Overview

This section provides various general best practices for sizing your VDI deployment.

Platform configurations

With several configurations to choose from, consider these basic differences:

• Density Optimized—This configuration provides a good balance of performance and scalability for various general-purpose VDI workloads.
• Virtual Workstation—This configuration provides the highest levels of performance for more specialized VDI workloads, which means it can be used with ISV and high-end computing workloads.

CPU

User density and graphics considerations include:

• Architectures with Sapphire Rapids processors:

• Task workers—2.4 users per core (for example, 38 task users with dual eight-core processors)

• Graphics:

• For high-end graphics configurations with NVIDIA vWS graphics enabled, choose higher clock speeds over higher core counts. Many applications that benefit from high-end graphics are engineered with single-threaded CPU components. Higher clock speeds benefit users more in these workloads.
• For NVIDIA vPC configurations, use higher core counts over faster clock speeds to reduce oversubscription.

Note: Most graphics configurations do not experience high CPU oversubscription because vGPU resources are likely to be the resource constraint in the appliance.

Memory best practices

Memory allocation and configuration guidance:

• Do not overcommit memory when sizing because memory is often not the constraining resource. Overcommitting memory increases the possibility of performance degradation if contention for memory resources, such as swapping and ballooning of memory, occurs. Overcommitted memory can also affect storage performance when swap files are created.
• Populate memory in units of eight DIMMs per CPU to yield the highest performance. Dell PowerEdge servers using 4th Generation Intel Xeon Scalable processors have eight memory channels per CPU, which are controlled by four internal memory controllers, each handling two memory channels. To ensure that your environment has the optimal memory configuration, use a balanced configuration, where each CPU supports a maximum of 16 DIMMs (or 32 DIMMs for a dual-CPU server). The most effective configuration is 16 DIMMs (8 per processor) with Intel Xeon Scalable processors.

NVIDIA vGPU considerations best practices

When sizing and configuring solutions requiring graphics accelerators, consider that:

• vPC licenses support up to 2 GB of frame buffer and up to two 4K monitors, or a single 5K monitor to cover most traditional VDI users. Maximum node density for graphics-accelerated use can typically be calculated as the available frame buffer per node divided by the frame buffer size.
• The addition of GPU cards does not necessarily reduce CPU utilization. Instead, it enhances the user experience and offloads specific operations best performed by the GPU.
• Dell Technologies recommends using the BLAST protocol for vGPU enabled desktops. NVIDIA GPUs are equipped with encoders that support BLAST.
• Virtual Workstations are typically configured with at least 2 GB video buffer.

Sizing considerations

General best practices for sizing your deployment:

• User density—If concurrency is a concern, calculate how many users need the environment during the peak utilization. For example, if only 80 percent are using the environment at any time, the environment must support only that number of users (plus a failure capacity).
• Disaster recovery (DR)—For DR planning, implement a dual or multi-site solution, as recommended by Dell Technologies. The goal is to keep the environment online and, if there is an outage, to perform an environment recovery with minimum disruption to the business.
• Management and compute clusters—Dell Technologies recommends that you separate the management and compute layers into separate clusters. You can use a combined management and compute cluster for small environments. Consider using the PowerEdge R660 platform to reduce data center footprint when creating a management cluster for a large-scale deployment. With larger storage and graphics capabilities, Dell Technologies recommends R760 for compute clusters.
• Network isolation—When designing for larger-scale deployments, consider physically separating the management and VDI traffic from the vSAN traffic for traffic isolation and to improve network performance and scalability. This design illustrates a two-NIC configuration per appliance with all the traffic separated logically using VLAN.
• FTT—Dell Technologies recommends sizing storage with NumberOfFailuresToTolerate (FTT) set to 1, which means that you must double the amount of total storage to accommodate the mirroring of each VMDK.
• Slack space—Dell Technologies recommends adding an additional 30 percent of slack space to prevent automatic rebalancing of storage, which impacts performance. Automatic balancing occurs when the storage reaches 80 percent of the full threshold. Therefore, 70 percent is recommended to reserve a 10 percent buffer.
• All-Flash compared with hybrid:

• Hybrid and all-flash configurations have similar performance results. Because hybrid uses spinning drives, consider the durability of the disks.
• Only all-flash configurations offer deduplication and compression for vSAN. Dell Technologies recommends all-flash configurations for simplified data management.
• All-flash configurations need considerably less storage capacity than hybrid configurations to produce similar FTT, as shown in the following table.

Table 9.      FTT comparisons

Note: The Citrix Design Decision: Designing StoreFront and Multi-Site Aggregation provide more details about multi-site design considerations for Citrix Virtual Apps and Desktops.