Management system and management method for managing a plurality of storage subsystems

• US 8,863,139 B2
• Filed: 04/12/2011
• Issued: 10/14/2014
• Est. Priority Date: 04/12/2011
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Kakeda, Tomoaki, Kusama, Takato
• Primary Examiner(s): Shah, Sanjiv
• Assistant Examiner(s): Waddy, Jr., Edward
• Application Number:
  US13/139,872
• Publication Number:
  US 20120266177A1
• Time in Patent Office: 1,281 Days
• Field of Search: 711/114, 711/170, 711/E12.001, 711/118, 718/104, 718/1, 718/105, 715/700, 715/771
• US Class Current: 718/104
• 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 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0632 by initialisation or re-initialisation of storage systems
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• 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

The present invention provides a technique capable of improving use efficiency of storage devices. In this regard, a computer system of the present invention includes: a plurality of storage subsystems; an information processing apparatus coupled to the storage subsystems and including a virtual layer for virtually providing information from the storage subsystems; and the a management system that manages the plurality of storage subsystems and the information processing apparatus. The management system manages, on a memory, configuration information of logical volumes allocated to virtual instances managed on a virtual layer of the information processing apparatus and operation information of hardware resources included in the storage subsystems. The management system evaluates use efficiency of the virtual instances based on the configuration information of the logical volumes and the operation information of the hardware resources and outputs an evaluation result.

Claims

1. A management system that manages a plurality of storage subsystems and an information processing apparatus coupled to the storage subsystems and including a virtual layer for virtually providing information from the storage subsystems, the management system comprising:

a memory that stores configuration information of logical volumes allocated to virtual instances managed on the virtual layer of the information processing apparatus and operation information of shared hardware resources included in the storage subsystems; and

a processor that evaluates use efficiency of the virtual instances based on the configuration information of the logical volumes and the operation information of the shared hardware resources and that outputs an evaluation result of evaluation values of the shared hardware resources;

the management system configured to;

(A) from first storage subsystems, acquire correspondence information between a first logical volume and hardware resources, and performance information about the hardware resources;

(B) from second storage subsystems, acquire correspondence information between pages and first and second logical volumes;

(C) from the second storage subsystems or GUI screen of the management system, acquire access characteristics of a virtual logical volume;

(D) based on the information acquired by (A) and (C), determine correspondences between the pages and the first and second logical volumes,

wherein the second storage subsystem migrate data of the pages between the first and second logical volumes according to determined correspondences,

wherein the hardware resources further include a cache, and the performance information includes a capacity of the cache and performance of the cache, and

wherein the process (D) further considers a cache utilization of the each first storage subsystem, and a sequential random access ratio respecting address space of the virtual logical volume; and

wherein according to the process (D), if the sequential random ratio is high, the pages are migrated to a first storage subsystem about which the cache utilization is low, and wherein according to the process (D), if the sequential random ratio is low, the pages are migrated to a first storage subsystem about which the cache utilization is high.

2. A management system according to claim 1, wherein

the memory further stores access characteristic information indicating access characteristics to the virtual instances, and

the processor takes the access characteristic information into account to evaluate the use efficiency of the virtual instances.

3. A management system according to claim 2, wherein

the processor evaluates responsivity to an I/O request of the storage subsystems and load in the logical volumes associated with the virtual instances to evaluate the use efficiency of the virtual instances.

4. A management system according to claim 3, wherein

the access characteristic information indicates an access tendency to the virtual instances, and

the processor determines importance of the hardware resources included in the storage subsystems in the calculation of the evaluation in accordance with the access characteristic information to evaluate the responsivity of the storage subsystems in the access characteristics.

5. A management system according to claim 4, wherein

the processor evaluates load of the disk drives of the storage subsystems that provide the logical volumes.

6. A management system according to claim 3, wherein

the processor outputs an optimal logical volume that should be associated with the virtual instances as the evaluation result.

7. A management system according to claim 6, wherein

the processor automatically, or in response to an inputted instruction, performs data migration to change a logical volume of an allocation destination if the optimal logical volume outputted as the evaluation result is different from a current logical volume allocated to the virtual instances.

8. A management system according to claim 7, wherein

the processor displays the evaluation result on a display screen of a display device as a GUI.

9. A management system according to claim 1, wherein

the information processing apparatus is a controller storage subsystem that virtually provides the plurality of storage subsystems as the same storage subsystems,

the virtual instances are virtual volumes to which the logical volumes provided by the plurality of storage subsystems are allocated, and

the virtual layer is a pool arranged in the controller storage subsystem and associated with the virtual logical volumes.

10. A management system according to claim 1, wherein

the information processing apparatus is a computer that provides a plurality of virtual servers that can access the plurality of storage subsystems,

the virtual instances are the virtual servers, and

the virtual layer is virtual machine software that manages the virtual servers.

11. A computer system comprising:

a plurality of storage subsystems;

an information processing apparatus coupled to the storage subsystems and including a virtual layer for virtually providing information from the storage subsystems; and

the management system according to claim 1, wherein

the management system communicates with the plurality of storage subsystems and the information processing apparatus, acquires configuration information of the logical volumes allocated to the virtual instance and operation information of hardware resources included in the storage subsystems, and stores the information in the memory.

