Systems and methods for data channel queue control in a communications network

• US 5,802,310 A
• Filed: 05/30/1996
• Issued: 09/01/1998
• Est. Priority Date: 05/30/1996
• Status: Expired due to Fees

• Current Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Original Assignee: International Business Machines Corporation
• Inventors: Rajaraman, Bala
• Primary Examiner(s): Rinehart, Mark H.
• Application Number:
  US08/655,720
• Time in Patent Office: 824 Days
• Field of Search: 395/200.62, 395/200.63, 395/200.64, 395/200.65, 395/872, 395/873, 395/876, 395/877, 370/231, 370/232, 370/236, 370/229, 370/235, 711/11
• US Class Current: 709/234
• CPC Class Codes: H04L 49/90 Buffering arrangements
• CPC Class Codes: H04L 49/9078 using an external memory or storage device

Abstract

Data transfer from an application at a node of a network to a queue for a data channel is disabled when the amount of queued data in the queue is greater than a first limit and enabled when the amount of queued data in the queue is less than a second limit. The first queue limit preferably is increased when data transfer is disabled and the amount of queued data in the queue is less than the buffer storage capacity and decreased when data transfer is enabled and the data flow rate of the data channel is decreased. The second queue limit preferably is increased when data transfer is enabled and the amount of queued data in the queue is less than a predetermined data channel starvation threshold and decreased if, after data transfer from the application to the queue becomes enabled and an amount of queued data the same as the second queue limit has been communicated from the queue to the data channel, the amount of queued data in the queue is greater than a predetermined threshold. Preferably, the limits include an integral multiple of the predetermined amount of data in a burst, and are increased and decreased by an integral multiple of the predetermined amount of data in a burst. In response to a decrease in the available global storage capacity, the first and second queue limits may be reduced by first and second predetermined amounts, respectively, the first and second predetermined amounts preferably being the same.

Claims

1. A system for controlling data transfer from an application resident at a node of a network to a queue for a data channel which communicates data from the node, the queue including an amount of queued data and occupying portions of a communications buffer having a buffer storage capacity, the data channel communicating queued data at a data flow rate, the system comprising:

application data transfer controlling means, responsive to the queue, for disabling data transfer from the application and the queue such that data transfer from the application to the queue when the amount of queued data in the queue is greater than a first queue limit and for enabling data transfer from the application to the queue when the amount of queued data in the queue is less than a second queue limit;

queue limit determining means, responsive to the queue and to said application data transfer controlling means, for dynamically and automatically determining said first and second queue limits based upon multiple criteria including at least the amount of queued data queued in the queue, the data flow rate of the data channel, the buffer storage capacity and the state of said application data transfer controlling means.

2. A system for controlling data transfer from an application resident at a node of a network to a queue for a data channel which communicates data from the node, the queue including an amount of queued data and occupying portions of a communications buffer having a buffer storage capacity, the data channel communicating queued data at a data flow rate, wherein the data channel communicates queued data in bursts including a predetermined amount of data during a plurality of burst intervals, the system comprising:

application data transfer controlling means, responsive to the queue, for disabling data transfer from the application and the queue such that data transfer from the application to the queue when the amount of queued data in the queue is greater than a first queue limit and for enabling data transfer from the application to the queue when the amount of queued data in the queue is less than a second queue limit;

queue limit determining means, responsive to the queue and to said application data transfer controlling means, for dynamically and automatically determining said first and second queue limits from the amount of queued data queued in the queue, the data flow rate of the data channel, the buffer storage capacity and the state of said application data transfer controlling means, wherein said queue limit determining means comprises;

means for increasing said first queue limit when data transfer from the application to the queue is disabled and the amount of queued data in the queue is less than the buffer storage capacity;

means for decreasing said first queue limit when data transfer from the application to the queue is enabled and the data flow rate of the data channel is decreased;

means for increasing said second queue limit when data transfer from the application to the queue is enabled and the amount of queued data in the queue is less than a predetermined data channel starvation threshold; and

means for decreasing said second queue limit if, after data transfer from the application to the queue becomes enabled and an amount of queued data the same as said second queue limit has been communicated from the queue to the data channel, the amount of queued data in the queue is greater than a predetermined threshold.

3. A system according to claim 2 wherein said first queue limit and said second queue limit each comprise an integral multiple of the predetermined amount of data in a burst.

4. A system according to claim 3:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by an integral multiple of said predetermined amount of data in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by an integral multiple of said predetermined amount of data in a burst.

5. A system according to claim 4:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by the predetermined amount of data in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by the predetermined amount of data in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by the predetermined amount of data in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by the predetermined amount of data in a burst.

6. A system according to claim 2 wherein the node includes global storage having an available global storage capacity, wherein the communications buffer occupies portions of the global storage, and further comprising:

means for reducing said first queue limit by a first predetermined amount when the available global storage capacity decreases; and

means for reducing said second queue limit by a second predetermined amount when the available global storage capacity decreases.

