The VDI market is heating up and it’s a real Battle Royale out there between all of the different VDI reference architectures that promise to deliver more VDI for less Moolah. There have been at least 4 major reference architectures published by different vendors in 2014 for Citrix VDI. All providing a scalable building block for a few thousand users, and that can be scaled up from there. But not all of the reference architectures are created equal. This article will compare different vendors solutions based on publicly available reference architecture documents and data and contrast traditional converged platforms to what can be delivered by hyperconverged web-scale architecture. Let the battle begin.
Below I will compare all of the traditional converged infrastructure solutions RA’s to the only hyper-converged option that has a Citrix Validated Solution, Nutanix (my employer). The performance results between the different options have been validated by each company using LoginVSI. The data is based solely on the details of the RA’s and calculations by Martijn Bosschaart, Senior System Engineer at Nutanix, who also covered the comparison here.
The Reference Architectures that will battle it out in the Battle Royale are as follows:
Cisco + EMC VSPEX (1000 mixed users)
FlexPod (2000 mixed users)
vBlock (2500 VDI users)
Cisco UCS Mini + Nimble
Nutanix Citrix Validated Solution (1000 users HSD or 1000 users VDI)
Let’s see how they compare to the Hyper-Converged option with Nutanix Web-Scale Converged Infrastructure. Comparison costs in Euro’s, adjust power and cooling costs for your market. All RA’s used LoginVSI to validate performance results.
Round One: VSPEX, Fight!
Round Two: vBlock, Fight!
Round Three: FlexPod, Fight!
Round Four: Cisco UCS Mini + Nimble, Fight!
Battle RA Royale Winner: Nutanix. Based on the publicly available reference architectures current at the time this article is published.
What this demonstrates is a fairly compelling reason to take a look at hyper-converged web-scale solutions, such as the ones Nutanix provide, for your VDI (of any kind) projects, if they are Citrix or VMware Horizon based. However as with any vendor comparisons you should take the results with a grain of salt unless you’ve verified them yourself, with a workload similar to what you expect to run. While all care has been taken to make the comparisons valid, using similar workload modeling and verification techniques published in the RA’s, there could be errors. Also this is a point in time comparison and software and hardware changes fairly rapidly, so adjust any results with software/hardware combinations that are newer if necessary. When doing your own comparisons get updated data from your chosen vendors.
This post first appeared on the Long White Virtual Clouds blog at longwhiteclouds.com. By Michael Webster +. Copyright © 2012 – 2014 – IT Solutions 2000 Ltd and Michael Webster +. All rights reserved. Not to be reproduced for commercial purposes without written permission.
One of the additional factor is the HR cost required to plan, design, deploy and operate. And then again comes the refresher cycle.
Definitely agree with that and the traditional converged solutions have a much higher overhead in those areas as well, especially when the inevitable refresh comes along, and on the complexity training, planning, designing and deployment front. Here is a good example of that – https://twitter.com/hdex/status/56791210517045657….
[…] The above solution delivers power consumption for power user desktops for < 5W per desktop and < 2.5W for task workers. Take a look at the Nutanix VDI Assurance program, go through the Nutanix Product Info and Tech Papers, and check out the Case Studies. As always your feedback and comments are appreciated. Let me know your thoughts on scalable, large scale VDI design. If you want to see how the Nutanix solution compares to other reference architectures check out Battle RA Royale: More VDI For Less Moolah. […]