Technical data
Solution Architectural Overview
VMware Horizon View 5.3 and VMware vSphere for up to 2,000 Virtual
Desktops Enabled by Brocade Network Fabrics, EMC VNX, and EMC Next-
Generation Backup
75
the server is being actively used, vSphere might resort to swapping portions
of a virtual machine's memory.
Non-Uniform Memory Access (NUMA)
vSphere uses a NUMA load-balancer to assign a home node to a virtual
machine. Memory access is local and provides the best performance
possible because memory for the virtual machine is allocated from the
home node. Applications that do not directly support NUMA benefit from
this feature.
Transparent page sharing
Virtual machines running similar operating systems and applications
typically have identical sets of memory content. Page sharing allows the
hypervisor to reclaim the redundant copies and keep only one copy,
which frees up the total host memory consumption. If most of your
application virtual machines run the same operating system and
application binaries, the total memory usage can be reduced to increase
consolidation ratios.
Memory ballooning
By using a balloon driver loaded in the guest operating system, the
hypervisor can reclaim host physical memory if memory resources are
under contention with little to no impact on the application’s
performance.
This section provides guidelines for allocating memory to virtual machines,
which take into account vSphere memory overhead and the virtual
machine memory settings.
vSphere memory overhead
There is some associated overhead for the virtualization of memory
resources. The memory space overhead has two components.
The system overhead for the VMkernel
Additional overhead for each virtual machine
The amount of additional overhead memory for the VMkernel is fixed,
whereas the amount of additional memory for each virtual machine
depends on the number of virtual CPUs and the configured memory for
the guest operating system.
Allocating memory to virtual machines
The proper sizing of memory for a virtual machine in VSPEX architectures is
based on many factors. Because of the number of application services
and use cases available, determining a suitable configuration for an
environment requires creating a baseline configuration, testing, and
making adjustments, as discussed in this paper. In this solution, each virtual
machine is assigned two GB of memory in fixed mode, as listed in Table 6.
Memory
configuration
guidelines