End-to-end provisioning of storage clouds

• US 8,478,845 B2
• Filed: 08/16/2010
• Issued: 07/02/2013
• Est. Priority Date: 08/16/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Agarwala, Sandip, Chavda, Kavita, Gopisetty, Sandeep, Ayala, Richard J.
• Primary Examiner(s): Keehn, Richard G
• Application Number:
  US12/857,005
• Publication Number:
  US 20120042055A1
• Time in Patent Office: 1,051 Days
• Field of Search: 709/220
• US Class Current: 709/220
• CPC Class Codes: G06F 15/177 Initialisation or configuration control processor initialisation G06F9/4405
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0629 Configuration or reconfiguration of storage systems
• 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 9/5061 Partitioning or combining of resources
• CPC Class Codes: H04L 41/5054 Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
• 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

Embodiments discussed in this disclosure provide an integrated provisioning framework that automates the process of provisioning storage resources, end-to-end, for an enterprise storage cloud environment. Such embodiments configure and orchestrate the deployment of a user'"'"'s workload and, at the same time, provide optimization across a multitude of storage cloud resources. Along these lines, input is received in the form of workload requirements and configuration information for available system resources. Based on the input, a set (at least one) of storage cloud configuration plans is developed that satisfy the workload requirements. A set of scripts is then generated that orchestrate the deployment and configuration of different software and hardware components based on the plans.

Claims

1. A computer-implemented method for end-to-end provisioning of storage clouds, comprising:

accessing a set of workload requirements and a set of system resource configurations for a set of hardware and software components associated with a storage cloud;

determining a number and a configuration of each of the available system resources;

generating a set of plans for provisioning the storage cloud to meet the set of workload requirements,

the set of plans describing a configuration of a General Parallel File System (GPFS) cluster associated with the storage cloud,

the set of plans proposing an adjustment based on at least one formulaic calculation accounting for a minimum number of network shared disk (NSD) servers, the formulaic calculation comprising;

i.sum.N Si .greater than or equal to i.sum.M Wi

generating a set of scripts to carry out the set of plans, the set of scripts being configured to orchestrate a deployment and a configuration of the set of hardware and software components;

deploying a final number of NSD servers, wherein the final number of NSD servers equals r .times. M;

mapping each of a set of logical unit numbers (LUNs) to at least two of the NSD servers; and

wherein N is a number of NSD servers, Si is an input/output (I/O) capacity of each NSD server, M is a number of workloads, Wi is an average I/O requirement of a workload “

i” and

“

r”

is a redundancy factor.

2. The computer-implemented method of claim 1, further comprising discovering available resources associated with the storage cloud.

3. The computer-implemented method of claim 1, the set of configuration plans identifying a size and a type of the logical unit numbers (LUNs) associated with the storage cloud.

4. The computer-implemented method of claim 1, the set of configuration plans identifying a number and a type of GPFS nodes associated with the storage cloud.

5. A system for end-to-end provisioning of storage clouds, comprising:

a bus;

a processor coupled to the bus; and

a memory medium coupled to the bus, the memory medium comprising instructions to;

access a set of workload requirements and a set of system resource configurations for a set of hardware and software components associated with a storage cloud;

determine a number and a configuration of each of the available system resources;

generate a set of plans for provisioning the storage cloud to meet the set of workload requirements,

the set of plans describing a configuration of a General Parallel File System (GPFS) cluster associated with the storage cloud,

the set of plans proposing an adjustment based on at least one formulaic calculation accounting for a minimum number of network shared disk (NSD) servers, the formulaic calculation comprising;

i.sum.N Si .greater than or equal to i.sum.M Wi

generate a set of scripts to carry out the set of plans, the set of scripts being configured to orchestrate a deployment and a configuration of the set of hardware and software components;

deploy a final number of NSD servers, wherein the final number of NSD servers equals r .times. M;

map each of a set of logical unit numbers (LUNs) to at least two of the NSD servers; and

wherein N is a number of NSD servers, Si is an input/output (I/O) capacity of each NSD server, M is a number of workloads, Wi is an average I/O requirement of a workload “

i”

, and “

r”

is a redundancy factor.

