STORAGE UNIT SELECTION FOR VIRTUALIZED STORAGE UNITS

• US 20140281308A1
• Filed: 03/15/2013
• Published: 09/18/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: Bracket Computing Incorporated (Broadcom, Inc.)
• Inventors: LANGO, Jason A., Edwards, John K.
• Granted Patent: US 9,335,932 B2
• Time in Patent Office: Days
• US Class Current: 711/162
• CPC Class Codes: G06F 12/1036 for multiple virtual address spaces, e.g. segmentation G06F12/1045 takes precedence
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0628 making use of a particular technique
• CPC Class Codes: G06F 3/0634 by changing the state or mode of one or more devices
• CPC Class Codes: G06F 3/0649 Lifecycle management
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors

Abstract

Performance information for storage units located at a virtual data center is determined by executing storage administrator logic whose execution is controlled by a management entity different than the virtual data center provider. Performance expectations are automatically determined based on the determined performance information. In response to determining that a particular storage unit is incompatible with performance expectations applicable to the particular storage unit, embodiments cause a reduction in utilization of the particular storage unit. Based on determined performance information, another embodiment determines that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred. In response to determining that the performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred, the embodiment disables use of a selected storage unit of the first storage unit or the second storage unit for at least a particular purpose.

Claims

1. A method comprising:

determining performance information for each storage unit of a plurality of storage units located at a virtual data center, wherein the determining is performed by executing storage administrator logic whose execution is controlled by a management entity different than the virtual data center provider;

determining, automatically based on the determined performance information, performance expectations;

determining particular performance expectations applicable to a particular storage unit;

determining that performance of the particular storage unit is incompatible with the particular performance expectations;

causing, at least partially in response to determining that performance of the storage unit is incompatible with the performance expectations, a reduction in utilization of the particular storage unit;

wherein the method is performed by one or more computing devices.

2. The method of claim 1, wherein the particular performance expectations indicate a particular minimum speed of accessing or saving data and determining that performance of the particular storage unit is incompatible with the one or more performance expectations comprises determining that a speed of accessing or saving data to the particular storage unit is frequently slower than particular minimum speed.

3. The method of claim 1, wherein the particular performance expectations are applicable to a particular class of storage units, wherein the particular class of storage units is defined as storage units that are associated with a usage cost that is within a particular cost range.

4. The method of claim 1, comprising determining the particular performance expectations based on observed performance information received from a plurality of modules within two or more virtual machines, wherein each virtual machine of the two or more virtual machines is capable of communicating directly with at least one storage unit of the plurality of storage units.

5. The method of claim 1, wherein causing a reduction in utilization of the particular storage unit comprises instructing a virtual machine to transfer data stored on the particular storage unit to a different storage unit.

6. The method of claim 1, comprising directing requests to read or write data to one or more different target storage units instead of the particular storage unit.

7. The method of claim 1, wherein at least a first storage unit of the plurality of storage units is at a first virtual data center and at least a second storage unit of the plurality of storage units is at a second, different virtual data center.

8. A method comprising:

determining performance information for each storage unit of a plurality of storage units located at a virtual data center, wherein the determining is performed by executing storage administrator logic whose execution is controlled by a management entity different than a virtual data center provider;

based on the determined performance information, determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred;

in response to determining that the performance pattern has occurred, disabling use of a selected storage unit of the first storage unit or the second storage unit for at least a particular purpose;

wherein the method is performed by one or more devices.

9. The method of claim 8, comprising determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred by determining that response rates of the first storage unit and the second storage unit have been sufficiently similar on a plurality of different occasions.

10. The method of claim 8, comprising determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred by determining that a pattern of a first storage unit having a performance rate that is inversely correlated with a workload capacity of a second storage unit has occurred.

11. The method of claim 8, comprising determining the performance information based on observed performance information received from a plurality of virtual machines, wherein each virtual machine of the plurality of virtual machines communicates directly with at least one storage unit of the plurality of storage units.

12. The method of claim 8, comprising performing, at a storage unit management computer, the determining that the performance pattern has occurred and the disabling use of a selected storage unit of the first storage unit or the second storage unit for at least a particular purpose;

further comprising receiving, at the storage unit management computer, all requests to read information from or write information to the plurality of storage units from a client system before routing the requests to a storage unit of the plurality of storage units.

