Method and apparatus for dissolving hot spots in storage systems

• US 20090300283A1
• Filed: 05/29/2008
• Published: 12/03/2009
• Est. Priority Date: 05/29/2008
• Status: Abandoned Application

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Kudo, Yutaka
• Application Number:
  US12/155,046
• Publication Number:
  US 20090300283A1
• Time in Patent Office: Days
• US Class Current: 711/114
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• 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 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Hot spots in a storage system may be located and dissolved in a smallest feasible time. A particular volume can be selected to be migrated from a hot spot with a minimum workload, and the most appropriate destination for receiving the migration is identified prior to beginning the migration. A management computer may monitor the load of each array group in the storage system in order to detect hot spots, and calculate estimated migration times for selecting a volume to be migrated from a hot spot according to shortest estimated time. Furthermore, because the storage controller needs to re-write data that is updated in an already-migrated area by a host computer during the migration, choosing the smallest volume is not the only consideration taken into account. Write access rates by host computers to the volume be migrated are taken into consideration when determining a candidate for migration.

Claims

1. An information system comprising:

a processor in communication with a plurality of storage mediums; and

a plurality of array groups formed on the storage mediums, wherein said processor is configured to identify a first array group of said plurality of array groups whose load exceeds a predetermined threshold, said first array group having a plurality of logical volumes created thereon,

wherein said processor is configured to calculate an estimated time for migrating each of said plurality of volumes from said first array group to another array group, and

wherein said processor is configured to instruct migration of a first volume of said plurality of volumes to the other array group, said first volume having a shortest estimated time for migration from among said plurality of volumes.

2. The information system according to claim 1,

wherein said estimated time to migrate a particular volume includes a first time estimated for copying data contained in the particular volume to another volume plus a second time estimated for copying re-write data comprised of data portions of the particular volume which are updated during the migration.

3. The information system according to claim 2,

wherein the second time estimated for copying the re-write data is based upon a statistical probability of a predicted number of updates to data portions of the particular volume which will have already been migrated.

4. The information system according to claim 2,

wherein said estimated time to migrate the particular volume further includes calculating an estimated busy rate for the first array group and basing the estimated time to migrate at least in part upon maintaining the busy rate for the first array group below a maximum allowable busy rate threshold.

5. The information system according to claim 1,

wherein said other array group is one of a plurality of second array groups different from said first array group, and

wherein said processor is configured to select said other array group from among said plurality of second array groups based at least in part upon current loads on said second array groups.

6. The information system according to claim 5,

wherein, when there are multiple second array groups available for receiving the migration, said process is configured to select as said other array group one of said second array groups having a same storage medium type and/or RAID configuration type as said first array group.

7. The information system according to claim 1, further comprising:

a storage controller in communication with said storage mediums for controlling access to said storage mediums; and

a management computer in communication with said storage controller via a network, wherein said processor is located in said management computer.

8. The information system according to claim 7,

wherein said management computer is configured to obtain from said storage controller information regarding the loads on each of said plurality of array groups for use in determining whether the loads on any of said array groups exceed said predetermined threshold.

9. The information system according to claim 1,

wherein the data stored in said first volume is copied to a second volume in the other array group during the migration, and

wherein, following completion of the migration, a logical identifier used by a host computer to access the first volume is reassigned to the second volume to enable the host computer to continue to access the data following migration of the data to the second volume.

10. The information system according to claim 1,

wherein said processor is configured to identify the first array group of said array groups whose load exceeds the predetermined threshold by obtaining a measurement of a load on each array group formed from said storage mediums, and determining from the obtained load measurement for each array group whether any of said array groups exceeds said predetermined threshold.

11. A method of operating an information system, comprising:

creating a plurality of array groups on a plurality of storage mediums configured for storing data;

identifying a first array group of said plurality of array groups whose load exceeds a predetermined threshold, said first array group having a plurality of logical volumes created there on;

calculating an estimated time for migrating each of said plurality of volumes from said first array group to another array group of said plurality of array groups; and

instructing migration of a first volume of said plurality of volumes to the other array group, said first volume being selected based at least in part upon said estimated times for migrating calculated for each of said plurality of volumes.

12. The method according to claim 11,

wherein the step of calculating said estimated time for migrating a particular volume further includes:

calculating a first time estimated for copying data of the particular volume to another volume in the other array group; and

adding the first time to a second time estimated for copying re-write data comprised of data portions of the particular volume which have been updated during the migration.

13. The method according to claim 12,

wherein the step of calculating said estimated time for migrating a particular volume further includes:

calculating an estimated busy rate for the first array group and basing the estimated time for migrating at least in part upon maintaining the busy rate for the first array group below a maximum allowable busy rate threshold.

14. The method according to claim 11,

wherein said other array group is one of a plurality of second array groups different from said first array group, and further including a step of selecting said other array group from among said plurality of second array groups based at least in part upon current loads on said second array groups and available capacity of said second array groups.

15. The method according to claim 11, further including a step of

selecting as said other array group one of said second array groups having a same storage medium type and/or RAID configuration type as said first array group when there are multiple second array groups available for receiving the migration.

16. The method according to claim 11, further including steps of

providing a storage controller in communication with said storage mediums for controlling access to said storage mediums;

providing a management computer in communication with said storage controller via a network; and

obtaining, by said management computer from said storage controller, information regarding the loads on each of said plurality of array groups for use in determining whether the loads on any of said array groups exceed said predetermined threshold.

17. The method according to claim 11, further including steps of

copying data stored in said first volume to a second volume in the other array group in response to the instruction for migrating;

and

reassigning a logical identifier used by a host computer to access the first volume to the second volume to enable the host computer to continue to access the data following migration of the data to the second volume.

18. A method of operating an information system, comprising:

providing a management computer in communication with a storage system, said storage system having a storage controller for controlling access to a plurality of storage mediums;

creating a plurality of array groups on the plurality of storage mediums;

requesting, by said management computer, load information from said storage controller regarding loads on the array groups;

identifying a first array group of said plurality of array groups whose load exceeds a predetermined threshold, said first array group having a plurality of logical volumes created thereon and being accessed by I/O operations; and

calculating an estimated time for migrating each of said plurality of volumes from said first array group, said estimated time for migrating each particular volume being based upon a first estimated time for copying data contained in the particular volume plus a second estimated time for copying be write data comprised of data portions of the particular volume which have been updated during the migration.

19. The method according to claim 18, further including a step of

instructing migration of a first volume of said plurality of volumes to the other array group, said first volume being selected based at least in part upon said estimated times for migrating calculated for each of said plurality of volumes.

20. The method according to claim 18,

wherein the step of calculating said estimated time for migrating a particular volume further includes:

calculating an estimated busy rate for the first array group and basing the estimated time for migrating at least in part upon maintaining the busy rate for the first array group below a maximum allowable busy rate threshold.