12. A method by a management system managing a plurality of storage subsystems and an information processing apparatus coupled to the storage subsystems and including a virtual layer for virtually providing information from the storage subsystems,

the management system comprising:

a processor; and

a memory that stores configuration information of logical volumes allocated to virtual instances managed on the virtual layer of the information processing apparatus, operation information of shared hardware resources included in the storage subsystems, and access characteristic information indicating access characteristics to the virtual instances,

the method comprising;

reading, by the processor, the configuration information of the logical volumes, the operation information of the shared hardware resources, and the access characteristic information from the memory;

evaluating, by the processor, use efficiency of the virtual instances based on the read configuration information of the logical volumes, the operation information of the shared hardware resources, and the access characteristic information; and

outputting, by the processor, an evaluation result of evaluation values of the shared hardware resources;

the management system configured to;

(A) from first storage subsystems, acquiring correspondence information between a first logical volume and hardware resources, and performance information about the hardware resources;

(B) from second storage subsystems, acquiring correspondence information between pages and first and second logical volumes;

(C) from the second storage subsystems or GUI screen of the management system, acquiring access characteristics of a virtual logical volume;

(D) based on the information acquired by (A) and (C), determining correspondences between the pages and the first and second logical volumes,

wherein the second storage subsystem migrating data of the pages between the first and second logical volumes according to determined correspondences,

wherein the hardware resources further include a cache, and the performance information includes a capacity of the cache and performance of the cache, and

wherein the process (D) further considering a cache utilization of the each first storage subsystem, and a sequential random access ratio respecting address space of the virtual logical volume; and

wherein according to the process (D), if the sequential random ratio is high, the pages migrating to a first storage subsystem about which the cache utilization is low, and wherein according to the process (D), if the sequential random ratio is low, the pages migrating to a first storage subsystem about which the cache utilization is high.

13. A method according to claim 12, wherein

in the evaluating, the processor evaluates responsivity to an I/O request of the storage subsystems and load in the logical volumes associated with the virtual instances to evaluate the use efficiency of the virtual instances.

14. A method according to claim 13, wherein

the access characteristic information indicates an access tendency to the virtual instances, and

in the evaluating, the processor determines importance of the hardware resources included in the storage subsystems in the calculation of the evaluation in accordance with the access characteristic information to evaluate the responsivity of the storage subsystems in the access characteristics.

15. A method according to claim 14, wherein

in the evaluating, the processor evaluates load of the disk drives of the storage subsystems that provide the logical volumes.

16. A computer system comprising:

a host computer;

a plurality of first storage subsystems, each including hardware resources at least including first RAID groups, wherein the each first storage subsystem provide a first logical volume using the hardware resources;

a second storage subsystem coupled to the host computer and including a second RAID group, wherein, to the host computer, the second storage subsystem defines a storage pool including the first logical volume and a second logical volume defined in the second RAID group, and provides a virtual logical volume separated into pages corresponding to the first and second logical volumes in the storage pool; and

a management system configured to;

(A) from the first storage subsystems, acquire correspondence information between the first logical volume and the hardware resources, and performance information about the hardware resources;

(B) from the second storage subsystems, acquire correspondence information between the pages and the first and second logical volumes;

(C) from the second storage subsystems or GUI screen of the management system, acquire access characteristics of the virtual logical volume;

(D) based on the information acquired by (A) and (C), determine correspondences between the pages and the first and second logical volumes, and

wherein the second storage subsystem migrate data of the pages between the first and second logical volumes according to the determined correspondences,

wherein the hardware resources further include a cache, and the performance information includes a capacity of the cache and performance of the cache,

wherein the process (D) further considers a cache utilization of the each first storage subsystem, and a sequential random access ratio respecting the address space of the virtual logical volume, and

wherein according to the process (D), if the sequential random ratio is high, the pages are migrated to a first storage subsystem about which the cache utilization is low, and wherein according to the process (D), if the sequential random ratio is low, the pages are migrated to a first storage subsystem about which the cache utilization is high.

17. A management system for a computer system having:

a host computer, a plurality of first storage subsystems, each including hardware resources at least including first RAID groups, wherein each first storage subsystem provides a first logical volume using the hardware resources, a second storage subsystem coupled to the host computer and including a second RAID group, wherein, to the host computer, the second storage subsystem defines a storage pool including the first logical volume and a second logical volume defined in the second RAID group, and provides a virtual logical volume separated into pages corresponding to the first and second logical volumes in the storage pool,

the management system configured to;

(A) from the first storage subsystems, acquire correspondence information between the first logical volume and the hardware resources, and performance information about the hardware resources;

(B) from the second storage subsystems, acquire correspondence information between the pages and the first and second logical volumes;

(C) from the second storage subsystems or GUI screen of the management system, acquire access characteristics of the virtual logical volume;

(D) based on the information acquired by (A) and (C), determine correspondences between the pages and the first and second logical volumes, and

wherein the second storage subsystem migrate data of the pages between the first and second logical volumes according to the determined correspondences,

wherein the hardware resources further include a cache, and the performance information includes a capacity of the cache and performance of the cache,

wherein the process (D) further considers a cache utilization of the each first storage subsystem, and a sequential random access ratio respecting the address space of the virtual logical volume, and

wherein according to the process (D), if the sequential random ratio is high, the pages are migrated to a first storage subsystem about which the cache utilization is low, and wherein according to the process (D), if the sequential random ratio is low, the pages are migrated to a first storage subsystem about which the cache utilization is high.