7. A system according to claim 6 wherein said second predetermined amount is the same as said first predetermined amount.

8. A system according to claim 2:

wherein the data channel packetizes data from the application into data packets and communicates bursts including a predetermined number of data packets during a successive plurality of burst intervals; and

wherein said first and second queue limit each comprise an integral multiple of the predetermined number of data packets in a burst.

9. A system according to claim 8:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by an integral multiple of said predetermined number of data packets in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by an integral multiple of said predetermined number of data packets in a burst.

10. A system according to claim 9:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by the predetermined number of data packets in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by the predetermined number of data packets in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by the predetermined number of data packets in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by the predetermined number of data packets in a burst.

11. A system for communicating data from an application resident at a node of a network, the node including a communications buffer having a buffer storage capacity, the system comprising:

a queue, occupying portions of the communications buffer, which queues an amount of data from the application;

a data channel which communicates queued data from said queue at a data flow rate;

application data transfer controlling means, responsive to said queue, for disabling data transfer from the application to said queue when the amount of queued data in said queue is greater than a first queue limit and for enabling data transfer from the application to said queue when the amount of queued data in said queue is less than a second queue limit;

queue limit determining means, responsive to said queue and to said application data transfer controlling means, for dynamically and automatically determining said first and second queue limits based upon multiple criteria including at least the amount of queued data queued in said queue, the data flow rate of said data channel, the buffer storage capacity and the state of said application data transfer controlling means.

12. A system for communicating data from an application resident at a node of a network, the node including a communications buffer having a buffer storage capacity, the system comprising:

a queue, occupying portions of the communications buffer, which queues an amount of data from the application;

a data channel which communicates queued data from said queue at a data flow rate;

application data transfer controlling means, responsive to said queue, for disabling data transfer from the application to said queue when the amount of queued data in said queue is greater than a first queue limit and for enabling data transfer from the application to said queue when the amount of queued data in said queue is less than a second queue limit;

queue limit determining means, responsive to said queue and to said application data transfer controlling means, for dynamically and automatically determining said first and second queue limits from the amount of queued data queued in said queue, the data flow rate of said data channel, the buffer storage capacity and the state of said application data transfer controlling means;

wherein said data channel communicates queued data from said queue in bursts during a plurality of burst intervals, each burst including a predetermined amount of data; and

wherein said queue limit determining means comprises;

means, responsive to said queue and said application data transfer controlling means, for increasing said first queue limit when data transfer from the application to said queue is disabled and the amount of queued data in said queue is less than the buffer storage capacity;

means, responsive to said queue and said application data transfer controlling means, for decreasing said first queue limit when data transfer from the application to said queue is enabled and the data flow rate of said data channel is decreased;

means, responsive to said queue and said application data transfer controlling means, for increasing said second queue limit when data transfer from the application to said queue is enabled and the amount of queued data in said queue is less than a predetermined data channel starvation threshold; and

means, responsive to said queue and said application data transfer controlling means, for decreasing said second queue limit if, after data transfer from the application to said queue becomes enabled and an amount of queued data the same as said second queue limit has been communicated from said queue to said data channel, the amount of queued data in said queue is greater than a predetermined threshold.

13. A system according to claim 12 wherein said first queue limit and said second queue limit each comprise an integral multiple of the predetermined amount of data in a burst.

14. A system according to claim 13:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by an integral multiple of said predetermined amount of data in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by an integral multiple of said predetermined amount of data in a burst.

15. A system according to claim 14:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by the predetermined amount of data in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by the predetermined amount of data in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by the predetermined amount of data in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by the predetermined amount of data in a burst.

16. A system according to claim 12 wherein the network includes global storage having an available global storage capacity, wherein the communications buffer occupies portions of the global storage, and further comprising:

means for reducing said first queue limit by a first predetermined amount when the available global storage capacity decreases; and

means for reducing said second queue limit by a second predetermined amount when the available global storage capacity decreases.

17. A system according to claim 16 wherein said second predetermined amount is the same as said first predetermined amount.

18. A system according to claim 12:

wherein said data channel packetizes data from the application into data packets and communicates bursts including a predetermined number of data packets during a successive plurality of burst intervals; and

wherein said first and second queue limit each comprise an integral multiple of the predetermined number of data packets in a burst.

19. A system according to claim 18:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by an integral multiple of said predetermined number of data packets in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by an integral multiple of said predetermined number of data packets in a burst.

20. A system according to claim 19:

wherein said means for increasing said first queue limit comprises means for increasing said first queue limit by the predetermined number of data packets in a burst;

wherein said means for decreasing said first queue limit comprises means for decreasing said first queue limit by the predetermined number of data packets in a burst;

wherein said means for increasing said second queue limit comprises means for increasing said second queue limit by the predetermined number of data packets in a burst; and

wherein said means for decreasing said second queue limit comprises means for decreasing said second queue limit by the predetermined number of data packets in a burst.

