STORAGE MIRRORING OVER WIDE AREA NETWORK CIRCUITS WITH DYNAMIC ON-DEMAND CAPACITY

• US 20160359968A1
• Filed: 06/05/2015
• Published: 12/08/2016
• Est. Priority Date: 06/05/2015
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Chitti, Mark V., Freimuth, Douglas M., Hollingsworth, John F., Mandalia, Baiju D.
• Granted Patent: US 9,923,965 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes

Abstract

An approach is provided for managing an allocation of a bandwidth of a dedicated channel in a network being utilized by an application performing a replication of data from a first to a second storage resource. Checks of parameters specified by the application are determined. The parameters include, but are not limited to, average compression ratio, compression ratio trend, throughput, throughput trend, and round trip time. Respective high and low threshold values for the parameters are determined. At least one of the checks of the parameters is executed, which determines a violation of a threshold value for one of the parameters. If the violation of the high threshold value is determined, an increase in the bandwidth is triggered. If the violation of the low threshold value is determined, a decrease in the bandwidth is triggered.

Claims

1. A method of managing an allocation of a bandwidth of a dedicated channel in a network being utilized by an application performing a replication of data from a first storage resource to a second storage resource, the method comprising the steps of:

a computer determining checks of parameters specified by the application, the parameters including an average compression ratio of the data over a first amount of time, a trend of the average compression ratio of the data, an average throughput over a second amount of time, a trend of the average throughput, and a round trip time of the data in the replication being sent from the first storage resource to the second storage resource;

the computer determining respective high and low threshold values for the parameters;

the computer executing at least one of the checks of the parameters, which determines a violation of a high or low threshold value for one of the parameters; and

if the violation of the high threshold value is determined, the computer triggering an increase in the bandwidth, the increase being a first specified amount associated with the high threshold value, or if the violation of the low threshold value is determined, the computer triggering a decrease in the bandwidth, the decrease being a second specified amount associated with the low threshold value.

2. The method of claim 1, further comprising the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer determining the violation of the high threshold value, which indicates an increase in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the increase in the bandwidth, the computer sending a request to a transport device of a network service provider to dynamically increase the bandwidth during the replication, which avoids a slowdown of the application as a result of the increase in the current or expected demand.

3. The method of claim 1, further comprising the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer determining the violation of the low threshold value, which indicates a decrease in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the decrease in the bandwidth, the computer sending a request to a transport device of a network service provider to dynamically decrease the bandwidth during the replication, which avoids an over-provisioning of the bandwidth as a result of the decrease in the current or expected demand, and which reduces a cost of the replication.

4. The method of claim 1, wherein the step of determining the checks includes determining the checks of parameters further including an amount of network buffers in an input/output (I/O) device being used in the replication, buffer credits remaining on the second storage resource, a transfer time required to move the data from the first storage resource to the second storage resource, an amount of new data included in the data being transferred in the replication, a response time of a communication port of the I/O device, and a recovery point objective for the data.

5. The method of claim 1, further comprising the steps of:

the computer receiving a limit on the bandwidth for the replication and receiving a time window within which the replication is required to be completed;

the computer determining an amount of bandwidth required to complete the replication;

the computer determining whether the amount of bandwidth required to complete the replication exceeds the limit; and

if the amount of bandwidth required to complete the replication exceeds the limit, the computer sending an alert of the limit being exceeded.

6. The method of claim 5, further comprising the step of in response to the alert being sent, the computer receiving a request to increase of the limit and in response to the request being received, the computer increasing the limit so that the amount of bandwidth required to complete the replication does not exceed the increased limit.

7. The method of claim 5, further comprising the step of the computer determining a look ahead value of a compression ratio for the data in a future time period of the replication, wherein the step of determining whether the amount of bandwidth required to complete the replication exceeds the limit is based on the look ahead value of the compression ratio.

8. The method of claim 1, further comprising the steps of:

the computer determining a series of N mutually exclusive sets of the parameters, N being an integer greater than or equal to two, and the series being ordered from greatest to least amounts of increases of the bandwidth associated with violations of the respective high threshold values and from greatest to least amounts of decreases of the bandwidth associated with violations of the respective low threshold values;

the computer executing one or more checks of one or more parameters in a set included in the series of N mutually exclusive sets; and

responsive to the one or more checks, the computer determining whether the violation of the high or low threshold value occurs, and (1) if the violation of the high threshold value occurs, the computer triggering the increase in the bandwidth without repeating the step of executing the one or more checks for the next set included in the series of N mutually exclusive sets, (2) if the violation of the low threshold value occurs, the computer triggering the decrease in the bandwidth, without repeating the step of executing the one or more checks for the next set included in the series of N mutually exclusive sets, or (3) if no violation of the high or low threshold value occurs, the computer repeating the steps of (i) executing the one or more checks for the next set included in the series of N mutually exclusive sets and (ii) determining whether the violation of the high or low threshold value occurs responsive to the one or more checks for the next set.

