System and method for automatic storage load balancing in virtual server environments

• US 8,595,364 B2
• Filed: 01/24/2013
• Issued: 11/26/2013
• Est. Priority Date: 12/31/2007
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Yahalom, Raphael, Levy, Assaf
• Primary Examiner(s): VICARY, KEITH E
• Application Number:
  US13/749,504
• Publication Number:
  US 20130139160A1
• Time in Patent Office: 306 Days
• Field of Search: None
• US Class Current: 709/226
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/815 Virtual middleware or OS functionality using virtual machines to implement generic software techniques for error detection or fault masking G06F11/1484
• CPC Class Codes: G06F 2206/1008 Graphical user interface [GUI]
• CPC Class Codes: G06F 2206/1012 Load balancing
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Methods and systems for periodically analyzing and correcting storage load imbalances in a storage network environment including virtual machines are described. These methods and systems account for various resource types, logical access paths, and relationships among different storage environment components. Load balancing may be managed in terms of input/output (I/O) traffic and storage utilization. The aggregated information is stored, and may be used to identify and correct load imbalances in a virtual server environment in order to prevent primary congestion and bottlenecks.

Claims

1. A method correcting a storage load imbalance in a storage network environment with virtual clusters, each having one or more virtual machines, the method comprising:

generating an input/output (I/O) ranking for each of the virtual machines based on I/O traffic between the virtual machines and storage devices associated with the virtual machines;

generating a storage utilization ranking for each of the storage devices based on I/O requests that are unavailable at an array cache, wherein the requests are from the virtual machines to associated storage devices;

identifying a first virtual machine on a first virtual cluster with an I/O ranking, which is higher than an I/O threshold, associated with a first storage device having a first storage utilization ranking which is higher than a threshold;

identifying a second virtual cluster associated with a second storage device having a second storage utilization ranking which is lower than the threshold; and

moving the first virtual machine from the first virtual cluster to the second virtual cluster.

2. The method of claim 1, wherein the moving the first virtual machine from the first virtual cluster to the second virtual cluster results in the first virtual machine being associated with the second storage device instead of the first storage device.

3. The method of claim 1, further comprising:

creating an alert in response to a determination that the I/O ranking is higher than the I/O threshold, wherein the moving the first virtual machine is responsive to the alert.

4. The method of claim 1, further comprising:

creating an alert in response to a determination that the second storage utilization ranking is lower than the threshold, wherein the moving the first virtual machine is responsive to the alert.

5. The method of claim 1, wherein the I/O threshold comprises a predetermined number of requests per time period.

6. The method of claim 1, wherein the threshold comprises a predetermined level of storage utilization.

7. The method of claim 1, wherein the generating an I/O ranking comprises:

deriving one or more access paths in the storage network environment and analyzing I/O traffic along the one or more access paths, wherein each of the one or more access paths comprises an end-to-end relationship between at least one virtual machine and an associated storage device in the storage network environment; and

collecting information from components in the storage network environment, the information including state and connectivity information of the virtual machines.

8. The method of claim 7, wherein deriving an access path includes:

determining a sequence of components starting with an application on a virtual server, a sequence of one or more switches and physical communication links leading to a storage controller, and a storage device containing a data object that is associated with the virtual server;

collecting one of logical and configuration information for the sequence of components;

determining if the sequence of components is configured for data flow along the sequence of components; and

if the sequence of components is configured for data flow, storing the sequence of components and the collected information, thereby deriving an access path.

9. The method of claim 1, wherein storage utilization is computed as a ratio of an amount of total I/O requests from a virtual machine provided by a physical storage device which are unavailable at the array cache to a storage capability of the physical storage device.

10. The method of claim 1, wherein the moving the first virtual machine comprises copying the first virtual machine from the first virtual cluster to the second virtual cluster, deleting the first virtual machine from the first virtual cluster, and reconfiguring the second virtual cluster.

11. The method of claim 1, wherein the first storage device is associated with a first data object comprising at least one of a volume, a datastore, and a file system, and wherein the second storage device is included in a second data object comprising at least one of a volume, a datastore, and a file system.

12. A computer program product implemented in a non-transitory computer-readable medium, the computer program product comprising:

computer code that generates an input/output (I/O) ranking for each of virtual machines of a storage network environment based on I/O traffic between the virtual machines and storage devices associated with the virtual machines, wherein the virtual machines are included in virtual clusters of the storage network environment;

computer code that generates a storage utilization ranking for each of the storage devices based on I/O requests that are unavailable at an array cache, wherein the requests are from the virtual machines to associated storage devices;

computer code that identifies a first virtual machine on a first virtual cluster with an I/O ranking, which is higher than an I/O threshold, associated with a first storage device having a first storage utilization ranking which is higher than a threshold;

computer code that identifies a second virtual cluster associated with a second storage device having a second storage utilization ranking which is lower than the threshold; and

computer code that moves the first virtual machine from the first virtual cluster to the second virtual cluster.

13. The computer program product of claim 12, wherein, when the first virtual machine is moved from the first virtual cluster to the second virtual cluster, the first virtual machine is associated with the second storage device instead of the first storage device.

14. The computer program product of claim 12, further comprising:

computer code that creates an alert in response to a determination that the high I/O ranking is higher than the I/O threshold, wherein the first virtual machine is moved from the first virtual cluster to the second virtual cluster responsive to the alert.

