Technologies for deploying virtual machines in a virtual network function infrastructure

Abstract

Technologies for deploying virtual machines (VMs) in a virtual network function (VNF) infrastructure include a compute device configured to collect a plurality of performance metrics based on a set of key performance indicators, determine a key performance indicator value for each of the set of key performance indicators based on the collected plurality of performance metrics, and determine a service quality index for a virtual machine (VM) instance of a plurality of VM instances managed by the compute as a function each key performance indicator value. Additionally, the compute device is configured to determine whether the determined service quality index is acceptable and perform, in response to a determination that the determined service quality index is not acceptable, an optimization action to ensure the VM instance is deployed on an acceptable host of the compute device. Other embodiments are described herein.

1 - 20 . (canceled) 
     
     
         21 . A compute device in a virtual network function (VNF) infrastructure, the compute device comprising:
 circuitry to:
 collect a plurality of metrics for a virtual machine (VM) instance, the plurality of metrics to include a processor utilization metric, a memory utilization metric and network metrics, wherein the network metrics include ingress queue information and egress queue information for a virtual switch, network packet loss, network packet delivery latency, network packets received, and network packets transmitted; 
 determine an indicator value for the VM instance based on at least one of the collected metrics; 
 compare the determined indicator value to a threshold indicator value associated with a service level agreement for the VM instance to process a workload; and 
 adjust, based on the comparison indicating the determined indicator value is above the threshold indicator value, a hardware configuration of the compute device arranged to support the VM instance to process the workload. 
   
     
     
         22 . The compute device of  claim 21 , wherein to collect the plurality of metrics comprises to (i) identify a workload type for the workload to be processed by the VM instance, (ii) determine a set of key performance indicators based on the identified workload type, and (iii) collect the plurality of metrics based on the determined set of key performance indicators. 
     
     
         23 . The compute device of  claim 21 , wherein the indicator value for the VM instance comprises a service quality index value. 
     
     
         24 . The compute device of  claim 21 , wherein the processor utilization metric includes a processor response time, a processor wait time, or a processor utilization percentage. 
     
     
         25 . The compute device of  claim 21 , wherein the memory utilization metric includes host memory usage data, guest memory usage data, page sharing, memory bandwidth monitoring, or compression related data. 
     
     
         26 . The compute device of  claim 21 , wherein to collect the plurality of metrics further comprises to collect orchestrator metrics associated with a service orchestrator of the compute device. 
     
     
         27 . The compute device of  claim 26 , wherein to collect the orchestrator metrics comprises to collect an amount of registered services, a service lookup time, a client discovery count, a number of connection retries, or an amount of connection failures. 
     
     
         28 . The compute device of  claim 21 , wherein to collect the plurality of metrics further comprises to collect virtual network function metrics associated with the VM instance processing the workload associated with a virtual network function, and wherein to collect the virtual network function metrics includes to collect a number of a VM stall count, a VM premature release ratio, a VM scheduling latency, or a VM clock error. 
     
     
         29 . The compute device of  claim 21 , wherein to adjust the hardware configuration of the compute device comprises turning on hardware offloads, supporting large pages, adjusting a memory access priority, or data plane processor pinning. 
     
     
         30 . One or more non-transitory machine-readable storage media comprising a plurality of instructions stored thereon that, in response to being executed, cause a compute device to:
 collect a plurality of metrics for a virtual machine (VM) instance, the plurality of metrics to include a processor utilization metric, a memory utilization metric and network metrics, wherein the network metrics include ingress queue information and egress queue information for a virtual switch, network packet loss, network packet delivery latency, network packets received, and network packets transmitted;   determine an indicator value for the VM instance based on at least one of the collected metrics;   compare the determined indicator value to a threshold indicator value associated with a service level agreement for the VM instance to process a workload; and   adjust, based on the comparison indicating the determined indicator value is above the threshold indicator value, a hardware configuration of the compute device arranged to support the VM instance to process the workload.   
     
     
         31 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein to collect the plurality of metrics comprises to (i) identify a workload type for the workload to be processed by the VM instance, (ii) determine a set of key performance indicators based on the identified workload type, and (iii) collect the plurality of metrics based on the determined set of key performance indicators. 
     
     
         32 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein the indicator value for the VM instance comprises a service quality index value. 
     
     
         33 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein the processor utilization metric includes a processor response time, a processor wait time, or a processor utilization percentage. 
     
     
         34 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein the memory utilization metric includes host memory usage data, guest memory usage data, page sharing, memory bandwidth monitoring, or compression related data. 
     
     
         35 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein to collect the plurality of metrics further comprises to collect orchestrator metrics associated with a service orchestrator of the compute device. 
     
     
         36 . The one or more non-transitory machine-readable storage media of  claim 35 , wherein to collect the orchestrator metrics comprises to collect an amount of registered services, a service lookup time, a client discovery count, a number of connection retries, or an amount of connection failures. 
     
     
         37 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein to collect the plurality of metrics further comprises to collect virtual network function metrics associated with the VM instance processing a workload associated with a virtual network function, and wherein to collect the virtual network function metrics includes to collect a number of a VM stall count, a VM premature release ratio, a VM scheduling latency, or a VM clock error. 
     
     
         38 . The one or more non-transitory machine-readable storage media of  claim 30 , wherein to adjust the hardware configuration of the compute device comprises turning on hardware offloads, supporting large pages, adjusting a memory access priority, or data plane processor pinning.