Quasi-agentless cloud resource management

• US 10,419,437 B2
• Filed: 06/30/2017
• Issued: 09/17/2019
• Est. Priority Date: 06/30/2017
• Status: Active Grant

• Current Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Inventors: Hu, Luhui, Zang, Hui, Hu, Ziang
• Primary Examiner(s): Moorthy, Aravind K
• Application Number:
  US15/640,080
• Publication Number:
  US 20190007410A1
• Time in Patent Office: 809 Days
• Field of Search: 713151, 713168, 713171, 713178
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/20 Network management software packages
• CPC Class Codes: H04L 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities
• CPC Class Codes: H04L 41/5096 wherein the managed service relates to distributed or central networked applications
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/106 using time related information in packets, e.g. by adding timestamps
• CPC Class Codes: H04L 43/55 Testing of service level quality, e.g. simulating service usage
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/826 Involving periods of time
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 63/0281 Proxies
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources
• CPC Class Codes: H04L 63/166 at the transport layer
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 9/14 using a plurality of keys or algorithms
• CPC Class Codes: H04L 9/3297 involving time stamps, e.g. generation of time stamps

Abstract

A system, computer readable medium, and method are provided for a resource management in a cloud architecture. The method includes the steps of collecting a first time stamped data (TSD), and a second TSD, and generating a prediction model based on the first TSD and the second TSD. The method further includes collecting a third TSD, and predicting a fourth TSD based on the prediction model and the third TSD. With more data are obtained via the prediction, the resource management is more efficient and accurate.

Claims

1. A method for a resource management in a cloud architecture, comprising:

collecting a first time stamped data (TSD), wherein the first TSD includes a first timestamp, a first field and a second field, wherein the first field indicates a resource type of a first resource unit at the first timestamp, and the second field indicates a utilization of the first resource unit at the first timestamp;

collecting a second TSD with an agent, wherein the second TSD includes the first timestamp and a first key value pair;

generating a prediction model based on the first TSD and the second TSD;

collecting a third TSD, wherein the third TSD includes a second timestamp, a third field and a fourth field, wherein the third field indicates a resource type of a second resource unit at the second timestamp, and the fourth field indicates a utilization of the second resource unit at the second timestamp; and

predicting a fourth TSD based on the prediction model and the third TSD, wherein the fourth TSD includes the second timestamp and a second key value pair.

2. The method of claim 1, wherein the first key value pair includes a key indicating a performance metric, and a value of the performance metric at the second timestamp.

3. The method of claim 1, wherein a structure of the first key value pair is the same as a structure of the second key value pair.

4. The method of claim 1, wherein the predicting is performed by a physically distributed but logically centralized cloud plane (PDLCCP), and the method further comprises:

receiving, by the PDLCCP, the first TSD from a first built-in software;

receiving, by the PDLCCP, the second TSD from the agent; and

receiving, by the PDLCCP, the third TSD from a second built-in software.

5. The method of claim 1, wherein the predicting is performed by a controller in the cloud architecture, and the method further comprises:

sending, by a PDLCCP, the prediction model to the controller, wherein the controller comprises a resource manager or a fabric controller in the cloud architecture.

6. The method of claim 5, wherein the method further comprises:

sending, by the controller, the fourth TSD to the PDLCCP.

7. The method of claim 1, wherein the first TSD further comprises a container field, a pod field, and a scale unit (SU) field, wherein the container field indicates a container the first resource unit belongs to, the pod field indicates a pod the first resource unit belongs to, and the SU field indicates a SU the first resource unit belongs to.

8. The method of claim 1, wherein the first TSD is sent to a PDLCCP, via a resource proxy.

9. The method of claim 8, wherein the first TSD sent to the PDLCCP are encrypted TSD.

10. A system for a resource management in a cloud architecture, comprising:

a non-transitory memory storage comprising instructions; and

one or more processors in communication with the memory, wherein the one or more processors execute the instructions to;

collect a first time stamped data (TSD), wherein the first TSD includes a first timestamp, a first field and a second field, wherein the first field indicates a resource type of a first resource unit at the first timestamp, and the second field indicates a utilization of the first resource unit at the first timestamp;

collect a second TSD with an agent, wherein the second TSD includes the first timestamp, and a first key value pair;

generate a prediction model based on the first TSD and the second TSD;

collect a third TSD, wherein the third TSD includes a second timestamp, a third field and a fourth field, wherein the third field indicates a resource type of a second resource unit at the second timestamp, and the fourth field indicates a utilization of the second resource unit at the second timestamp; and

predict a fourth TSD based on the prediction model and the third TSD, wherein the fourth TSD includes the second timestamp and a second key value pair.

11. The system of claim 10, wherein the first key value pair includes a key indicating a performance metric and a value of the performance metric at the second timestamp.

12. The system of claim 10, wherein a structure of the first key value pair is the same as a structure of the second key value pair.

13. The system of claim 10, wherein the one or more processors execute the instructions to:

receive the first TSD from a first built-in software;

receive the second TSD from the agent; and

receive the third TSD from a second built-in software.

14. The system of claim 10, wherein the one or more processors execute the instructions to:

send the prediction model to a controller, wherein the controller comprises a resource manager or a fabric controller in the cloud architecture.

15. The system of claim 10, wherein the first TSD further comprises a container field, a pod field, and a scale unit (SU) field, wherein the container field indicates a container the first resource unit belongs to, the pod field indicates a pod the first resource unit belongs to, and the SU field indicates a SU the first resource unit belongs to.

16. A non-transitory computer-readable medium storing computer instructions for a resource management in a cloud architecture, when executed by one or more processors, cause the one or more processors to perform the steps of:

collecting a first time stamped data (TSD), wherein the first TSD includes a first timestamp, a first field and a second field, wherein the first field indicates a resource type of a first resource unit at the first timestamp, and the second field indicates a utilization of the first resource unit at the first timestamp;

collecting a second TSD with an agent, wherein the second TSD includes the first timestamp and a first key value pair;

generating a prediction model based on the first TSD and the second TSD;

collecting a third TSD, wherein the third TSD includes a second timestamp, a third field and a fourth field, wherein the third field indicates a resource type of a second resource unit at the second timestamp, and the fourth field indicates a utilization of the second resource unit at the second timestamp; and

predicting a fourth TSD based on the prediction model and the third TSD, wherein the fourth TSD includes the second timestamp and a second key value pair.

17. The non-transitory computer-readable medium of claim 16, wherein the first key value pair includes a key indicating a performance metric and a value of the performance metric at the second timestamp.

18. The non-transitory computer-readable medium of claim 16, wherein a structure of the first key value pair is the same as a structure of the second key value pair.

19. The non-transitory computer-readable medium of claim 16, wherein the computer instructions when executed by one or more processors, cause the one or more processors to perform the steps of:

receiving the first TSD from a first built-in software;

receiving the second TSD from the agent; and

receiving the third TSD from a second built-in software.

20. The non-transitory computer-readable medium of claim 16, wherein the computer instructions when executed by one or more processors, cause the one or more processors to perform the steps of:

sending the prediction model to a controller, wherein the controller comprises a resource manager or a fabric controller in the cloud architecture.