Lab and BM RA alignment towards CNTT RA2:
Cloud Infrastructure Software Profile Capabilities
Reference Model Section | Reference | Description | Requirement for Basic Profile | Requirement for Network Intensive Profile | BM RA Notes | OPNFV Intel Lab |
e.cap.001 | Max number of vCPU that can be assigned to a single Pod by the Cloud Infrastructure | At least 16 (1) | At least 16 (1) | [OK] POD 19: 22c/44t [OK] POD 21: 20c/44t | ||
e.cap.002 | Max memory in MB that can be assigned to a single Pod by the Cloud Infrastructure | at least 32 GB(1) | at least 32 GB(1) | [OK] POD 19: 64G [OK] POD 21: 192G | ||
e.cap.003 | Max storage in GB that can be assigned to a single Pod by the Cloud Infrastructure | at least 320 GB(1) | at least 320 GB(1) | [OK] POD 19: 3TB (HDD) [OK] POD 21: 800G (SSD) | ||
e.cap.004 | Max number of connection points that can be assigned to a single Pod by the Cloud Infrastructure | 6 | 6 | Possible through Multus + CNI (vEth, SR-IOV) | ||
e.cap.005 | Max storage in GB that can be attached / mounted to Pod by the Cloud Infrastructure | Up to 16TB(2) | Up to 16TB(2) | |||
e.cap.006 | CPU pinning support | Not required | Must support | Possible through CMK (or Privileged flag) | ||
e.cap.007 | NUMA support | Not required | Must support | (Maybe) Possible through CMK (or other BM RA tool) | ||
e.cap.008 | IPSec Acceleration using the virtio-ipsec interface | Not required | Optional | (??) Might be covered by QAT device plugin | QAT support depends on chipset | |
e.cap.009 | Crypto Acceleration using the virtio-crypto interface | Not required | Optional | (??) Might be covered by QAT device plugin | QAT support depends on chipset | |
e.cap.010 | Transcoding Acceleration | Not required | Not required | (??) | ||
e.cap.011 | Programmable Acceleration | Not required | Not required | (??) | ||
e.cap.012 | Enhanced Cache Management: L=Lean; E=Equal; X=eXpanded | E | E | (??) | ||
e.cap.013 | SR-IOV over PCI-PT | Must support | Not required | Not sure if this is specifically supported | ||
e.cap.014 | Hardware coprocessor support (GPU/NPU) | Not required | Not required | GPU Device Plugin | Depends on Lab HW | |
e.cap.015 | SmartNICs | Optional | Not required | (Maybe) Not sure if supported. | Depends on Lab HW | |
e.cap.016 | FPGA/other Acceleration H/W | Optional | Not required | FPGA Device Plugin | Depends on Lab HW | |
e.cap.017 | Ability to monitor L2-L7 data from workload | n/a(3) | n/a(3) | |||
i.cap.014 | Indicates the number of CPU cores consumed by the Cloud Infrastructure on the worker nodes | 2 | 2 | IIRC this is possible with BM RA. Expecting it to be "core 0" on each socket | ||
i.cap.015 | Indicates the memory consumed by Cloud Infrastructure on the worker nodes | 16 GB | 16GB | TBD | ||
i.cap.016 | Number of virtual cores per physical core; also known as CPU overbooking ratio that is required | 1:1 | 1:1 | Should be default with K8s request/limit | ||
i.cap.017 | QoS enablement of the connection point (vNIC or interface) | Not required | Must support | TBD | ||
i.cap.018 | Support for huge pages | Not required | Must support | Part of K8s | ||
i.pm.001 | Monitor worker node CPU usage, per nanosecond | Must support | Must support | TBD | ||
i.pm.002 | Monitor pod CPU usage, per nanosecond | Must support | Must support | TBD | ||
i.pm.003 | Monitor worker node CPU utilisation (%) | Must support | Must support | TBD | ||
i.pm.004 | Monitor pod CPU utilisation | Must support | Must support | TBD | ||
i.pm.005 | Measure external storage IOPs | Must support | Must support | TBD | ||
i.pm.006 | Measure external storage throughput | Must support | Must support | TBD | ||
i.pm.007 | Measure external storage capacity | Must support | Must support | TBD |
Cloud Infrastructure Software Profile Requirements
Reference Model Section | Reference | Description | Requirement for Basic Profile | Requirement for Network Intensive Profile | BM RA Notes | OPNFV Intel Lab |
infra.com.cfg.001 | CPU allocation ratio | 1:1 | 1:1 | See above | ||
infra.com.cfg.002 | NUMA awareness | Must support | Must support | See above | ||
infra.com.cfg.003 | CPU pinning capability | Must support | Must support | See above | ||
infra.com.cfg.004 | Huge Pages | Must support | Must support | See above | ||
