Abstract: There is disclosed in one example a computing apparatus, including: a local platform including a hardware platform; a management interface to communicatively couple the local platform to a management controller; a virtualization infrastructure to operate on the hardware platform and to provide a local virtualized function; and a resiliency controller to operate on the hardware platform, and configured to: receive a resiliency policy from the management controller via the management interface, the resiliency policy including information to handle a fault in the virtualized function; detect a fault in the local virtualized function; and effect a resiliency action responsive to detecting the fault.

Abstract: There is disclosed in one example a computing apparatus, including: a local platform including a hardware platform; a management interface to communicatively couple the local platform to a management controller; a virtualization infrastructure to operate on the hardware platform and to provide a local virtualized function; and a resiliency controller to operate on the hardware platform, and configured to: receive a resiliency policy from the management controller via the management interface, the resiliency policy including information to handle a fault in the virtualized function; detect a fault in the local virtualized function; and effect a resiliency action responsive to detecting the fault.

Abstract: Examples include techniques to use a network service header to monitor Quality of Service (QoS). Examples include implementation of a QoS stamping policy to monitor one or more QoS fields of a network packet routed through nodes arranged to separately provide individual service functions included in a service function chain. A determination is made as to whether the QoS stamping information indicates a consistent QoS configuration in the one or more QoS fields of the network packet at node ingress or node egress of the network packet as routed through the nodes.

Abstract: Described herein are devices and techniques for deterministic service chaining between virtual network functions (VNFs). A control device can comprise a wide area network (WAN) interface, at least one local interface, and processing circuitry. The WAN interface can communicate with a plurality of WAN links. The at least one local interface can communicate with VNFs. The processing circuitry configured to: receive performance indicators, identify one of the plurality of devices having a value for a performance indicator that exceeds a threshold for a corresponding key performance indicator, and provide notification of a violation based on the identifying. The performance indicators can include latency and resource usage from the WAN interface and the at least one local interface. Also described are other embodiments.

Abstract: Technologies for load-aware traffic steering include a compute device that includes a multi-homed network interface controller (NIC) with a plurality of NICs. The compute device determines a target virtual network function (VNF) of a plurality of VNFs to perform a processing operation on a network packet. The compute device further identifies a first steering point of a first NIC to steer the received network packet to virtual machines (VMs) associated with the target VNF and retrieves a resource utilization metric that corresponds to a usage level of a component of the compute device used by the VMs to process the network packet. Additionally, the compute device determines whether the resource utilization metric indicates a potential overload condition and provides a steering instruction to a second steering point of a second NIC that is usable to redirect the network traffic to the other VMs via the identified second steering point.

Abstract: Particular embodiments described herein provide for a network element that can be configured to determine a pre-execution performance test, where the pre-execution performance test is at least partially based on requirements for a process to be executed, cause the pre-execution performance test to be executed on a platform before the process is executed on the platform, where the platform is a dynamically allocated group of resources, analyze results of the pre-execution performance test, and cause the process to be executed on the platform if the results of the pre-execution performance test satisfy a condition. In an example, the process is a virtual network function.

Abstract: There is disclosed in an example, a computing apparatus, including: a processor having a resource direction capability; and one or more logic elements providing a network function virtualization orchestrator (NFVO) engine to: store for a virtual machine (VM) an extended performance profile, comprising a metric from the resource direction capability.

Abstract: Methods, systems, and storage media for monitoring service function path are disclosed herein. In an embodiment, a service function chain classifier module may receive a network data packet and applying to it a network packet service control that establishes an ordered chain of network service functions to apply to the network data packet as it traverses a service function path. The service function chain classifier module may incorporate into the network packet service control an indicator to obtain time information relating to application of one or more of the plural service functions to the network data packet. A network service performance module may receive the time information relating to the application of the one or more of the plural service functions to the network data packet and to monitor the time information. Other embodiments may be disclosed or claimed.

Abstract: Examples include techniques to use a network service header to monitor Quality of Service (QoS). Examples include implementation of a QoS stamping policy to monitor one or more QoS fields of a network packet routed through nodes arranged to separately provide individual service functions included in a service function chain. A determination is made as to whether the QoS stamping information indicates a consistent QoS configuration in the one or more QoS fields of the network packet at node ingress or node egress of the network packet as routed through the nodes.

Abstract: Described herein are devices and techniques for deterministic service chaining between virtual network functions (VNFs). A control device can comprise a wide area network (WAN) interface, at least one local interface, and processing circuitry. The WAN interface can communicate with a plurality of WAN links. The at least one local interface can communicate with VNFs. The processing circuitry configured to: receive performance indicators, identify one of the plurality of devices having a value for a performance indicator that exceeds a threshold for a corresponding key performance indicator, and provide notification of a violation based on the identifying. The performance indicators can include latency and resource usage from the WAN interface and the at least one local interface. Also described are other embodiments.

Abstract: Methods, systems, and storage media for monitoring service function path are disclosed herein. In an embodiment, a service function chain classifier module may receive a network data packet and applying to it a network packet service control that establishes an ordered chain of network service functions to apply to the network data packet as it traverses a service function path. The service function chain classifier module may incorporate into the network packet service control an indicator to obtain time information relating to application of one or more of the plural service functions to the network data packet. A network service performance module may receive the time information relating to the application of the one or more of the plural service functions to the network data packet and to monitor the time information. Other embodiments may be disclosed or claimed.