Command process load balancing system

• US 10,348,815 B2
• Filed: 08/09/2016
• Issued: 07/09/2019
• Est. Priority Date: 12/19/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Takatsu, Noriaki, Yokoi, Atsushi
• Primary Examiner(s): Woolcock, Madhu
• Application Number:
  US15/232,087
• Publication Number:
  US 20160352822A1
• Time in Patent Office: 1,064 Days
• Field of Search: 709226
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1004 Server selection for load balancing
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30

Abstract

A command process load balancing system performs load balancing of received commands among a number of server processes to resolve access contention for virtual software resources. These contentions are resolved through a history recording unit that records a history including contents of a processed command and a response time of a process for the command into a history database. A prediction unit predicts, in a case where a set of commands to be processed is assigned to a server process, whether or not a load that is equal to or higher than a reference value is applied, on the basis of the history recorded in the history database. An assigning unit assigns at least one command included in the set of commands to be processed to a different server process, in accordance with prediction that a load that is equal to or higher than the reference.

Claims

1. A computer-implemented method for load balancing a first set of commands among a plurality of server processes, the method comprising:

receiving a first command of the first set of commands;

predicting that a load associated with a first server process of the plurality of server processes processing the first command and at least a second command of the first set of commands is greater than or equal to a reference value, wherein the predicting comprises;

determining a second set of processed commands based at least in part on a similarity of each command in the second set of processed commands to a respective command in the first set of commands;

accessing a first recorded history of the second set of processed commands, the first recorded history comprising a respective response time associated with processing of each command in the second set of processed commands;

determining that a combined response time for the second set of processed commands is greater than or equal to the reference value;

determining a third set of processed commands, wherein at least one command in the third set of processed commands is dissimilar from each command in the first set of commands;

accessing a second recorded history of the third set of processed commands, the second recorded history comprising a respective response time associated with processing of each command in the third set of processed commands;

determining a combined response time for the third set of processed commands; and

predicting that the load is greater than or equal to the reference value based at least in part on the combined response time for the second set of processed commands and the combined response time for the third set of processed commands;

assigning the first command for processing by a second server process of the plurality of server processes, wherein the second server process is different from the first server process; and

executing, by the second server process, the first command.

2. The computer-implemented method of claim 1, wherein the reference value is a reference time, and wherein the predicting comprises predicting that a response time associated with the first server process processing the first command and at least the second command is greater than or equal to the reference time.

3. The computer-implemented method of claim 1, wherein predicting that the load is greater than or equal to the reference value comprises determining that the combined response time for the second set of processed commands is greater than or equal to the combined response time for the third set of processed commands multiplied by a coefficient.

4. The computer-implemented method of claim 1, wherein determining the second set of processed commands further comprises determining that a particular command in the second set of processed commands is similar to the first command by determining at least one of:

i) that the particular command and the first command are a same type of command or share a first specific keyword or ii) that the particular command and the first command have a same command filename and same command folder name or share a second specific keyword.

5. The computer-implemented method of claim 1, wherein the first server process is a front-end server process, the second server process is a back-end server process, the first command is received by the front-end server process, and the first command is assigned to the back-end server process, the method further comprising:

processing the first command by the back-end server process;

sending results of the processing of the first command from the back-end server process to the front-end server process; and

recording a history comprising the results of the processing of the first command.

6. An information processing apparatus for load balancing a first set of commands among a plurality of server processes, the information processing apparatus comprising:

at least one memory storing computer-executable instructions; and

at least one processor configured to access the at least one memory and execute the computer-executable instructions to;

receive a first command of the first set of commands;

predict that a load associated with a first server process of the plurality of server processes processing the first command and at least a second command of the first set of commands is greater than or equal to a reference value, wherein the prediction unit predicts by;

determine a second set of processed commands based at least in part on a similarity of each command in the second set of processed commands to a respective command in the first set of commands;

access a first recorded history of the second set of processed commands, the first recorded history comprising a respective response time associated with processing of each command in the second set of processed commands;