infra.stg.cfg.002 | Storage Block | Must support | Must support | TBD | ||
infra.stg.cfg.003 | Storage with replication | Not required | Must support | TBD | ||
infra.stg.cfg.004 | Storage with encryption | Must support | Must support | TBD | ||
infra.stg.acc.cfg.001 | Storage IOPS oriented | Not required | Must support | TBD | ||
infra.stg.acc.cfg.002 | Storage capacity oriented | Not required | Not required | TBD | ||
infra.net.cfg.001 | IO virtualisation using virtio1.1 | Must support(1) | Must support(1) | Considering (1), this should be fine with SR-IOV Device Plugin and CNI | ||
infra.net.cfg.002 | The overlay network encapsulation protocol needs to enable ECMP in the underlay to take advantage of the scale-out features of the network fabric.(2) | Must support VXLAN, MPLSoUDP, GENEVE, other | No requirement specified | TBD | TBD | |
infra.net.cfg.003 | Network Address Translation | Must support | Must support | (??) Is this possible in K8s by default | ||
infra.net.cfg.004 | Security Groups | Must support | Must support | TBD | ||
infra.net.cfg.005 | SFC support | Not required | Must support | TBD | ||
infra.net.cfg.006 | Traffic patterns symmetry | Must support | Must support | TBD | ||
infra.net.acc.cfg.001 | vSwitch optimisation | Not required | Must support DPDK(3) | (??) Part of BM RA (with additional configuration needed?) | ||
infra.net.acc.cfg.002 | Support of HW offload | Not required | Must support SmartNic | See above | ||
infra.net.acc.cfg.003 | Crypto acceleration | Not required | Must support | See above | ||
infra.net.acc.cfg.004 | Crypto Acceleration Interface | Not required | Must support | See above |
(1) Workload Transition Guidelines. might have other interfaces (such as SR-IOV VFs to be directly passed to a VM or a Pod) or NIC-specific drivers on guest machines transiently allowed until mature enough solutions are available with a similar efficiency level (for example regarding CPU and energy consumption).
(2) In Kubernetes based infrastructures network separation is possible without an overlay (e.g.: with IPVLAN)
(3) This feature is not applicable for Kubernetes based infrastructures due to lack of vSwitch however workloads need access to user space networking solutions.
Cloud Infrastructure Hardware Profile Requirements
Reference Model Section | Reference | Description | Requirement for Basic Profile | Requirement for Network Intensive Profile | BM RA Notes | OPNFV Intel Lab |
infra.hw.cpu.cfg.001 | Number of CPU (Sockets) | 2 | 2 | [OK] POD 19: x2 [OK] POD 21: x2 | ||
infra.hw.cpu.cfg.002 | Number of Cores per CPU | 20 | 20 | [OK] POD 19: 22 [OK] POD 21: 20 | ||
infra.hw.cpu.cfg.003 | NUMA | Not required | Must support | Supported by default (?) | ||
infra.hw.cpu.cfg.004 | Simultaneous Multithreading/Hyperthreading (SMT/HT) | Must support | Must support | Depends on BIOS configuration (can be enabled) | ||
infra.hw.cac.cfg.001 | GPU | Not required | Not required | Depends on HW configuration | ||
infra.hw.stg.hdd.cfg.001 | Local Storage HDD | No requirement specified | No requirement specified | [OK] POD 19: 3TB HDD [!] POD 21: Only SSD | ||
infra.hw.stg.ssd.cfg.002 | Local Storage SSD | Should support | Should support | [OK] POD 19: 190GB [OK] POD 21: 800GB | ||
infra.hw.nic.cfg.001 | Total Number of NIC Ports available in the host | 4 | 4 | OK, assuming no requirement on port speed (1/10Gbps) | ||
infra.hw.nic.cfg.002 | Port speed specified in Gbps (minimum values) | 10 | 25 | [OK] Basic Profile [!] Network Intensive Profile | ||
infra.hw.pci.cfg.001 | Number of PCIe slots available in the host | 8 | 8 | TBD | ||
infra.hw.pci.cfg.002 | PCIe speed | Gen 3 | Gen 3 | Should be OK | ||
infra.hw.pci.cfg.003 | PCIe Lanes | 8 | 8 | Should be OK | ||
infra.hw.nac.cfg.001 | Cryptographic Acceleration | Not required | Optional | Depends on HW configuration | ||
infra.hw.nac.cfg.002 | A SmartNIC that is used to offload vSwitch functionality to hardware | Not required | Optional(1) | Not likely, but depends on HW configuration | ||
infra.hw.nac.cfg.003 | Compression | No requirement specified | No requirement specified | TBD |
(1) There is no vSwitch in case of containers, but a SmartNIC can be used to offload any other network processing.