6. The system of claim 5, the memory medium further comprising instructions to discover available resources associated with the storage cloud.

7. The system of claim 5, the set of configuration plans identifying:

a number, a size, and a type of logical unit numbers (LUNs) associated with the storage cloud; and

a number and a type of GPFS nodes associated with the storage cloud.

8. The system of claim 7, the set of configuration plans further providing a mapping of LUNs to the network shared disk (NSD) servers.

9. A computer program product for end-to-end provisioning of storage clouds, the computer program product comprising a non-transitory computer readable storage medium, and program instructions stored on the non-transitory computer readable storage medium, to:

access a set of workload requirements and a set of system resource configurations for a set of hardware and software components associated with a storage cloud;

determine a number and a configuration of each of the available system resources;

generate a set of plans for provisioning the storage cloud to meet the set of workload requirements,

the set of plans describing a configuration of a General Parallel File System (GPFS) cluster associated with the storage cloud,

the set of plans proposing an adjustment based on at least one formulaic calculation accounting for a minimum number of network shared disk (NSD) servers, the formulaic calculation comprising;

i.sum.N Si .greater than or equal to i.sum.M Wi

generate a set of scripts to carry out the set of plans, the set of scripts being configured to orchestrate a deployment and a configuration of the set of hardware and software components;

deploy a final number of NSD servers, wherein the final number of NSD servers equals r .times. M;

map each of a set of logical unit numbers (LUNs) to at least two of the final number of NSD servers; and

wherein N is a number of NSD servers, Si is an input/output (I/O) capacity of each NSD server, M is a number of workloads, Wi is an average I/O requirement of a workload “

i”

, and “

r”

is a redundancy factor.

10. The computer program product of claim 9, further comprising program instructions stored on the non-transitory computer readable storage medium to discover available resources associated with the storage cloud.

11. The computer program product of claim 9, the set of configuration plans identifying:

a size and a type of the logical unit numbers (LUNs) associated with the storage cloud; and

a number and a type of GPFS nodes associated with the storage cloud.

12. A method for deploying a system for end-to-end provisioning of storage clouds, comprising:

providing a computer infrastructure being operable to;

access a set of workload requirements and a set of system resource configurations for a set of hardware and software components associated with a storage cloud;

determine a number and a configuration of each of the available system resources;

generate a set of plans for provisioning the storage cloud to meet the set of workload requirements,

the set of plans describing a configuration of a General Parallel File System (GPFS) cluster associated with the storage cloud,

the set of plans proposing an adjustment based on at least one formulaic calculation accounting for a minimum number of network shared disk (NSD) servers, the formulaic calculation comprising;

i.sum.N Si .greater than or equal to i.sum.M Wi

generate a set of scripts to carry out the set of plans, the set of scripts being configured to orchestrate a deployment and a configuration of the set of hardware and software components;

deploy a final number of NSD servers, wherein the final number of NSD servers equals r .times. M;

map each of a set of logical unit numbers (LUNs) to at least two of the final number of NSD servers; and

wherein N is a number of NSD servers, Si is an input/output (I/O) capacity of each NSD server, M is a number of workloads, Wi is an average I/O requirement of a workload “

i”

, and “

r”

is a redundancy factor.

13. The method for deploying a system for end-to-end provisioning of storage clouds of claim 12, the set of configuration plans identifying a size and a type of the LUNs associated with the storage cloud.

14. The method for deploying a system for end-to-end provisioning of storage clouds of claim 12, the set of configuration plans identifying a number and a type of GPFS nodes associated with the storage cloud.

15. The method for deploying a system for end-to-end provisioning of storage clouds of claim 12, the computer infrastructure being further operable to discover available resources associated with the storage cloud.