Specifications
Best Practices for Virtualizing and Managing Exchange 2013
45
45
reports client access and server usage information of Exchange Server deployments. The reports and
proposals provided by the MAP toolkit include a server consolidation report, server consolidation
proposal, workload discovery report, and cost savings and ROI assessment. The information provided in
these reports and proposals can be used to consolidate Exchange workloads, better utilize hardware
resources, and determine licensing needs.
Exchange 2013 Server Role Requirements Calculator
Before an Exchange 2013 deployment, whether physical or virtual, accurate capacity planning and sizing is
imperative for success. The Exchange Product Team has produced a significant amount of information and
guidance to help with the sizing of different Exchange 2013 roles. Using this guidance in conjunction with
the best practices and recommendations in this paper can help you to better plan and deploy an
Exchange 2013 infrastructure.
Best Practices and Recommendations
For detailed sizing guidance for Exchange 2013, refer to Sizing Exchange 2013 Deployments on
the Exchange Team Blog. In addition, the Exchange 2013 Server Role Requirements Calculator can
help to accelerate the sizing decisions for Exchange 2013 deployments across both physical and
virtual infrastructures.
Exchange 2013 Virtual Machine CPU Considerations
This subsection discusses Non-Uniform Memory Access from the virtual machine perspective.
Best Practices and Recommendations
It is important to note that Exchange 2013 as an application is not NUMA-aware. However,
when sizing a virtual machine, you must still understand the underlying physical NUMA topology
to ensure the highest levels of performance at the guest level.
Non-Uniform Memory Access – Virtual Machine Perspective
In Windows Server 2012, NUMA is extended to the virtual environment (virtual NUMA) by making virtual
NUMA topology available to the guest operating systems. High-performance applications support NUMA
and use the computer’s NUMA topology to increase performance by considering NUMA when scheduling
threads or allocating memory. Therefore, by reflecting the underlying NUMA topology into virtual
machines, organizations can maximize performance gains from running NUMA-aware workloads in
virtualized farm environments on NUMA. Exchange 2013 is not a NUMA-aware workload, but it
appreciates NUMA to the same level as any other non-NUMA-aware application.
To identify and adapt to the virtual NUMA topology within the virtual machines, the NUMA-aware guest
operating system and applications use their inherent NUMA performance optimizations. In this way with