PREDICTIVE SYNCHRONIZATION FOR CLUSTERED DEVICES

• US 20120057591A1
• Filed: 09/07/2010
• Published: 03/08/2012
• Est. Priority Date: 09/07/2010
• Status: Active Grant

• Current Assignee: Check Point Software Technologies Limited
• Original Assignee: Check Point Software Technologies Limited
• Inventors: Erman, Amir, Perlmutter, Amnon, Weissman, Ben Zion
• Granted Patent: US 8,406,233 B2
• Time in Patent Office: Days
• US Class Current: 370/389
• CPC Class Codes: G06F 11/1464 for networked environments
• CPC Class Codes: H04L 45/46 Cluster building
• CPC Class Codes: H04L 63/0218 Distributed architectures, e.g. distributed firewalls
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/142 Managing session states for stateless protocols; Signalling session states; State transitions; Keeping-state mechanisms
• CPC Class Codes: H04L 69/22 Parsing or analysis of headers
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06
• CPC Class Codes: H04L 7/00 Arrangements for synchronising receiver with transmitter synchronisation of generators of electric oscillations or pulses H03L7/00

Abstract

A method and system is provided for a scalable clustered system. The method and system may handle asynchronous traffic as well as session backup. In the method and system, a home cluster member having ownership of a local session predicts designation of a an other cluster member to receive a packet associated with the local session and sends appropriate state information or forwarding instruction to the other network member.

Claims

11. A computer-readable storage media comprising computer-executable instructions stored thereon, the computer-executable instructions, when executed, configuring a clustered system to perform actions comprising:

a) relaying of information associated with a packet from a first member of the clustered system to a second member of the clustered system before arrival of said packet to said second member, and

b) predicting designation of said second member to receive said packet.

12. The computer-readable storage media of claim 11, wherein said predicting includes computing a deterministic function.

13. The computer-readable storage media of claim 11, wherein said predicting includes computing a hashing function.

14. The computer-readable storage media of claim 11, wherein the actions further comprise:

c) bouncing said packet from said second member to said first member.

15. The computer-readable storage media of claim 11, wherein said relaying is not to a third member of the clustered system.

16. The computer-readable storage media of claim 11, wherein said relaying is unicast.

17. The computer-readable storage media of claim 11, wherein the computer-executable instructions when executed configure the clustered system to perform said relaying subsequent to said predicting.

18. The computer-readable storage media of claim 11, wherein the actions further comprise:

c) discarding of an illegitimate packet by the first member.

19. A clustered system including a plurality of members, comprising:

a) a memory accessible to a first member of the plurality of members, said memory configured to store

i) a state machine and

ii) an algorithm for predicting designation of a second member of the plurality of members to receive a packet, and

b) a processor accessible to said first member, said processor configured to execute said algorithm.

1. A method of synchronizing a clustered system having at least a first member and a second member, the method comprising:

a) relaying from the first member to the second member information associated with a packet before arrival of said packet to the second member, and

b) predicting designation of the second member to receive said packet.

2. The method of claim 1, wherein said packet is an asynchronous reply packet.

3. The method of claim 1, wherein said second member is a backup member.

4. The method of claim 1, wherein said predicting includes computing a deterministic function.

5. The method of claim 4, wherein said predicting includes computing a hashing function.

6. The method of claim 1, further comprising:

c) bouncing said packet from the second member to the first member.

7. The method of claim 1, wherein said relaying is not to a third member of the clustered system.

8. The method of claim 1, wherein said relaying is unicast.

9. The method of claim 1, wherein said relaying is subsequent to said predicting.

10. The method of claim 1, further comprising:

c) discarding of an illegitimate packet by the first member.

20. The clustered system of claim 19, wherein said processor is further configured for relaying information associated with said packet to said second member.

21. The clustered system of claim 19, wherein said information includes instructions for said second member to bounce said packet to said first member.

22. The clustered system of claim 19, wherein said second member is a backup member.

23. The clustered system of claim 19, wherein said processor is further configured to not relay said information to a third member of said plurality of members.

24. The clustered system of claim 19, wherein said processor is further configured to discard an illegitimate packet.

23-1. The clustered system of claim 19, wherein said processor is further configured to relay said information by unicast communication.