Technologies for managing a flexible host interface of a network interface controller
Technologies for processing network packets by a host interface of a network interface controller (NIC) of a compute device. The host interface is configured to retrieve, by a symmetric multi-purpose (SMP) array of the host interface, a message from a message queue of the host interface and process, by a processor core of a plurality of processor cores of the SMP array, the message to identify a long-latency operation to be performed on at least a portion of a network packet associated with the message. The host interface is further configured to generate another message which includes an indication of the identified long-latency operation and a next step to be performed upon completion. Additionally, the host interface is configured to transmit the other message to a corresponding hardware unit scheduler as a function of the subsequent long-latency operation to be performed. Other embodiments are described herein.
1. At least one non-transitory machine-readable storage medium storing instructions for execution by at least one machine that is to be associated with at least one server node, the at least one server node to be associated with distributed data center-associated resources, the distributed data center-associated resources being configurable to comprise virtual resources to be associated with physical compute resources, physical storage resources, and/or physical accelerator resources, the at least one server node comprising network interface controller circuitry that is configured to be used in network communication with at least one network node, the instructions, when executed by the at least one machine, resulting in the at least one machine being configured to enable performance of operations comprising:
managing, based upon quality of service data, machine-learning, and workload-related data, allocation of the distributed data center-associated resources for use in providing at least one software-defined infrastructure (SDI) resource and/or at least one SDI service, the managing of the allocation of the distributed data center-associated resources being configurable to be implemented based upon telemetry data associated with the distributed data center-associated resources;
dynamically reallocating at least certain of the distributed data center-associated resources based upon resource utilization data; and
utilizing accelerator circuitry of the network interface controller circuitry in association with implementation of service agreements associated with the providing of the at least one SDI resource and/or the at least one SDI service;
wherein:
the distributed data center-associated resources are comprised, at least in part, in the at least one server node and the at least one network node;
the accelerator circuitry is configurable to implement cryptographic-related operations and network communication-related operations in association with the implementation of the service agreements;
the implementation of the service agreements is configurable to comprise enforcement of quality of service;
the physical compute resources and/or physical accelerator resources are configurable to comprise physical central processing unit circuitry, graphics processing unit circuitry, and/or field programmable gate array (FPGA) circuitry;
at least respective portions of the distributed data center-associated resources are configurable as at least one pool of resources; and
at least some of the distributed data center-associated resources are physically disaggregated from each other.
2. The at least one non-transitory machine-readable storage medium of claim 1 , wherein:
the network interface controller circuitry is to be associated with cache memory; and
the cache memory is to store network communication-related data for use in the network communication-related operations.
3. The at least one non-transitory machine-readable storage medium of claim 1 , wherein:
the resource utilization data comprises predicted workload resource utilization data.
4. The at least one non-transitory machine-readable storage medium of claim 3 , wherein:
the network communication is to be carried out via at least one distributed virtual switch; and
the at least one distributed virtual switch is to be implemented, at least in part, by disaggregated resources.
5. The at least one non-transitory machine-readable storage medium of claim 3 , wherein:
the at least one SDI service is related, at least in part, to:
software as a service;
platform as a service; and/or
infrastructure as a service.
6. A method implemented using at least one server node, the at least one server node to be associated with distributed data center-associated resources, the distributed data center-associated resources being configurable to comprise virtual resources to be associated with physical compute resources, physical storage resources, and/or physical accelerator resources, the at least one server node comprising network interface controller circuitry that is configured to be used in network communication with at least one network node, the method comprising:
managing, based upon quality of service data, machine-learning, and workload-related data, allocation of the distributed data center-associated resources for use in providing at least one software-defined infrastructure (SDI) resource and/or at least one SDI service, the managing of the allocation of the distributed data center-associated resources being configurable to be implemented based upon telemetry data associated with the distributed data center-associated resources;
dynamically reallocating at least certain of the distributed data center-associated resources based upon resource utilization data; and
utilizing accelerator circuitry of the network interface controller circuitry in association with implementation of service agreements associated with the providing of the at least one SDI resource and/or the at least one SDI service;
wherein:
the distributed data center-associated resources are comprised, at least in part, in the at least one server node and the at least one network node;
the accelerator circuitry is configurable to implement cryptographic-related operations and network communication-related operations in association with the implementation of the service agreements;
the implementation of the service agreements is configurable to comprise enforcement of quality of service;
the physical compute resources and/or physical accelerator resources are configurable to comprise physical central processing unit circuitry, graphics processing unit circuitry, and/or field programmable gate array (FPGA) circuitry;
at least respective portions of the distributed data center-associated resources are configurable as at least one pool of resources; and
at least some of the distributed data center-associated resources are physically disaggregated from each other.
7. The method of claim 6 , wherein:
the network interface controller circuitry is to be associated with cache memory; and
the cache memory is to store network communication-related data for use in the network communication-related operations.
8. The method of claim 6 , wherein:
the resource utilization data comprises predicted workload resource utilization data.
