Network protocol proxy

• US 8,966,112 B1
• Filed: 11/29/2010
• Issued: 02/24/2015
• Est. Priority Date: 11/30/2009
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Software, Inc. (Dell Technologies Inc.)
• Inventors: McDonald, Michael, Franke, Michael
• Primary Examiner(s): Winder, Patrice
• Assistant Examiner(s): Chang, Julian
• Application Number:
  US12/955,791
• Time in Patent Office: 1,548 Days
• Field of Search: 709217-219, 709223-237, 370229-240, 370252-253
• US Class Current: 709/235
• CPC Class Codes: G06F 16/182 Distributed file systems
• 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 47/115 using a dedicated packet
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 47/193 at the transport layer, e.g. TCP related
• CPC Class Codes: H04L 47/25 with rate being modified by the source upon detecting a change of network conditions
• CPC Class Codes: H04L 65/1045 Proxies, e.g. for session initiation protocol [SIP]
• CPC Class Codes: H04L 69/14 Multichannel or multilink protocols
• CPC Class Codes: H04L 69/163 In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/321 Interlayer communication protocols or service data unit [SDU] definitions; Interfaces between layers

Abstract

A network proxy can be provided as a layer between an application layer protocol (such as the Remote Desktop Protocol) and a transport layer protocol (such as TCP). The network proxy can intercept communications between the application layer protocol and the transport layer protocol. The network proxy can transmit communications on multiple connections, without the application layer or transport layer protocols being aware of the parallelization.

Claims

1. A method of managing a plurality of network connections, the method comprising:

by a computer system comprising computer hardware;

receiving a message from an application for transmission over a network;

determining a characteristic of the application;

selecting a number of parallel logical network connections to establish based at least partly on the application characteristic;

establishing the parallel logical network connections to a remote host system;

establishing a congestion control connection with the remote host system, wherein a network proxy implemented on a host system is configured to send test packets to a remote network proxy implemented on the remote host system;

monitoring, by at least one of the network proxy and the remote network proxy, the congestion control connection to determine a level of congestion; and

transmitting the message over the parallel logical network connections to the remote host system.

2. The method of claim 1, wherein the application characteristic comprises a type of the application.

3. The method of claim 2, wherein said selecting the number of parallel logical network connections comprises selecting relatively more connections when the application is a higher bandwidth-intensive application than when the application is a lower bandwidth-intensive application.

4. The method of claim 1, further comprising selecting a buffer size for one or more of the parallel logical network connections based at least in part on the application characteristic.

5. The method of claim 1, wherein said receiving the message from the application comprises intercepting the message from the application, such that said establishing the parallel logical network connections is abstracted from the application.

6. A non-transitory computer-readable storage medium comprising computer-executable instructions configured to implement a method of managing a plurality of network connections, the method comprising:

receiving a message from an application for transmission over a network;

determining a characteristic of the network;

selecting a number of parallel logical network connections to establish based at least partly on the network characteristic;

establishing the parallel logical network connections to a remote host system;

establishing a congestion control connection with the remote host system, wherein a network proxy implemented on a host system is configured to send test packets to a remote network proxy implemented on the remote host system;

monitoring, by at least one of the network proxy and the remote network proxy, the congestion control connection to determine a level of congestion; and

transmitting the message over the parallel logical network connections to the remote host system.

7. The non-transitory computer-readable storage medium of claim 6, wherein the characteristic of the network comprises available bandwidth.

8. The non-transitory computer-readable storage medium of claim 7, wherein said selecting the number of parallel logical network connections comprises selecting relatively more connections when the available bandwidth is relatively higher and selecting relatively fewer connections when the available bandwidth is relatively lower.

9. The non-transitory computer-readable storage medium of claim 6, wherein the characteristic of the network comprises latency.

10. The non-transitory computer-readable storage medium of claim 9, wherein said selecting the number of parallel logical network connections comprises selecting relatively more connections when the latency is relatively higher and selecting relatively fewer connections when the latency is relatively lower.

11. The non-transitory computer-readable storage medium of claim 6, wherein the method further comprises selecting a buffer size for one or more of the parallel logical network connections based at least in part on the network characteristic.

12. The non-transitory computer-readable storage medium of claim 6, wherein said receiving the message from the application comprises intercepting the message from the application, such that said establishing the parallel logical network connections is abstracted from the application.

13. A method of managing a plurality of network connections, the method comprising:

by computer system comprising computer hardware;

receiving a message from an application for transmission over a network;

establishing the parallel logical network connections to a remote host system;

transmitting the message over the parallel logical network connections to the remote host system;

establishing a congestion control connection with the remote host system, wherein a network proxy implemented on a host system is configured to send test packets to a remote network proxy implemented on the remote host system;

monitoring, by at least one of the network proxy and the remote network proxy, one or more characteristics of at least one of the parallel logical network connections, the application, and the congestion control connection; and

automatically adjusting one or more of the parallel logical network connections based at least in part on a change in the monitored characteristic; and

transmitting the message over the parallel logical network connections to the remote host system.

14. The method of claim 13, wherein the one or more monitored characteristics comprises one or more of available bandwidth and latency of the network.

15. The method of claim 14, wherein said automatically adjusting one or more of the parallel logical network connections comprises closing one or more of the connections in response to a drop in the available bandwidth.

16. The method of claim 14, wherein said automatically adjusting one or more of the parallel logical network connections comprises opening one or more additional connections in response to an increase in the latency.

17. The method of claim 13, further comprising receiving a second message from a second application, the second application being of a different type of application than the application from which the message is initially received.

18. The method of claim 17, wherein said automatically adjusting one or more of the parallel logical network connections is further performed based on the type of the second application.

19. The method of claim 13, wherein said automatically adjusting one or more of the parallel logical network connections further comprises adjusting a buffer size associated with one or more of the parallel logical network connections.

20. A system for managing a plurality of network connections, the system comprising:

a first network proxy implemented on a hardware appliance on a host computer system, the first network proxy comprising;

an interceptor module configured to intercept data intended to be sent by an application to a remote host system over a single Transmission Control Protocol (TCP) connection, and

a connections manager configured to;

determine one or more characteristics of one or both of the application and the network;

select a number of parallel TCP connections to establish in place of the single TCP connection based at least partly on the one or more characteristics;

establish the parallel TCP connections to a second network proxy implemented in the remote host system, the parallel TCP connections being abstracted from the application;

transmit a message over the parallel TCP connections to the remote host system;

establish a congestion control connection with the second network proxy, wherein the first network proxy is configured to send test packets to the second network proxy;

monitor, by at least one of the first network proxy and the second network proxy, one or more characteristics of at least one of the application, the network, and the congestion control connection, the one or more monitored characteristics comprising one or more of available bandwidth and latency; and

automatically adjust one or more of the parallel TCP connections based on a change in the one or more monitored characteristics.

21. The system of claim 20, wherein the connections manager is further configured to automatically adjust one or more of the parallel TCP connections by at least closing one or more of the connections in response to a drop in the available bandwidth.

22. The system of claim 20, wherein the connections manager is further configured to automatically adjust one or more of the parallel TCP connections by at least opening one or more additional parallel TCP connections in response to an increase in the latency.