determine that a combined response time for the second set of processed commands is greater than or equal to the reference value;

determine a third set of processed commands, wherein at least one command in the third set of processed commands is dissimilar from each command in the first set of commands;

access a second recorded history of the third set of processed commands, the second recorded history comprising a respective response time associated with processing of each command in the third set of processed commands;

determine a combined response time for the third set of processed commands; and

predict that the load is greater than or equal to the reference value based at least in part on the combined response time for the second set of processed commands and the combined response time for the third set of processed commands;

assign the first command for processing by a second server process of the plurality of server processes, wherein the second server process is different from the first server process; and

execute the first command using the second server process.

7. The information processing apparatus of claim 6, wherein the reference value is a reference time, and wherein the at least one processor is configured to predict that the load is greater than or equal to the reference value by predicting that a response time associated with the first server process processing the first command and at least the second command is greater than or equal to the reference time.

8. The information processing apparatus of claim 6, wherein the at least one processor is configured to predict that the load is greater than or equal to the reference value by determining that the combined response time for the second set of processed commands is greater than or equal to the combined response time for the third set of processed commands multiplied by a coefficient.

9. The information processing apparatus of claim 6, wherein the at least one processor is configured to determine the second set of processed commands by determining that a particular command in the second set of processed commands is similar to the first command by determining at least one of i) that the particular command and the first command are a same type of command or share a first specific keyword or ii) that the particular command and the first command have a same command filename and same command folder name or share a second specific keyword.

10. The information processing apparatus of claim 6, wherein the first server process is a front-end server process that executes on a front-end processing unit, and the second server process is a back-end server process that executes on a back-end processing unit, and wherein the at least one processor is further configured to execute the computer-executable instructions to:

send results of the processing of the first command by the back-end server process executing on the back-end processing unit to the front-end server process; and

record a history comprising the results of the processing of the first command.

11. A computer program product for load balancing a first set of commands among a plurality of server processes, the computer program product comprising a non-transitory storage medium readable by a processing circuit, the non-transitory storage medium storing instructions executable by the processing circuit to cause a method to be performed, the method comprising:

receiving a first command of the first set of commands;

predicting that a load associated with a first server process of the plurality of server processes processing the first command and at least a second command of the first set of commands is greater than or equal to a reference value, wherein the predicting comprises;

determining a second set of processed commands based at least in part on a similarity of each command in the second set of processed commands to a respective command in the first set of commands;

accessing a first recorded history of the second set of processed commands, the first recorded history comprising a respective response time associated with processing of each command in the second set of processed commands;

determining that a combined response time for the second set of processed commands is greater than or equal to the reference value;

determining a third set of processed commands, wherein at least one command in the third set of processed commands is dissimilar from each command in the first set of commands;

accessing a second recorded history of the third set of processed commands, the second recorded history comprising a respective response time associated with processing of each command in the third set of processed commands;

determining a combined response time for the third set of processed commands; and

predicting that the load is greater than or equal to the reference value based at least in part on the combined response time for the second set of processed commands and the combined response time for the third set of processed commands;

assigning the first command for processing by a second server process of the plurality of server processes, wherein the second server process is different from the first server process; and

executing, by the second server process, the first command.

12. The computer program product of claim 11, wherein the reference value is a reference time, and wherein the predicting comprises predicting that a response time associated with the first server process processing the first command and at least the second command is greater than or equal to the reference time.

13. The computer program product of claim 11, wherein predicting that the load is greater than or equal to the reference value comprises determining that the combined response time for the second set of processed commands is greater than or equal to the combined response time for the third set of processed commands multiplied by a coefficient.

14. The computer program product of claim 11, wherein the first server process is a front-end server process, the second server process is a back-end server process, the first command is received by the front-end server process, and the first command is assigned to the back-end server process, the method further comprising:

processing the first command by the back-end server process;

sending results of the processing of the first command from the back-end server process to the front-end server process; and

recording a history comprising the results of the processing of the first command.