Method and system to detect a network deficiency

• US 8,135,824 B2
• Filed: 10/01/2007
• Issued: 03/13/2012
• Est. Priority Date: 10/01/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Saha, Debashis, Kimmet, Tim, Lee, Sangjin, Bigian, Armond, El-Charif, Rami, Yang, Connie Y.
• Primary Examiner(s): Moore, Ian N
• Assistant Examiner(s): Huynh, Dung B
• Application Number:
  US11/865,206
• Publication Number:
  US 20090089418A1
• Time in Patent Office: 1,625 Days
• Field of Search: 709/224, 709/226, 709/229, 709/232
• US Class Current: 709/224
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

A system to detect a network deficiency, in one example embodiment, comprises a receiving module to receive utilization metrics of at least one network resource, wherein the utilization metrics are collected and made available at a network level, an aggregator to aggregate the utilization metrics of at least one network resource with the utilization metrics of a plurality of the network resources, a processing module to determine a level of aggregated utilization metrics of the network resources, and a detecting module to detect a precursor indicative of a network traffic deterioration based on the level of the aggregated utilization metrics.

Claims

1. A method comprising:

receiving utilization metrics of at least one network resource, the utilization metrics being collected and made available at a network level, the utilization metrics being based on monitoring application transactions at the network level;

aggregating, using one or more processors, the utilization metrics of the at least one network resource with the utilization metrics of a plurality of network resources, the aggregating comprising recognizing and filtering out the utilization metrics of the network resources in a degraded mode, wherein the aggregated utilization metrics comprise a central processing unit utilization, a memory exhaustion, a thread pool utilization, and a transaction time;

determining a level of aggregated utilization metrics of the network resources;

detecting a precursor to a network traffic deterioration based on the level of the aggregated utilization metrics; and

identifying the precursor as being indicative of imminent network traffic deterioration.

2. The method of claim 1, wherein the aggregating of the utilization metrics of the at least one network resource with the utilization metrics of the plurality of the network resources is limited to aggregating the utilization metrics of the plurality of the network resources received from a group of homogeneous network resources.

3. The method of claim 1, further comprising displaying the aggregated utilization metrics on a graphical user interface.

4. The method of claim 1, further comprising issuing an alarm in response to the detecting of the precursor to the network traffic deterioration.

5. The method of claim 1, wherein the aggregating of the utilization metrics of the network resource with the utilization metrics of the plurality of the network resources is customizable to allow a selection of the utilization metrics.

6. The method of claim 1, further comprising reporting of the aggregated utilization metrics to a policy engine execution module in response to the detecting of the precursor to the network traffic deterioration.

7. A system comprising:

a receiving module to receive utilization metrics of at least one network resource, the utilization metrics being collected and made available at a network resource level, the utilization metrics being based on monitoring application transactions at the network level;

an aggregator to aggregate the utilization metrics of the at least one network resource with the utilization metrics of a plurality of network resources, the aggregator to aggregate by recognizing and filtering out the utilization metrics of the network resources in a degraded mode, wherein the aggregated utilization metrics comprise a central processing unit utilization, a memory exhaustion, a thread pool utilization, and a transaction time;

a processing module to determine a level of aggregated utilization metrics of the network resources; and

a detecting module to detect, using one or more processors, a precursor to a network traffic deterioration based on the level of the aggregated utilization metrics and to identify the precursor as being indicative of imminent network traffic deterioration.

8. The system of claim 7, wherein the aggregator that is to aggregate the utilization metrics of the at least one network resource with the utilization metrics of the plurality of the network resources is limited to aggregating component utilization metrics of the plurality of the network resources received from a group of homogeneous network resources.

9. The system of claim 7, further comprising a display to display the aggregated utilization metrics on a graphical user interface.

10. The system of claim 7, further comprising an alarming module to issue an alarm in response to the detecting of the precursor to the network traffic deterioration.

11. The system of claim 7, wherein the aggregator is configurable to aggregate a selection of the utilization metrics of the network resource with the utilization metrics of the plurality of the network resources.

12. The system of claim 7, further comprising a reporting module to report the aggregated utilization metrics to a policy engine execution module in response to the detecting of the precursor to the network traffic deterioration.

13. A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more processors, perform operations comprising:

receiving utilization metrics of at least one network resource, the utilization metrics being collected and made available at a network level, the utilization metrics being based on monitoring application transactions at the network level;

aggregating the utilization metrics of the at least one network resource with the utilization metrics of a plurality of the network resources the aggregating comprising recognizing and filtering out the utilization metrics of the network resources in a degraded mode, wherein the aggregated utilization metrics comprise a central processing unit utilization, a memory exhaustion, a thread pool utilization, and a transaction time;

determining a level of aggregated utilization metrics of the network resources;

detecting a precursor to a network traffic deterioration based on the level of the aggregated utilization metrics; and

identifying the precursor as being indicative of imminent network traffic deterioration.