Rebalancing storage I/O workloads by storage controller selection and redirection

Patent metadata

Field	Value
Publication number	US-11169706-B2
Application number	US-201715607251-A
Country	US
Kind code	B2
Filing date	May 26, 2017
Priority date	May 26, 2016
Publication date	Nov 9, 2021
Grant date	Nov 9, 2021

Abstract

Systems and methods for rebalancing storage-oriented workloads across resources of a distributed data storage facility. Communications are initiated between a client computing device and a plurality of storage target devices of a distributed storage system. The distributed storage system comprises one or more computing nodes that can host virtualized controllers. A client computing device interfaced with the distributed storage system uses an IP address to access an initial virtualized controller. Upon detecting a change event, conditions of the computing environment are analyzed to determine rebalancing options. Analysis of the rebalancing options results in identification of an alternative virtualized controller. A redirect message that identifies the alternative virtualized controller is sent to the computing device. The client computing device connects to the alternative virtualized controller. Messages are sent between the client computing device and the alternative virtualized controller to access one of the storage target devices for performing storage I/O protocols.

First claim

What is claimed is:

1. A method, comprising:
receiving, at a first virtualized controller from a computer external to a distributed storage system, a storage request to access a storage target in the distributed storage system;
selecting, by the first virtualized controller, a second virtualized controller at least by analyzing quality of service pertaining to at least the storage request and the first and the second virtualized controllers,
the first and the second virtualized controllers respectively executing with a first hypervisor on a first node and a second hypervisor on a second node, either virtualized controller of the first and the second virtualized controllers configured to service the storage request to access the storage target; and

after selecting the second virtualized controller, redirecting the computer to the second virtualized controller at least by sending a redirection message from the first virtualized controller to the computer external to the distributed storage system for servicing the storage request by the second virtualized controller.

2. The method of claim 1 , further comprising detecting an event pertaining to selecting the second virtualized controller in the distributed storage system, wherein detecting the event is based at least in part on at least one of a threshold associated with a controller selection policy attribute, a policy specification pertaining to the quality of service, a node loading attribute, or a node topology attribute.

3. The method of claim 1 , redirecting the computer to the second virtualized controller comprising attaching the storage target to the computer at least by establishing a first connection between the computer and the storage target based at least in part on identification information of or login information for the storage target in the redirection message.

4. The method of claim 3 , wherein redirecting the computer to the second virtualized controller further comprises closing a second connection between the computer and the first virtualized controller.

5. The method of claim 1 , further comprising:
selecting a virtualized controller from the first and the second virtualized controllers for balancing a workload on the distributed storage system at least by performing a corresponding redirection operation in response to a receipt of a different storage request from the computer or from a separate computer to access a storage target, wherein the storage target is managed by any virtualized controller of at least the first and the second virtualized controllers in the distributed storage system, and the different storage request is received at a virtual network identifier that is assigned to the first virtualized controller.

6. The method of claim 5 , balancing the workload on the distributed storage system further comprising at least one of quiescing a first storage I/O operation, completing a second storage I/O (input/output) operation, canceling a first storage I/O request, or rejecting a second storage I/O request.

7. The method of claim 1 , further comprising identifying the storage target from a list of storage targets based at least in part upon a storage protocol of the storage target, wherein the list of storage targets is generated with a discovery request by the first virtualized controller, and the list of storage targets is identified from a storage pool managed by at least one of at least the first and the second virtualized controllers in the distributed storage system via at least a mapping that indicates the first and the second virtual virtualized controllers as respective proxies for the storage pool.

8. The method of claim 1 , wherein the quality of service corresponds to at least one of a virtualized controller failure, a virtualized controller addition, a virtualized controller removal, a virtualized controller loading, or a broken connection.

9. The method of claim 1 , wherein the redirection message comprises a discovery or function that identifies at least one storage target in the distributed storage system available for the computer to login, wherein at least one of a login command for the computer to login to separate storage target or a redirect, export, or bind command is used to redirect the computer from the first virtualized controller to the second virtualized controller for accessing the storage target.

10. The method of claim 1 , further comprising issuing a separate redirection message to the computer in response to a detection of a change in the quality of service pertaining to a storage pool managed by at least the first and the second virtualized controllers in the distributed storage system, wherein the separate redirection message comprises identification information of a separate storage target and login information for the computer to log in to the separate storage target in the distributed storage system.

11. A non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a distributed storage system, causes the distributed storage system to perform a set of acts, the set of acts comprising:
receiving, at a first virtualized controller from a computer external to a distributed storage system, a storage request to access a storage target in the distributed storage system;
selecting, by the first virtualized controller, a second virtualized controller at least by analyzing quality of service pertaining to at least the storage request and the first and the second virtualized controllers,
the first and the second virtualized controllers respectively executing with a first hypervisor on a first node and a second hypervisor on a second node, either virtualized controller of the first and the second virtualized controller configured to service the storage request to access the storage; and

after selecting the second virtualized controller, redirecting the computer to the second virtualized controller at least by sending a redirection message from the first virtualized controller to the computer external to the distributed storage system for servicing the storage request at the second virtualized controller.

12. The non-transitory computer readable medium of claim 11 , further comprising detecting an event pertaining to selecting the second virtualized controller in the distributed storage system, wherein detecting the event is based at least in part on a threshold associated with at least one of a controller selection policy attribute, a policy specification pertaining to the quality of service, a node loading attribute, or a node topology attribute.

13. The non-transitory computer readable medium of claim 11 , redirecting the computer to the second virtualized controller comprising attaching the storage target to the computer at least by establishing a first connection between the computer and the storage target based at least in part on identification information of or login information for the storage target in the redirection message.

14. The non-transitory computer readable medium of claim 13 , wherein redirecting the computer to the second virtualized controller further comprises closing a second connection between the computer and the first virtualized controller.

15. The non-transitory computer readable medium of claim 11 , further comprising instructions which, when stored in the memory and executed by the distributed storage system, cause the distributed storage system to perform an act of selecting a virtualized controller from the first and the second virtualized controllers for balancing a workload on the distributed storage system at

Assignees

• Nutanix Inc

Inventors

• Memon Tabrez
• Singhvi Jaya
• Cui Miao
• Gill Binny Sher

Classifications

• G06F9/45533 Primary

  Hypervisors; Virtual machine monitors · CPC title

• H04L67/61

  taking into account QoS or priority requirements · CPC title

• H04L67/1001

  for accessing one among a plurality of replicated servers · CPC title

• H04L67/148

  Migration or transfer of sessions · CPC title

• G06F2009/4557

  Distribution of virtual machine instances; Migration and load balancing · CPC title