Host NUMA Topology

Host NUMA Topology: A pNUMA topology (physical NUMA topology) is the topology of the host NUMA nodes predefined by the CPU vendor based on the host NUMA architecture.

Definitions

• Non-Uniform Memory Access (NUMA): Non-uniform memory access (NUMA) is a computer memory design where the memory access time depends on the memory location relative to the CPU. Under NUMA, a processor can access its own local memory faster than non-local memory and thus improves VM performance.
• pNUMA Node: A pNUMA node (physical NUMA node) is a host NUMA node predefined based on the host NUMA architecture. It is used to manage the CPUs and memory of the host. A host can have one or more pNUMA nodes. A pNUMA node primarily consists of one or more physical CPU cores (pCPU) and local memory.
• vNUMA Node: A vNUMA node (virtual NUMA node) is generated by passing-through associated pNUMA nodes via CPU pinning. It is used to manage the CPUs and memory of a virtual machine. A vNUMA node primarily consists of one or more virtual CPU cores (vCPU) and local memory.
• vNUMA Topology: A vNUMA topology (virtual NUMA topology) is the topology of VM NUMA nodes generated by passing-through associated pNUMA nodes via CPU pinning.
• Local Memory: Local memory is the memory that a CPU (pCPU or vCPU) accesses through the Uncore iMC (Integrated Memory Controller) of the same NUMA (pNUMA or vNUMA) node. Compared with accessing non-local memory, accessing local memory has lower latencies.

Functionality Principle

After adding the host, ZSvirt supports viewing the host's pNUMA topology and configuring vNUMA for virtual machines running on the host based on this topology.

ZSvirt Virtual machine vNUMA configuration is achieved through CPU pinning, which strictly associates the virtual machine's vCPU with the host's pCPU, allocating specific pCPUs to the virtual machine. During vNUMA configuration, all vCPUs of the virtual machine are pinned to pCPUs, and each vCPU's pinned pCPUs are located within the same pNUMA node.

After vNUMA configuration, the virtual machine directly passes through the associated host pNUMA node topology, generating one or more vNUMA nodes that form the virtual machine's vNUMA topology. Virtual machine vCPUs prioritize accessing local memory within the same node based on the vNUMA topology.

pNUMA Topology

Go to the target host's Overview, and click View pNUMA Topology in the hardware overview information box. ZSvirt host pNUMA topology information is as follows:

• Displays all pNUMA nodes of the host and the virtual machine information associated with each node.
• Total memory is the local memory of the pNUMA node that can be directly accessed by the pCPU.
• Free memory is the local free memory of the pNUMA node that can be directly accessed by the pCPU.
• Both total memory and free memory are based on the actual hardware physical memory capacity of the pNUMA node.