Top Ways to Ensure Peak Performance with Citrix
January 23, 2023
Despite the location, remote and office-based employees need reliable digital applications and infrastructure to complete their duties efficiently and meet business demands.
Keeping Up With 1,200 Toggles Per Day
The VDI and DaaS spaces continue to grow as virtual work environments become the norm. For example, in many cases, applications like Microsoft Teams and Slack replace in-person communication and enable instant connection from anywhere to anywhere—if the app works.
But what happens when it doesn’t? Research shows the average knowledge worker toggles between apps 1,200 times in a single day—that’s five working weeks a year spent bouncing from app to app and back.
Making sure your environments stay at peak level and applications are always available for use is no small task. Winning enterprises like Citrix know better than anyone the importance of maintaining digital workspaces and guaranteeing the quality of their products.
Blair Parkhill, our Director of Products at Login VSI, and Rody Kossen, Senior Principal Quality Engineer at Citrix, recently met to discuss the importance of capacity planning and how Citrix uses Login Enterprise to maximize digital environments and their products.
Here are a few learnings from the discussion:
Why is capacity planning research and work so important?
We have seen Citrix evolve over many decades. Their solutions have gotten smarter and faster, covering many types of use cases and bringing performance and excellent end-user experience to their customers.
Login Enterprise has evolved along with Citrix to provide value beyond load testing and becoming much more than a benchmarking tool. In the context of virtual desktops and remote applications, there are three main areas Login Enterprise covers:
- Continuous performance monitoring – From a proactive stance, you can pinpoint when things are trending in the wrong direction, like when user experience starts to slow, an application is unavailable, or scalability changes.
- Optimize costs and avoid budget overruns – Eliminate wasted spending by avoiding surprise costs in the cloud, determine and optimize cost per user, and spot areas for potential savings.
- Manage capacity and plan for change – Quickly determine the suitable trade-off between density and performance and detect when upgrades are needed to maintain or optimize existing environments.
How Citrix Leverages Login Enterprise
Use case 1: Size and scale considerations for Cloud Connectors.
The Citrix Cloud Connector unlocks the advantages of cloud management by bridging on-prem and cloud deployments without requiring complex networking or infrastructure configuration. Citrix offers a size and scale considerations guide for Cloud Connectors that indicate sizing suggestions, but how did they determine their recommendations?
They performed rigorous testing like:
- Session login/launch storm to simulate what happens with a high volume of logon periods
- VDA registrations storm and VDA power action storm
- Non-rendezvous connections using Login VSI’s real-user workloads to simulate high network traffic and understand how the cloud connector performs.
“This is one of the areas where you can really utilize a tool like Login Enterprise for replacing real users with workloads to understand scaling and sizing. It is always good to test for your specific situation, but this guide helps to set a benchmark. Then, you can take it a step further by simulating your workloads, and lastly, test your environment and monitor to ensure everything is going well,” says Rody.
Use case 2: Sizing VDA Instances on Google Cloud Compute Engine.
There are many cloud options, whether Amazon, Google, Microsoft Azure, Oracle, or IBM Solutions. Regardless of your chosen solution, it is critical to evaluate which is the right for you as picking the wrong instance will impact scalability, cost, and performance.
Over the past year, Login VSI has worked with Citrix on a study they conducted to determine single instance scalability and cost guidance for enterprises deploying Citrix VDAs on Google Cloud Compute Engine.
Here’s what the findings from the Citrix study determined:
- For a large percentage of use cases (workloads), the performance of a Citrix VDA tends to be limited by CPU vs. disk or network.
- The best end-user experience was provided by the latest processors available on Google Cloud at the time of publication. These are available in the N2, N2D, and C2 instance families and leverage Intel’s Cascade Lake and AMD’s Milan processors.
- The 4-vCPU and 8-vCPU instance sizes delivered the highest density and lowest costs per user.
- The N2D-Standard-8 instance type (with the AMD Milan processor) was the most cost-effective for our heavy test workload.
- With the latest processors, the storage type used for persistent disk does not have a material impact on instance scalability.
- While not explicitly tested as part of this study, workloads that require a GPU must run on N1 instance types. Where GPU acceleration is a requirement, leveraging Skylake processors and Premium SSD persistent disk storage will likely yield the best performance and highest scalability.
To conduct this study, Citrix worked closely with Login VSI to use our scoring system called the EUX score. The EUX score quantifies the responsiveness of a user’s experience within a desktop or application session.
According to Citrix, “We recommend testing your workloads in Google Cloud before committing to a specific architecture. You can leverage Login Enterprise tool to create a custom workload that will approximate your user’s daily activities and provide a EUX score to help you gauge their experience.”