METHOD FOR THRESHOLD MIGRATION BASED ON FUZZY LOGIC TRIGGERS

• US 20080183642A1
• Filed: 01/07/2008
• Published: 07/31/2008
• Est. Priority Date: 01/08/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fauth, Jens, Akelbein, Jens-Peter
• Granted Patent: US 7,930,265 B2
• Time in Patent Office: Days
• US Class Current: 706/3
• CPC Class Codes: G06F 11/348 Circuit details, i.e. tracer hardware
• CPC Class Codes: G06F 11/349 for interfaces, buses
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

Automigration mechanisms having fuzzy-logic based automigration control mechanisms for implementing control schemes controlling start, stop and/or bandwidth of the automigration process are provided. The automigration control mechanisms read, into a memory of an automigration controller circuit, configuration parameters characterizing the hardware and software properties of the source storage and target storage and, that of the network connection between them. The mechanisms further derive fuzzy variables from the values of the input variables and of the configuration parameters. The mechanisms further provide a predetermined fuzzy function with the fuzzy variables, wherein said where the fuzzy function reflects the exhaustion level of the source executing the fuzzy function yielding a fuzzy result value. The mechanisms apply the fuzzy result value to one of the control schemes, yielding a control result. The mechanisms control the start, stop, and/or bandwidth of the automigration of data by aid of the control result.

Claims

1. A method for automigrating electronic data in a networked environment from a source storage device to a target storage device, comprising:

reading, into a memory of an automigration controller, configuration parameters characterizing at least one of hardware or software properties of the source storage device, the target storage device, and a network connection between, the source storage device and the target storage device;

deriving fuzzy variables from values of the configuration parameters;

feeding a predetermined fuzzy function with the fuzzy variables, wherein the fuzzy function reflects the exhaustion level of the source;

executing the fuzzy function yielding a fuzzy result value;

applying the fuzzy result value to a control scheme, yielding a control result; and

controlling at least one of start, stop, or bandwidth of automigration of data based on the control result.

2. The method according to claim 1, wherein reading configuration parameters comprises:

reading at least one value of a group of input variables comprising at least one of;

the source storage device'"'"'s storage capacity currently in use,

the source storage device'"'"'s increase of used storage capacity,

the source storage device'"'"'s velocity of used storage capacity increase,

the target storage device'"'"'s storage capacity currently in use,

the target storage device'"'"'s increase of used storage capacity,

the target storage device'"'"'s velocity of used storage capacity increase,

a current time,

a current day of week,

attributes of data objects to be migrated,

deletion rates of a source storage system,

creation rates of a target storage system,

average age of data objects to be migrated,

system quota,

user quota, or

information about an origin or use of data to be migrated.

3. The method according to claim 1, wherein the target storage device is used in relation to the source storage device as one of:

a backup system,

a long-term archive system,

a cooperating storage system of a same type as a source storage system, or

an element of a storage pool, of which the source storage system is also an element.

4. The method according to claim 1, wherein controlling at least one of start, stop, or bandwidth of automigrating data includes determining a bandwidth of the migrating process by defining a number of target systems used in parallel.

9. The method of claim 1, wherein the configuration parameters comprise at least one of:

a total amount of online and nearline capacity;

a maximum bandwidth of an associated input/output path;

a maximum number of associated storage resources which can be used for automigrating electronic data;

a maximum bandwidth of a single associated storage resource; and

historical data of file system usage indicating a maximum amount of data ever written in the past in a certain amount of time.

10. The method of claim 1, wherein deriving fuzzy variables from values of the configuration parameters comprises associating ranges of values of the configuration parameters with categories of the fuzzy variables, and wherein the fuzzy function transforms fuzzy variables into a probability for each category in the categories.

11. The method of claim 1, further comprising:

sensing one or more input parameter values using sensors of a throughput monitoring mechanism coupled to an input bus of a source storage system, wherein the one or more input parameter values represent a data throughput of at least one of the source storage system or a target storage system, and wherein the fuzzy variables are further derived based on the one or more input parameter values.

12. The method of claim 1, further comprising:

determining, based on the one or more input parameter values, whether the automigration of electronic data is to be performed, wherein reading, deriving, feeding, executing, applying, and controlling are performed in response to a determination that automigration of electronic data is to be performed based on the one or more input parameter values.