9. A computer program product, comprising:

a computer-readable, storage device; and

a computer-readable program code stored in the computer-readable, storage device, the computer-readable program code containing instructions that are executed by a central processing unit (CPU) of a computer system to implement a method of managing an allocation of a bandwidth of a dedicated channel in a network being utilized by an application performing a replication of data from a first storage resource to a second storage resource, the method comprising the steps of;

the computer system determining checks of parameters specified by the application, the parameters including an average compression ratio of the data over a first amount of time, a trend of the average compression ratio of the data, an average throughput over a second amount of time, a trend of the average throughput, and a round trip time of the data in the replication being sent from the first storage resource to the second storage resource;

the computer system determining respective high and low threshold values for the parameters;

the computer system executing at least one of the checks of the parameters, which determines a violation of a high or low threshold value for one of the parameters; and

if the violation of the high threshold value is determined, the computer system triggering an increase in the bandwidth, the increase being a first specified amount associated with the high threshold value, or if the violation of the low threshold value is determined, the computer system triggering a decrease in the bandwidth, the decrease being a second specified amount associated with the low threshold value.

10. The computer program product of claim 9, wherein the method further comprises the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer system determining the violation of the high threshold value, which indicates an increase in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the increase in the bandwidth, the computer system sending a request to a transport device of a network service provider to dynamically increase the bandwidth during the replication, which avoids a slowdown of the application as a result of the increase in the current or expected demand.

11. The computer program product of claim 9, wherein the method further comprises the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer system determining the violation of the low threshold value, which indicates a decrease in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the decrease in the bandwidth, the computer system sending a request to a transport device of a network service provider to dynamically decrease the bandwidth during the replication, which avoids an over-provisioning of the bandwidth as a result of the decrease in the current or expected demand, and which reduces a cost of the replication.

12. The computer program product of claim 9, wherein the step of determining the checks includes determining the checks of parameters further including an amount of network buffers in an input/output (1/0) device being used in the replication, buffer credits remaining on the second storage resource, a transfer time required to move the data from the first storage resource to the second storage resource, an amount of new data included in the data being transferred in the replication, a response time of a communication port of the I/O device, and a recovery point objective for the data.

13. The computer program product of claim 9, further comprising the steps of:

the computer system receiving a limit on the bandwidth for the replication and receiving a time window within which the replication is required to be completed;

the computer system determining an amount of bandwidth required to complete the replication;

the computer system determining whether the amount of bandwidth required to complete the replication exceeds the limit; and

if the amount of bandwidth required to complete the replication exceeds the limit, the computer system sending an alert of the limit being exceeded.

14. The computer program product of claim 13, wherein the method further comprises the step of in response to the alert being sent, the computer system receiving a request to increase of the limit and in response to the request being received, the computer system increasing the limit so that the amount of bandwidth required to complete the replication does not exceed the increased limit.

15. A computer system comprising:

a central processing unit (CPU);

a memory coupled to the CPU; and

a computer readable storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of managing an allocation of a bandwidth of a dedicated channel in a network being utilized by an application performing a replication of data from a first storage resource to a second storage resource, the method comprising the steps of;

the computer system determining checks of parameters specified by the application, the parameters including an average compression ratio of the data over a first amount of time, a trend of the average compression ratio of the data, an average throughput over a second amount of time, a trend of the average throughput, and a round trip time of the data in the replication being sent from the first storage resource to the second storage resource;

the computer system determining respective high and low threshold values for the parameters;

the computer system executing at least one of the checks of the parameters, which determines a violation of a high or low threshold value for one of the parameters; and

if the violation of the high threshold value is determined, the computer system triggering an increase in the bandwidth, the increase being a first specified amount associated with the high threshold value, or if the violation of the low threshold value is determined, the computer system triggering a decrease in the bandwidth, the decrease being a second specified amount associated with the low threshold value.

16. The computer system of claim 15, wherein the method further comprises the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer system determining the violation of the high threshold value, which indicates an increase in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the increase in the bandwidth, the computer system sending a request to a transport device of a network service provider to dynamically increase the bandwidth during the replication, which avoids a slowdown of the application as a result of the increase in the current or expected demand.

17. The computer system of claim 15, wherein the method further comprises the steps of:

in response to the step of executing the at least one of the checks of the parameters, the computer system determining the violation of the low threshold value, which indicates a decrease in a current demand or an expected demand for the bandwidth; and

in response to the step of triggering the decrease in the bandwidth, the computer system sending a request to a transport device of a network service provider to dynamically decrease the bandwidth during the replication, which avoids an over-provisioning of the bandwidth as a result of the decrease in the current or expected demand, and which reduces a cost of the replication.

18. The computer system of claim 15, wherein the step of determining the checks includes determining the checks of parameters further including an amount of network buffers in an input/output (I/O) device being used in the replication, buffer credits remaining on the second storage resource, a transfer time required to move the data from the first storage resource to the second storage resource, an amount of new data included in the data being transferred in the replication, a response time of a communication port of the I/O device, and a recovery point objective for the data.

19. The computer system of claim 15, further comprising the steps of:

the computer system receiving a limit on the bandwidth for the replication and receiving a time window within which the replication is required to be completed;

the computer system determining an amount of bandwidth required to complete the replication;

the computer system determining whether the amount of bandwidth required to complete the replication exceeds the limit; and

if the amount of bandwidth required to complete the replication exceeds the limit, the computer system sending an alert of the limit being exceeded.

20. The computer program product of claim 19, wherein the method further comprises the step of in response to the alert being sent, the computer system receiving a request to increase of the limit and in response to the request being received, the computer system increasing the limit so that the amount of bandwidth required to complete the replication does not exceed the increased limit.