15. The computer program product of claim 12, further comprising:

computer code that creates an alert in response to a determination that the second storage utilization ranking is lower than the threshold, wherein the first virtual machine is moved from the first virtual cluster to the second virtual cluster responsive to the alert.

16. The computer program product of claim 12, wherein the I/O threshold comprises a predetermined number of requests per time period.

17. The computer program product of claim 12, wherein the threshold comprises a predetermined level of storage utilization.

18. The computer program product of claim 12, wherein the computer code that generates an I/O ranking comprises:

computer code that collects information from components in the storage network environment, the information including state and connectivity information of the virtual machines; and

computer code that derives one or more access paths in the storage network environment and analyzes I/O traffic along the one or more access paths, wherein each of the one or more access paths comprises an end-to-end relationship between at least one virtual machine and an associated storage device in the storage network environment.

19. The computer program product of claim 18, wherein the computer code that derives one or more access path comprises:

computer code that determines a sequence of components starting with an application on a virtual server, a sequence of one or more switches and physical communication links leading to a storage controller, and a storage device containing a data object that is associated with the virtual server;

computer code that collects one of logical and configuration information for the sequence of components;

computer code that determines if the sequence of components is configured for data flow along the sequence of components; and

computer code that stores the sequence of components and the collected information, thereby deriving an access path if the sequence of components is configured for data flow.

20. The computer program product of claim 12, wherein storage utilization is computed as a ratio of an amount of total I/O requests from a virtual machine provided by storage devices which are unavailable at the array cache to a storage capability of the storage devices.

21. The computer program product of claim 12, wherein moving the first virtual machine comprises copying the first virtual machine from the first virtual cluster to the second virtual cluster, deleting the first virtual machine from the first virtual cluster, and reconfiguring the second virtual cluster.

22. The computer program product of claim 12, wherein the first storage device is associated with a first data object comprising at least one of a volume, a datastore, and a file system, and wherein the second storage device is included in a second data object comprising at least one of a volume, a datastore, and a file system.

23. A system operable with a storage network environment with virtual clusters, each having one or more virtual machines, the system comprising:

a storage management platform in communication with components of the storage network environment, the storage network environment implementing the virtual clusters, each having the one or more virtual machines, wherein the storage management platform includes a virtual machine load balancer operable to provide management of the virtual machines to correct a storage load imbalance, the virtual machine load balancer operable to;

generate an input/output (I/O) ranking for each of the virtual machines based on I/O traffic between the virtual machines and storage devices associated with the virtual machines;

generate a storage utilization ranking for each of the storage devices based on I/O requests that are unavailable at an array cache, wherein the requests are from the virtual machines to associated storage devices;

identify a first virtual machine on a first virtual cluster with an I/O ranking, which is higher than an I/O threshold, associated with a first storage device having a first storage utilization ranking which is higher than a threshold;

identify a second virtual cluster associated with a second storage device having a second storage utilization ranking is lower than the threshold; and

move the first virtual machine from the first virtual cluster to the second virtual cluster.

24. The system of claim 23, wherein the virtual machine load balancer being operable to move the first virtual machine from the first virtual cluster to the second virtual cluster results in the first virtual machine being associated with the second storage device instead of the first storage device.

25. The system of claim 23, wherein the virtual machine load balancer is further operable to:

create an alert in response to a determination that the high I/O ranking is higher than the I/O threshold, wherein the moving the first virtual machine is responsive to the alert.

26. The system of claim 23, wherein the machine load balancer is further operable to:

create an alert in response to a determination that the second storage utilization ranking is lower than the threshold, wherein the moving the first virtual machine is responsive to the alert.

27. The system of claim 23, wherein the I/O threshold comprises a predetermined number of requests per time period.

28. The system of claim 23, wherein the threshold comprises a predetermined level of storage utilization.

29. The system of claim 23, wherein the virtual machine load balancer being operable to generate an I/O ranking comprises:

the virtual machine load balancer being operable to collect information from components in the storage network environment, the information including state and connectivity information of the virtual machines; and

the virtual machine load balancer being operable to derive one or more access paths in the storage network environment and analyzing I/O traffic along the one or more access paths, wherein each of the one or more access paths comprises an end-to-end relationship between at least one virtual machine and an associated storage device in the storage network environment.

30. The system of claim 29, wherein the virtual machine load balancer being operable to derive an access path includes:

the virtual machine load balancer being operable to determine a sequence of components starting with an application on a virtual server, a sequence of one or more switches and physical communication links leading to a storage controller, and a storage device containing a data object that is associated with the virtual server;

the virtual machine load balancer being operable to collect one of logical and configuration information for the sequence of components;

the virtual machine load balancer being operable to determine if the sequence of components is configured for data flow along the sequence of components; and

if the sequence of components is configured for data flow, the virtual machine load balancer is operable to store the sequence of components and the collected information, thereby deriving an access path.

31. The system of claim 23, wherein storage utilization is computed as a ratio of an amount of total I/O requests from a virtual machine provided by storage devices which are unavailable at the array cache to a storage capability of the storage devices.

32. The system of claim 23, wherein virtual machine load balancer being operable to move the first virtual machine comprises copying the first virtual machine from the first virtual cluster to the second virtual cluster, deleting the first virtual machine from the first virtual cluster, and reconfiguring the second virtual cluster.

33. The system of claim 23, wherein the first storage device is associated with a first data object comprising at least one of a volume, a datastore, and a file system, and wherein the second storage device is included in a second data object comprising at least one of a volume, a datastore, and a file system.