Dynamic Resource Optimization For High Availability Virtual Network Functions

Abstract

Dynamically allocating workloads to a fixed number of CPU resources within a compute platform. Determining whether a workload should be in a Dedicated Class of workloads and assigned to a dedicated CPU resource or in a Shared Class of workloads that is handled by a set of at least one shared CPU resource, wherein a shared CPU resource may service more than one workload. The determination may be made based on a comparison of a parameter from two samples of a parameter taken at different times. The determination may be made using metadata associated with the workload. The determination may be made repeatedly so that some workloads may change from being in the Dedicated Class to the Shared Class or from the Shared Class to the Dedicated Class. High availability virtual network functions may be handled economically by deeming the failover workloads to be in the Shared Class.

What is claimed is: 
     
         1 . A method of deploying a set of at least one high availability virtual network function on a pair of servers, the method comprising:
 obtaining a first server and a second server, each server having a set of CPU cores;   assigning a set of CPU cores on the first server for use with a set of Dedicated Class workloads;   assigning a set of at least one CPU core on the first server for use with a set of Shared Class workloads including at least one Shared Class workload for a non-time-critical workload;   assigning a set of CPU cores on the second server for use with a set of Dedicated Class workloads;   assigning a set of at least one CPU core on the second server for use with a set of Shared Class workloads including at least one Shared Class workload for a non-time-critical workload;   on the first server, assigning a set of at least one workload for an active portion of a first high availability virtual network function to the set of Dedicated Class workloads and assigning each of the set of at least one workloads to a separate CPU core on the first server so that each of the set of at least one workload for the active portion of the first high availability virtual network function is a sole workload on one of the separate CPU cores; and   on the second server, assigning a set of at one workload for failover for the first high availability virtual network function to a set of Shared Class workloads and assigning all of the set of Shared Class workloads to the set of at least one CPU core on the second server for use with a set of Shared Class workloads.   
     
     
         2 . The method of  claim 1  wherein the second server reacts to a change of status from inactive to active for each of the set of at least one workload for failover by reassigning the set of at least one workload for failover for the first high availability virtual network function to the set of Dedicated Class workloads. 
     
     
         3 . The method of  claim 2  wherein reassigning the set of at least one workload for failover for the first high availability virtual network function to the set of Dedicated Class workloads causes each of the set of at least one workload for failover for the first high availability virtual network function to be assigned to a CPU core that does not have any other workloads. 
     
     
         4 . The method of  claim 2  wherein reassigning the set of at least one workload for failover for the first high availability virtual network function to the set of Dedicated Class workloads causes each of the set of at least one workload for failover for the first high availability virtual network function to be assigned to a CPU core that is already assigned one Dedicated Class workload. 
     
     
         5 . The method of  claim 1  further comprising
 on the first server, assigning a set of at least one workload for an active portion of a second high availability virtual network function to the set of Dedicated Class workloads and assigning each of the set of at least one workload to a separate CPU core on the first server so that each of the set of at least one workload for the active portion of the second high availability virtual network function is a sole workload on one of the separate CPU cores; on the second server, assigning a set of at one workload for failover for the second high availability virtual network function to the set of Shared Class workloads; and 
 assigning all of the set of Shared Class workloads to the set of at least one CPU core on the second server which already has the set of at least one workload for failover for the first high availability virtual network function.