Forward packet recovery with constrained network overhead

• US 10,326,551 B2
• Filed: 03/12/2018
• Issued: 06/18/2019
• Est. Priority Date: 08/19/2016
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Silver Peak Systems Incorporated (Hewlett-Packard Enterprise Company)
• Inventors: Hughes, David Anthony
• Primary Examiner(s): Abraham, Esaw T
• Application Number:
  US15/918,807
• Publication Number:
  US 20180205494A1
• Time in Patent Office: 463 Days
• CPC Class Codes: H04L 1/0007 by modifying the frame length
• CPC Class Codes: H04L 1/0041 Arrangements at the transmitter end
• CPC Class Codes: H04L 1/0057 Block codes H04L1/0061, H04L1/0064 take precedence
• CPC Class Codes: H04L 1/0083 Formatting with frames or packets; Protocol or part of protocol for error control
• CPC Class Codes: H04L 1/0086 Unequal error protection H04L27/00 and H04L1/004 take precedence for layer 1/2 aspects, e.g. bit loading
• CPC Class Codes: H04L 69/22 Parsing or analysis of headers

Abstract

Disclosed herein are systems and methods for forward packet recovery in a communication network with constrained network bandwidth overhead. In exemplary embodiments, a target byte protection ratio is determined. Error correcting frames are dynamically generated by a first processor such that error correcting information can be generated to approximate the target byte protection ratio. The data packets and error correcting information are then transmitted across one or more communication networks to a second processor. The second processor can use the error correcting information to regenerate or replace data packets missing or corrupted in transmission across one or more communication networks.

Claims

1. A computer-implemented method for providing corrected data packets to a second processor, the method comprising:

receiving at a first processor, a data stream comprising a plurality of data packets for transmission across at least one communication network, the plurality of data packets comprising smaller size data packets and larger size data packets;

selecting a target byte protection ratio for the data stream, the target byte protection ratio representing a target number of bytes of error correcting information per bytes of data in the data stream;

dynamically generating one or more error correcting frames for the data stream;

generating one or more error correction data packets for each error correcting frame, in accordance with the target byte protection ratio; and

transmitting the plurality of data packets and the one or more error correction data packets across the at least one communication network to the second processor.

2. The method of claim 1, wherein the target byte protection ratio for the data stream is selected to correspond to a target network bandwidth usage for the error correcting information.

3. The method of claim 1, wherein the one or more error correcting frames are generated in accordance with a size policy, such that all data packets in an error correcting frame are approximately a same size.

4. The method of claim 1, wherein the one or more error correcting frames are generated in accordance with a timeout policy, such that all packets received within a certain period of time are determined to be within the one or more error correcting frames.

5. The method of claim 1, wherein the one or more error correcting frames are bounded based on a size of a sequential data packet in the data stream.

6. The method of claim 1, wherein the dynamically generating one or more error correcting frames is based on a size differential between two sequential data packets in the data stream.

7. The method of claim 1, wherein a terminal error correcting frame boundary is generated if a subsequent packet is larger in size or smaller in size by a predetermined threshold, compared to previous data packets in the error correcting frame.

8. The method of claim 1, wherein the generating one or more error correction data packets in accordance with the target byte protection ratio further comprises:

keeping a running tally of a number of error correction data packets generated for all error correcting frames in the data stream; and

adjusting an amount of error correction data packets generated for each subsequent frame based on the running tally of error correction data packets for the data stream, in accordance with the target byte protection ratio for the data stream.

9. The method of claim 1, wherein the receiving the plurality of data packets for transmission across a at least one communication network further comprises:

comparing a size of each data packet to a maximum transmission unit capacity of the at least one communication network; and

fragmenting each data packet above the capacity of the maximum transmission unit for the at least one communication network into two or more portions of substantially equal size.

10. The method of claim 1, wherein the dynamically generating one or more error correcting frames for the data stream comprises:

re-ordering the plurality of data packets according to size, such that all data packets of a comparable size are in a same error correcting frame.

11. The method of claim 1, wherein the dynamically generating one or more error correcting frames for the data stream further comprises:

categorizing the plurality of data packets in the data stream into a plurality of categories according to size, the categories comprising at least the smaller size data packets and the larger size data packets;

segmenting the larger size data packets into a first portion equivalent in size to at least one of the smaller size data packets and a second portion comprising a remainder of the larger size data packet;

generating at least one error correcting frame for the smaller size data packets and the first portion of the larger size data packets; and

generating at least one error correcting frame for the second portion of the larger size data packets.

12. The method of claim 1, wherein at least one of the plurality of data packets is received out of order at the second processor.

13. The method of claim 1, further comprising regenerating the data stream at the second processor by:

receiving the plurality of data packets and the one or more error correction data packets from the first processor; and

utilizing the received plurality of data packets and the received one or more error correction data packets to regenerate the data stream by correcting at least one lost, corrupt, or out of order data packet in the data stream.

14. The method of claim 1, wherein the error correcting information is generated using Reed-Solomon coding.

15. A computing system for providing corrected data packets to a second network appliance, the system comprising:

a first network appliance in communication with a second network appliance via at least one communication network;

wherein the first network appliance comprises at least one processor configured to;

receive a data stream comprising a plurality of data packets for transmission across the at least one communication network to the second network appliance;

select a target byte protection ratio for the data stream, the target byte protection ratio representing a target number of bytes of error correcting information per bytes of data in the data stream;

dynamically generate one or more error correcting frames for the data stream;

generate one or more error correction data packets for each dynamically generated error correcting frame, in accordance with the target byte protection ratio; and

transmit the plurality of data packets and the one or more error correction data packets across the at least one communication network to the second network appliance.

16. The system of claim 15, wherein the second network appliance comprises at least one processor configured to:

receive the plurality of data packets and the one or more error correction data packets from the first network appliance; and

utilize the received plurality of data packets and the received one or more error correction data packets to regenerate the data stream by correcting at least one lost, corrupt, or out of order data packet in the data stream.

17. The system of claim 15, wherein the target byte protection ratio for the data stream is selected to correspond to a target network bandwidth usage for the error correcting information.

18. The system of claim 15, wherein the one or more error correcting frames are generated in accordance with a size policy, such that all data packets in an error correcting frame are approximately a same size.

19. The system of claim 15, wherein the one or more error correcting frames are bounded based on a size of a sequential data packet in the data stream.

20. The system of claim 15, wherein a terminal error correcting frame boundary is generated if a subsequent packet is larger in size or smaller in size by a predetermined threshold, compared to previous data packets in the error correcting frame.