13. The method of claim 1, wherein executing the fuzzy function comprises executing a plurality of fuzzy functions, each fuzzy function providing a different fuzzy result value, and wherein at least one OR operator is applied to the different fuzzy result values to generate a single fuzzy result that is input to a start/stop trigger function.

14. The method of claim 13, wherein the start/stop trigger function generates the control result which is converted to a control signal to either start or stop the automigration of the electronic data.

15. The method of claim 1, wherein a configuration of the automigration controller is stored in a configuration file, wherein the configuration of the automigration controller is for a specific usage scenario, and wherein the configuration of the automigration controller configures the logic of the automigration controller to customize the logic for implementing the specific usage scenario.

16. The method of claim 15, wherein there are a plurality of configuration files for configuring the automigration controller and wherein a desired configuration file for configuring the logic of the automigration controller is selected for a desired usage scenario.

5-8. -8. (canceled)

17. A computer program product comprising a computer recordable medium having a computer readable program recorded thereon, wherein the computer readable program, when executed on a computing device, causes the computing device to:

read, into a memory of an automigration controller, configuration parameters characterizing at least one of hardware or software properties of the source storage device, the target storage device, and a network connection between the source storage device and the target storage device;

derive fuzzy variables from values of the configuration parameters;

feed a predetermined fuzzy function with the fuzzy variables, wherein the fuzzy function reflects the exhaustion level of the source;

execute the fuzzy function yielding a fuzzy result value;

apply the fuzzy result value to a control scheme, yielding a control result; and

control at least one of start, stop, or bandwidth of automigration of data based on the control result.

18. The computer program product according to claim 17, wherein the computer readable program causes the computing device to control at least one of start, stop, or bandwidth of automigrating data by determining a bandwidth of the migrating process by defining a number of target systems used in parallel.

19. The computer program product of claim 17, wherein the computer readable program causes the computing device to derive fuzzy variables from values of the configuration parameters by associating ranges of values of the configuration parameters with categories of the fuzzy variables, and wherein the fuzzy function transforms fuzzy variables into a probability for each category in the categories.

20. The computer program product of claim 17, wherein the computer readable program further causes the computing device to:

sense one or more input parameter values using sensors of a throughput monitoring mechanism coupled to an input bus of a source storage system, wherein the one or more input parameter values represent a data throughput of at least one of the source storage system or a target storage system, and wherein the fuzzy variables are further derived based on the one or more input parameter values.

21. The computer program product of claim 17, wherein the computer readable program further causes the computing device to:

determine, based on the one or more input parameter values, whether the automigration of electronic data is to be performed, wherein the computer readable program causes the computing device to perform the read, derive, feed, execute, apply, and control operations in response to a determination that automigration of electronic data is to be performed based on the one or more input parameter values.

22. The computer program product of claim 17, wherein the computer readable program causes the computing device to execute the fuzzy function by executing a plurality of fuzzy functions, each fuzzy function providing a different fuzzy result value, and wherein at least one OR operator is applied to the different fuzzy result values to generate a single fuzzy result that is input to a start/stop trigger function.

23. The computer program product of claim 17, wherein:

a configuration of the automigration controller is stored in a configuration file,

the configuration of the automigration controller is for a specific usage scenario,

the configuration of the automigration controller configures the logic of the automigration controller to customize the logic for implementing the specific usage scenario,

there are a plurality of configuration files for configuring the automigration controller, and po1 a desired configuration file for configuring the logic of the automigration controller is selected for a desired usage scenario.

24. An apparatus, comprising:

an automigration control unit; and

a source storage device coupled to the automigration control unit; and

a target storage device coupled to the source storage device, wherein the automigration control unit;

reads, into a memory of the automigration control unit, configuration parameters characterizing at least one of hardware or software properties of the source storage device, the target storage device, and a network connection between the source storage device and the target storage device;

derives fuzzy variables from values of the configuration parameters;

feeds a predetermined fuzzy function with the fuzzy variables, wherein the fuzzy function reflects the exhaustion level of the source;

executes the fuzzy function yielding a fuzzy result value;

applies the fuzzy result value to a control scheme, yielding a control result; and

control at least one of start, stop, or bandwidth of automigration of data based on the control result.