Apparatus and Method for Efficient Handling of Mostly Read Data in a Computer Server

• US 20070288524A1
• Filed: 06/07/2006
• Published: 12/13/2007
• Est. Priority Date: 06/07/2006
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Luick, David A.
• Granted Patent: US 7,490,111 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• 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: Y10S 707/966 Distributed
• CPC Class Codes: Y10S 707/99953 Recoverability

Abstract

An apparatus and method is described for improving access to mostly read data on network servers. The preferred embodiments more efficiently utilize replicated data servers to minimize server response time for improved performance of data access to network servers by workload managing client requests across the primary server and all replicated servers when it is possible to do so. In preferred embodiments, a load balancer supplies the most current data for mostly read data transactions while maximizing server usage by workload managing client requests across the primary server and all replicated servers. Client requests are managed by a load balancer in the workload manager. Client requests are sent by the load balancer to replicated servers when a routing table (stale data marker list) indicates that the data is in a safe period. Clients are directed exclusively to the primary server only during data update times.

Claims

1. A computer apparatus comprising:

at least one processor;

a memory coupled to the at least one processor;

a client server program in the memory executing by the at least one processor that receives data requests from a client, the client server program comprising;

a stale data marker list with stale data markers corresponding to stale data on a replicated server; and

a workload manager that routes data requests exclusively to a primary server when there is an entry in the stale data marker list corresponding to the requested data, and where the workload manager workload manages data requests to the primary server and one or more replicated servers when there is no entry in the stale data marker list corresponding to the requested data.

2. The computer apparatus of claim 1 wherein the client server program resides on the same computer hardware as the client making the data requests.

3. The computer apparatus of claim 1 further comprising a data server program residing on a second computer apparatus that receives data requests from the client server program wherein the data server program further comprises a second stale data marker list that indicates stale data residing on the second computer system.

4. The computer apparatus of claim 1 wherein the stale data marker includes a key that corresponds to stale data.

5. The computer apparatus of claim 1 wherein the stale data marker includes a data change time and a replication time.

6. The computer apparatus of claim 5 wherein the change time and replication time are used by the workload manager to determine when data on a server is stale.

7. The apparatus of claim 1 wherein the client server is part of WebSphere.

8. A computer method for workload managing mostly read transactions, the method comprising the steps of:

(A) a client server receiving a data request from a client;

(B) extracting a key from the data request;

(C) routing the data request to a primary server if the data corresponding to the key is stale; and

(D) routing the data request to a replicated server if the data corresponding to the key is not stale.

9. The method of claim 8 further comprising the steps of:

(E) monitoring changes to the data;

(F) extracting historical propagation times and change times;

(G) calculating the replication time from the propagation time;

(H) updating a stale data marker with the replication time; and

(I) replicating the stale data marker to one or more replicated data servers.

10. The method of claim 8 further comprising the steps of:

(J) inserting a timestamp for a stale data marker in a request for data to a data server;

(K) the data server comparing the timestamp with a timestamp for a local stale data marker list; and

(L) forwarding the request for data to a primary server if the timestamps do not match and processing the request for data at the local data server if the timestamps match.

11. The method of claim 8 further comprising the steps of:

(M) selecting the next stale data marker in a stale data marker list;

(N) determining if the stale data marker is still needed by comparing the time elapsed with the replication time; and

(O) clearing the stale data marker from the stale data marker list if the elapsed time is greater than the replication time.

12. The method of claim 8 wherein the client server is part of WebSphere.

13. A computer-readable program product comprising:

a client server program that receives data requests from a client, the client server program comprising;

a stale data marker list with stale data markers corresponding to stale data on a replicated server; and

a workload manager that routes data requests exclusively to a primary server when there is an entry in the stale data marker list corresponding to the requested data, and where the workload manager workload manages data requests to the primary server and one or more replicated servers when there is no entry in the stale data marker list corresponding to the requested data; and

recordable media bearing the client server program.

14. The program product of claim 13 wherein the client server program resides on the same computer hardware as the client making the data requests.

15. The program product of claim 13 further comprising a data server program residing on a second computer apparatus that receives data requests from the client server program wherein the data server program further comprises a second stale data marker list that indicates stale data residing on the second computer system.

16. The program product of claim 13 wherein the stale data marker includes a data key that corresponds to stale data.

17. The program product of claim 13 wherein the stale data marker includes a data change time and a replication time.

18. The program product of claim 17 wherein the change time and replication time are used by the workload manager to determine when data on a server is stale.

19. The program product of claim 13 wherein the client server is part of WebSphere