13. The method of claim 8, wherein the particular purpose is storing data for a particular client.

14. The method of claim 8, wherein the particular purpose is storing a copy of data stored in a non-selected storage unit of the first storage unit and the second storage unit.

15. A non-transitory computer-readable storage medium comprising one or more sequences of instructions which when executed by one or more processors cause the one or more processors to perform:

determining performance information for each storage unit of a plurality of storage units located at a virtual data center, wherein the determining is performed by executing storage administrator logic whose execution is controlled by a management entity different than the virtual data center provider;

determining, automatically based on the determined performance information, performance expectations;

determining particular performance expectations applicable to a particular storage unit;

determining that performance of the particular storage unit is incompatible with the particular performance expectations;

causing, at least partially in response to determining that performance of the storage unit is incompatible with the performance expectations, a reduction in utilization of the particular storage unit.

16. The non-transitory computer-readable storage medium of claim 15, wherein the performance expectations indicate a particular minimum speed of accessing or saving data and determining that performance of the particular storage unit is incompatible with the one or more performance expectations comprises determining that a speed of accessing or saving data to the particular storage unit is frequently slower than particular minimum speed.

17. The non-transitory computer-readable storage medium of claim 15, wherein the particular performance expectations are applicable to a particular class of storage units, wherein the particular class of storage units is defined as storage units that are associated with a usage cost that is within a particular cost range.

18. The non-transitory computer-readable storage medium of claim 15, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

determining the particular performance expectations based on observed performance information received from a plurality of modules within two or more virtual machines, wherein each virtual machine of the two or more virtual machines is capable of communicating directly with at least one storage unit of the plurality of storage units.

19. The non-transitory computer-readable storage medium of claim 15, wherein causing a reduction in utilization of the particular storage unit comprises instructing a virtual machine to transfer data stored on the particular storage unit to a different storage unit.

20. The non-transitory computer-readable storage medium of claim 15, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

directing requests to read or write data to one or more different target storage units instead of the particular storage unit.

21. The non-transitory computer-readable storage medium of claim 15, wherein at least a first storage unit of the plurality of storage units is at a first virtual data center and at least a second storage unit of the plurality of storage units is at a second, different virtual data center.

22. A non-transitory computer-readable storage medium comprising one or more sequences of instructions which when executed by one or more processors cause the one or more processors to perform:

determining performance information for each storage unit of a plurality of storage units located at a virtual data center, wherein the determining is performed by executing storage administrator logic whose execution is controlled by a management entity different than a virtual data center provider;

based on the determined performance information, determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred;

in response to determining that the performance pattern has occurred, disabling use of a selected storage unit of the first storage unit or the second storage unit for at least a particular purpose.

23. The non-transitory computer-readable storage medium of claim 22, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred by determining that response rates of the first storage unit and the second storage unit have been sufficiently similar on a plurality of different occasions.

24. The non-transitory computer-readable storage medium of claim 22, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

determining that a performance pattern indicating a physical co-location of a first storage unit and a second storage unit has occurred by determining that a pattern of a first storage unit having a performance rate that is inversely correlated with a workload capacity of a second storage unit has occurred.

25. The non-transitory computer-readable storage medium of claim 22, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

determining the performance information based on observed performance information received from a plurality of virtual machines, wherein each virtual machine of the plurality of virtual machines communicates directly with at least one storage unit of the plurality of storage units.

26. The non-transitory computer-readable storage medium of claim 22, wherein the sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:

performing, at a storage unit management computer, the determining that the performance pattern has occurred and the disabling use of a selected storage unit of the first storage unit or the second storage unit for at least a particular purpose;

receiving, at the storage unit management computer, all requests to read information from or write information to the plurality of storage units from a client system before routing the requests to a storage unit of the plurality of storage units.

27. The non-transitory computer-readable storage medium of claim 22, wherein the particular purpose is storing data for a particular client.

28. The non-transitory computer-readable storage medium of claim 22, wherein the particular purpose is storing a copy of data stored in a non-selected storage unit of the first storage unit and the second storage unit.