Chapter 3. Requirements for NFV
Before you deploy your network functions virtualization (NFV) in a Red Hat OpenStack Services on OpenShift (RHOSO) environment, become familiar with the hardware and software requirements.
3.1. Tested NICs for NFV Copy linkLink copied to clipboard!
For a list of tested NICs for NFV, see the Red Hat Knowledgebase solution Network Adapter Fast Datapath Feature Support Matrix.
Use the default driver for the supported NIC, unless you are configuring NVIDIA (Mellanox) network interfaces. For NVIDIA network interfaces, you must specify the kernel driver during configuration.
- Example
- In this example, an OVS-DPDK port is being configured. Because the NIC being used is an NVIDIA ConnectX-5, the driver must be specified:
members
- type: ovs_dpdk_port
name: dpdk0
driver: mlx5_core
members:
- type: interface
name: enp3s0f0
3.2. Discover your NUMA node topology Copy linkLink copied to clipboard!
For network functions virtualization (NFV) environments, you must discover the NUMA topology of your Compute node to partition the CPU and memory resources for optimum performance.
Procedure
- Enable hardware introspection to retrieve this information from bare-metal nodes.
- Log on to each bare-metal node to manually collect the information.
3.3. NFV BIOS settings Copy linkLink copied to clipboard!
NFV environments require appropriate values for a variety of BIOS parameters.
The following table describes those BIOS parameters.
You must enable SR-IOV global and NIC settings in the BIOS, or your RHOSO deployment with SR-IOV Compute nodes will fail.
| Parameter | Setting |
|---|---|
|
| Disabled. |
|
| Disabled. |
|
| Enabled. |
|
| Enabled. |
|
| Enabled. |
|
| Enabled. |
|
| Performance. |
|
| Enabled. |
|
| Disabled in NFV deployments that require deterministic performance. Enabled in all other scenarios. |
|
| Enabled for Intel cards if VFIO functionality is needed. |
|
| Disabled. |
If you are using the TuneD CPU-partitioning power saving profile, cpu-partitioning-powersave, then you must enable the appropriate C-states power state level in the firmware. For more information about BIOS settings, contact your hardware vendor.
On processors that use the intel_idle driver, Red Hat Enterprise Linux can ignore BIOS settings and re-enable the processor C-state.
You can disable intel_idle and instead use the acpi_idle driver by specifying the key-value pair intel_idle.max_cstate=0 on the kernel boot command line.
Confirm that the processor is using the acpi_idle driver by checking the contents of current_driver:
$ cat /sys/devices/system/cpu/cpuidle/current_driver
- Sample output
acpi_idle
You will experience some latency after changing drivers, because it takes time for the Tuned daemon to start. However, after Tuned loads, the processor does not use the deeper C-state.
3.4. Supported drivers for NFV Copy linkLink copied to clipboard!
For a complete list of supported drivers for network functions virtualization (NFV) on Red Hat OpenStack Services on OpenShift (RHOSO) environments, see Component, Plug-In, and Driver Support in Red Hat OpenStack Platform .
For a list of NICs tested for NFV on RHOSO environments, see Tested NICs for NFV.