Read Latency on Virtual desktops

We have several users complaining of slowness on their virtual desktops.  When looking at monitoring in VSphere, I notice high spikes of read latency.  Write latency, no issues.  The virtual machines are 1 CPU, 2 Cores, 32-bit windows 7 machines with vmagent 5.3.5.  Hosts are ESX Cisco UCS boxes running 5.5.  

Any suggestions
Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

Andrew Hancock (VMware vExpert / EE Fellow)VMware and Virtualization ConsultantCommented:
Have you observed this slowness, and is it acceptable, and affecting service and users expectations ?

Is it worse now, that when you qualified the virtual machines, at Implementation.

We always find users complain of slowness!

This is often the issue with Virtual Machine, and Windows 7 Virtual Desktops, and it can be overcome, by changing the datastore to a All Flash, Hybrid Flash, or using Flash Cache, such as FVP -

What underlying datastore are you using ? All Flash ?

We've been using and deploying/implenting Fusion-IO products since 2008/2009, Fusion-IO have come along way, and now their products are OEM and rebranded by HP and Dell.

We have been using the IO-DriveDuo 640GB, sized accordingly for the number of VDI desktops required. Fusion IO has been acquired now by SanDisk

FusionIO IO-DriveDuo 640GB
(~200,000 IOPS and >800MB/s throughput per card)

and we now also use all flash arrays, Tegile Systems, or we use which its before the spinning rust.

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
FloRod621Author Commented:
We use a vendor brand SAN with fiber channels. We have 200 virtual machines.  I've tried to move the affected VM to another datastore and same result. I've been monitoring this same virtual machine and in a 1 hour period, it spike to 359ms one time and another to alittle over 100ms. Again, only read, write never spikes over 10-20ms.  We currently have 4 datastores with DRS turned on.  It's roughly 5-10 users out of the 200.  Different Host and Different Datastores.  Too many variables, hence the reason I'm asking here...
Andrew Hancock (VMware vExpert / EE Fellow)VMware and Virtualization ConsultantCommented:
What are these VMs doing ?
FloRod621Author Commented:
I would say simple operational tasks.  The affected folks are business, not IT or anything like that.  They might have several office apps open at the same time, IE, nothing major really.
It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today

From novice to tech pro — start learning today.