Management system and computer system management method

• US 8,332,615 B2
• Filed: 07/19/2010
• Issued: 12/11/2012
• Est. Priority Date: 04/02/2010
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Fukui, Yoshiki, Beniyama, Nobuo
• Primary Examiner(s): Song, Jasmine
• Assistant Examiner(s): BERNARD, DANIEL J
• Application Number:
  US12/838,537
• Publication Number:
  US 20110246745A1
• Time in Patent Office: 876 Days
• Field of Search: None
• US Class Current: 711/209
• CPC Class Codes: G06F 12/02 Addressing or allocation; Relocation program address sequencing G06F9/00; arrangements for selecting an address in a digital store G11C8/00

Abstract

A management system detects a peak time period during which accesses are concentrated on a logical page included in a logical volume, and reallocates this logical page to an appropriate physical page. A management server detects an access variation of each logical volume, and selects a volume with a large access variation as a target volume. The management server measures the access status of each logical page in the target volume, and allocates a logical page to a more appropriate physical page.

Claims

1. A management system for managing a computer system that comprises a host computer and a storage,

wherein the storage provides multiple logical volumes to the host computer by associating each logical page in the respective logical volumes with a physical page of each of multiple storage devices,

the management system comprises:

a microprocessor;

a memory that is used by the microprocessor;

a user interface that is used by the microprocessor; and

a communication interface for the microprocessor to communicate with the host computer and the storage,

the memory stores;

first chronological information in which performance measurement values for each of the logical volumes in a predetermined time period including at least a first time period are chronologically arranged, and

second chronological information in which performance measurement values for each of the logical pages in another predetermined time period including at least a second time period that is later than the first time period are chronologically arranged,

the microprocessor outputs, via the user interface, at least any one or both of the first chronological information and the second chronological information stored in the memory, and

the logical page, for which the second chronological information is created, is selected based on a predetermined amount which is computed from the first chronological information and indicates the degree to which the performance measurement value for each of the logical volumes deviates from an average value of the first chronological information.

2. A management system according to claim 1, wherein the microprocessor obtains, as the predetermined amount, the area determined based on the region among the first chronological information in which the performance measurement value is continuously equal to or greater than a first threshold which is configured at a value that is equal to or greater than the average value.

3. A management system according to claim 2, wherein the microprocessor computes a sum of the predetermined amounts for each of the logical volumes, selects, as a target logical volume, a predetermined number of logical volumes in descending order from the sum of the predetermined amounts for each of the logical volumes, and creates the second chronological information for the logical page included in the target logical volume.

4. A management system according to claim 2, wherein the microprocessor computes a sum of the predetermined amounts for each of the logical volumes, displays via the user interface multiple logical volumes in descending order from the sum of the predetermined amounts for each of the logical volumes, selects as a target logical volume a logical volume selected by the user via the user interface, and creates the second chronological information for the logical page included in the target logical volume.

5. A management system according to claim 4, wherein the microprocessor graphically displays, via the user interface, the first chronological information in descending order from the sum of the predetermined amounts for each of the logical volumes.

6. A management system according to claim 2, wherein the microprocessor computes an access frequency representing a frequency of accesses to each of the logical pages included in the second chronological information, and instructs the storage via the communication interface to perform a reallocation in order to associate each logical page to a physical page that has performance corresponding to each access frequency.

7. A management system according to claim 6, wherein the microprocessor computes, as another predetermined amount, the area determined based on the region among the second chronological information in which the performance measurement value is continuously equal to or greater than a second threshold which is configured at a value that is equal to or greater than an average value of the second chronological information, detects a region comprising a maximum value of a multiple of the other predetermined amounts included in the second chronological information as a peak region, computes a performance measurement value per unit of time in the peak region as the access frequency, and instructs the storage via the communication interface to perform a reallocation in order to associate the logical page for which the access frequency has been computed, with a physical page that has performance of equal to or greater than the access frequency.

8. A management system according to claim 6, wherein the microprocessor estimates the sum of the predetermined amounts for each of the logical volumes subsequent to the reallocation having been performed by the storage, and outputs an estimation result via the user interface.

9. A management system according to claim 2, wherein a relatively high-performance storage device and a relatively low-performance storage device are mixed together in the multiple storage devices, and a logical page associated with a physical page of the high-performance storage device and a logical page associated with a physical page of the low-performance storage device are mixed together in the multiple logical pages that comprise the logical volume.

10. A method for managing a computer system comprising a host computer, a storage, and a management system,

wherein the storage comprises multiple logical volumes that are provided to the host computer, multiple storage devices each comprising multiple physical pages, and a control part for associating each logical page included in the each logical volume with any one of the physical pages,

the computer system management method causing the management system to execute the steps of:

creating and storing, based on information acquired from the storage, first chronological information in which performance measurement values for each of the logical volumes in a predetermined time period including at least a first time period are chronologically arranged,

selecting a measurement-target logical page from among the respective logical pages based on a predetermined amount which is computed from the first chronological information and indicates the degree to which the performance measurement value for each of the logical volumes deviates from an average value of the first chronological information,

creating and storing, based on information acquired from the storage, second chronological information in which performance measurement values for the each measurement-target logical volume in another predetermined time period including at least a second time period that is later than the first time period are chronologically arranged, and

outputting, via the user interface, at least any one or both of the stored first chronological information and the second chronological information.

11. A computer system management method according to claim 10, wherein the management system obtains, as the predetermined amount, the area determined based on the region among the first chronological information in which the performance measurement value is continuously equal to or greater than a first threshold which is configured at a value that is equal to or greater than the average value.

12. A computer system management method according to claim 11, wherein the management system computes a sum of the predetermined amounts for each of the logical volumes, selects, as the target logical volume, a predetermined number of logical volumes in descending order from the sum of the predetermined amounts for each of the logical volumes, and creates the second chronological information for the logical page included in the target logical volume.

13. A computer system management method according to claim 11, wherein the management system computes a sum of the predetermined amounts for each of the logical volumes, displays via the user interface multiple logical volumes in descending order from the sum of the predetermined amounts for each of the logical volumes, selects as a target logical volume a logical volume selected by the user via the user interface, and creates the second chronological information for the logical page included in the target logical volume.

14. A computer system management method according to claim 11, wherein the management system computes an access frequency representing a frequency of accesses to each of the logical pages included in the second chronological information, and instructs the storage via the communication interface to perform a reallocation in order to associate each logical page to a physical page that has performance corresponding to each access frequency.

15. A computer system management method according to claim 14, wherein the management system computes, as another predetermined amount, the area determined based on the region among the second chronological information in which the performance measurement value is continuously equal to or greater than a second threshold which is configured at a value that is equal to or greater than an average value of the second chronological information, detects a region comprising a maximum value of a multiple of the other predetermined amounts included in the second chronological information as a peak region, computes a performance measurement value per unit of time in the peak region as the access frequency, and instructs the storage via the communication interface to perform a reallocation in order to associate the logical page for which the access frequency has been computed, with a physical page that has performance of equal to or greater than the access frequency.