Workload prediction based cpu frequency scaling

Patent metadata

Field	Value
Publication number	US-2019272002-A1
Application number	US-201815909083-A
Country	US
Kind code	A1
Filing date	Mar 1, 2018
Priority date	Mar 1, 2018
Publication date	Sep 5, 2019
Grant date	—

Abstract

A method comprises predicting, based on corresponding historical workload data, a change in virtual network function demand during a future workload period, wherein the virtual network function is supported by a node. The method further comprises determining a target clock speed of one or more physical CPU cores of one or more processors of one or more servers in the node corresponding to the change in the virtual network function demand and adjusting the CPU CORE of the node to the target clock speed corresponding to the change in the virtual network function demand for the future workload period.

First claim

What is claimed is:

1 . A method, comprising:
predicting, based on historical workload data, a predicted change in virtual network function demand during a future workload period, wherein the virtual network function is supported by a node; determining a target clock speed of a physical central processing unit (CPU) core in the node corresponding to the predicted change in the virtual network function demand; and adjusting the physical CPU core of the node to the target clock speed corresponding to the predicted change in the virtual network function demand for the future workload period.

2 . The method of claim 1 , wherein adjusting the physical CPU core of the node is coordinated to a latency.

3 . The method of claim 2 , further comprising:
calculating the latency, wherein the latency is based on an adjustment delay associated with changing the clock speed of the physical CPU core from an initial clock speed to the target clock speed.

4 . The method of claim 3 , wherein the latency is based on a network delay.

5 . The method of claim 1 , further comprising:
collecting the historical workload data.

6 . The method of claim 5 , wherein the historical workload data is based on a time period.

7 . The method of claim 6 , wherein the time period is a date and time.

8 . The method of claim 1 , further comprising:
comparing a recent virtual network function demand to the historical workload data to determine a difference between the recent virtual network function demand and the historical workload data, wherein predicting the change in virtual network function demand is further based on the difference.

9 . The method of claim 8 , wherein the comparison is based on a date or a time.

10 . The method of claim 8 , wherein the comparison is based on a usage pattern.

11 . The method of claim 8 , wherein the comparison identifies an anomalous event.

12 . A method, comprising:
predicting, based on historical workload data, a future demand during a future workload interval, wherein the demand supports a virtual network function or container, and wherein the demand is met by a server; determining a target clock speed of at least one central processing unit (CPU) core corresponding to the future demand, wherein the at least one CPU core is within a processor in the server; and causing the at least one CPU core to adjust to the target clock speed corresponding to the future demand for the future workload interval.

13 . The method of claim 12 , further comprising:
determining a target clock speed of at least one hyper-thread of a central processing unit (CPU) core corresponding to the future demand, wherein two or more hyper threads are supported by the at least one CPU core.

14 . A system, comprising:
a virtual element workload database configured to store historical workload data for a virtual network function, wherein the virtual network function is supported by one or more host central processing unit (CPU) cores; and an analytics engine configured to predict a target clock speed for the one or more host CPU cores during a future load period based on the historical workload data.

15 . The system of claim 14 , wherein the analytics engine causes the one or more host CPU cores to adjust to the target clock speed.

16 . The system of claim 15 , wherein adjusting to the target clock speed is timed according to a latency.

17 . The system of claim 14 , wherein the analytics engine is configured to predict the target clock speed based on a corresponding time period.

18 . The system of claim 14 , wherein the analytics engine is configured to predict the target clock speed based on a workload model.

19 . The system of claim 14 , wherein the virtual element workload database is configured to store historical workload data for a plurality of virtual network functions.

20 . The system of claim 14 , wherein the analytics engine is configured to predict a plurality of target clock speeds for a plurality of host processors, wherein the one or more CPU cores are in the plurality of host processors.

Assignees

• At & T Ip I Lp

Inventors

• Seenappa Vikram
• Mhatre Vivek

Classifications

• G06F1/324 Primary

  by lowering clock frequency · CPC title

• G06F1/08 Primary

  Clock generators with changeable or programmable clock frequency · CPC title

• G06F2009/45595

  Network integration; Enabling network access in virtual machine instances · CPC title

• G06F9/45558

  Hypervisor-specific management and integration aspects · CPC title

• G06F17/30309

  Physics · mapped topic