Adaptive, Application-Aware Selection of Differentiated Network Services

• US 20090182874A1
• Filed: 02/11/2009
• Published: 07/16/2009
• Est. Priority Date: 03/29/2004
• Status: Active Grant

• Current Assignee: CA, Inc. (d/b/a CA Technologies) (Broadcom, Inc.)
• Original Assignee: Packeteer Incorporated (Gen Digital Inc.)
• Inventors: Morford, Michael Robert, Purvy, Robert E.
• Granted Patent: US 7,783,754 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 41/0213 Standardised network management protocols, e.g. simple network management protocol [SNMP]
• CPC Class Codes: H04L 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/0852 Delays

Abstract

Methods, apparatuses and systems that dynamically adjust the selection of differentiated network services for selected classes of traffic in response to changing network conditions or application performance levels. In one implementation, the present invention allows for a differentiated network services scheme that adapts to existing network conditions and, in one implementation, selects higher, generally more expensive classes of differentiated network service for certain data flows when the performance of selected applications degrades below a threshold level. The present invention, in one implementation, allows for bandwidth cost savings without sacrificing application performance.

Claims

1. A method comprising:

marking packets associated with a network application for transfer at a first service level over a differentiated-services network that supports a plurality of service levels;

monitoring performance of the network application involving the transfer of packets between a first set of hosts and a second set of hosts over the differentiated-services network;

marking packets associated with the network application for transfer at a second service level of the plurality of service levels supported by the differentiated services network in response to a degradation in the performance of the network application; and

if the performance of the network application does not improve after marking packets associated with the network application for transfer at the second service level, then returning to marking packets associated with the network application for transfer at the first service level over the differentiated-services network.

2. The method of claim 1 wherein the monitoring step comprises monitoring the response times between at least one host in the first set and at least one host in the second set.

3. The method of claim 2 wherein the monitoring the response times step comprises

recording, at a network device disposed between a first set of hosts and a second set of hosts, the arrival time of the packets associated with the network application;

and

computing, based on the recorded packet arrival times, one or more parameters characterizing the response time between at least one host in the first set and at least one host in the second set.

4. The method of claim 1 wherein designating the packets comprises adding labels to the packets.

5. The method of claim 4 wherein the differentiated services network is a Multi-Protocol Label Switching (MPLS) network, and wherein the labels are MPLS tags.

6. The method of claim 1 wherein designating the packets comprises adding tags to the packets.

7. The method of claim 6 wherein the differentiated services network is a diffserv network, and wherein the tags are diffserv tags.

8. The method of claim 1 wherein the monitoring step comprises monitoring the packet exchange (PET) time observed over the differentiated services network.

9. The method of claim 1 wherein the monitoring step comprises measuring the network delay attributable to the differentiated services network.

10. A method comprising:

marking packets associated with a network application for transfer at a first service level over a differentiated-services network that supports a plurality of service levels;

monitoring performance of the network application involving the transfer of packets between a first set of hosts and a second set of hosts over the differentiated-services network;

in response to a degradation in the performance of the network application, marking packets associated with the network application for transfer at a second service level of the plurality of service levels supported by the differentiated services network and initiating synthetic transactions involving the transfer of packets at the first service level to and from a remote host over the differentiated-services network; and

if the performance of the synthetic transactions over the differentiated-services network crosses a threshold, then returning to marking packets associated with the network application for transfer at the first service level over the differentiated-services.

11. The method of claim 10 further comprising

determining a metric characterizing the performance of the synthetic transactions when the returning to marking packets associated with the network application for transfer at the first service level is implemented;

using the metric to adjust the threshold based on monitored performance of the network application subsequent to the returning to marking packets associated with the network application for transfer at the first service level.

12. The method of claim 10 wherein the monitoring step comprises monitoring the response times between at least one host in the first set and at least one host in the second set.

13. The method of claim 12 wherein the monitoring the response times step comprises

recording, at a network device disposed between a first set of hosts and a second set of hosts, the arrival time of the packets associated with the network application;

and

computing, based on the recorded packet arrival times, one or more parameters characterizing the response time between at least one host in the first set and at least one host in the second set.

14. The method of claim 10 wherein designating the packets comprises adding labels to the packets.

15. The method of claim 14 wherein the differentiated services network is a Multi-Protocol Label Switching (MPLS) network, and wherein the labels are MPLS tags.

16. A method comprising:

marking packets associated with a first network application for transfer at a first service level over a differentiated-services network that supports a plurality of service levels;

monitoring performance of the network application involving the transfer of packets between a first set of hosts and a second set of hosts over the differentiated-services network;

marking packets associated with the network application for transfer at a second service level of the plurality of service levels supported by the differentiated services network in response to a degradation in the performance of the network application; and

if performance of one or more additional network applications involving transfer of packets at the first service level over the differentiated-services network improves, then returning to marking packets associated with the first network application for transfer at the first service level over the differentiated-services network.

17. The method of claim 16 further comprising

determining a first performance metric of the one or more additional network applications when the marking packets associated with the network application for transfer at the second service level is implemented;

and

periodically comparing the first performance metric of the one or more additional network applications to subsequently determined performance metrics associated with the one or more additional network applications to determine whether the performance has improved.

18. The method of claim 16 wherein the monitoring step comprises monitoring the response times between at least one host in the first set and at least one host in the second set.

19. The method of claim 18 wherein the monitoring the response times step comprises

recording, at a network device disposed between a first set of hosts and a second set of hosts, the arrival time of the packets associated with the network application;

and

computing, based on the recorded packet arrival times, one or more parameters characterizing the response time between at least one host in the first set and at least one host in the second set.

20. The method of claim 16 wherein designating the packets comprises adding labels to the packets.