6.5.1

Table Of Contents
Using NUMA Systems with ESXi 14
ESXi supports memory access optimization for Intel and AMD Opteron processors in server architectures
that support NUMA (non-uniform memory access).
After you understand how ESXi NUMA scheduling is performed and how the VMware NUMA algorithms
work, you can specify NUMA controls to optimize the performance of your virtual machines.
This chapter includes the following topics:
n
“What is NUMA?,” on page 107
n
“How ESXi NUMA Scheduling Works,” on page 108
n
“VMware NUMA Optimization Algorithms and Seings,” on page 109
n
“Resource Management in NUMA Architectures,” on page 110
n
“Using Virtual NUMA,” on page 110
n
“Specifying NUMA Controls,” on page 111
What is NUMA?
NUMA systems are advanced server platforms with more than one system bus. They can harness large
numbers of processors in a single system image with superior price to performance ratios.
For the past decade, processor clock speed has increased dramatically. A multi-gigaher CPU, however,
needs to be supplied with a large amount of memory bandwidth to use its processing power eectively.
Even a single CPU running a memory-intensive workload, such as a scientic computing application, can be
constrained by memory bandwidth.
This problem is amplied on symmetric multiprocessing (SMP) systems, where many processors must
compete for bandwidth on the same system bus. Some high-end systems often try to solve this problem by
building a high-speed data bus. However, such a solution is expensive and limited in scalability.
NUMA is an alternative approach that links several small, cost-eective nodes using a high-performance
connection. Each node contains processors and memory, much like a small SMP system. However, an
advanced memory controller allows a node to use memory on all other nodes, creating a single system
image. When a processor accesses memory that does not lie within its own node (remote memory), the data
must be transferred over the NUMA connection, which is slower than accessing local memory. Memory
access times are not uniform and depend on the location of the memory and the node from which it is
accessed, as the technology’s name implies.
Challenges for Operating Systems
Because a NUMA architecture provides a single system image, it can often run an operating system with no
special optimizations.
VMware, Inc.
107