a technical roadblock.
Join Now