System and method for highly reliable data replication

• US 8,209,283 B1
• Filed: 02/19/2009
• Issued: 06/26/2012
• Est. Priority Date: 02/19/2009
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Wang, Haihong
• Primary Examiner(s): Fleurantin, Jean B
• Assistant Examiner(s): Girma, Anteneh
• Application Number:
  US12/378,819
• Time in Patent Office: 1,223 Days
• Field of Search: 707/610, 707/201.999, 709/230
• US Class Current: 707/610
• CPC Class Codes: G06F 16/178 Techniques for file synchronisation in file systems
• CPC Class Codes: Y10S 707/99952 Coherency, e.g. same view to multiple users

Abstract

Data replication includes generating replication data that is part of a replicated file system to be sent over a communication channel to a destination replication device; adding additional verification information to at least a portion of the replication data to prevent data corruption; and sending the replication data and the additional verification information over the communication channel to the destination replication device. The replication data with additional verification information is sent over the communication channel using a reliable protocol that allows the replication data to be verified by the reliable protocol at the destination replication device. The reliable protocol is a protocol capable of detecting most but not all data corruption introduced by the communication channel. The additional verification information includes information for verifying that replication data sent using the reliable protocol does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol.

Claims

1. A reliable replication system comprising:

a processor configured to;

generate replication data that is part of a replicated file system to be sent over a communication channel to a destination replication device, wherein the replication data is included in a first container and wherein the first container is to be included in a second container associated with a reliable protocol;

add additional verification information to at least a portion of the replication data included in the first container to prevent data corruption; and

an interface coupled to the processor, configured to send the second container including the first container including the replication data with additional verification information over the communication channel to the destination replication device;

wherein;

the second container including the first container including the replication data with additional verification information is sent over the communication channel using the reliable protocol that allows at least a portion of the second container to be verified by the reliable protocol at the destination replication device;

the reliable protocol is a protocol capable of detecting most but not all data corruption introduced by the communication channel; and

the additional verification information included in the first container includes information for verifying that replication data, included in the first container, sent using the reliable protocol does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol;

wherein upon receipt by the destination replication device, the replication data is configured to be verified by determining whether at least a portion of the second container can be verified using the reliable protocol and in the event that the second container is verified by the reliable protocol, then checking the additional verification information included in the first container to further verify that the replication data does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol.

2. The system of claim 1, wherein the replication data includes a data segment.

3. The system of claim 1, wherein the replication data includes a data segment reference.

4. The system of claim 1, wherein the reliable protocol detects data corruption introduced by the communication channel using a reliable protocol checksum;

and the additional verification information includes an additional verification checksum that includes more bits than the reliable protocol checksum.

5. The system of claim 1, wherein the reliable protocol is Transport Control Protocol (TCP).

6. The system of claim 1, wherein the reliable protocol is Transport Control Protocol (TCP), and the additional verification information includes a value that is greater in length than a TCP checksum.

7. The system of claim 1, wherein the additional verification information is generated using a Message-Digest algorithm 5 (MD5) function.

8. The system of claim 1, wherein the additional verification information is included in a Remote Procedure Call (RPC) argument.

9. The system of claim 1, wherein the additional verification information is included in a Remote Procedure Call (RPC) argument and is determined based at least in part on at least one other RPC argument.

10. A data replication method comprising:

generating replication data that is part of a replicated file system to be sent over a communication channel to a destination replication device, wherein the replication data is included in a first container and wherein the first container is to be included in a second container associated with a reliable protocol;

adding additional verification information to at least a portion of the replication data included in the first container to prevent data corruption; and

sending the second container including the first container including the replication data and the additional verification information over the communication channel to the destination replication device;

wherein;

the second container including the first container including the replication data with additional verification information is sent over the communication channel using the reliable protocol that allows at least a portion of the second container to be verified by the reliable protocol at the destination replication device;

the reliable protocol is a protocol capable of detecting most but not all data corruption introduced by the communication channel; and

the additional verification information included in the first container includes information for verifying that replication data, included in the first container, sent using the reliable protocol does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol;

wherein upon receipt by the destination replication device, the replication data is configured to be verified by determining whether at least a portion of the second container can be verified using the reliable protocol and in the event that the second container is verified by the reliable protocol, then checking the additional verification information included in the first container to further verify that the replication data does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol.

11. The method of claim 10, wherein the replication data includes a data segment.

12. The method of claim 10, wherein the replication data includes a data segment reference.

13. The method of claim 10, wherein the reliable protocol detects data corruption introduced by the communication channel using a reliable protocol checksum;

and the additional verification information includes an additional verification checksum that includes more bits than the reliable protocol checksum.

14. The method of claim 10, wherein the reliable protocol is Transport Control Protocol (TCP).

15. The method of claim 10, wherein the reliable protocol is Transport Control Protocol (TCP), and the additional verification information includes a value that is greater in length than a TCP checksum.

16. The method of claim 10, wherein the additional verification information is generated using a Message-Digest algorithm 5 (MD5) function.

17. The method of claim 10, wherein the additional verification information is included in a Remote Procedure Call (RPC) argument.

18. The method of claim 10, wherein the additional verification information is included in a Remote Procedure Call (RPC) argument and is determined based at least in part on at least one other RPC argument.

19. A computer program product for data replication, the computer program product being embodied in a computer readable storage medium and comprising computer instructions for:

generating replication data that is part of a replicated file system to be sent over a communication channel to a destination replication device, wherein the replication data is included in a first container and wherein the first container is to be included in a second container associated with a reliable protocol;

adding additional verification information to at least a portion of the replication data included in the first container to prevent data corruption; and

sending the second container including the first container including the replication data and the additional verification information over the communication channel to the destination replication device;

wherein;

the second container including the first container including the replication data with additional verification information is sent over the communication channel using the reliable protocol that allows at least a portion of the second container to be verified by the reliable protocol at the destination replication device;

the reliable protocol is a protocol capable of detecting most but not all data corruption introduced by the communication channel; and

the additional verification information included in the first container includes information for verifying that replication data, included in the first container, sent using the reliable protocol does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol;

wherein upon receipt by the destination replication device, the replication data is configured to be verified by determining whether at least a portion of the second container can be verified using the reliable protocol and in the event that the second container is verified by the reliable protocol, then checking the additional verification information included in the first container to further verify that the replication data does not include data corruption that was introduced by the communication channel and undetected by the reliable protocol.