Network function virtualization infrastructure performance
This disclosure describes systems, methods, and apparatuses related to network function virtualization infrastructure (NFVI) performance. An apparatus may receive performance data from a network function virtualization infrastructure (NFVI) associated with one or more virtualized resources (VRs) of the NFVI. The apparatus may determine a collection method based on the received performance data. The apparatus may determine a performance measurement associated with the collection method. The apparatus may perform the performance measurement using the received performance data and the collection method. The apparatus may generate one or more outputs based on the performance measurement. The apparatus may cause to send the one or more outputs to a VNF manager (VNFM).
1. A non-transitory computer-readable medium storing computer-executable instructions which when executed by one or more processors result in performing operations comprising:
polling, by a ceilometer polling agent of a network function virtualization infrastructure (NFVI), one or more virtual machines at a predetermined interval;
receiving usage data associated with the one or more virtual machines;
causing to send the usage data to a virtualized infrastructure manager (VIM);
determining a performance measurement associated with the usage data and received from the VIM, and wherein the performance measurement is determined during a collection interval; and
adjusting resources associated with the one or more virtual machines based on the performance measurement.
2. The non-transitory computer-readable medium of claim 1 , wherein the usage data is associated with a central processing unit (CPU) utilization measurement, a memory utilization measurement, a disk utilization measurement, a network incoming bytes measurement; a network outgoing bytes measurement, a network incoming packets measurement, or a network outgoing packets measurement.
3. The non-transitory computer-readable medium of claim 1 , wherein the receiving of the usage data comprises receiving the usage data during a sampling interval.
4. The non-transitory computer-readable medium of claim 1 , wherein the performance measurement is associated with an OpenStack deployment; and wherein one or more outputs are generated and sent to a VNF manager (VNFM) based on the performance measurement.
5. The non-transitory computer-readable medium of claim 3 , wherein the collection interval is a multiple of the sampling interval.
6. The non-transitory computer-readable medium of claim 1 , wherein the performance measurement comprises at least one of a mean virtual CPU usage, a mean memory usage, a mean disk usage, a peak disk usage, a number of incoming bytes on a networking resource, a number of outgoing bytes on a networking resource, a number of incoming packets on a networking resource, or a number of outgoing packets on a networking resource.