9. The method of claim 8 , wherein:
the network communication is to be carried out via at least one distributed virtual switch; and
the at least one distributed virtual switch is to be implemented, at least in part, by disaggregated resources.
10. The method of claim 8 , wherein:
the at least one SDI service is related, at least in part, to:
software as a service;
platform as a service; and/or
infrastructure as a service.
11. At least one server node to be associated with distributed data center-associated resources, the distributed data center-associated resources being configurable to comprise virtual resources to be associated with physical compute resources, physical storage resources, and/or physical accelerator resources, the at least one server node to be used in association with at least one network node, the at least one server node comprising:
network interface controller circuitry to be configured to be used in network communication with the at least one network node; and
processor circuitry to execute instructions, the instructions, when executed by the processor circuitry, resulting in the processor circuitry being configured to enable performance of operations comprising:
managing, based upon quality of service data, machine-learning, and workload-related data, allocation of the distributed data center-associated resources for use in providing at least one software-defined infrastructure (SDI) resource and/or at least one SDI service, the managing of the allocation of the distributed data center-associated resources being configurable to be implemented based upon telemetry data associated with the distributed data center-associated resources;
dynamically reallocating at least certain of the distributed data center-associated resources based upon resource utilization data; and
utilizing accelerator circuitry of the network interface controller circuitry in association with implementation of service agreements associated with the providing of the at least one SDI resource and/or the at least one SDI service;
wherein:
the distributed data center-associated resources are comprised, at least in part, in the at least one server node and the at least one network node;
the accelerator circuitry is configurable to implement cryptographic-related operations and network communication-related operations in association with the implementation of the service agreements;
the implementation of the service agreements is configurable to comprise enforcement of quality of service;
the physical compute resources and/or physical accelerator resources are configurable to comprise physical central processing unit circuitry, graphics processing unit circuitry, and/or field programmable gate array (FPGA) circuitry;
at least respective portions of the distributed data center-associated resources are configurable as at least one pool of resources; and
at least some of the distributed data center-associated resources are physically disaggregated from each other.
12. The at least one server node of claim 11 , wherein:
the network interface controller circuitry is to be associated with cache memory; and
the cache memory is to store network communication-related data for use in the network communication-related operations.
13. The at least one server node of claim 11 , wherein:
the resource utilization data comprises predicted workload resource utilization data.
14. The at least one server node of claim 13 , wherein:
the network communication is to be carried out via at least one distributed virtual switch; and
the at least one distributed virtual switch is to be implemented, at least in part, by disaggregated resources.
15. The at least one server node of claim 13 , wherein:
the at least one SDI service is related, at least in part, to:
software as a service;
platform as a service; and/or
infrastructure as a service.
16. At least one data center comprising:
at least one network node;
distributed data center-associated resources configurable to comprise virtual resources to be associated with physical compute resources, physical storage resources, and/or physical accelerator resources; and
at least one server node to be used in association with the at least one network node, the at least one server node comprising:
network interface controller circuitry to be configured to be used in network communication with the at least one network node; and
processor circuitry to execute instructions, the instructions, when executed by the processor circuitry, resulting in the processor circuitry being configured to enable performance of operations comprising:
managing, based upon quality of service data, machine-learning, and workload-related data, allocation of the distributed data center-associated resources for use in providing at least one software-defined infrastructure (SDI) resource and/or at least one SDI service, the managing of the allocation of the distributed data center-associated resources being configurable to be implemented based upon telemetry data associated with the distributed data center-associated resources;
dynamically reallocating at least certain of the distributed data center-associated resources based upon resource utilization data; and
utilizing accelerator circuitry of the network interface controller circuitry in association with implementation of service agreements associated with the providing of the at least one SDI resource and/or the at least one SDI service;
wherein:
the distributed data center-associated resources are comprised, at least in part, in the at least one server node and the at least one network node;
the accelerator circuitry is configurable to implement cryptographic-related operations and network communication-related operations in association with the implementation of the service agreements;
the implementation of the service agreements is configurable to comprise enforcement of quality of service;
the physical compute resources and/or physical accelerator resources are configurable to comprise physical central processing unit circuitry, graphics processing unit circuitry, and/or field programmable gate array (FPGA) circuitry;
at least respective portions of the distributed data center-associated resources are configurable as at least one pool of resources; and
at least some of the distributed data center-associated resources are physically disaggregated from each other.
17. The at least one data center of claim 16 , wherein:
the network interface controller circuitry is to be associated with cache memory; and
the cache memory is to store network communication-related data for use in the network communication-related operations.
18. The at least one data center of claim 16 , wherein:
the resource utilization data comprises predicted workload resource utilization data.
19. The at least one data center of claim 18 , wherein:
the network communication is to be carried out via at least one distributed virtual switch; and
the at least one distributed virtual switch is to be implemented, at least in part, by disaggregated resources.
20. The at least one data center of claim 18 , wherein:
the at least one SDI service is related, at least in part, to:
software as a service;
platform as a service; and/or
infrastructure as a service.