System and method for adaptive optimization of resource utilization for redundancy elimination

• US 8,681,649 B2
• Filed: 08/01/2011
• Issued: 03/25/2014
• Est. Priority Date: 08/01/2011
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Parekh, Bharat Z., Jiang, Lianjun
• Primary Examiner(s): Wong, Xavier Szewai
• Application Number:
  US13/195,623
• Publication Number:
  US 20130033994A1
• Time in Patent Office: 967 Days
• Field of Search: 370216-252, 370/254, 375/240.12, 375/240.16
• US Class Current: 370/252
• CPC Class Codes: H04L 43/026 using flow identification
• CPC Class Codes: H04L 43/028 by filtering
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation

Abstract

An example method may include calculating a parameter for traffic propagating in a network between a sender and a receiver, where the traffic comprises encoding information and decoding information; determining whether the parameter meets a predetermined value; classifying the traffic as uni-directional if the parameter meets the predetermined value; and classifying the traffic as bi-directional if the parameter does not meet the predetermined value.

Claims

1. A method for improving caching in data redundancy elimination (DRE) entities, comprising:

calculating a parameter for traffic propagating in a network between a sender and a receiver, wherein the parameter includes one or more network traffic characteristics which indicates whether the traffic is uni-directional network traffic or bi-directional network traffic, and the traffic comprises encoding information and decoding information;

determining whether the parameter meets a predetermined value;

classifying the traffic as uni-directional if the parameter meets the predetermined value; and

classifying the traffic as bi-directional if the parameter does not meet the predetermined value;

if the traffic is classified as uni-directional, causing a first DRE cache at the sender to maintain encoding information and to not maintain decoding information, and causing a second DRE cache at the receiver to maintain decoding information and to not maintain encoding information; and

if the traffic is classified as bi-directional, causing the first DRE cache to maintain both encoding information and decoding information, and causing the second DRE cache to maintain both encoding information and decoding information.

2. The method of claim 1, wherein the parameter is entropy.

3. The method of claim 2, wherein the predetermined value is a floor, above which the traffic is classified as uni-directional.

4. The method of claim 1, wherein the parameter is compressibility.

5. The method of claim 4, wherein the predetermined value is a ceiling, below which the traffic is classified as uni-directional.

6. The method of claim 1, further comprising:

evaluating the traffic;

identifying a pattern that is based, at least, on classifying content within the traffic; and

classifying the traffic as uni-directional or bi-directional based on the pattern.

7. The method of claim 1, wherein the sender is a data center, the receiver is a branch office, and the network is a wide area network (WAN).

8. A non-transitory computer-readable medium/media that is encoded with logic that includes code for execution and when said logic is executed by a processor configured to perform operations for improving caching in data redundancy elimination (DRE) entities, said operations comprising:

calculating a parameter for traffic propagating in a network between a sender and a receiver, wherein the parameter includes one or more network traffic characteristics which indicates whether the traffic is uni-directional network traffic or bi-directional network traffic, and the traffic comprises encoding information and decoding information;

determining whether the parameter meets a predetermined value;

classifying the traffic as uni-directional if the parameter meets the predetermined value; and

classifying the traffic as bi-directional if the parameter does not meet the predetermined value;

if the traffic is classified as uni-directional, causing a first DRE cache at the sender to maintain encoding information and to not maintain decoding information, and causing a second DRE cache at the receiver to maintain decoding information and to not maintain encoding information; and

if the traffic is classified as bi-directional, causing the first DRE cache to maintain both encoding information and decoding information, and causing the second DRE cache to maintain both encoding information and decoding information.

9. The non-transitory computer readable medium/media of claim 8, wherein the parameter is entropy.

10. The non-transitory computer readable medium/media of claim 9, wherein the predetermined value is a floor, above which the traffic is classified as uni-directional.

11. The non-transitory computer readable medium/media of claim 8, wherein the parameter is compressibility.

12. The non-transitory computer readable medium/media of claim 11, wherein the predetermined value is a ceiling, below which the traffic is classified as uni-directional.

13. The non-transitory computer readable medium/media of claim 8, the operations further comprising:

evaluating the traffic;

identifying a pattern that is based, at least, on classifying content within the traffic; and

classifying the traffic as uni-directional or bi-directional based on the pattern.

14. A system for improving caching in data redundancy elimination (DRE) entities, said operations, comprising:

a memory element;

a processor configured to execute instructions associated with electronic code; and

one or more wide area application services (WAAS) modules configured to interface with the processor such that the system is configured for;

calculating a parameter for traffic propagating in a network between a sender and a receiver, wherein the parameter includes one or more network traffic characteristics which indicates whether the traffic is likely uni-directional network traffic or bi-directional network traffic, and the traffic comprises encoding information and decoding information;

determining whether the parameter meets a predetermined value;

classifying the traffic as uni-directional if the parameter meets the predetermined value; and

classifying the traffic as bi-directional if the parameter does not meet the predetermined value;

if the traffic is classified as uni-directional, causing a first DRE cache at the sender to maintain encoding information and to not maintain decoding information, and causing a second DRE cache at the receiver to maintain decoding information and to not maintain encoding information; and

if the traffic is classified as bi-directional, causing the first DRE cache to maintain both encoding information and decoding information, and causing the second DRE cache to maintain both encoding information and decoding information.

15. The system of claim 14, wherein the parameter is entropy, and wherein the predetermined value is a floor, above which the traffic is classified as uni-directional.

16. The system of claim 14, wherein the parameter is compressibility, and wherein the predetermined value is a ceiling, below which the traffic is classified as uni-directional.

17. The system of claim 14, wherein the system is further configured for:

evaluating the traffic;

identifying a pattern that is based, at least, on classifying content within the traffic; and

classifying the traffic as uni-directional or bi-directional based on the pattern.

18. The system of claim 14, wherein the system is associated with a data center, and the network is a wide area network (WAN).