21. A method of controlling data transfer from an application resident at a node of a network to a queue for a data channel which communicates data from the node, the queue including an amount of queued data and occupying portions of a communications buffer having a buffer storage capacity, the data channel communicating queued data at a data flow rate, the method comprising the steps of:

disabling transfer of data from the application to the queue when the amount of queued data in the queue is greater than a first queue limit;

enabling transfer of data from the application to the queue when the amount of queued data in the queue is less than a second queue limit;

dynamically and automatically determining the first and second queue limits based on multiple criteria including at least the amount of queued data queued in the queue, the data flow rate of the data channel, the buffer storage capacity and whether data transfer from the application is enabled.

22. A method of controlling data transfer from an application resident at a node of a network to a queue for a data channel which communicates data from the node, the queue including an amount of queued data and occupying portions of a communications buffer having a buffer storage capacity, the data channel communicating queued data at a data flow rate, wherein the data channel communicates queued data in bursts including a predetermined amount of data during a plurality of burst intervals, the method comprising the steps of:

disabling transfer of data from the application to the queue when the amount of queued data in the queue is greater than a first queue limit;

enabling transfer of data from the application to the queue when the amount of queued data in the queue is less than a second queue limit; and

dynamically and automatically determining the first and second queue limits based on the amount of queued data queued in the queue, the data flow rate of the data channel, the buffer storage capacity and whether data transfer from the application is enabled;

wherein said step of determining the first and second queue limits comprises the steps of;

increasing the first queue limit when data transfer from the application to the queue is disabled and the amount of queued data in the queue is less than the buffer storage capacity;

decreasing the first queue limit when data transfer from the application to the queue is enabled and the data flow rate of the data channel is decreased;

increasing the second queue limit when data transfer from the application to the queue is enabled and the amount of queued data in the queue is less than a predetermined data channel starvation threshold; and

decreasing the second queue limit if, after data transfer from the application to the queue becomes enabled and an amount of queued data the same as the second queue limit has been communicated from the queue to the data channel, the amount of queued data in the queue is greater than a predetermined threshold.

23. A method according to claim 22 wherein the first queue limit and the second queue limit each comprise an integral multiple of the predetermined amount of data in a burst.

24. A method according to claim 23:

wherein said step of increasing the first queue limit comprises the step of increasing the first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said step of decreasing the first queue limit comprises the step of decreasing the first queue limit by an integral multiple of the predetermined amount of data in a burst;

wherein said step of increasing the second queue limit comprises the step of increasing the second queue limit by an integral multiple of the predetermined amount of data in a burst; and

wherein said step of decreasing the second queue limit comprises the step of decreasing the second queue limit by an integral multiple of the predetermined amount of data in a burst.

25. A method according to claim 24:

wherein said step of increasing the first queue limit comprises the step of increasing the first queue limit by the predetermined amount of data in a burst;

wherein said step of decreasing the first queue limit comprises the step of decreasing the first queue limit by the predetermined amount of data in a burst;

wherein said step of increasing the second queue limit comprises the step of increasing the second queue limit by the predetermined amount of data in a burst; and

wherein said step of decreasing the second queue limit comprises the step of decreasing the second queue limit by the predetermined amount of data in a burst.

26. A method according to claim 22 wherein the node includes global storage having an available global storage capacity, wherein the communications buffer occupies portions of the global storage, and further comprising the steps of:

reducing the first queue limit by a first predetermined amount when the available global storage capacity decreases; and

reducing the second queue limit by a second predetermined amount when the available global storage capacity decreases.

27. A method according to claim 26 wherein the second predetermined amount is the same as the first predetermined amount.

28. A method according to claim 22 wherein the data channel packetizes data from the application into data packets and communicates bursts including a predetermined number of data packets during a successive plurality of burst intervals, and wherein the first and second queue limit each comprise an integral multiple of the predetermined number of data packets in a burst.

29. A method according to claim 28:

wherein said step of increasing the first queue limit comprises the step of increasing the first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said step of decreasing the first queue limit comprises the step of decreasing the first queue limit by an integral multiple of the predetermined number of data packets in a burst;

wherein said step of increasing the second queue limit comprises the step of increasing the second queue limit by an integral multiple of the predetermined number of data packets in a burst; and

wherein said step of decreasing the second queue limit comprises the step of decreasing the second queue limit by an integral multiple of the predetermined number of data packets in a burst.

30. A method according to claim 29:

wherein said step of increasing the first queue limit comprises the step of increasing the first queue limit by the predetermined number of data packets in a burst;

wherein said step of decreasing the first queue limit comprises the step of decreasing the first queue limit by the predetermined number of data packets in a burst;

wherein said step of increasing the second queue limit comprises the step of increasing the second queue limit by the predetermined number of data packets in a burst; and

wherein said step of decreasing the second queue limit comprises the step of decreasing the second queue limit by the predetermined number of data packets in a burst.