Peer protocol status query in clustered computer system

• US 7,769,844 B2
• Filed: 12/07/2000
• Issued: 08/03/2010
• Est. Priority Date: 12/07/2000
• Status: Expired due to Fees

• Current Assignee: LinkedIn Corporation (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Miller, Robert
• Primary Examiner(s): EL CHANTI, HUSSEIN A
• Application Number:
  US09/732,189
• Publication Number:
  US 20020073153A1
• Time in Patent Office: 3,526 Days
• Field of Search: 709/223, 709/224, 709/228, 709/230, 709/234, 709/237, 709/248
• US Class Current: 709/224
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• 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 9/40 Network security protocols

Abstract

An apparatus, program product and method locally track protocol progress information within each member of a group in a clustered computer system that is capable of identifying at least one problematic member of the group. By locally tracking such information, any member of the group may be directed to provide such information on demand in response to a query directed to such member.

Claims

1. A method of determining a status of a peer protocol initiated on a plurality of members of a group in a clustered computer system, the method comprising:

(a) locally tracking protocol progress information for a peer protocol within each of a plurality of members collectively managed as a group by a clustered computer system, wherein the peer protocol is of the type wherein each member of the group receives a message associated with the peer protocol and returns an acknowledgment in association with locally processing the peer protocol; and

(b) responding to a query directed to a selected member of the group by providing the protocol progress information locally tracked by the selected member, wherein the query comprises a request for the protocol progress information.

2. The method of claim 1, wherein locally tracking protocol progress information includes tracking, within a first member of the group, acknowledgment (ACK) messages directed to the first member by each other member of the group.

3. The method of claim 1, wherein locally tracking protocol progress information includes:

(a) tracking, within a first member of the group, a current acknowledgment (ACK) round for the first member, the current ACK round associated with a current peer protocol being processed by the first member; and

(b) tracking, within the first member, a last ACK round received parameter associated with each other member of the group, the last ACK round received parameter for each other member identifying a peer protocol associated with a last received ACK message from such other member.

4. The method of claim 3, wherein locally tracking protocol progress information further includes updating the current ACK round for the first member in response to receipt of ACK messages for the current peer protocol from all other members of the group.

5. The method of claim 1, wherein locally tracking protocol progress information includes updating the protocol progress information for a first member of the group in response to receipt of an acknowledgment (ACK) message directed to the first member.

6. The method of claim 1, further comprising:

(a) waiting on a resource required by a protocol being processed on the selected member; and

(b) monitoring for receipt of the query by the selected member while waiting on the resource.

7. The method of claim 6, wherein the protocol is a peer protocol, and wherein waiting on the resource includes waiting for receipt of an acknowledgment (ACK) message directed to the selected member.

8. The method of claim 6, wherein the protocol is a local protocol, and wherein waiting on the resource includes waiting on a local resource requested by the selected member.

9. The method of claim 8, wherein the local resource is selected from the group consisting of a lock and a creation of a new job.

10. The method of claim 6, wherein waiting on the resource includes waiting for receipt of a message by a local message queue for the selected member, and wherein monitoring for receipt of the query includes monitoring the local message queue for receipt of a query message.

11. The method of claim 1, wherein locally tracking protocol progress information within each member of the group includes locally tracking within the selected member protocol progress information associated with at least one other member in the group.

12. The method of claim 1, wherein locally tracking protocol progress information within each member of the group includes locally tracking within the selected member protocol progress information associated with all other members in the group.

13. The method of claim 1, wherein locally tracking protocol progress information within each member of the group includes locally tracking within each member protocol progress information associated with each other member in the group.

14. An apparatus, comprising:

(a) a memory; and

(b) a program resident in the memory, the program configured to determine a status of a peer protocol initiated on a plurality of members that are collectively managed as a group by a clustered computer system by locally tracking protocol progress information within at least one member of the group, and providing the protocol progress information locally tracked by a member of the group in response to a query directed to such member, wherein the peer protocol is of the type wherein each member of the group receives a message associated with the peer protocol and returns an acknowledgment in association with locally processing the peer protocol, and wherein the query comprises a request for the protocol progress information.

15. The apparatus of claim 14, wherein the program is configured to locally track protocol progress information by tracking, within a first member of the group, acknowledgment (ACK) messages directed to the first member by each other member of the group.

16. The apparatus of claim 14, wherein the program is configured to locally track protocol progress information by tracking, within a first member of the group, a current acknowledgment (ACK) round for the first member, and tracking, within the first member, a last ACK round received parameter associated with each other member of the group, wherein the current ACK round is associated with a current peer protocol being processed by the first member, and wherein the last ACK round received parameter for each other member identifies a peer protocol associated with a last received ACK message from such other member.

17. The apparatus of claim 14, wherein the program is further configured to wait on a resource required by a protocol being processed on the selected member, and monitor for receipt of the query by the selected member while waiting on the resource.

18. The apparatus of claim 17, wherein the protocol is a peer protocol, and wherein the program is configured to wait on the resource by waiting for receipt of an acknowledgment (ACK) message directed to the selected member.

19. The apparatus of claim 17, wherein the protocol is a local protocol, and wherein the program is configured to wait on the resource by waiting on a local resource requested by the selected member.

20. The apparatus of claim 17, wherein the program is configured to locally track protocol progress information by locally tracking within a first member protocol progress information associated with at least one other member in the group.

21. The apparatus of claim 17, wherein the program is configured to locally track protocol progress information by locally tracking within each member protocol progress information associated with each other member in the group.

22. A clustered computer system, comprising:

(a) a plurality of nodes coupled to one another over a network;

(b) a plurality of members collectively managed as a group by the clustered computer system and configured to be executed by at least one of the plurality of nodes; and

(c) a program configured to be executed by at least one of the plurality of nodes to determine a status of a peer protocol initiated on the plurality of members by locally tracking protocol progress information within at least one member of the group, and providing the protocol progress information locally tracked by a member of the group in response to a query directed to such member, wherein the peer protocol is of the type wherein each member of the group receives a message associated with the peer protocol and returns an acknowledgment in association with locally processing the peer protocol, and wherein the query comprises a request for the protocol progress information.